To see the other types of publications on this topic, follow the link: SUPERVISED TECHNOLOGY.
Dissertations / Theses on the topic 'SUPERVISED TECHNOLOGY'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'SUPERVISED TECHNOLOGY.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Persson, Travis. "Semi-Supervised Learning for Predicting Biochemical Properties." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-447652.
Full textAbstract:
The predictive performance of supervised learning methods relies on large amounts of labeled data. Data sets used in Quantitative Structure Activity Relationship modeling often contain a limited amount of labeled data, while unlabeled data is abundant. Semi-supervised learning can improve the performance of supervised methods by incorporating a larger set of unlabeled samples with fewer labeled instances. A semi-supervised learning method known as Label Spreading was compared to a Random Forest in its effectiveness for correctly classifying the binding properties of molecules on ten different sets of compounds. Label Spreading using a k-Nearest Neighbors (LS-KNN) kernel was found to, on average, outperform the Random Forest. Using a randomly sampled labeled data set of sizes 50 and 100, LS-KNN achieved a mean accuracy of 4.03% and 1.97% higher than that of the Random Forest.The outcome was similar for the mean area under the Receiver Operating Characteristic curve (AUC). For large sets of labeled data, the performances between the methods were indistinguishable. It was also found that sampling labeled data from generated clusters using a k-Means clustering algorithm, as opposed to random sampling, increased the performance of all applied methods. For a labeled data set ofsize 50, Label Spreading using a Radial Basis Function kernel increased its meanaccuracy and AUC by 7.52% and 3.08%, respectively, when sampling from clusters. In conclusion, semi-supervised learning could be beneficial when applied to similar modeling scenarios. However, the improvements heavily depend on the underlying data, suggesting that there is no one-size-fits-all method.
2
Kola, Lokesh, and Vigneshwar Muriki. "A Comparison on Supervised and Semi-Supervised Machine Learning Classifiers for Diabetes Prediction." Thesis, Blekinge Tekniska Högskola, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-21816.
Full textAbstract:
Background: The main cause of diabetes is due to high sugar levels in the blood. There is no permanent cure for diabetes. However, it can be prevented by early diagnosis. In recent years, the hype for Machine Learning is increasing in disease prediction especially during COVID-19 times. In the present scenario, it is difficult for patients to visit doctors. A possible framework is provided using Machine Learning which can detect diabetes at early stages. Objectives: This thesis aims to identify the critical features that impact gestational (Type-3) diabetes and experiments are performed to identify the efficient algorithm for Type-3 diabetes prediction. The selected algorithms are Decision Trees, RandomForest, Support Vector Machine, Gaussian Naive Bayes, Bernoulli Naive Bayes, Laplacian Support Vector Machine. The algorithms are compared based on the performance. Methods: The method consists of gathering the dataset and preprocessing the data. SelectKBestunivariate feature selection was performed for selecting the important features, which influence the Type-3 diabetes prediction. A new dataset was created by binning some of the important features from the original dataset, leading to two datasets, non-binned and binned datasets. The original dataset was imbalanced due to the unequal distribution of class labels. The train-test split was performed on both datasets. Therefore, the oversampling technique was performed on both training datasets to overcome the imbalance nature. The selected Machine Learning algorithms were trained. Predictions were made on the test data. Hyperparameter tuning was performed on all algorithms to improve the performance. Predictions were made again on the test data and accuracy, precision, recall, and f1-score were measured on both binned and non-binned datasets. Results: Among selected Machine Learning algorithms, Laplacian Support Vector Machineattained higher performance with 89.61% and 86.93% on non-binned and binned datasets respectively. Hence, it is an efficient algorithm for Type-3 diabetes prediction. The second best algorithm is Random Forest with 74.5% and 72.72% on non-binned and binned datasets. The non-binned dataset performed well for the majority of selected algorithms. Conclusions: Laplacian Support Vector Machine scored high performance among the other algorithms on both binned and non-binned datasets. The non-binned dataset showed the best performance in almost all Machine Learning algorithms except Bernoulli naive Bayes. Therefore, the non-binned dataset is more suitable for the Type-3 diabetes prediction.
3
Aboushady, Moustafa. "Semi-supervised learning with HALFADO: two case studies." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-425888.
Full textAbstract:
This thesis studies the HALFADO algorithm[1], a semi-supervised learning al- gorithm designed for detecting anomalies in complex information flows. This report assesses HALFADO’s performance in terms of detection capabilities (pre- cision and recall) and computational requirements. We compare the result of HALFADO with a standard supervised and unsupervised learning approach.The results of two case studies are reported: (1) HALFADO as applied to a FinTech example with a flow of financial transactions, and (2) HALFADO as applied to detecting hate speech in a social media feed. Those results point to the benefits of using HALFADO in environments where one has only modest computational resources.
4
Rollenhagen, Svante. "Classification of social gestures : Recognizing waving using supervised machinelearning." Thesis, KTH, Skolan för teknikvetenskap (SCI), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-230678.
Full textAbstract:
This paper presents an approach to gesture recognition including the use of a tool in order to extract certain key-points of the human body in each frame, and then processing this data and extracting features from this. The gestures recognized were two-handed waving and clapping. The features used were the maximum co-variance from a sine-fit to time-series of arm angles, as well as the max and min of this fitted sinus function. A support vector machine was used for the learning. The result was a promising accuracy of 93% ± 4% using 5-fold cross-validation. The limitations of the methods used are then discussed, which includes lack of support for more than one gesture in the data as well as some lack of generality in means of the features used. Finally some suggestions are made as to what improvements and further explorations could be made.I den har rapporten presenteras ett försök att göra gestigenkanning av gesterna vinkning samt handklappning med hjälp av ett verktyg som kan kanna igen ett antal punkter hos den mänskliga kroppen från videodata. At- tributen som användes är den maximala kovariansen från en sinus-anpassning till vinkeldata, samt det maximala och minimala värdet av anpassningen. En stodvektormaskin (Support Vector Machine) användes for inlärningen. Resultatet var en precision på 93% ± 4% där femdelad korsvalidering användes. Begränsningarna hos de använda metoderna diskuteras sedan, vilket inkluderar: brist på support for mer an en gest i video-datan, samt brister i generalitet nar det kommer till vilka attribut som anvandes. Slutligen ges förslag på framtida utvecklingar och förbättringar.
5
Eggertsson, Gunnar Atli. "Classification of Seismic Body Wave Phases Using Supervised Learning." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-423977.
Full textAbstract:
The task of accurately distinguishing between arrivals of different types of seismic waves is a common and important task within the field of seismology. For data generated by seismic stations operated by SNSN this task generally requires manual effort. In this thesis, two automatic classification models which distinguish between two types of body waves, P- and S-waves, are implemented and compared, with the aim of reducing the need for manual input. The algorithms are logistic regression and feed-forward artificial neural network. The applied methods use labelled historical data from seismological events in Sweden to train a set of classifiers, with a unique classifier associated with each seismic station. When evaluated on test data, the logistic regression classifiers achieve a mean accuracy of approximately 96% over all stations compared to approximately 98% for the neural network classifiers. The results suggest that both implemented classifiers represent a good option for automatic body wave classification in Sweden.
6
Elf, Sebastian, and Christopher Öqvist. "Comparison of supervised machine learning models forpredicting TV-ratings." Thesis, KTH, Hälsoinformatik och logistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-278054.
Full textAbstract:
Abstract Manual prediction of TV-ratings to use for program and advertisement placement can be costly if they are wrong, as well as time-consuming. This thesis evaluates different supervised machine learning models to see if the process of predicting TV-ratings can be automated with better accuracy than the manual process. The results show that of the two tested supervised machine learning models, Random Forest and Support Vector Regression, Random Forest was the better model. Random Forest was better on both measurements, mean absolute error and root mean squared error, used to compare the models. The conclusion is that Random Forest, evaluated with the dataset and methods used, are not accurate enough to replace the manual process. Even though this is the case, it could still potentially be used as part of the manual process to ease the workload of the employees. Keywords Machine learning, supervised learning, TV-rating, Support Vector Regression, Random Forest.SammanfattningAtt manuellt förutsäga tittarsiffor för program- och annonsplacering kan vara kostsamt och tidskrävande om de är fel. Denna rapport utvärderar olika modeller som utnyttjar övervakad maskininlärning för att se om processen för att förutsäga tittarsiffror kan automatiseras med bättre noggrannhet än den manuella processen. Resultaten visar att av de två testade övervakade modellerna för maskininlärning, Random Forest och Support Vector Regression, var Random Forest den bättre modellen. Random Forest var bättre med båda de två mätningsmetoder, genomsnittligt absolut fel och kvadratiskt medelvärde fel, som används för att jämföra modellerna. Slutsatsen är att Random Forest, utvärderad med de data och de metoderna som används, inte är tillräckligt exakt för att ersätta den manuella processen. Även om detta är fallet, kan den fortfarande potentiellt användas som en del av den manuella processen för att underlätta de anställdas arbetsbelastning.Nyckelord Maskininlärning, övervakad inlärning, tittarsiffror, Support Vector Regression, Random Forest.
7
Pein, Raoul Pascal. "Semi-supervised image classification based on a multi-feature image query language." Thesis, University of Huddersfield, 2010. http://eprints.hud.ac.uk/id/eprint/9244/.
Full textAbstract:
The area of Content-Based Image Retrieval (CBIR) deals with a wide range of research disciplines. Being closely related to text retrieval and pattern recognition, the probably most serious issue to be solved is the so-called \semantic gap". Except for very restricted use-cases, machines are not able to recognize the semantic content of digital images as well as humans. This thesis identifies the requirements for a crucial part of CBIR user interfaces, a multimedia-enabled query language. Such a language must be able to capture the user's intentions and translate them into a machine-understandable format. An approach to tackle this translation problem is to express high-level semantics by merging low-level image features. Two related methods are improved for either fast (retrieval) or accurate(categorization) merging. A query language has previously been developed by the author of this thesis. It allows the formation of nested Boolean queries. Each query term may be text- or content-based and the system merges them into a single result set. The language is extensible by arbitrary new feature vector plug-ins and thus use-case independent. This query language should be capable of mapping semantics to features by applying machine learning techniques; this capability is explored. A supervised learning algorithm based on decision trees is used to build category descriptors from a training set. Each resulting \query descriptor" is a feature-based description of a concept which is comprehensible and modifiable. These descriptors could be used as a normal query and return a result set with a high CBIR based precision/recall of the desired category. Additionally, a method for normalizing the similarity profiles of feature vectors has been developed which is essential to perform categorization tasks. To prove the capabilities of such queries, the outcome of a semi-supervised training session with \leave-one-object-out" cross validation is compared to a reference system. Recent work indicates that the discriminative power of the query-based descriptors is similar and is likely to be improved further by implementing more recent feature vectors.
8
Persson, Martin. "Semantic Mapping using Virtual Sensors and Fusion of Aerial Images with Sensor Data from a Ground Vehicle." Doctoral thesis, Örebro : Örebro University, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-2186.
Full text
9
Hussein, Abdul Aziz. "Identifying Crime Hotspot: Evaluating the suitability of Supervised and Unsupervised Machine learning." University of Cincinnati / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1624914607243042.
Full text
10
Chetry, Roshan. "Web genre classification using feature selection and semi-supervised learning." Kansas State University, 2011. http://hdl.handle.net/2097/8855.
