To see the other types of publications on this topic, follow the link: Classification supervisée possibiliste.
Journal articles on the topic 'Classification supervisée possibiliste'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Classification supervisée possibiliste.'
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 journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Biondi, Riccardo, Nico Curti, Francesca Coppola, Enrico Giampieri, Giulio Vara, Michele Bartoletti, Arrigo Cattabriga, et al. "Classification Performance for COVID Patient Prognosis from Automatic AI Segmentation—A Single-Center Study." Applied Sciences 11, no. 12 (June 11, 2021): 5438. http://dx.doi.org/10.3390/app11125438.
Full textAbstract:
Background: COVID assessment can be performed using the recently developed individual risk score (prediction of severe respiratory failure in hospitalized patients with SARS-COV2 infection, PREDI-CO score) based on High Resolution Computed Tomography. In this study, we evaluated the possibility of automatizing this estimation using semi-supervised AI-based Radiomics, leveraging the possibility of performing non-supervised segmentation of ground-glass areas. Methods: We collected 92 from patients treated in the IRCCS Sant’Orsola-Malpighi Policlinic and public databases; each lung was segmented using a pre-trained AI method; ground-glass opacity was identified using a novel, non-supervised approach; radiomic measurements were collected and used to predict clinically relevant scores, with particular focus on mortality and the PREDI-CO score. We compared the prediction obtained through different machine learning approaches. Results: All the methods obtained a well-balanced accuracy (70%) on the PREDI-CO score but did not obtain satisfying results on other clinical characteristics due to unbalance between the classes. Conclusions: Semi-supervised segmentation, implemented using a combination of non-supervised segmentation and feature extraction, seems to be a viable approach for patient stratification and could be leveraged to train more complex models. This would be useful in a high-demand situation similar to the current pandemic to support gold-standard segmentation for AI training.
2
Madhu, Anjali, Anil Kumar, and Peng Jia. "Exploring Fuzzy Local Spatial Information Algorithms for Remote Sensing Image Classification." Remote Sensing 13, no. 20 (October 18, 2021): 4163. http://dx.doi.org/10.3390/rs13204163.
Full textAbstract:
Fuzzy c-means (FCM) and possibilistic c-means (PCM) are two commonly used fuzzy clustering algorithms for extracting land use land cover (LULC) information from satellite images. However, these algorithms use only spectral or grey-level information of pixels for clustering and ignore their spatial correlation. Different variants of the FCM algorithm have emerged recently that utilize local spatial information in addition to spectral information for clustering. Such algorithms are seen to generate clustering outputs that are more enhanced than the classical spectral-based FCM algorithm. Nonetheless, the scope of integrating spatial contextual information with the conventional PCM algorithm, which has several advantages over the FCM algorithm for supervised classification, has not been explored much. This study proposed integrating local spatial information with the PCM algorithm using simpler but proven approaches from available FCM-based local spatial information algorithms. The three new PCM-based local spatial information algorithms: Possibilistic c-means with spatial constraints (PCM-S), possibilistic local information c-means (PLICM), and adaptive possibilistic local information c-means (ADPLICM) algorithms, were developed corresponding to the available fuzzy c-means with spatial constraints (FCM-S), fuzzy local information c-means (FLICM), and adaptive fuzzy local information c-means (ADFLICM) algorithms. Experiments were conducted to analyze and compare the FCM and PCM classifier variants for supervised LULC classifications in soft (fuzzy) mode. The quantitative assessment of the soft classification results from fuzzy error matrix (FERM) and root mean square error (RMSE) suggested that the new PCM-based local spatial information classifiers produced higher accuracies than the PCM, FCM, or its local spatial variants, in the presence of untrained classes and noise. The promising results from PCM-based local spatial information classifiers suggest that the PCM algorithm, which is known to be naturally robust to noise, when integrated with local spatial information, has the potential to result in more efficient classifiers capable of better handling ambiguities caused by spectral confusions in landscapes.
3
Amiryousefi, Ali, Ville Kinnula, and Jing Tang. "Bayes in Wonderland! Predictive Supervised Classification Inference Hits Unpredictability." Mathematics 10, no. 5 (March 5, 2022): 828. http://dx.doi.org/10.3390/math10050828.
Full textAbstract:
The marginal Bayesian predictive classifiers (mBpc), as opposed to the simultaneous Bayesian predictive classifiers (sBpc), handle each data separately and, hence, tacitly assume the independence of the observations. Due to saturation in learning of generative model parameters, the adverse effect of this false assumption on the accuracy of mBpc tends to wear out in the face of an increasing amount of training data, guaranteeing the convergence of these two classifiers under the de Finetti type of exchangeability. This result, however, is far from trivial for the sequences generated under Partition Exchangeability (PE), where even umpteen amount of training data does not rule out the possibility of an unobserved outcome (Wonderland!). We provide a computational scheme that allows the generation of the sequences under PE. Based on that, with controlled increase of the training data, we show the convergence of the sBpc and mBpc. This underlies the use of simpler yet computationally more efficient marginal classifiers instead of simultaneous. We also provide a parameter estimation of the generative model giving rise to the partition exchangeable sequence as well as a testing paradigm for the equality of this parameter across different samples. The package for Bayesian predictive supervised classifications, parameter estimation and hypothesis testing of the Ewens sampling formula generative model is deposited on CRAN as PEkit package.
4
Singh, Abhishek, and Anil Kumar. "Introduction of Local Spatial Constraints and Local Similarity Estimation in Possibilistic c-Means Algorithm for Remotely Sensed Imagery." Journal of Modeling and Optimization 11, no. 1 (June 15, 2019): 51–56. http://dx.doi.org/10.32732/jmo.2019.11.1.51.
Full textAbstract:
This paper presents a unique Possibilistic c-Means with constraints (PCM-S) with Adaptive Possibilistic Local Information c-Means (ADPLICM) in a supervised way by incorporating local information through local spatial constraints and local similarity measures in Possibilistic c-Means Algorithm. PCM-S with ADPLICM overcome the limitations of the known Possibilistic c-Means (PCM) and Possibilistic c-Means with constraints (PCM-S) algorithms. The major contribution of proposed algorithm to ensure the noise resistance in the presence of random salt & pepper noise. The effectiveness of proposed algorithm has been analysed on random “salt and pepper” noise added on original dataset and Root Mean Square Error (RMSE) has been calculated between original dataset and noisy dataset. It has been observed that PCM-S with ADPLICM is effective in minimizing noise during supervised classification by introducing local convolution.
5
Jankowski, Maciej. "Deep Generative Model with Supervised Latent Space for Text Classification." MATEC Web of Conferences 292 (2019): 03009. http://dx.doi.org/10.1051/matecconf/201929203009.
Full textAbstract:
Recent advances in applying deep neural networks to Bayesian Modelling, sparked resurgence of in- terest in Variational Methods. Notably, the main contribution in this area is Reparametrization Trick introduced in [1] and [2]. VAE model [1], is unsupervised and therefore its application to classification is not optimal. In this work, we research the possibility to extend the model to supervised case. We first start with the model known as Supervised Variational Autoencoder that is researched in the literature in various forms [3] and [4]. We then modify objective function in such a way, that latent space can be better fitted to multiclass problem. Finally, we introduce a new method that uses information about classes to modify latent space, so it even better reflects differences between classes. All of this, will use only two dimensions. We will show, that mainstream classifiers applied to such a space, achieve significantly better performance than if applied to original datasets and VAE generated data. We also show, how our novel approach can be used to calculate better classification score, and how it can be used to generate data for a given class.
6
Adamiak, Krzysztof, Piotr Duch, and Krzysztof Ślot. "Object Classification Using Support Vector Machines with Kernel-based Data Preprocessing." Image Processing & Communications 21, no. 3 (September 1, 2016): 45–53. http://dx.doi.org/10.1515/ipc-2016-0015.
Full textAbstract:
Abstract The paper explores possibility of improving Support Vector Machine-based classification performance by introducing an input data dimensionality reduction step. Feature extraction by means of two different kernel methods are considered: kernel Principal Component Analysis (kPCA) and Supervised kernel Principal Component Analysis. It is hypothesized that input domain transformation, aimed at emphasizing between-class differences, would facilitate classification problem. Experiments, performed on three different datasets show that one can benefit from the proposed approach, as it provides lower variability in classification performance at similar, high recognition rates.
7
Jing-Yu, Chen, and Wang Ya-Jun. "Semi-Supervised Fake Reviews Detection based on AspamGAN." March 2022 4, no. 1 (March 30, 2022): 17–36. http://dx.doi.org/10.36548/jaicn.2022.1.002.
Full textAbstract:
With the popularization of social software and e-business in recent years, more and more consumers like to share their consumption experiences on social networks and refer to other consumers' reviews and opinions when making consumption decisions. Online reviews have become an essential part of browsing on websites such as shopping, and people's reliance on informative reviews have contributed to the rise of fake reviews. The traditional classification method is affected by the label dataset, which is not only time-consuming, laborious, and subjective, but also the extraction of artificial features also affects the classification accuracy. Due to the relative length of the online text, the possibility of the classifier losing important information increases, this weakens the model’s detection capability. To solve this aforementioned problem, a semi-supervised Generative Adversarial Network (AspamGAN) fake reviews detection method incorporating an attention mechanism is proposed. Using labeled and unlabeled data to correctly learn input distributions, the features required for classification are automatically discovered using deep neural networks, providing better prediction accuracy for online reviews. The approach includes attention mechanisms in the classifier to obtain an adequate semantic representation and relies on a limited dataset of labeled data to detect false reviews, and is applied on the TripAdvisor dataset. Experimental results show that the proposed algorithm outperforms state-of-the-art semi-supervised fake review detection techniques when the label dataset is limited.