Full textAbstract:
Master of ScienceDepartment of Computing and Information Sciences
Doina Caragea
As the web pages continuously change and their number grows exponentially, the need for genre classification of web pages also increases. One simple reason for this is given by the need to group web pages into various genre categories in order to reduce the complexities of various web tasks (e.g., search). Experts unanimously agree on the huge potential of genre classification of web pages. However, while everybody agrees that genre classification of web pages is necessary, researchers face problems in finding enough labeled data to perform supervised classification of web pages into various genres. The high cost of skilled manual labor, rapid changing nature of web and never ending growth of web pages are the main reasons for the limited amount of labeled data. On the contrary unlabeled data can be acquired relatively inexpensively in comparison to labeled data. This suggests the use of semi-supervised learning approaches for genre classification, instead of using supervised approaches. Semi-supervised learning makes use of both labeled and unlabeled data for training - typically a small amount of labeled data and a large amount of unlabeled data. Semi-supervised learning have been extensively used in text classification problems. Given the link structure of the web, for web-page classification one can use link features in addition to the content features that are used for general text classification. Hence, the feature set corresponding to web-pages can be easily divided into two views, namely content and link based feature views. Intuitively, the two feature views are conditionally independent given the genre category and have the ability to predict the class on their own. The scarcity of labeled data, availability of large amounts of unlabeled data, richer set of features as compared to the conventional text classification tasks (specifically complementary and sufficient views of features) have encouraged us to use co-training as a tool to perform semi-supervised learning. During co-training labeled examples represented using the two views are used to learn distinct classifiers, which keep improving at each iteration by sharing the most confident predictions on the unlabeled data. In this work, we classify web-pages of .eu domain consisting of 1232 labeled host and 20000 unlabeled hosts (provided by the European Archive Foundation [Benczur et al., 2010]) into six different genres, using co-training. We compare our results with the results produced by standard supervised methods. We find that co-training can be an effective and cheap alternative to costly supervised learning. This is mainly due to the two independent and complementary feature sets of web: content based features and link based features.
11
Jönsson, Mattias, and Lucas Borg. "How to explain graph-based semi-supervised learning for non-mathematicians?" Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20339.
Full textAbstract:
Den stora mängden tillgänglig data på internet kan användas för att förbättra förutsägelser genom maskininlärning. Problemet är att sådan data ofta är i ett obehandlat format och kräver att någon manuellt bestämmer etiketter på den insamlade datan innan den kan användas av algoritmen. Semi-supervised learning (SSL) är en teknik där algoritmen använder ett fåtal förbehandlade exempel och därefter automatiskt bestämmer etiketter för resterande data. Ett tillvägagångssätt inom SSL är att representera datan i en graf, vilket kallas för graf-baserad semi-supervised learning (GSSL), och sedan hitta likheter mellan noderna i grafen för att automatiskt bestämma etiketter.Vårt mål i denna uppsatsen är att förenkla de avancerade processerna och stegen för att implementera en GSSL-algoritm. Vi kommer att gå igen grundläggande steg som hur utvecklingsmiljön ska installeras men även mer avancerade steg som data pre-processering och feature extraction. Feature extraction metoderna som uppsatsen använder sig av är bag-of-words (BOW) och term frequency-inverse document frequency (TF-IDF). Slutgiltligen presenterar vi klassificering av dokument med Label Propagation (LP) och Multinomial Naive Bayes (MNB) samt en detaljerad beskrivning över hur GSSL fungerar.Vi presenterar även prestanda för klassificering-algoritmerna genom att klassificera 20 Newsgroup datasetet med LP och MNB. Resultaten dokumenteras genom två olika utvärderingspoäng vilka är F1-score och accuracy. Vi gör även en jämförelse mellan MNB och LP med två olika typer av kärnor, KNN och RBF, på olika mängder av förbehandlade träningsdokument. Resultaten ifrån klassificering-algoritmerna visar att MNB är bättre på att klassificera datasetet än LP.The large amount of available data on the web can be used to improve the predictions made by machine learning algorithms. The problem is that such data is often in a raw format and needs to be manually labeled by a human before it can be used by a machine learning algorithm. Semi-supervised learning (SSL) is a technique where the algorithm uses a few prepared samples to automatically prepare the rest of the data. One approach to SSL is to represent the data in a graph, also called graph-based semi-supervised learning (GSSL), and find similarities between the nodes for automatic labeling.Our goal in this thesis is to simplify the advanced processes and steps to implement a GSSL-algorithm. We will cover basic tasks such as setup of the developing environment and more advanced steps such as data preprocessing and feature extraction. The feature extraction techniques covered are bag-of-words (BOW) and term frequency-inverse document frequency (TF-IDF). Lastly, we present how to classify documents using Label Propagation (LP) and Multinomial Naive Bayes (MNB) with a detailed explanation of the inner workings of GSSL. We showcased the classification performance by classifying documents from the 20 Newsgroup dataset using LP and MNB. The results are documented using two different evaluation scores called F1-score and accuracy. A comparison between MNB and the LP-algorithm using two different types of kernels, KNN and RBF, was made on different amount of labeled documents. The results from the classification algorithms shows that MNB is better at classifying the data than LP.
12
Apprey-Hermann, Joseph Kwame. "Evaluating The Predictability of Pseudo-Random Number Generators Using Supervised Machine Learning Algorithms." Youngstown State University / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1588805461290138.
Full text
13
Rodwell, David Alexander Richard. "Investigating perceptions of emerging technology in driver education." Thesis, Queensland University of Technology, 2019. https://eprints.qut.edu.au/132171/1/David_Rodwell_Thesis.pdf.
Full textAbstract:
The introduction of advanced technologies into novice driver education may improve its efficacy as a young driver crash countermeasure. Underpinned by the Goals for Driver Education and the Technology Acceptance Model, and using a mixed-methods approach, this thesis examined how young drivers, professional driver educators, and parents perceive five advanced technologies used for professional driver education, with a particular focus on driving simulators. Findings suggest that the perceptions of these groups are largely aligned. However, there is complexity in the way they view some technologies, particularly medium fidelity driving simulators and PC-based hazard perception training.
14
Lai, Daphne Teck Ching. "An exploration of improvements to semi-supervised fuzzy c-means clustering for real-world biomedical data." Thesis, University of Nottingham, 2014. http://eprints.nottingham.ac.uk/14232/.
Full textAbstract:
This thesis explores various detailed improvements to semi-supervised learning (using labelled data to guide clustering or classification of unlabelled data) with fuzzy c-means clustering (a ‘soft’ clustering technique which allows data patterns to be assigned to multiple clusters using membership values), with the primary aim of creating a semi-supervised fuzzy clustering algorithm that shows good performance on real-world data. Hence, there are two main objectives in this work. The first objective is to explore novel technical improvements to semi-supervised Fuzzy c-means (ssFCM) that can address the problem of initialisation sensitivity and can improve results. The second objective is to apply the developed algorithm on real biomedical data, such as the Nottingham Tenovus Breast Cancer (NTBC) dataset, to create an automatic methodology for identifying stable subgroups which have been previously elicited semi-manually. Investigations were conducted into detailed improvements to the ss-FCM algorithm framework, including a range of distance metrics, initialisation and feature selection techniques and scaling parameter values. These methodologies were tested on different data sources to demonstrate their generalisation properties. Evaluation results between methodologies were compared to determine suitable techniques on various University of California, Irvine (UCI) benchmark datasets. Results were promising, suggesting that initialisation techniques, feature selection and scaling parameter adjustment can increase ssFCM performance. Based on these investigations, a novel ssFCM framework was developed, applied to the NTBC dataset, and various statistical and biological evaluations were conducted. This demonstrated highly significant improvement in agreement with previous classifications, with solutions that are biologically useful and clinically relevant in comparison with Sorias study [141]. On comparison with the latest NTBC study by Green et al. [63], similar clinical results have been observed, confirming stability of the subgroups. Two main contributions to knowledge have been made in this work. Firstly, the ssFCM framework has been improved through various technical refinements, which may be used together or separately. Secondly, the NTBC dataset has been successfully automatically clustered (in a single algorithm) into clinical sub-groups which had previously been elucidated semi-manually. While results are very promising, it is important to note that fully, detailed validation of the framework has only been carried out on the NTBC dataset, and so there is limit on the general conclusions that may be drawn. Future studies include applying the framework on other biomedical datasets and applying distance metric learning into ssFCM. In conclusion, an enhanced ssFCM framework has been proposed, and has been demonstrated to have highly significant improved accuracy on the NTBC dataset.
15
Pettersson, Ruiz Eric. "Combating money laundering with machine learning : A study on different supervised-learning algorithms and their applicability at Swedish cryptocurrency exchanges." Thesis, KTH, Skolan för industriell teknik och management (ITM), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-300375.
Full textAbstract:
In 2018, Europol (2018) estimated that more than $22 billion dollars were laundered in Europe by using cryptocurrencies. The Financial Action Task Force explains that moneylaunderers may exchange their illicitly gained fiat-money for crypto, launder that crypto by distributing the funds to multiple accounts and then re-exchange the crypto back to fiat-currency. This process of exchanging currencies is done through a cryptocurrency exchange, giving the exchange an ideal position to prevent money laundering from happening as it acts as middleman (FATF, 2021). However, current AML efforts at these exchanges have shown to be outdated and need to be improved. Furthermore, Weber et al. (2019) argue that machine learning could be used for this endeavor. The study's purpose is to investigate how machine learning can be used to combat money laundering activities performed using cryptocurrency. This is done by exploring what machine learning algorithms are suitable for this purpose. In addition, the study further seeks to understand the applicability of the investigated algorithms by exploring their fit at cryptocurrency exchanges. To answer the research question, four supervised-learning algorithms are compared by using the Bitcoin Elliptic Dataset. Moreover, with the objective of quantitively understanding the algorithmic performance differences, three key evaluation metrics are used: F1-score, precision and recall. Then, in order to understand the investigated algorithms applicability, two complementary qualitative interviews are performed at Swedish cryptocurrency exchanges. The study cannot conclude if there is a most suitable algorithm for detecting transactions related to money-laundering. However, the applicability of the decision tree algorithm seems to be more promising at Swedish cryptocurrency exchanges, compared to the other three algorithms.Europol (2018) uppskattade år 2018, att mer än 22 miljarder USD tvättades i Europa genom användning av kryptovalutor. Financial Action Task Force förklarar att penningtvättare kan byta deras olagligt förvärvade fiat-valutor mot kryptovaluta, tvätta kryptovalutan genom att fördela tillgångarna till ett flertal konton och sedan återväxla kryptovalutan tillbaka till fiat-valuta. Denna process, att växla valutor, görs genom en kryptovalutaväxlare, vilket ger växlaren en ideal position för att förhindra att tvättning sker eftersom de agerar som mellanhänder (FATF, 2021). Dock har de aktuella AMLansträngningarna vid dessa växlare visat sig vara föråldrade och i behov av förbättring. Dessutom hävdar Weber et al. (2019) att maskininlärning skulle kunna användas i denna strävan. Denna studies syfte är att undersöka hur maskininlärning kan användas för att bekämpa penningtvättaktiviteter där kryptovaluta används. Detta görs genom att utforska vilka maskininlärningsalgoritmer som är användbara för detta ändamål. Dessutom strävar undersökningen till att ge förståelse för tillämpligheten hos de undersökta algoritmerna genom att utforska deras lämplighet hos kryptovalutaväxlare. För att besvara frågeställningen har fyra supervised-learning algoritmer jämförts genom att använda Bitcoin Elliptic Dataset. För att kvantitativt förstå olikheterna i algoritmisk prestanda, har tre utvärderingsverktyg använts: F1-score, Precision och Recall. Slutligen, för att ytterligare förstå de undersökta algoritmernas tillämplighet, har två kompletterande kvalitativa intervjuer med svenska kryptovalutaväxlare gjorts. Studien kan inte dra slutsatsen att det finns en bästa algoritm för att upptäcka transaktioner som kan relateras till penningtvätt. Dock verkar tillämpbarheten hos decision tree algoritmen vara mer lovande vid de svenska kyptovalutaväxlarna än de tre andra algoritmerna.
16
Björk, Gabriella. "Evaluation of system design strategies and supervised classification methods for fruit recognition in harvesting robots." Thesis, KTH, Skolan för industriell teknik och management (ITM), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-217859.