8
Babushka, Andriy, Lyubov Babiy, Borys Chetverikov, and Andriy Sevruk. "GEODESY, CARTOGRAPHY AND AERIAL PHOTOGRAPHY." GEODESY, CARTOGRAPHY AND AERIAL PHOTOGRAPHY 94, 2021, no. 94 (December 28, 2021): 35–43. http://dx.doi.org/10.23939/istcgcap2021.94.035.
Full textAbstract:
Earth remote sensing and using the satellite images play an important role when monitoring the effects of forest fires and assessing damage. Applying different methods of multispectral space images processing, we can determine the risk of fire distribution, define hot spots and determine thermal parameters, mapping the damaged areas and assess the consequences of fire. The purpose of the work is the severity assessment connected with the post-fire period on the example of the forests in the Chornobyl Exclusion Zone. The tasks of the study are to define the area of burned zones using space images of different time which were obtained from the Sentinel-2 satellite applying the method of a normalized burn ratio (NBR) and method of supervised classification. Space images taken from the Sentinel-2 satellite before and after the fire were the input data for the study. Copernicus Open Access Hub service is a source of images and its spatial resolution is 10 m for visible and near infrared bands of images, and 20 m for medium infrared bands of images. We used method of Normalized Burn Ratio (NBR) and automatically calculated the area damaged with fire. Using this index we were able to identify areas of zones after active combustion. This index uses near and middle infrared bands for the calculations. In addition, a supervised classification was performed on the study area, and signature files were created for each class. According to the results of the classification, the areas of the territories damaged by the fire were also calculated. The scientific novelty relies upon the application of a method of using the normalized combustion coefficient (NBR) and supervised classification for space images obtained before and after the fire in the Chernobyl Exclusion Zone. The practical significance lies in the fact that the studied methods of GIS technologies can be used to identify territories and calculate the areas of vegetation damaged by fires. These results can be used by local organizations, local governments and the Ministry of Emergency Situations to monitor the condition and to plan reforestation. The normalized burned ratio (NBR) gives possibility efficiently and operatively to define and calculate the area which were damaged by fires, that gives possibility operatively assess the consequences of such fires and estimate the damage. The normalized burned ratio allows to calculate the area of burned forest almost 2 times more accurately than the supervised classification. The calculation process itself also takes less time and does not require additional procedures (set of signatures). Supervised classification in this case gives worse accuracy, the process itself is longer, but allows to determine the area of several different classes.
9
Mehta, Kushal, Arshita Jain, Jayalakshmi Mangalagiri, Sumeet Menon, Phuong Nguyen, and David R. Chapman. "Lung Nodule Classification Using Biomarkers, Volumetric Radiomics, and 3D CNNs." Journal of Digital Imaging 34, no. 3 (February 2, 2021): 647–66. http://dx.doi.org/10.1007/s10278-020-00417-y.
Full textAbstract:
AbstractWe present a hybrid algorithm to estimate lung nodule malignancy that combines imaging biomarkers from Radiologist’s annotation with image classification of CT scans. Our algorithm employs a 3D Convolutional Neural Network (CNN) as well as a Random Forest in order to combine CT imagery with biomarker annotation and volumetric radiomic features. We analyze and compare the performance of the algorithm using only imagery, only biomarkers, combined imagery + biomarkers, combined imagery + volumetric radiomic features, and finally the combination of imagery + biomarkers + volumetric features in order to classify the suspicion level of nodule malignancy. The National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) IDRI dataset is used to train and evaluate the classification task. We show that the incorporation of semi-supervised learning by means of K-Nearest-Neighbors (KNN) can increase the available training sample size of the LIDC-IDRI, thereby further improving the accuracy of malignancy estimation of most of the models tested although there is no significant improvement with the use of KNN semi-supervised learning if image classification with CNNs and volumetric features is combined with descriptive biomarkers. Unexpectedly, we also show that a model using image biomarkers alone is more accurate than one that combines biomarkers with volumetric radiomics, 3D CNNs, and semi-supervised learning. We discuss the possibility that this result may be influenced by cognitive bias in LIDC-IDRI because malignancy estimates were recorded by the same radiologist panel as biomarkers, as well as future work to incorporate pathology information over a subset of study participants.
10
Angulo-Saucedo, Gilbert A., Jersson X. Leon-Medina, Wilman Alonso Pineda-Muñoz, Miguel Angel Torres-Arredondo, and Diego A. Tibaduiza. "Damage Classification Using Supervised Self-Organizing Maps in Structural Health Monitoring." Sensors 22, no. 4 (February 15, 2022): 1484. http://dx.doi.org/10.3390/s22041484.
Full textAbstract:
Improvements in computing capacity have allowed computers today to execute increasingly complex tasks. One of the main benefits of these improvements is the possibility of developing machine learning algorithms, of which the fields of application are extensive and varied. However, an area in which this type of algorithms acquires an increasing relevance is structural health monitoring (SHM), where inspection strategies and guided wave-based approaches make the evaluation of the structural conditions of an aircraft, vessel or building among others possible, by detecting and classifying existing damages. The use of sensors, data acquisition systems (DAQ) and computation has also allowed these damage detection and classification tasks to be carried out automatically. Despite today’s advances, it is still necessary to continue with the development of more robust, reliable, and low-cost structural health monitoring systems. For this reason, this work contemplates three key points: (i) the configuration of a data acquisition system for signal gathering from an an active piezoelectric (PZT) sensor network; (ii) the development of a damage classification methodology based on signal processing techniques (normalization and PCA), from which the models that describe the structural conditions of the plate are built; and (iii) the use of machine learning algorithms, more specifically, three variants of the self-organizing maps called CPANN (counterpropagation artificial neural network), SKN (supervised Kohonen) and XYF (X–Y fused Kohonen). The data obtained allowed one to carry out an experimental validation of the damage classification methodology, to determine the presence of damages in two aluminum plates of different sizes, where masses were added to change the vibrational responses captured by the sensor network and a composite (CFRP) plate with real damages, such as delamination and cracks. This classification methodology allowed one to obtain excellent results by validating the usefulness of the SKN and XYF networks in damage classification tasks, showing overall accuracies of 73.75% and 72.5%, respectively, according to the cross-validation process. These percentages are higher than those obtained in comparison with other neural networks such as: kNN, discriminant analysis, classification trees, partial least square discriminant analysis, and backpropagation neural networks, when the cross-validation process was applied.
11
Andreeva, Elena E. "APPLICATION OF A RISK-ORIENTED MODEL FOR THE REDISTRIBUTION OF STAFFING RESOURCES OF THE OFFICE OF SERVICE FOR SUPERVISION OF CONSUMER RIGHTS PROTECTION AND HUMAN WELFARE IN THE CITY OF MOSCOW." Hygiene and sanitation 97, no. 5 (May 15, 2018): 441–44. http://dx.doi.org/10.18821/0016-9900-2018-97-5-441-444.
Full textAbstract:
The article shows the classification of the supervised objects of the Office of Service for Supervision of Consumer Rights Protection and Human Welfare in the city of Moscow depending on the index of the potential risk for harm to public health in the conditions of the application of the risk-oriented approach. There is considered the possibility of the control and surveillance activities with the redistribution of human resources of the Office of Service for Supervision of Consumer Rights Protection and Human Welfare in the city of Moscow with respect to supervised objects 1 and 2 classes of the potential risk for harm to the health of the population on the risk-oriented approach.
12
Mylona, Eleftheria, Vassiliki Daskalopoulou, Olga Sykioti, Konstantinos Koutroumbas, and Athanasios Rontogiannis. "Classification of Sentinel-2 Images Utilizing Abundance Representation." Proceedings 2, no. 7 (March 22, 2018): 328. http://dx.doi.org/10.3390/ecrs-2-05141.
Full textAbstract:
This paper deals with (both supervised and unsupervised) classification of multispectral Sentinel-2 images, utilizing the abundance representation of the pixels of interest. The latter pixel representation uncovers the hidden structured regions that are not often available in the reference maps. Additionally, it encourages class distinctions and bolsters accuracy. The adopted methodology, which has been successfully applied to hyperpsectral data, involves two main stages: (I) the determination of the pixel’s abundance representation; and (II) the employment of a classification algorithm applied to the abundance representations. More specifically, stage (I) incorporates two key processes, namely (a) endmember extraction, utilizing spectrally homogeneous regions of interest (ROIs); and (b) spectral unmixing, which hinges upon the endmember selection. The adopted spectral unmixing process assumes the linear mixing model (LMM), where each pixel is expressed as a linear combination of the endmembers. The pixel’s abundance vector is estimated via a variational Bayes algorithm that is based on a suitably defined hierarchical Bayesian model. The resulting abundance vectors are then fed to stage (II), where two off-the-shelf supervised classification approaches (namely nearest neighbor (NN) classification and support vector machines (SVM)), as well as an unsupervised classification process (namely the online adaptive possibilistic c-means (OAPCM) clustering algorithm), are adopted. Experiments are performed on a Sentinel-2 image acquired for a specific region of the Northern Pindos National Park in north-western Greece containing water, vegetation and bare soil areas. The experimental results demonstrate that the ad-hoc classification approaches utilizing abundance representations of the pixels outperform those utilizing the spectral signatures of the pixels in terms of accuracy.