Full textAbstract:
This master thesis project is carried out by one student at the Royal Institute of Technology in collaboration with Cybercom Group. The aim was to evaluate and compare system design strategies for fruit recognition in harvesting robots and the performance of supervised machine learning classification methods when applied to this specific task. The thesis covers the basics of these systems; to which parameters, constraints, requirements, and design decisions have been investigated. The framework is used as a foundation for the implementation of both sensing system, and processing and classification algorithms. A plastic tomato plant with fruit of varying maturity was used as a basis for training and testing, and a Kinect v2 for Windows including sensors for high resolution color-, depth, and IR data was used for image acquisition. The obtained data were processed and features of objects of interest extracted using MATLAB and a SDK for Kinect provided by Microsoft. Multiple views of the plant were acquired by having the plant rotate on a platform controlled by a stepper motor and an Ardunio Uno. The algorithms tested were binary classifiers, including Support Vector Machine, Decision Tree, and k-Nearest Neighbor. The models were trained and validated using a five fold cross validation in MATLABs Classification Learner application. Peformance metrics such as precision, recall, and the F1-score, used for accuracy comparison, were calculated. The statistical models k-NN and SVM achieved the best scores. The method considered most promising for fruit recognition purposes was the SVM.Det här masterexamensarbetet har utförts av en student från Kungliga Tekniska Högskolan i samarbete med Cybercom Group. Målet var att utvärdera och jämföra designstrategier för igenkänning av frukt i en skörderobot och prestandan av klassificerande maskininlärningsalgoritmer när de appliceras på det specifika problemet. Arbetet omfattar grunderna av dessa system; till vilket parametrar, begränsningar, krav och designbeslut har undersökts. Ramverket användes sedan som grund för implementationen av sensorsystemet, processerings- och klassifikationsalgoritmerna. En tomatplanta i pplast med frukter av varierande mognasgrad användes som bas för träning och validering av systemet, och en Kinect för Windows v2 utrustad med sensorer för högupplöst färg, djup, och infraröd data anvöndes för att erhålla bilder. Datan processerades i MATLAB med hjälp av mjukvaruutvecklingskit för Kinect tillhandahållandet av Windows, i syfte att extrahera egenskaper ifrån objekt på bilderna. Multipla vyer erhölls genom att låta tomatplantan rotera på en plattform, driven av en stegmotor Arduino Uno. De binära klassifikationsalgoritmer som testades var Support Vector MAchine, Decision Tree och k-Nearest Neighbor. Modellerna tränades och valideras med hjälp av en five fold cross validation i MATLABs Classification Learner applikation. Prestationsindikatorer som precision, återkallelse och F1- poäng beräknades för de olika modellerna. Resultatet visade bland annat att statiska modeller som k-NN och SVM presterade bättre för det givna problemet, och att den sistnömnda är mest lovande för framtida applikationer.
17
Rutter, Wilbur Cliff IV. "USING MACHINE LEARNING TO PREDICT ACUTE KIDNEY INJURIES AMONG PATIENTS TREATED WITH EMPIRIC ANTIBIOTICS." UKnowledge, 2018. https://uknowledge.uky.edu/pharmacy_etds/86.
Full textAbstract:
Acute kidney injury (AKI) is a significant adverse effect of many medications that leads to increased morbidity, cost, and mortality among hospitalized patients. Recent literature supports a strong link between empiric combination antimicrobial therapy and increased AKI risk. As briefly summarized below, the following chapters describe my research conducted in this area.
Chapter 1 presents and summarizes the published literature connecting combination antimicrobial therapy with increased AKI incidence. This chapter sets the specific aims I aim to achieve during my dissertation project.
Chapter 2 describes a study in which patients receiving vancomycin (VAN) in combination with piperacillin-tazobactam (TZP) or cefepime (CFP). I matched over 1,600 patients receiving both combinations and found a significantly lower incidence of AKI among patient receiving the CFP+VAN combination when controlling for confounders. The conclusion of this study is that VAN+TZP has significantly increased risk of AKI compared to CFP+VAN, confirming the results of previous literature.
Chapter 3 presents a study of patients receiving VAN in combination with meropenem (MEM) or TZP. This study included over 10,000 patients and used inverse probability of treatment weighting to conserve data for this population. After controlling for confounders, VAN+TZP was associated with significantly more AKI than VAN+MEM. This study demonstrates that MEM is clinically viable alternative to TZP in empiric antimicrobial therapy.
Chapter 4 describes a study in which patients receiving TZP or ampicillin-sulbactam (SAM) with or without VAN were analyzed for AKI incidence. The purpose of this study was to identify whether the addition of a beta-lactamase inhibitor to a beta-lactam increased the risk of AKI. This study included more than 2,400 patients receiving either agent and found that there were no differences in AKI among patients receiving SAM or TZP; however, AKI was significantly more common in the TZP group when stratified by VAN exposure. This study shows that comparisons of TZP to other beta-lactams without beta-lactamase inhibitors are valid.
Chapter 5 presents a study of almost 30,000 patients who received combination antimicrobial therapy over an 8-year period. This study demonstrates similar AKI incidence to previous literature and the studies presented in the previous chapters. Additionally, the results of the predictive models suggest that further work in this research area is needed.
The studies conducted present a clear message that patients receiving VAN+TZP are at significantly greater risk of AKI than alternative regimens for empiric coverage of infection.
18
Korduner, Lars, and Mattias Sundquist. "Determining an optimal approach for human occupancy recognition in a study room using non-intrusive sensors and machine learning." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20632.
Full textAbstract:
Mänskligt igenkännande med användning av sensorer och maskininlärning är ett fält med många praktiska tillämpningar. Det finns några kommersiella produkter som på ett tillförlitligt sätt kan känna igen människor med hjälp av videokameror. Dock ger videokameror ofta en oro för inkräktning i privatlivet, men genom att läsa det relaterade arbetet kan man hävda att i vissa situationer är en videokamera inte nödvändigtvis mer tillförlitlig än billiga, icke-inkräktande sensorer. Att känna igen antalet människor i ett litet studie / kontorsrum är en sådan situation. Även om det har gjorts många framgångsrika studier för igenkänning av människor med olika sensorer och maskininlärningsalgoritmer, kvarstår en fråga om vilken kombination av sensorer och maskininlärningsalgoritmer som är allmänt bättre. Denna avhandling utgår från att testa fem lovande sensorer i kombination med sex olika maskininlärningsalgoritmer för att bestämma vilken kombination som överträffade resten. För att uppnå detta byggdes en arduino prototyp för att samla in och spara läsningarna från alla fem sensorer i en textfil varje sekund. Arduinon, tillsammans med sensorerna, placerades i ett litet studierum på Malmö universitet för att samla data vid två separata tillfällen medan studenterna använde rummet som vanligt. Den insamlade datan användes sedan för att träna och utvärdera fem maskininlärningsklassificerare för var och en av de möjliga kombinationerna av sensorer och maskininlärningsalgoritmer, för både igenkänningsdetektering och igenkänningsantal. I slutet av experimentet konstaterades det att alla algoritmer kunde uppnå en precision på minst 90% med vanligtvis mer än en kombination av sensorer. Den högsta träffsäkerheten som uppnåddes var 97%.Human recognition with the use of sensors and machine learning is a field with many practical applications. There exists some commercial products that can reliably recognise humans with the use of video cameras. Video cameras often raises a concern about privacy though, by reading the related work one could argue that in some situations a video camera is not necessarily more reliable than low-cost, non-intrusive, ambient sensors. Human occupancy recognition in a small sized study/office room is one such situation. While there has been a lot of successful studies done on human occupancy recognition with various sensors and machine learning algorithms, a question about which combination of sensors and machine learning algorithms is more viable still remains. This thesis sets out to test five promising sensors in combination with six different machine learning algorithms to determine which combination outperformed the rest. To achieve this, an arduino prototype was built to collect and save the readings from all five sensors into a text file every second. The arduino, along with the sensors, was placed in a small study room at Malmö University to collect data on two separate occasions whilst students used the room as they would usually do. The collected data was then used to train and evaluate five machine learning classifier for each of the possible combinations of sensors and machine learning algorithms, for both occupancy detection and occupancy count. At the end of the experiment it was found that all algorithms could achieve an accuracy of at least 90% with usually more than one combination of sensors. The highest hit-rate achieved was 97%.
19
Anavberokhai, Isah. "Mapping land-use in north-western Nigeria (Case study of Dutse)." Thesis, University of Gävle, Department of Technology and Built Environment, 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-143.
Full textAbstract:
This project analyzes satellite images from 1976, 1985 and 2000 of Dutse, Jigawa state, in north-western Nigeria. The analyzed satellite images were used to determine land-use and vegetation changes that have occurred in the land-use from 1976 to 2000 will help recommend possible planning measures in order to protect the vegetation from further deterioration.
Studying land-use change in north-western Nigeria is essential for analyzing various ecological and developmental consequences over time. The north-western region of Nigeria is of great environmental and economic importance having land cover rich in agricultural production and livestock grazing. The increase of population over time has affected the land-use and hence agricultural and livestock production.
On completion of this project, the possible land use changes that have taken place in Dutse will be analyzed for future recommendation. The use of supervised classification and change detection of satellite images have produced an economic way to quantify different types of landuse and changes that has occurred over time.
The percentage difference in land-use between 1976 and 2000 was 37%, which is considered to be high land-use change within the period of study. The result in this project is being used to propose planning strategies that could help in planning sustainable land-use and diversity in Dutse.
20
Hansen, Vedal Amund. "Comparing performance of convolutional neural network models on a novel car classification task." Thesis, KTH, Medieteknik och interaktionsdesign, MID, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-213468.
Full textAbstract:
Recent neural network advances have lead to models that can be used for a variety of image classification tasks, useful for many of today’s media technology applications. In this paper, I train hallmark neural network architectures on a newly collected vehicle image dataset to do both coarse- and fine-grained classification of vehicle type. The results show that the neural networks can learn to distinguish both between many very different and between a few very similar classes, reaching accuracies of 50.8% accuracy on 28 classes and 61.5% in the most challenging 5, despite noisy images and labeling of the dataset.Nya neurala nätverksframsteg har lett till modeller som kan användas för en mängd olika bildklasseringsuppgifter, och är därför användbara många av dagens medietekniska applikationer. I detta projektet tränar jag moderna neurala nätverksarkitekturer på en nyuppsamlad bilbild-datasats för att göra både grov- och finkornad klassificering av fordonstyp. Resultaten visar att neurala nätverk kan lära sig att skilja mellan många mycket olika bilklasser, och även mellan några mycket liknande klasser. Mina bästa modeller nådde 50,8% träffsäkerhet vid 28 klasser och 61,5% på de mest utmanande 5, trots brusiga bilder och manuell klassificering av datasetet.
21
Nyman, David. "Injector diagnosis based on engine angular velocity pulse pattern recognition." Thesis, Uppsala universitet, Signaler och system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-414967.
Full textAbstract:
In a modern diesel engine, a fuel injector is a vital component. The injectors control the fuel dosing into the combustion chambers. The accuracy in the fuel dosing is very important as inaccuracies have negative effects on engine out emissions and the controllability. Because of this, a diagnosis that can classify the conditions of the injectors with good accuracy is highly desired. A signal that contains information about the injectors condition, is the engine angular velocity. In this thesis, the classification performance of six common machine learning methods is evaluated. The input to the methods is the engine angular velocity. In addition to the classification performance, also the computational cost of the methods, in a deployed state, is analysed. The methods are evaluated on data from a Scania truck that has been run just like any similar commercial vehicle. The six methods evaluated are: logistic regression, kernel logistic regression, linear discriminant analysis, quadratic discriminant analysis, fully connected neural networks and, convolutional neural networks. The results show that the neural networks achieve the best classification performance. Furthermore, the neural networks also achieve the best classification performance from a, in a deployed state, computational cost effectiveness perspective. Results also indicate that the neural networks can avoid false alarms and maintain high sensitivity.
22
Tovedal, Sofiea. "On The Effectiveness of Multi-TaskLearningAn evaluation of Multi-Task Learning techniques in deep learning models." Thesis, Umeå universitet, Institutionen för datavetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-172257.