13
Grilli, E., F. Poux, and F. Remondino. "UNSUPERVISED OBJECT-BASED CLUSTERING IN SUPPORT OF SUPERVISED POINT-BASED 3D POINT CLOUD CLASSIFICATION." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B2-2021 (June 28, 2021): 471–78. http://dx.doi.org/10.5194/isprs-archives-xliii-b2-2021-471-2021.
Full textAbstract:
Abstract. The number of approaches available for semantic segmentation of point clouds has grown exponentially in recent years. The availability of numerous annotated datasets has resulted in the emergence of deep learning approaches with increasingly promising outcomes. Even if successful, the implementation of such algorithms requires operators with a high level of expertise, large quantities of annotated data and high-performance computers. On the contrary, the purpose of this study is to develop a fast, light and user-friendly classification approach valid from urban to indoor or heritage scenarios. To this aim, an unsupervised object-based clustering approach is used to assist and improve a feature-based classification approach based on a standard machine learning predictive model. Results achieved over four different large scenarios demonstrate the possibility to develop a reliable, accurate and flexible approach based on a limited number of features and very few annotated data.
14
Mudinas, Andrius, Dell Zhang, and Mark Levene. "Bootstrap Domain-Specific Sentiment Classifiers from Unlabeled Corpora." Transactions of the Association for Computational Linguistics 6 (December 2018): 269–85. http://dx.doi.org/10.1162/tacl_a_00020.
Full textAbstract:
There is often the need to perform sentiment classification in a particular domain where no labeled document is available. Although we could make use of a general-purpose off-the-shelf sentiment classifier or a pre-built one for a different domain, the effectiveness would be inferior. In this paper, we explore the possibility of building domain-specific sentiment classifiers with unlabeled documents only. Our investigation indicates that in the word embeddings learned from the unlabeled corpus of a given domain, the distributed word representations (vectors) for opposite sentiments form distinct clusters, though those clusters are not transferable across domains. Exploiting such a clustering structure, we are able to utilize machine learning algorithms to induce a quality domain-specific sentiment lexicon from just a few typical sentiment words (“seeds”). An important finding is that simple linear model based supervised learning algorithms (such as linear SVM) can actually work better than more sophisticated semi-supervised/transductive learning algorithms which represent the state-of-the-art technique for sentiment lexicon induction. The induced lexicon could be applied directly in a lexicon-based method for sentiment classification, but a higher performance could be achieved through a two-phase bootstrapping method which uses the induced lexicon to assign positive/negative sentiment scores to unlabeled documents first, a nd t hen u ses those documents found to have clear sentiment signals as pseudo-labeled examples to train a document sentiment classifier v ia supervised learning algorithms (such as LSTM). On several benchmark datasets for document sentiment classification, our end-to-end pipelined approach which is overall unsupervised (except for a tiny set of seed words) outperforms existing unsupervised approaches and achieves an accuracy comparable to that of fully supervised approaches.
15
Baardman, Rolf H., and Rob F. Hegge. "Machine learning approaches for use in deblending." Leading Edge 39, no. 3 (March 2020): 188–94. http://dx.doi.org/10.1190/tle39030188.1.
Full textAbstract:
Machine learning has grown into a topic of much interest in the seismic industry. Recently, machine learning was introduced in the field of seismic processing for applications such as demultiple, regularization, and tomography. Here, two novel machine learning algorithms are introduced that can perform deblending and automated blending noise classification. Conventional deblending algorithms require a priori information and user expertise to properly select and parameterize a specific algorithm. The potential benefits of machine learning methods include their hands-off implementation and their ability to learn an efficient deblending algorithm directly from data. The introduced methods are supervised learning methods. Their specific tasks (deblending/noise classification) are learned from training data consisting of data example pairs of input and labeled output. For instance, training a deblending algorithm requires pairs of blended data with their unblended counterparts. The availability of training data or the possibility of creating training data are key to the success of these supervised methods. Another aspect is how well the algorithms generalize. Can we expect good performance on (unseen) data that vary from the training data? We address these aspects and further illustrate with synthetic and field data examples. The classification and deblending examples show promising results, indicating that these machine learning algorithms can support and/or replace existing deblending approaches.
16
Ayogu, I. I. "Exploring multinomial naïve Bayes for Yorùbá text document classification." Nigerian Journal of Technology 39, no. 2 (July 16, 2020): 528–35. http://dx.doi.org/10.4314/njt.v39i2.23.