Full textAbstract:
Multi-Task Learning is today an interesting and promising field which many mention as a must for achieving the next level advancement within machine learning. However, in reality, Multi-Task Learning is much more rarely used in real-world implementations than its more popular cousin Transfer Learning. The questionis why that is and if Multi-Task Learning outperforms its Single-Task counterparts. In this thesis different Multi-Task Learning architectures were utilized in order to build a model that can handle labeling real technical issues within two categories. The model faces a challenging imbalanced data set with many labels to choose from and short texts to base its predictions on. Can task-sharing be the answer to these problems? This thesis investigated three Multi-Task Learning architectures and compared their performance to a Single-Task model. An authentic data set and two labeling tasks was used in training the models with the method of supervised learning. The four model architectures; Single-Task, Multi-Task, Cross-Stitched and the Shared-Private, first went through a hyper parameter tuning process using one of the two layer options LSTM and GRU. They were then boosted by auxiliary tasks and finally evaluated against each other.
23
Gustafsson, Andreas. "Winner Prediction of Blood Bowl 2 Matches with Binary Classification." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20368.
Full textAbstract:
Being able to predict the outcome of a game is useful in many aspects. Such as,to aid designers in the process of understanding how the game is played by theplayers, as well as how to be able to balance the elements within the game aretwo of those aspects. If one could predict the outcome of games with certaintythe design process could possibly be evolved into more of an experiment basedapproach where one can observe cause and effect to some degree. It has previouslybeen shown that it is possible to predict outcomes of games to varying degrees ofsuccess. However, there is a lack of research which compares and evaluates severaldifferent models on the same domain with common aims. To narrow this identifiedgap an experiment is conducted to compare and analyze seven different classifierswithin the same domain. The classifiers are then ranked on accuracy against eachother with help of appropriate statistical methods. The classifiers compete onthe task of predicting which team will win or lose in a match of the game BloodBowl 2. For nuance three different datasets are made for the models to be trainedon. While the results vary between the models of the various datasets the general consensus has an identifiable pattern of rejections. The results also indicatea strong accuracy for Support Vector Machine and Logistic Regression across allthe datasets.
24
Andersson, Melanie, Arvola Maja, and Sara Hedar. "Sketch Classification with Neural Networks : A Comparative Study of CNN and RNN on the Quick, Draw! data set." Thesis, Uppsala universitet, Institutionen för teknikvetenskaper, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-353504.
Full textAbstract:
The aim of the study is to apply and compare the performance of two different types of neural networks on the Quick, Draw! dataset and from this determine whether interpreting the sketches as sequences gives a higher accuracy than interpreting them as pixels. The two types of networks constructed were a recurrent neural network (RNN) and a convolutional neural network (CNN). The networks were optimised and the final architectures included five layers. The final evaluation accuracy achieved was 94.2% and 92.3% respectively, leading to the conclusion that the sequential interpretation of the Quick, Draw! dataset is favourable.
25
Bolstad, K. S. "Systematics of the Onychoteuthidae Gray, 1847 (Cephalopoda: Oegopsida) a thesis submitted to the Earth & Oceanic Sciences Research Institute, Auckland University of Technology in fulfilment of the requirements for the degree of Doctor of Philosophy, supervised by Dr Steve O'Shea, 2008." Click here to access this resource online, 2008. http://hdl.handle.net/10292/414.
Full text
26
Hunsche, Sandra. "PROFESSOR FAZEDOR DE CURRÍCULOS: DESAFIOS NO ESTÁGIO CURRICULAR SUPERVISIONADO EM ENSINO DE FÍSICA." Universidade Federal de Santa Maria, 2010. http://repositorio.ufsm.br/handle/1/6909.
Full textAbstract:
Fundação de Apoio à Pesquisa Científica e Tecnológica do Estado de Santa CatarinaIn the face of current educational problems, indicated by research, as the propedeutic education and the separation between the "world of life" and the "world of school," the conception of science and technology neutral, among others, it is necessary to "make changes" in curriculum. Moreover, it is argued that teachers should be part of the process of curriculum reconfiguration. So, in this research, it is looked for identify and critically analyze challenges and potential faced by trainees in physics in the process of reconfiguring a curriculum guided by the approach of social themes marked by the Science and Technology. More specifically, focus on the elaboration and implementation of themes under the Supervised Internship Course in Teaching of Physics. The structure of these themes is referenced by an approximation of the presuppositions of the educator Paulo Freire and the Science-Technology-Society movement (CTS). The research problem is characterized by the following questions: 1) What dimensions the school context influences the execution of curriculum reconfigurations based on themes? 2) What are the constraints that the training of future teachers, has in the process of elaboration/implementation of themes? The research, entered on the Research Line called School Practice and Public Policies (PPGE/UFSM), is developed according to the dynamics of participative research. The instruments to obtain the "data" were used the Teacher's Journal, a semi-structured interviews and analysis of reportsfiled by the student teacher. The analysis was done using content analysis. The results were organized under four thematic categories: Training Fragmented; From Rigor" to the Curricular Flexibility; Real Problems and Epistemological Curiosity, and Student Problem or Curriculum Problem?.
Frente a atuais problemas educacionais, apontados pelas pesquisas, como o ensino propedêutico, a desvinculação entre o mundo da vida e o mundo da escola , a concepção de ciência e tecnologia neutras, entre outros, considera-se necessário mexer no currículo. Além disto, defende-se que os professores devem fazer parte do processo de reconfiguração curricular. Neste sentido, busca-se, nesta pesquisa, identificar e analisar criticamente desafios e potencialidades encontradas por estagiários de Física, no processo de uma reconfiguração curricular pautada pela abordagem de temas sociais marcados pela Ciência-Tecnologia. Mais especificamente, focalizar a elaboração e implementação de temáticas no âmbito do Estágio Curricular Supervisionado em Ensino de Física. A estruturação destas temáticas é referenciada por uma aproximação entre pressupostos do educador Paulo Freire e do movimento Ciência-Tecnologia-Sociedade (CTS). O problema de investigação é caracterizado pelas seguintes questões: 1) Em que dimensões o contexto escolar influencia a efetivação de reconfigurações curriculares baseadas em temáticas? 2) Quais os condicionamentos que a formação, destes futuros professores, exerce no processo de elaboração/implementação de temáticas? A pesquisa, inserida na Linha de Pesquisa Práticas Escolares e Políticas Públicas (PPGE/UFSM), é desenvolvida segundo a dinâmica da Pesquisa Participante. Como instrumentos, para a obtenção dos dados , foram utilizados o Diário do Professor, uma entrevista semi-estruturada e a análise dos relatórios entregues pelos estagiários. Em termos de análise, fez-se uso da análise de conteúdo. Os resultados foram sistematizados sob quatro categorias temáticas: Formação Fragmentada; Do Rigor à Flexibilidade Curricular; Problemas Reais e Curiosidade Epistemológica; e Aluno Problema ou Currículo Problema?.
27
Sörman, Paulsson Elsa. "Evaluation of In-Silico Labeling for Live Cell Imaging." Thesis, Umeå universitet, Institutionen för fysik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-180590.
Full textAbstract:
Today new drugs are tested on cell cultures in wells to minimize time, cost, andanimal testing. The cells are studied using microscopy in different ways and fluorescentprobes are used to study finer details than the light microscopy can observe.This is an invasive method, so instead of molecular analysis, imaging can be used.In this project, phase-contrast microscopy images of cells together with fluorescentmicroscopy images were used. We use Machine Learning to predict the fluorescentimages from the light microscopy images using a strategy called In-Silico Labeling.A Convolutional Neural Network called U-Net was trained and showed good resultson two different datasets. Pixel-wise regression, pixel-wise classification, andimage classification with one cell in each image was tested. The image classificationwas the most difficult part due to difficulties assigning good quality labels tosingle cells. Pixel-wise regression showed the best result.
28
Araujo, Izabel Cristina de 1966. "Desenvolvimento de uma proposta didático-pedagógica para ambiente virtual de aprendizagem assistida por computador." [s.n.], 2013. http://repositorio.unicamp.br/jspui/handle/REPOSIP/319168.
Full textAbstract:
Orientador: Sérgio Ferreira do AmaralTese (doutorado) - Universidade Estadual de Campinas, Faculdade de Educação
Made available in DSpace on 2018-08-25T19:14:27Z (GMT). No. of bitstreams: 1 Araujo_IzabelCristinade_D.pdf: 4104644 bytes, checksum: b2e270b8879cdf763e6800edb77559f1 (MD5) Previous issue date: 2013
Resumo: Essa pesquisa tem como objetivo geral desenvolver uma proposta didático-pedagógica para ambiente virtual de aprendizagem assistida por computador (AAC). Os objetivos específicos situam-se em: identificar referenciais didático-pedagógicos junto à literatura e especialistas da área, construir um quadro indicativo dos referenciais didático-pedagógicos de ambiente virtual de AAC e sistematizar os referenciais encontrados, agrupando-os em unidades de análise para composição das diretrizes norteadoras do desenvolvimento da proposta didático-pedagógica. O problema da pesquisa apresentou-se em: Como referenciais didático-pedagógicos podem nortear ações educativas em ambientes virtuais de AAC? Realizamos trabalho de campo com levantamento e revisão da literatura, anotações em diário de campo advindas da observação em campo e entrevista semi-estruturada. Tivemos a participação de 36 pesquisadores de diferentes universidades americanas, asiáticas, europeias e da Oceania. A análise dos dados de predominância qualitativa norteou as conclusões, quais sejam: que o investimento em pesquisa na área de educação com inovação tecnológica proporciona resultados práticos, impactando na formulação de políticas públicas e na formação de professores; a relevância da autoria do professor na ação educativa em ambiente virtual de AAC; o professor-autor como mediador da aprendizagem; as destrezas e os conhecimentos necessários para utilizar os materiais de ambiente de AAC se apresentam mais eficazes se autores e coautores contarem com formação básica para a utilização das ferramentas tecnológicas. Daí a importância de fazê-lo gradualmente para que sejam capazes de aumentar seu nível de autonomia frente a sua própria aprendizagem.Essa pesquisa tem como objetivo geral desenvolver uma proposta didático-pedagógica para ambiente virtual de aprendizagem assistida por computador (AAC). Os objetivos específicos situam-se em: identificar referenciais didático-pedagógicos junto à literatura e especialistas da área, construir um quadro indicativo dos referenciais didático-pedagógicos de ambiente virtual de AAC e sistematizar os referenciais encontrados, agrupando-os em unidades de análise para composição das diretrizes norteadoras do desenvolvimento da proposta didático-pedagógica. O problema da pesquisa apresentou-se em: Como referenciais didático-pedagógicos podem nortear ações educativas em ambientes virtuais de AAC? Realizamos trabalho de campo com levantamento e revisão da literatura, anotações em diário de campo advindas da observação em campo e entrevista semi-estruturada. Tivemos a participação de 36 pesquisadores de diferentes universidades americanas, asiáticas, europeias e da Oceania. A análise dos dados de predominância qualitativa norteou as conclusões, quais sejam: que o investimento em pesquisa na área de educação com inovação tecnológica proporciona resultados práticos, impactando na formulação de políticas públicas e na formação de professores; a relevância da autoria do professor na ação educativa em ambiente virtual de AAC; o professor-autor como mediador da aprendizagem; as destrezas e os conhecimentos necessários para utilizar os materiais de ambiente de AAC se apresentam mais eficazes se autores e coautores contarem com formação básica para a utilização das ferramentas tecnológicas. Daí a importância de fazê-lo gradualmente para que sejam capazes de aumentar seu nível de autonomia frente a sua própria aprendizagem
Abstract: The overall goal of this research work is to develop a didactic proposal for Computer Assisted Learning (CAL) environments. The specific goals are: to identify the didactic requirements from both the literature and the specialists in the field; to build a conceptual framework of the didactic requirements of a virtual CAL environment; and to organize the requirements found by creating categories based on units of analysis so as to build up the main requirements of the development of a teaching proposal. The main concern was: How can pedagogical criteria set the foundations for sound educational actions in computer-assisted learning environments? 36 researchers from different universities in America, Asia, Europe and Australia participated in the research. The data analysis led to the following conclusions: a) the investment in research in the field of technology-enhanced teaching and learning leads to practical results which in turn foster the emergence of public policies and the improvement of teacher training; b) the relevance of teacher authorship in education in virtual CAL environments should be pointed out, the starting point being the social and cultural environment of the school where the teaching-learning process takes place; c) the role of the teacher-author as a mediator in learning should be borne in mind; d) the skills and knowledge needed when using the materials of a CAL environment become more effective when used by authors and co-authors trained in the use of technological tools. This means that it is important to provide authors and co-authors with the opportunity to develop those competences gradually so as to increase their level of autonomy regarding their own learning process
Doutorado
Ciencias Sociais na Educação
Doutora em Educação
29
Heidfors, Filip, and Elias Moltedo. "Maskininlärning: avvikelseklassificering på sekventiell sensordata. En jämförelse och utvärdering av algoritmer för att klassificera avvikelser i en miljövänlig IoT produkt med sekventiell sensordata." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20742.
Full textAbstract:
Ett företag har tagit fram en miljövänlig IoT produkt med sekventiell sensordata och vill genom maskininlärning kunna klassificera avvikelser i sensordatan. Det har genom åren utvecklats ett flertal väl fungerande algoritmer för klassificering men det finns emellertid ingen algoritm som fungerar bäst för alla olika problem. Syftet med det här arbetet var därför att undersöka, jämföra och utvärdera olika klassificerare inom "supervised machine learning" för att ta reda på vilken klassificerare som ger högst träffsäkerhet att klassificera avvikelser i den typ av IoT produkt som företaget tagit fram. Genom en litteraturstudie tog vi först reda på vilka klassificerare som vanligtvis använts och fungerat bra i tidigare vetenskapliga arbeten med liknande applikationer. Vi kom fram till att jämföra och utvärdera Random Forest, Naïve Bayes klassificerare och Support Vector Machines ytterligare. Vi skapade sedan ett dataset på 513 exempel som vi använde för träning och validering för respektive klassificerare. Resultatet visade att Random Forest hade betydligt högre träffsäkerhet med 95,7% jämfört med Naïve Bayes klassificerare (81,5%) och Support Vector Machines (78,6%). Slutsatsen för arbetet är att Random Forest med sina 95,7% ger en tillräckligt hög träffsäkerhet så att företaget kan använda maskininlärningsmodellen för att förbättra sin produkt. Resultatet pekar också på att Random Forest, för det här arbetets specifika klassificeringsproblem, är den klassificerare som fungerar bäst inom "supervised machine learning" men att det eventuellt finns möjlighet att få ännu högre träffsäkerhet med andra tekniker som till exempel "unsupervised machine learning" eller "semi-supervised machine learning".A company has developed a environment-friendly IoT device with sequential sensor data and want to use machine learning to classify anomalies in their data. Throughout the years, several well working algorithms for classifications have been developed. However, there is no optimal algorithm for every problem. The purpose of this work was therefore to investigate, compare and evaluate different classifiers within supervised machine learning to find out which classifier that gives the best accuracy to classify anomalies in the kind of IoT device that the company has developed. With a literature review we first wanted to find out which classifiers that are commonly used and have worked well in related work for similar purposes and applications. We concluded to further compare and evaluate Random Forest, Naïve Bayes and Support Vector Machines. We created a dataset of 513 examples that we used for training and evaluation for each classifier. The result showed that Random Forest had superior accuracy with 95.7% compared to Naïve Bayes (81.5%) and Support Vector Machines (78.6%). The conclusion for this work is that Random Forest, with 95.7%, gives a high enough accuracy for the company to have good use of the machine learning model. The result also indicates that Random Forest, for this thesis specific classification problem, is the best classifier within supervised machine learning but that there is a potential possibility to get even higher accuracy with other techniques such as unsupervised machine learning or semi-supervised machine learning.
30
Ferrer, Martínez Claudia. "Machine Learning for Solar Energy Prediction." Thesis, Högskolan i Gävle, Avdelningen för elektronik, matematik och naturvetenskap, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-27423.
Full textAbstract:
This thesis consists of the study of different Machine Learning models used to predict solar power data in photovoltaic plants. The process of implement a model of Machine Learning will be reviewed step by step: to collect the data, to pre-process the data in order to make it able to use as input for the model, to divide the data into training data and testing data, to train the Machine Learning algorithm with the training data, to evaluate the algorithm with the testing data, and to make the necessary changes to achieve the best results. The thesis will start with a brief introduction to solar energy in one part, and an introduction to Machine Learning in another part. The theory of different models and algorithms of supervised learning will be reviewed, such as Decision Trees, Naïve Bayer Classification, Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Linear Regression, Logistic Regression, Artificial Neural Network (ANN). Then, the methods Linear Regression, SVM Regression and Artificial Neural Network will be implemented using MATLAB in order to predict solar energy from historical data of photovoltaic plants. The data used to train and test the models is extracted from the National Renewable Energy Laboratory (NREL), that provides a dataset called “Solar Power Data for Integration Studies” intended for use by Project developers and university researchers. The dataset consist of 1 year of hourly power data for approximately 6000 simulated PV plants throughout the United States. Finally, once the different models have been implemented, the results show that the technique which provide the best results is Linear Regression.
31
Bosc, Guillaume. "Anytime discovery of a diverse set of patterns with Monte Carlo tree search." Thesis, Lyon, 2017. http://www.theses.fr/2017LYSEI074/document.
Full textAbstract:
La découverte de motifs qui caractérisent fortement une classe vis à vis d'une autre reste encore un problème difficile en fouille de données. La découverte de sous-groupes (Subgroup Discovery, SD) est une approche formelle de fouille de motifs qui permet la construction de classifieurs intelligibles mais surtout d'émettre des hypothèses sur les données. Cependant, cette approche fait encore face à deux problèmes majeurs : (i) comment définir des mesures de qualité appropriées pour caractériser l'intérêt d'un motif et (ii) comment sélectionner une méthode heuristique adaptée lorsqu’une énumération exhaustive de l'espace de recherche n'est pas réalisable. Le premier problème a été résolu par la fouille de modèles exceptionnels (Exceptional Model Mining, EMM) qui permet l'extraction de motifs couvrant des objets de la base de données pour lesquels le modèle induit sur les attributs de classe est significativement différent du modèle induit par l'ensemble des objets du jeu de données. Le second problème a été étudié en SD et EMM principalement avec la mise en place de méthodes heuristiques de type recherche en faisceau (beam-search) ou avec des algorithmes génétiques qui permettent la découverte de motifs non redondants, diversifiés et de bonne qualité. Dans cette thèse, nous soutenons que la nature gloutonne des méthodes d'énumération précédentes génère cependant des ensembles de motifs manquant de diversité. Nous définissons formellement la fouille de données comme un jeu que nous résolvons par l'utilisation de la recherche arborescente de Monte Carlo (Monte Carlo Tree Search, MCTS), une technique récente principalement utilisée pour la résolution de jeux et de problèmes de planning en intelligence artificielle. Contrairement aux méthodes traditionnelles d'échantillonnage, MCTS donne la possibilité d'obtenir une solution à tout instant sans qu'aucune hypothèse ne soit faite que ce soit sur la mesure de qualité ou sur les données. Cette méthode d'énumération converge vers une approche exhaustive si les budgets temps et mémoire disponibles sont suffisants. Le compromis entre l'exploration et l'exploitation que propose cette approche permet une augmentation significative de la diversité dans l'ensemble des motifs calculés. Nous montrons que la recherche arborescente de Monte Carlo appliquée à la fouille de motifs permet de trouver rapidement un ensemble de motifs diversifiés et de bonne qualité à l'aide d'expérimentations sur des jeux de données de référence et sur un jeu de données réel traitant de l'olfaction. Nous proposons et validons également une nouvelle mesure de qualité spécialement conçue pour des jeux de donnée multi labels présentant une grande variance de fréquences des labelsThe discovery of patterns that strongly distinguish one class label from another is still a challenging data-mining task. Subgroup Discovery (SD) is a formal pattern mining framework that enables the construction of intelligible classifiers, and, most importantly, to elicit interesting hypotheses from the data. However, SD still faces two major issues: (i) how to define appropriate quality measures to characterize the interestingness of a pattern; (ii) how to select an accurate heuristic search technique when exhaustive enumeration of the pattern space is unfeasible. The first issue has been tackled by Exceptional Model Mining (EMM) for discovering patterns that cover tuples that locally induce a model substantially different from the model of the whole dataset. The second issue has been studied in SD and EMM mainly with the use of beam-search strategies and genetic algorithms for discovering a pattern set that is non-redundant, diverse and of high quality. In this thesis, we argue that the greedy nature of most such previous approaches produces pattern sets that lack diversity. Consequently, we formally define pattern mining as a game and solve it with Monte Carlo Tree Search (MCTS), a recent technique mainly used for games and planning problems in artificial intelligence. Contrary to traditional sampling methods, MCTS leads to an any-time pattern mining approach without assumptions on either the quality measure or the data. It converges to an exhaustive search if given enough time and memory. The exploration/exploitation trade-off allows the diversity of the result set to be improved considerably compared to existing heuristics. We show that MCTS quickly finds a diverse pattern set of high quality in our application in neurosciences. We also propose and validate a new quality measure especially tuned for imbalanced multi-label data
32
Buttar, Sarpreet Singh. "Applying Machine Learning to Reduce the Adaptation Space in Self-Adaptive Systems : an exploratory work." Thesis, Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-77201.
Full textAbstract:
Self-adaptive systems are capable of autonomously adjusting their behavior at runtime to accomplish particular adaptation goals. The most common way to realize self-adaption is using a feedback loop(s) which contains four actions: collect runtime data from the system and its environment, analyze the collected data, decide if an adaptation plan is required, and act according to the adaptation plan for achieving the adaptation goals. Existing approaches achieve the adaptation goals by using formal methods, and exhaustively verify all the available adaptation options, i.e., adaptation space. However, verifying the entire adaptation space is often not feasible since it requires time and resources. In this thesis, we present an approach which uses machine learning to reduce the adaptation space in self-adaptive systems. The approach integrates with the feedback loop and selects a subset of the adaptation options that are valid in the current situation. The approach is applied on the simulator of a self-adaptive Internet of Things application which is deployed in KU Leuven, Belgium. We compare our results with a formal model based self-adaptation approach called ActivFORMS. The results show that on average the adaptation space is reduced by 81.2% and the adaptation time by 85% compared to ActivFORMS while achieving the same quality guarantees.
33
Helle, Valeria, Andra-Stefania Negus, and Jakob Nyberg. "Improving armed conflict prediction using machine learning : ViEWS+." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-354845.