Full textAbstract:
The recent increase in the emergence of Nigerian language text online motivates this paper in which the problem of classifying text documents written in Yorùbá language into one of a few pre-designated classes is considered. Text document classification/categorization research is well established for English language and many other languages; this is not so for Nigerian languages. This paper evaluated the performance of a multinomial Naive Bayes model learned on a research dataset consisting of 100 samples of text each from business, sporting, entertainment, technology and political domains, separately on unigram, bigram and trigram features obtained using the bag of words representation approach. Results show that the performance of the model over unigram and bigram features is comparable but significantly better than a model learned on trigram features. The results generally indicate a possibility for the practical application of NB algorithm to the classification of text documents written in Yorùbá language.
Keywords: Supervised learning, text classification, Yorùbá language, text mining, BoW Representation
17
ARMANO, GIULIANO, and FRANCESCO MASCIA. "A NOVEL METHOD FOR PARTITIONING FEATURE SPACES ACCORDING TO THEIR INHERENT CLASSIFICATION COMPLEXITY." International Journal of Pattern Recognition and Artificial Intelligence 27, no. 02 (March 2013): 1350007. http://dx.doi.org/10.1142/s0218001413500079.
Full textAbstract:
The evaluation of the intrinsic complexity of a supervised domain plays an important role in devising classification systems. Typically, the metrics used for this purpose produce an overall evaluation of the domain, without localizing the sources of complexity. In this work we propose a method for partitioning the feature space into subsets of different complexity. The most important outcome of the method is the possibility of preliminarily identifying hard and easy regions of the feature space. This possibility opens interesting theoretical and pragmatic scenarios, including the analysis of the classification error and the implementation of robust classification systems. A first group of experiments has been performed on synthetic datasets, devised to separately highlight specific and recurrent problems often found in real-world domains. In particular, the focus has been on class boundaries, noise, and density of samples. A second group of experiments, performed on selected real-world datasets, confirm the validity of the proposed method. The ultimate goal of our research is to devise a method for estimating the classification difficulty of a dataset. The proposed method makes a significant step in this direction, as it is able to partition a given dataset according to the inherent complexity of the samples contained therein.
18
Sabeti, Behnam, Hossein Abedi Firouzjaee, Reza Fahmi, Saeid Safavi, Wenwu Wang, and Mark D. Plumbley. "Credit Risk Rating Using State Machines and Machine Learning." International Journal of Trade, Economics and Finance 11, no. 6 (December 2020): 163–68. http://dx.doi.org/10.18178/ijtef.2020.11.6.683.
Full textAbstract:
Credit risk is the possibility of a loss resulting from a borrower’s failure to repay a loan or meet contractual obligations. With the growing number of customers and expansion of businesses, it’s not possible or at least feasible for banks to assess each customer individually in order to minimize this risk. Machine learning can leverage available user data to model a behavior and automatically estimate a credit score for each customer. In this research, we propose a novel approach based on state machines to model this problem into a classical supervised machine learning task. The proposed state machine is used to convert historical user data to a credit score which generates a data-set for training supervised models. We have explored several classification models in our experiments and illustrated the effectiveness of our modeling approach.
19
Rajendran, Sangeetha, and B. Kalpana. "Improvised Admissible Kernel Function for Support Vector Machines in Banach Space for Multiclass Data." INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY 11, no. 2 (October 10, 2013): 2273–78. http://dx.doi.org/10.24297/ijct.v11i2.1173.
Full textAbstract:
Classification based on supervised learning theory is one of the most significant tasks frequently accomplished by so-called Intelligent Systems. Contrary to the traditional classification techniques that are used to validate or contradict a predefined hypothesis, kernel based classifiers offer the possibility to frame new hypotheses using statistical learning theory (Sangeetha and Kalpana, 2010). Support Vector Machine (SVM) is a standard kernel based learning algorithm where it improves the learning ability through experience. It is highly accurate, robust and optimal kernel based classification technique that is well-suited to many real time applications. In this paper, kernel functions related to Hilbert space and Banach Space are explained. Here, the experimental results are carried out using benchmark multiclass datasets which are taken from UCI Machine Learning Repository and their performance are compared using various metrics like support vector, support vector percentage, training time and accuracy.
20
Waleed, Muhammad, Tai-Won Um, Tariq Kamal, and Syed Muhammad Usman. "Classification of Agriculture Farm Machinery Using Machine Learning and Internet of Things." Symmetry 13, no. 3 (March 1, 2021): 403. http://dx.doi.org/10.3390/sym13030403.
Full textAbstract:
In this paper, we apply the multi-class supervised machine learning techniques for classifying the agriculture farm machinery. The classification of farm machinery is important when performing the automatic authentication of field activity in a remote setup. In the absence of a sound machine recognition system, there is every possibility of a fraudulent activity taking place. To address this need, we classify the machinery using five machine learning techniques—K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) and Gradient Boosting (GB). For training of the model, we use the vibration and tilt of machinery. The vibration and tilt of machinery are recorded using the accelerometer and gyroscope sensors, respectively. The machinery included the leveler, rotavator and cultivator. The preliminary analysis on the collected data revealed that the farm machinery (when in operation) showed big variations in vibration and tilt, but observed similar means. Additionally, the accuracies of vibration-based and tilt-based classifications of farm machinery show good accuracy when used alone (with vibration showing slightly better numbers than the tilt). However, the accuracies improve further when both (the tilt and vibration) are used together. Furthermore, all five machine learning algorithms used for classification have an accuracy of more than 82%, but random forest was the best performing. The gradient boosting and random forest show slight over-fitting (about 9%), but both algorithms produce high testing accuracy. In terms of execution time, the decision tree takes the least time to train, while the gradient boosting takes the most time.
21
Hayashi, Haruo, Rajib Shaw, and Brian Doherty. "Exploring the Possibility of an Online Synthesis System for Disaster Risk Reduction as a Tool to Promote “Consilience” of Knowledge and Practice." Journal of Disaster Research 13, no. 7 (December 1, 2018): 1213–21. http://dx.doi.org/10.20965/jdr.2018.p1213.
Full textAbstract:
This paper proposes an international collaborative project to construct an online synthesis system initiated by the Japanese National Committee for Integrated Research on Disaster Risk (IRDR). The purpose of this project is to facilitate knowledge consilience on disaster and environmental risk reduction by improving disaster resilience, which is an indispensable element of sustainable development. This system will provide a free internet environment, named Design Trend Press, for users in each country or region. All stakeholders involved in disaster risk reduction can make and register their own contributions in various forms on this system, using their own language in terms of seven targets and four priority actions specified in the Sendai Framework for Disaster Risk Reduction (SFDRR, or Sendai Framework). To make this project successful, an international advisory board should be established to supervise the ontology of the keywords to be used for the classification and categorization of individual entries.
22
Abusnaina, Ahmed A., Rosni Abdullah, and Ali Kattan. "Self-Adaptive Mussels Wandering Optimization Algorithm with Application for Artificial Neural Network Training." Journal of Intelligent Systems 29, no. 1 (February 21, 2018): 345–63. http://dx.doi.org/10.1515/jisys-2017-0292.
Full textAbstract:
Abstract The mussels wandering optimization (MWO) is a recent population-based metaheuristic optimization algorithm inspired ecologically by mussels’ movement behavior. The MWO has been used successfully for solving several optimization problems. This paper proposes an enhanced version of MWO, known as the enhanced-mussels wandering optimization (E-MWO) algorithm. The E-MWO aims to overcome the MWO shortcomings, such as lack in explorative ability and the possibility to fall in premature convergence. In addition, the E-MWO incorporates the self-adaptive feature for setting the value of a sensitive algorithm parameter. Then, it is adapted for supervised training of artificial neural networks, whereas pattern classification of real-world problems is considered. The obtained results indicate that the proposed method is a competitive alternative in terms of classification accuracy and achieve superior results in training time.
23
Mustakim, Mustakim, Novia Kumala Sari, Jasril Jasril, Ismu Kusumanto, and Nurul Gayatri Indah Reza. "Eigenvalue of Analytic Hierarchy Process as The Determinant for Class Target on Classification Algorithm." Indonesian Journal of Electrical Engineering and Computer Science 12, no. 3 (December 1, 2018): 1257. http://dx.doi.org/10.11591/ijeecs.v12.i3.pp1257-1264.
Full textAbstract:
Data mining has two main concepts of data distribution, namely supervised learning and unsupervised learning. The most easily recognizable concepts from data distribution is related to the dataset, with and without target class. Analytic Hierarchy Process (AHP) technique that carries the concept of pairwise comparison able to answer the problem related to the dataset, which is to change unsupervised to be supervised by determining eigenvalue value of each attribute and sub attribute in AHP method. The case study conducted in this issue is related to determining the target classes used to predict the success of a student learning in UIN Suska Riau. The three main attributes are Procrastination, Total Credits (SKS) and Number of Repeated Courses, each having eigenvalues of 0.319; 0.189 and 0.171 which become the feedback in the determination of the Target Timely Graduation (TG) or Possibility of Timely Graduation (PTG). The biggest consistency ratio generated in the AHP case is 9.4% in the GPA attribute. This research recommends that further research should use datasets that have been arranged based on experimental combinations of the three main attributes above, then applied to the classification or prediction algorithm. So that it would obtain a decision of accuracy from data used against the real result on the field.<div style="mso-element: comment-list;"><div style="mso-element: comment;"><div id="_com_2" class="msocomtxt"><!--[if !supportAnnotations]--></div><!--[endif]--></div></div>
24
Deur, Martina, Mateo Gašparović, and Ivan Balenović. "Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods." Remote Sensing 12, no. 23 (November 30, 2020): 3926. http://dx.doi.org/10.3390/rs12233926.