Full textAbstract:
Our project, ViEWS+, expands the software functionality of the Violence EarlyWarning System (ViEWS). ViEWS aims to predict the probabilities of armed conflicts in the next 36 months using machine learning. Governments and policy-makers may use conflict predictions to decide where to deliver aid and resources, potentially saving lives. The predictions use conflict data gathered by ViEWS, which includes variables like past conflicts, child mortality and urban density. The large number of variables raises the need for a selection tool to remove those that are irrelevant for conflict prediction. Before our work, the stakeholders used their experience and some guesswork to pick the variables, and the predictive function with its parameters. Our goals were to improve the efficiency, in terms of speed, and correctness of the ViEWS predictions. Three steps were taken. Firstly, we made an automatic variable selection tool. This helps researchers use fewer, more relevant variables, to save time and resources. Secondly, we compared prediction functions, and identified the best for the purpose of predicting conflict. Lastly, we tested how parameter values affect the performance of the chosen functions, so as to produce good predictions but also reduce the execution time. The new tools improved both the execution time and the predictive correctness of the system compared to the results obtained prior to our project. It is now nine times faster than before, and its correctness has improved by a factor of three. We believe our work leads to more accurate conflict predictions, and as ViEWS has strong connections to the European Union, we hope that decision makers can benefit from it when trying to prevent conflicts.I detta projekt, vilket vi valt att benämna ViEWS+, har vi förbättrat olika aspekter av ViEWS (Violence Early-Warning System), ett system som med maskinlärning försöker förutsäga var i världen väpnade konflikter kommer uppstå. Målet med ViEWS är att kunna förutsäga sannolikheten för konflikter så långt som 36 månader i framtiden. Målet med att förutsäga sannoliketen för konflikter är att politiker och beslutsfattare ska kunna använda dessa kunskaper för att förhindra dem. Indata till systemet är konfliktdata med ett stort antal egenskaper, så som tidigare konflikter, barnadödlighet och urbanisering. Dessa är av varierande användbarhet, vilket skapar ett behov för att sålla ut de som inte är användbara för att förutsäga framtida konflikter. Innan vårt projekt har forskarna som använder ViEWS valt ut egenskaper för hand, vilket blir allt svårare i och med att fler introduceras. Forskargruppen hade även ingen formell metodik för att välja parametervärden till de maskinlärningsfunktioner de använder. De valde parametrar baserat på erfarenhet och känsla, något som kan leda till onödigt långa exekveringstider och eventuellt sämre resultat beroende på funktionen som används. Våra mål med projektet var att förbättra systemets produktivitet, i termer av exekveringstid och säkerheten i förutsägelserna. För att uppnå detta utvecklade vi analysverktyg för att försöka lösa de existerande problemen. Vi har utvecklat ett verktyg för att välja ut färre, mer användbara, egenskaper från datasamlingen. Detta gör att egenskaper som inte tillför någon viktig information kan sorteras bort vilket sparar exekveringstid. Vi har även jämfört prestandan hos olika maskinlärningsfunktioner, för att identifiera de bäst lämpade för konfliktprediktion. Slutligen har vi implementerat ett verktyg för att analysera hur resultaten från funktionerna varierar efter valet av parametrar. Detta gör att man systematiskt kan bestämma vilka parametervärden som bör väljas för att garantera bra resultat samtidigt som exekveringstid hålls nere. Våra resultat visar att med våra förbättringar sänkes exekveringstiden med en faktor av omkring nio och förutsägelseförmågorna höjdes med en faktor av tre. Vi hoppas att vårt arbete kan leda till säkrare föutsägelser och vilket i sin tur kanske leder till en fredligare värld.
34
Lannge, Jakob, and Ali Majed. "Classifying human activities through machine learning." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20115.
Full textAbstract:
Klassificering av dagliga aktiviteter (ADL) kan användas i system som bevakar människors aktiviteter i olika syften. T.ex., i nödsituationssystem. Med machine learning och bärbara sensor som samlar in data kan ADL klassificeras med hög noggrannhet. I detta arbete, ett proof-of-concept system med tre olika machine learning algoritmer utvärderas och jämförs mellan tre olika dataset, ett som är allmänt tillgängligt på (Ugulino, et al., 2012), och två som har samlats in i rapporten med hjälp av en android enhet. Algoritmerna som har använts är: Multiclass Decision Forest, Multiclass Decision Jungle and Multiclass Neural Network. Sensorerna som har använts är en accelerometer och ett gyroskop. Resultatet visar hur ett konceptuellt system kan byggas i Azure Machine Learning Studio, och hur tre olika algoritmer presterar vid klassificering av tre olika dataset. En algoritm visar högre precision vid klassning av Ugolino’s dataset, jämfört med machine learning modellen som ursprungligen används i rapporten.Classifying Activities of daily life (ADL) can be used in a system that monitor people’s activities for different purposes. For example, in emergency systems. Machine learning is a way to classify ADL with high accuracy, using wearable sensors as an input. In this paper, a proof-of-concept system consisting of three different machine learning algorithms is evaluated and compared between tree different datasets, one publicly available at (Ugulino, et al., 2012), and two collected in this paper using an android device’s accelerometer and gyroscope sensor. The algorithms are: Multiclass Decision Forest, Multiclass Decision Jungle and Multiclass Neural Network. The two sensors used are an accelerometer and a gyroscope. The result shows how a system can be implemented using Azure Machine Learning Studio, and how three different algorithms performs when classifying three different datasets. One algorithm achieves a higher accuracy compared to the machine learning model initially used with the Ugolino data set.
35
Na, Li. "Combination of supervised and unsupervised classifiers based on belief functions." Thesis, Rennes 1, 2020. http://www.theses.fr/2020REN1S041.
Full textAbstract:
La couverture terrestre se rapporte à la couverture biophysique de la surface terrestre de la Terre, identifiant ainsi la végétation, l’eau, le sol nu ou les surfaces imperméables, etc. L’identification de la couverture terrestre est essentielle pour la planification et la gestion des ressources naturelles (e.g. d développement, protection), la compréhension de la répartition des habitats ainsi que la modélisation des variables environnementales. L’identification des types de couverture terrestre fournit des informations de base pour la production d’autres cartes thématiques et établit une base de référence pour les activités de surveillance. Par conséquent, la classification de la couverture terrestre à l’aide de données satellitaires est l’une des applications les plus importantes de la télédétection. Une grande quantité d’informations au sol est généralement nécessaire pour générer une classification de la couverture terrestre de haute qualité. Toutefois, dans les zones naturelles complexes, la collecte d’informations au sol peut-être longue et extrêmement coûteuse. De nos jours, les technologies à capteurs multiples font l’objet d’une grande attention dans la classification de la couverture terrestre. Elles apportent des informations différentes et complémentaires des caractéristiques spectrales qui peuvent aider à surmonter les limitations causées par une information au sol inadéquate. Un autre problème causé par le manque d’informations au sol est l’ambiguïté des relations entre les cartes de la couverture des terres et les cartes d’utilisation des terres. Les cartes de l’occupation des sols fournissent des informations sur les caractéristiques naturelles qui peuvent-être directement observées à la surface de la Terre. Elle font également référence à la manière dont les gens utilisent les informations sur les paysages à fins différentes. Sans informations adéquates sur le terrain, il est difficile de produire des cartes d’utilisation des sols à partir des cartes de l’occupation des sols pour des zones complexes. Par conséquent, lorsque l’on combine plusieurs cartes hétérogènes de la couverture des sols, il faut envisager comment permettre aux utilisateurs de synthétiser le schéma des cartes d’utilisation des sols. Dans notre recherche, nous nous concentrons sur la fusion d’informations hétérogènes provenant de différentes sources. Le système de combinaison vise à résoudre les problèmes causés par le nombre limité d’ échantillon étiquetés et peut-être donc utilisé dans la classification de la couverture des terres pour les zones difficiles d’accès. Les étiquettes sémantiques pour la classification de l’occupation des sols provenant de chaque capteur peuvent être différentes et peuvent ne pas correspondre au schéma final d'étiquettes que les utilisateurs attendent. Par conséquent, un autre objectif de la combinaison est de fournir une interface avec un schéma final probablement diffèrent des cartes de l’occupation des sols d’entréeLand cover relates to the biophysical cover of the Earth’s terrestrial surface, identifying vegetation, water, bare soil, or impervious surfaces, etc. Identifying land cover is essential for planning and managing natural resources (e.g. development, protection), understanding the distribution of habitats, and for modeling environmental variables. Identification of land cover types provides basic information for the generation of other thematic maps and establishes a baseline for monitoring activities. Therefore, land cover classification using satellite data is one of the most important applications of remote sensing. A great deal of ground information (e.g. labeled samples) is usually required to generate high-quality land cover classification. However, in complex natural areas, collecting information on the ground can be time-consuming and extremely expensive. Nowadays, multiple sensor technologies have gained great attention in land cover classification. They bring different and complementary information—spectral characteristics that may help to overcome the limitations caused by inadequate ground information. In our research, we focus on the fusion of heterogeneous information from different sources. The combination system aims to solve the problems caused by limited labeled samples and can thus be used in land cover classification for hard-to-access areas. These mantic labels for the land cover classification from each sensor can be different, and may not corresponds to the final scheme of labels that users await. For instance, land cover classification methods of different sensors provide semantic labels for the ground. However, based on these land cover maps, an accessibility map is supposed to be generated to meet users’ needs. Therefore, another objective of the combination is to provide an interface with a final scheme probably different from the input land cover maps
36
Abou, El Houda Zakaria. "Security Enforcement through Software Defined Networks (SDN)." Thesis, Troyes, 2021. http://www.theses.fr/2021TROY0023.
Full textAbstract:
La conception originale d'Internet n'a pas pris en compte les aspects de sécurité du réseau, l’objectif prioritaire était de faciliter le processus de communication. Par conséquent, de nombreux protocoles de l'infrastructure Internet exposent un ensemble de vulnérabilités. Ces dernières peuvent être exploitées par les attaquants afin de mener un ensemble d’attaques. Les attaques par déni de service distribué (DDoS) représentent une grande menace; DDoS est l'une des attaques les plus dévastatrices causant des dommages collatéraux aux opérateurs de réseau ainsi qu'aux fournisseurs de services Internet. Les réseaux programmables (SDN) ont émergé comme un nouveau paradigme promettant de résoudre les limitations de l’architecture réseau actuelle en découplant le plan de contrôle du plan de données. D'une part, cette séparation permet un meilleur contrôle du réseau et apporte de nouvelles capacités pour mitiger les attaques par DDoS. D'autre part, cette séparation introduit de nouveaux défis en matière de sécurité du plan de contrôle. L’enjeu de cette thèse est double. D'une part, étudier et explorer l’apport du SDN à la sécurité afin de concevoir des solutions efficaces qui vont mitiger plusieurs vecteurs d’attaques. D'autre part, protéger le SDN contre ces attaques. À travers ce travail de recherche, nous contribuons à la mitigation des attaques par déni de service distribué sur deux niveaux (intra et inter-domaine), et nous contribuons au renforcement de la sécurité dans le SDNThe original design of Internet did not take into consideration security aspects of the network; the priority was to facilitate the process of communication. Therefore, many of the protocols that are part of the Internet infrastructure expose a set of vulnerabilities that can be exploited by attackers to carry out a set of attacks. Distributed Denial-of-Service (DDoS) represents a big threat and one of the most devastating and destructive attacks plaguing network operators and Internet service providers (ISPs) in stealthy way. Software defined networks (SDN) is an emerging technology that promises to solve the limitations of the conventional network architecture by decoupling the control plane from the data plane. On one hand, the separation of the control plane from the data plane allows for more control over the network and brings new capabilities to deal with DDoS attacks. On the other hand, this separation introduces new challenges regarding the security of the control plane. This thesis aims to deal with DDoS attacks while protecting the resources of the control plane. In this thesis, we contribute to the mitigation of both intra-domain and inter-domain DDoS attacks, and we contribute to the reinforcement of security aspects in SDN
37
O’Neil, Kason, Jennifer M. Krause, and Scott Douglas. "University Supervisor Perceptions of Live Remote Supervision in Physical Education Teacher Education." Digital Commons @ East Tennessee State University, 2017. https://dc.etsu.edu/etsu-works/4048.
Full textAbstract:
With advancement in modern technology, it is now possible for student teaching supervisors to virtually observe lessons remotely through the use of live video remote supervision. This innovation requires less overall funding (i.e., travel costs) and allows for highly qualified university professionals to provide direct feedback to student teachers. A phenomenological case-study approach was used to explore university supervisors’ perceptions and experiences with live remote supervision. Data from post-observation survey logs and a culminating focus group were collected from current physical education teacher education (PETE) program university supervisors (n = 3) from two separate higher education institutions. An interpretive phenomenological analysis (IPA) was conducted to best find meaning in the participants’ personal experiences. Qualitative results showed: (a) the iPad’s field of vision restricted the university supervisor from viewing all student teacher actions, though this was offset by increased ability to hear teacher through the Bluetooth, (b) initial and continual connectivity was problematic at times, (c) university supervisors rated the ability to hear every word the student teacher says to be very helpful (even more so than in live observations), (d) supervisors rated the quality of pre/post conferences and quality of observation to be high, though (e) this format did lose some of the personal touch of on-site visits. The findings suggest that remote supervision may prove to be a practical and cost-efficient way to facilitate supervision of field experiences in physical education and can potentially help shift towards a new paradigm of supervision in teacher education.
38
Brorson, Erik. "Classifying Hate Speech using Fine-tuned Language Models." Thesis, Uppsala universitet, Statistiska institutionen, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-352637.
Full textAbstract:
Given the explosion in the size of social media, the amount of hate speech is also growing. To efficiently combat this issue we need reliable and scalable machine learning models. Current solutions rely on crowdsourced datasets that are limited in size, or using training data from self-identified hateful communities, that lacks specificity. In this thesis we introduce a novel semi-supervised modelling strategy. It is first trained on the freely available data from the hateful communities and then fine-tuned to classify hateful tweets from crowdsourced annotated datasets. We show that our model reach state of the art performance with minimal hyper-parameter tuning.
39
Mathonat, Romain. "Rule discovery in labeled sequential data : Application to game analytics." Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEI080.
Full textAbstract:
Exploiter des jeux de données labelisés est très utile, non seulement pour entrainer des modèles et mettre en place des procédures d'analyses prédictives, mais aussi pour améliorer la compréhension d'un domaine. La découverte de sous-groupes a été l'objet de recherches depuis deux décennies. Elle consiste en la découverte de règles couvrants des ensembles d'objets ayant des propriétés intéressantes, qui caractérisent une classe cible donnée. Bien que de nombreux algorithmes de découverte de sous-groupes aient été proposés à la fois dans le cas des données transactionnelles et numériques, la découverte de règles dans des données séquentielles labelisées a été bien moins étudiée. Dans ce contexte, les stratégies d'exploration exhaustives ne sont pas applicables à des cas d'application rééls, nous devons donc nous concentrer sur des approches heuristiques. Dans cette thèse, nous proposons d'appliquer des modèles de bandit manchot ainsi que la recherche arborescente de Monte Carlo à l'exploration de l'espace de recherche des règles possibles, en utilisant un compromis exploration-exploitation, sur différents types de données tels que les sequences d'ensembles d'éléments, ou les séries temporelles. Pour un budget temps donné, ces approches trouvent un ensemble des top-k règles decouvertes, vis-à-vis de la mesure de qualité choisie. De plus, elles ne nécessitent qu'une configuration légère, et sont indépendantes de la mesure de qualité utilisée. A notre connaissance, il s'agit de la première application de la recherche arborescente de Monte Carlo au cas de la fouille de données séquentielles labelisées. Nous avons conduit des études appronfondies sur différents jeux de données pour illustrer leurs plus-values, et discuté leur résultats quantitatifs et qualitatifs. Afin de valider le bon fonctionnement d'un de nos algorithmes, nous proposons un cas d'utilisation d'analyse de jeux vidéos, plus précisémment de matchs de Rocket League. La decouverte de règles intéressantes dans les séquences d'actions effectuées par les joueurs et leur exploitation dans un modèle de classification supervisée montre l'efficacité et la pertinence de notre approche dans le contexte difficile et réaliste des données séquentielles de hautes dimensions. Elle permet la découverte automatique de techniques de jeu, et peut être utilisée afin de créer de nouveaux modes de jeu, d'améliorer le système de classement, d'assister les commentateurs de "e-sport", ou de mieux analyser l'équipe adverse en amont, par exempleIt is extremely useful to exploit labeled datasets not only to learn models and perform predictive analytics but also to improve our understanding of a domain and its available targeted classes. The subgroup discovery task has been considered for more than two decades. It concerns the discovery of rules covering sets of objects having interesting properties, e.g., they characterize a given target class. Though many subgroup discovery algorithms have been proposed for both transactional and numerical data, discovering rules within labeled sequential data has been much less studied. In that context, exhaustive exploration strategies can not be used for real-life applications and we have to look for heuristic approaches. In this thesis, we propose to apply bandit models and Monte Carlo Tree Search to explore the search space of possible rules using an exploration-exploitation trade-off, on different data types such as sequences of itemset or time series. For a given budget, they find a collection of top-k best rules in the search space w.r.t chosen quality measure. They require a light configuration and are independent from the quality measure used for pattern scoring. To the best of our knowledge, this is the first time that the Monte Carlo Tree Search framework has been exploited in a sequential data mining setting. We have conducted thorough and comprehensive evaluations of our algorithms on several datasets to illustrate their added-value, and we discuss their qualitative and quantitative results. To assess the added-value of one or our algorithms, we propose a use case of game analytics, more precisely Rocket League match analysis. Discovering interesting rules in sequences of actions performed by players and using them in a supervised classification model shows the efficiency and the relevance of our approach in the difficult and realistic context of high dimensional data. It supports the automatic discovery of skills and it can be used to create new game modes, to improve the ranking system, to help e-sport commentators, or to better analyse opponent teams, for example
40
Benammar, Riyadh. "Détection non-supervisée de motifs dans les partitions musicales manuscrites." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI112.
Full textAbstract:
Cette thèse s'inscrit dans le contexte de la fouille de données appliquées aux partitions musicales manuscrites anciennes et vise une recherche de motifs mélodiques ou rythmiques fréquents définis comme des séquences de notes répétitives aux propriétés caractéristiques. On rencontre un grand nombre de déclinaisons possibles de motifs : les transpositions, les inversions et les motifs dits « miroirs ». Ces motifs permettent aux musicologues d'avoir un niveau d'analyse approfondi sur les œuvres d'un compositeur ou d'un style musical. Dans un contexte d'exploration de corpus de grande taille où les partitions sont juste numérisées et non transcrites, une recherche automatisée de motifs vérifiant des contraintes ciblées devient un outil indispensable à leur étude. Pour la réalisation de l'objectif de détection de motifs fréquents sans connaissance a priori, nous sommes partis d'images de partitions numérisées. Après des étapes de prétraitements sur l'image, nous avons exploité et adapté un modèle de détection et de reconnaissance de primitives musicales (tête de notes, hampes...) de la famille de réseaux de neurones à convolutions de type Region-Proposal CNN (RPN). Nous avons ensuite développé une méthode d'encodage de primitives pour générer une séquence de notes en évitant la tâche complexe de transcription complète de l'œuvre manuscrite. Cette séquence a ensuite été analysée à travers l'approche CSMA (Contraint String Mining Algorithm) que nous avons conçue pour détecter les motifs fréquents présents dans une ou plusieurs séquences avec une prise en compte de contraintes sur leur fréquence et leur taille, ainsi que la taille et le nombre de sauts autorisés (gaps) à l'intérieur des motifs. La prise en compte du gap a ensuite été étudiée pour contourner les erreurs de reconnaissance produites par le réseau RPN évitant ainsi la mise en place d'un système de post-correction des erreurs de transcription des partitions. Le travail a été finalement validé par l'étude des motifs musicaux pour des applications d'identification et de classification de compositeursThis thesis is part of the data mining applied to ancient handwritten music scores and aims at a search for frequent melodic or rhythmic motifs defined as repetitive note sequences with characteristic properties. There are a large number of possible variations of motifs: transpositions, inversions and so-called "mirror" motifs. These motifs allow musicologists to have a level of in-depth analysis on the works of a composer or a musical style. In a context of exploring large corpora where scores are just digitized and not transcribed, an automated search for motifs that verify targeted constraints becomes an essential tool for their study. To achieve the objective of detecting frequent motifs without prior knowledge, we started from images of digitized scores. After pre-processing steps on the image, we exploited and adapted a model for detecting and recognizing musical primitives (note-heads, stems...) from the family of Region-Proposal CNN (RPN) convolution neural networks. We then developed a primitive encoding method to generate a sequence of notes without the complex task of transcribing the entire manuscript work. This sequence was then analyzed using the CSMA (Constraint String Mining Algorithm) approach designed to detect the frequent motifs present in one or more sequences, taking into account constraints on their frequency and length, as well as the size and number of gaps allowed within the motifs. The gap was then studied to avoid recognition errors produced by the RPN network, thus avoiding the implementation of a post-correction system for transcription errors. The work was finally validated by the study of musical motifs for composers identification and classification
41
Diedericks, Elsabé. "Flourishing of employees in the information technology industry in South Africa / Elsabé Diedericks." Thesis, North-West University, 2012. http://hdl.handle.net/10394/10278.
Full textAbstract:
Organisations worldwide are experiencing an explosion of knowledge in the current technological information age as well as a serious skills shortage. The fast-paced aggressive and highly cyclical nature of the profession which often does not provide employees with the necessary resources and support causes employees in the information technology (IT) industry to show high turnover intent which is extremely costly and detrimental to organisational success. IT specialists are becoming a scarce commodity in a highly competitive environment where financial gain is very important and employee well-being is not necessarily a prerogative. Employers are faced with additional obligations than just paying equitable salaries, such as creating an environment that is conducive towards well-being. Efforts to promote flourishing and optimal functioning of employees will affect individual and organisational outcomes. Flourishing and languishing are opposite end points on a continuum of mental health indicating the emotional, psychological and social well-being of individuals. An individual who feels well (emotional well-being) is more likely to function well (psychological and social well-being) which means meeting the criteria for positive mental health as flourishing. Investments in the well-being of employees lay the basis for positive employment relations. The aim of this study was to investigate the flourishing of employees in the information technology industry and to determine the antecedents and outcomes thereof. A cross-sectional survey design was used to gather data regarding the flourishing of IT professionals and its outcomes. A convenience sample (N = 205) was taken of employees in information technology organisations in South Africa. The measuring instruments used were the Mental Health Continuum Short Form, Job Satisfaction Scale, Work Engagement Scale, Work-related Basic Need Satisfaction Scale, Work Role Fit Scale, Psychological Contract Inventory, Violations of PC Questionnaire, Organisational Commitment Scale, Turnover Intention Scale and Counterproductive Work Behaviour measures. The results of study 1 showed that 58.5% of the IT professionals were neither languishing nor flourishing, while 3.9% were languishing. Flourishing strongly impacted job satisfaction and had minor to moderate direct and indirect effects on organisational citizenship behaviour and organisational commitment. Job satisfaction impacted directly and positively on organisational commitment and negatively on turnover intention; and moderately negatively on counterproductive behaviour. Flourishing had both a direct and positive effect, and an indirect and negative effect (via organisational commitment) on turnover intention. Study 2 showed that psychological contract breach and violation strongly and negatively impacted flourishing at work and in life. The results provided support for a model in which psychological contract breach and violation had both direct and indirect effects via satisfaction of psychological needs on job satisfaction, work engagement, turnover intention and flourishing of IT professionals. Study 3 showed that work role fit and the availability of resources were strong predictors of flourishing at work and in life. Work role fit, the availability of resources, and supervisor relations impacted job satisfaction and social well-being indirectly through autonomy satisfaction. The availability of resources impacted work engagement and psychological well-being indirectly via competence satisfaction. Furthermore, work role fit, the availability of resources, and supervisor relations impacted psychological well-being indirectly through relatedness. Recommendations for future research were made.PhD, Labour relations management, North-West University, Vaal Triangle Campus, 2012
42
Sköld, Martin. "Employee perspective on communication and engagement : A case study in a manufacturing organisation." Thesis, Luleå tekniska universitet, Institutionen för ekonomi, teknik och samhälle, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-75209.
Full textAbstract:
Purpose The purpose of this study was to gain a deeper understanding of how supervisor-employee communication affects the employee engagement on the shop floor of manufacturing organisations. To achieve this purpose, the two below research objectives were developed: To identify how supervisor-employee communication impacts employee engagement To identify any barriers to supervisor-employee communication Method The study had a deductive, qualitative research approach as a conceptual framework was developed from literature and then verified with empirical data collected through semi-structured interviews. The research strategy was holistic and single case as all eight interviews were conducted with respondents from a single organisation. The interviewees were selected using a maximum variation, purposive sampling technique. Lastly, the collected data was analysed using a form of thematic analysis. Findings The main finding was that supervisor-employee communication was proven to have a significant impact on the employee engagement among the shop floor workers in the manufacturing organisation. In addition, supervisor-employee communication was proven to affect the employee engagement in a similar way that literature suggested. Furthermore, the findings supported the definition of employee engagement as a shared responsibility between the employee and the supervisor. Theoretical implications This study provided additional data to the existing literature on supervisor-employee communication and employee engagement while investigating the relationship between these two concepts in a new setting. Not only did this study contribute with rather unique data from the manufacturing industry, but it also adopted the employee perspective of the phenomenon. Previous research has predominantly consisted of studies with the perspective of management rather than the employees. Therefore, this study offers a foundation upon which further, both qualitative and quantitative research within this area can be conducted. Practical implications The main practical implication that this study has offered is highlighting the importance of supervisor-employee communication when it comes to generating and maintaining employee engagement on the shop floor of manufacturing organisations. The supervisor’s role and way of communicating has been identified as crucial for the employees’ level of engagement and this study has provided some guidance for supervisors in this matter.
43
Dovgalecs, Vladislavs. "Indoor location estimation using a wearable camera with application to the monitoring of persons at home." Thesis, Bordeaux 1, 2011. http://www.theses.fr/2011BOR14384/document.
Full textAbstract:
L’indexation par le contenu de lifelogs issus de capteurs portées a émergé comme un enjeu à forte valeur ajoutée permettant l’exploitation de ces nouveaux types de donnés. Rendu plus accessible par la récente disponibilité de dispositifs miniaturisés d’enregistrement, les besoins pour l’extraction automatique d’informations pertinents générées par autres applications, la localisation en environnement intérieur est un problème difficile à l’analyse de telles données.Beaucoup des solutions existantes pour la localisation fonctionnent insuffisamment bien ou nécessitent une intervention important à l’intérieur de bâtiment. Dans cette thèse, nous abordons le problème de la localisation topologique à partir de séquences vidéo issues d’une camera portée en utilisant une approche purement visuelle. Ce travail complète d’extraction des descripteurs visuels de bas niveaux jusqu’à l’estimation finale de la localisation à l’aide d’algorithmes automatiques.Dans ce cadre, les contributions principales de ce travail ont été faites pour l’exploitation efficace des informations apportées par descripteurs visuels multiples, par les images non étiquetées et par la continuité temporelle de la vidéo. Ainsi, la fusion précoce et la fusion tardive des données visuelles ont été examinées et l’avantage apporté par la complémentarité des descripteurs visuels a été mis en évidence sur le problème de la localisation. En raison de difficulté à obtenir des données étiquetées en quantités suffisantes, l’ensemble des données a été exploité ; d’une part les approches de réduction de dimensionnalité non-linéaire ont été appliquées, afin d’améliorer la taille des données à traiter et la complexité associée ; d’autre part des approches semi-supervisés ont été étudiées pour utiliser l’information supplémentaire apportée par les images non étiquetées lors de la classification. Ces éléments ont été analysé séparément et on été mis en œuvre ensemble sous la forme d’une nouvelle méthode par co-apprentissage temporelle. Finalement nous avons également exploré la question de l’invariance des descripteurs, en proposant l’utilisation d’un apprentissage invariant à la transformation spatiale, comme un autre réponse possible un manque de données annotées et à la variabilité visuelle.Ces méthodes ont été évaluées sur des séquences vidéo en environnement contrôlé accessibles publiquement pour évaluer le gain spécifique de chaque contribution. Ce travail a également été appliqué dans le cadre du projet IMMED, qui concerne l’observation et l’indexation d’activités de la vie quotidienne dans un objectif d’aide au diagnostic médical, à l’aide d’une caméra vidéo portée. Nous avons ainsi pu mettre en œuvre le dispositif d’acquisition vidéo portée, et montrer le potentiel de notre approche pour l’estimation de la localisation topologique sur un corpus présentant des conditions difficiles représentatives des données réellesVisual lifelog indexing by content has emerged as a high reward application. Enabled by the recent availability of miniaturized recording devices, the demand for automatic extraction of relevant information from wearable sensors generated content has grown. Among many other applications, indoor localization is one challenging problem to be addressed.Many standard solutions perform unreliably in indoors conditions or require significant intervention. In this thesis we address from the perspective of wearable video camera sensors using an image-based approach. The key contribution of this work is the development and the study of a location estimation system composed of diverse modules, which perform tasks ranging from low-level visual information extraction to final topological location estimation with the aid of automatic indexing algorithms. Within this framework, important contributions have been made by efficiently leveraging information brought by multiple visual features, unlabeled image data and the temporal continuity of the video.Early and late data fusion were considered, and shown to take advantage of the complementarities of multiple visual features describing the images. Due to the difficulty in obtaining annotated data in our context, semi-supervised approaches were investigated, to use unlabeled data as additional source of information, both for non-linear data-adaptive dimensionality reduction, and for improving classification. Herein we have developed a time-aware co-training approach that combines late data-fusion with the semi-supervised exploitation of both unlabeled data and time information. Finally, we have proposed to apply transformation invariant learning to adapt non-invariant descriptors to our localization framework.The methods have been tested on controlled publically available datasets to evaluate the gain of each contribution. This work has also been applied to the IMMED project, dealing with activity recognition and monitoring of the daily living using a wearable camera. In this context, the developed framework has been used to estimate localization on the real world IMMED project video corpus, which showed the potential of the approaches in such challenging conditions
44
Frankenius, Joakim. "Från synt till drama : En kvalitativ fallstudie om den licensierade musikens narrativafunktioner i film." Thesis, Högskolan Dalarna, Ljud- och musikproduktion, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:du-27280.
Full textAbstract:
Populärmusik från film är något var person känner till och ibland lyssnar på dagligen. Men anledningarna till varför den sagda musiken blir vald står ofta obesvarat. Vilka funktioner har musiken, kallad licensierad musik, i film? För att analysera och förstå musikens funktioner bör en tackla frågorna runt ämnet ur en music supervisors perspektiv. Denna uppsats är en fallstudie som med en innehållsanalys analyserar den licensierade musiken i thrillern The Guest. Resultaten visar att musiken fyllde narrativa funktioner både som enskild låt för enskilda scener men även övergripande funktioner som etablerar plats, epok och karaktärers drag och utveckling.
45
Westerman, Christelle. "Work-related wellness of information technology professionals in South Africa / C. Westerman." Thesis, North-West University, 2005. http://hdl.handle.net/10394/2458.
Full text
46
Voisin, Aurélie. "Classification supervisée d'images d'observation de la Terre à haute résolution par utilisation de méthodes markoviennes." Phd thesis, Université de Nice Sophia-Antipolis, 2012. http://tel.archives-ouvertes.fr/tel-00747906.
Full textAbstract:
La classification d'images de télédétection incluant des zones urbaines permet d'établir des cartes d'utilisation du sol et/ou de couverture du sol, ou de zones endommagées par des phénomènes naturels (tremblements de terre, inondations...). Les méthodes de classification développées au cours de cette thèse sont des méthodes supervisées fondées sur des modèles markoviens. Une première approche a porté sur la classification d'images d'amplitudes issues de capteurs RSO (radar à synthèse d'ouverture) à simple polarisation et mono-résolution. La méthode choisie consiste à modéliser les statistiques de chacune des classes par des modèles de mélanges finis, puis à intégrer cette modélisation dans un champ de Markov. Afin d'améliorer la classification au niveau des zones urbaines, non seulement affectées par le bruit de chatoiement, mais aussi par l'hétérogénéité des matériaux qui s'y trouvent, nous avons extrait de l'image RSO un attribut de texture qui met en valeur les zones urbaines (typiquement, variance d'Haralick). Les statistiques de cette information texturelle sont combinées à celles de l'image initiale via des copules bivariées. Par la suite, nous avons cherché à améliorer la méthode de classification par l'utilisation d'un modèle de Markov hiérarchique sur quad-arbre. Nous avons intégré, dans ce modèle, une mise à jour de l'a priori qui permet, en pratique, d'aboutir à des résultats moins sensibles bruit de chatoiement. Les données mono-résolution sont décomposées hiérarchiquement en ayant recours à des ondelettes. Le principal avantage d'un tel modèle est de pouvoir utiliser des images multi-résolution et/ou multi-capteur et de pouvoir les intégrer directement dans l'arbre. En particulier, nous avons travaillé sur des données optiques (type GeoEye) et RSO (type COSMO-SkyMed) recalées. Les statistiques à chacun des niveaux de l'arbre sont modélisées par des mélanges finis de lois normales pour les images optiques et de lois gamma généralisées pour les images RSO. Ces statistiques sont ensuite combinées via des copules multivariées et intégrées dans le modèle hiérarchique. Les méthodes ont été testées et validées sur divers jeux de données mono-/multi-résolution RSO et/ou optiques.
47
Μαυρουδή, Σεφερίνα. "Combination of unsupervised and supervised learning for complex biomedical applications." Thesis, 2000. http://nemertes.lis.upatras.gr/jspui/handle/10889/3203.
Full text
48
Karmali, Tejan. "Landmark Estimation and Image Synthesis Guidance using Self-Supervised Networks." Thesis, 2022. https://etd.iisc.ac.in/handle/2005/5899.
Full textAbstract:
The exponential rise in the availability of data over the past decade has fuelled research in deep learning. While supervised deep learning models achieve near-human performance using annotated data, it comes with an additional cost of annotation. Additionally, there could be ambiguity in annotations due to human error. While an image classification task assigns one label to the whole image, as we increase the granularity of the task to landmark estimation, the annotator needs to pinpoint the landmark accurately. The self-supervised learning (SSL) paradigm overcomes these concerns by using pretext task based objectives to learn from large-scale unannotated data. In this work, we show how to extract relevant signals from pretrained self-supervised networks for a) a discriminative task of landmark estimation under limited annotations, and b) increasing perceptual quality of the images generated by generative adversarial network.
In this first part, we demonstrate the emergent correspondence tracking properties in the non-contrastive SSL framework. Using this as supervision, we propose LEAD which is an approach to discover landmarks from an unannotated collection of category-specific images. Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image, which are further used to learn landmarks in a semi-supervised manner. While there have been advances in self-supervised learning of image features for instance-level tasks like classification, these methods do not ensure dense equivariant representations. The property of equivariance is of interest for dense prediction tasks like landmark estimation. In this work, we introduce an approach to enhance the learning of dense equivariant representations in a self-supervised fashion. We follow a two-stage training approach: first, we train a network using the BYOL objective which operates at an instance level. The correspondences obtained through this network are further used to train a dense and compact representation of the image using a lightweight network. We show that having such a prior in the feature extractor helps in landmark detection, even under a drastically limited number of annotations while also improving generalization across scale variations.
Next, we utilize the rich feature space from the SSL framework as a “naturalness” prior to alleviate unnatural image generation from Generative Adversarial Networks (GAN), which is a popular class of generative models. Progress in GANs has enabled the generation of high-resolution photorealistic images of astonishing quality. StyleGANs allow for compelling attribute modification on such images via mathematical operations on the latent style vectors in the W/W+ space that effectively modulates the rich hierarchical representations of the generator. Such operations have recently been generalized beyond mere attribute swapping in the original StyleGAN paper to include interpolations. In spite of many significant improvements in StyleGANs, they are still seen to generate unnatural images. The quality of the generated images is a function of, (a) richness of the hierarchical representations learned by the generator, and, (b) linearity and smoothness of the style spaces. In this work, we propose Hierarchical Semantic Regularizer (HSR) which aligns the hierarchical representations learnt by the generator to corresponding powerful features learned by pretrained networks on large amounts of data. HSR not only improves generator representations but also the linearity and smoothness of the latent style spaces, leading to the generation of more natural-looking style-edited images. To demonstrate improved linearity, we propose a novel metric - Attribute Linearity Score (ALS). A significant reduction in the generation of unnatural images is corroborated by improvement in the Perceptual Path Length (PPL) metric by 15% across different standard datasets while simultaneously improving the linearity of attribute-change in the attribute editing tasks.
49
Lúcio, Simão Lopes. "Supervised Record Linkage For Banking Reconciliations." Master's thesis, 2020. https://hdl.handle.net/10216/133580.
Full text
50
Lúcio, Simão Lopes. "Supervised Record Linkage For Banking Reconciliations." Dissertação, 2020. https://hdl.handle.net/10216/133580.
Full text