Full textAbstract:
Spatially explicit information on tree species composition is important for both the forest management and conservation sectors. In combination with machine learning algorithms, very high-resolution satellite imagery may provide an effective solution to reduce the need for labor-intensive and time-consuming field-based surveys. In this study, we evaluated the possibility of using multispectral WorldView-3 (WV-3) satellite imagery for the classification of three main tree species (Quercus robur L., Carpinus betulus L., and Alnus glutinosa (L.) Geartn.) in a lowland, mixed deciduous forest in central Croatia. The pixel-based supervised classification was performed using two machine learning algorithms: random forest (RF) and support vector machine (SVM). Additionally, the contribution of gray level cooccurrence matrix (GLCM) texture features from WV-3 imagery in tree species classification was evaluated. Principal component analysis confirmed GLCM variance to be the most significant texture feature. Of the 373 visually interpreted reference polygons, 237 were used as training polygons and 136 were used as validation polygons. The validation results show relatively high overall accuracy (85%) for tree species classification based solely on WV-3 spectral characteristics and the RF classification approach. As expected, an improvement in classification accuracy was achieved by a combination of spectral and textural features. With the additional use of GLCM variance, the overall accuracy improved by 10% and 7% for RF and SVM classification approaches, respectively.
25
Strodthoff, Nils, Patrick Wagner, Markus Wenzel, and Wojciech Samek. "UDSMProt: universal deep sequence models for protein classification." Bioinformatics 36, no. 8 (January 8, 2020): 2401–9. http://dx.doi.org/10.1093/bioinformatics/btaa003.
Full textAbstract:
Abstract Motivation Inferring the properties of a protein from its amino acid sequence is one of the key problems in bioinformatics. Most state-of-the-art approaches for protein classification are tailored to single classification tasks and rely on handcrafted features, such as position-specific-scoring matrices from expensive database searches. We argue that this level of performance can be reached or even be surpassed by learning a task-agnostic representation once, using self-supervised language modeling, and transferring it to specific tasks by a simple fine-tuning step. Results We put forward a universal deep sequence model that is pre-trained on unlabeled protein sequences from Swiss-Prot and fine-tuned on protein classification tasks. We apply it to three prototypical tasks, namely enzyme class prediction, gene ontology prediction and remote homology and fold detection. The proposed method performs on par with state-of-the-art algorithms that were tailored to these specific tasks or, for two out of three tasks, even outperforms them. These results stress the possibility of inferring protein properties from the sequence alone and, on more general grounds, the prospects of modern natural language processing methods in omics. Moreover, we illustrate the prospects for explainable machine learning methods in this field by selected case studies. Availability and implementation Source code is available under https://github.com/nstrodt/UDSMProt. Supplementary information Supplementary data are available at Bioinformatics online.
26
Lewiński, Stanisław, and Karol Zaremski. "Examples of Object-Oriented Classification Performed on High-Resolution Satellite Images." Miscellanea Geographica 11, no. 1 (December 1, 2004): 349–58. http://dx.doi.org/10.2478/mgrsd-2004-0037.
Full textAbstract:
Abstract Information about the types of land cover and its use is obtained by the visual interpretation of the color composite of satellite images or by the use of automatic classification algorithms. For obvious reasons, the automatic classification methods make it possible to obtain information quicker and much faster than the traditional interpretation method. The commonly used automatic methods of satellite image classification, based on supervised or unsupervised classification algorithms, are the most accurate when used with low resolution images. In the case of images with 1-meter-sized pixels, showing a diversity of land cover forms, it is not possible to obtain satisfactory results. New classification techniques, based on object-oriented classification algorithms, have been developing for a couple of years now. In contrast to the traditional methods, the new operating procedure does not involve the classification of single pixels, but of entire objects, into which the content of the satellite image is divided. Aside from the spectral values of the pixels, the shape of the objects created by the pixels and the relationships between the objects, are also considered during the analysis. Similar to visual interpretation, variation in the texture of the image can also be taken into account in this case. The aim of this article is to present the possibility of using high density satellite images in object-oriented classification. The classification presented is that of a high-rise built area in Wrocław and of bridges on the Vistula River in Warsaw.
27
Damousis, I. G., S. Argyropoulos, and A. Muzet. "Classification of Physiology Indicators for the Automatic Detection of Potentially Hazardous Physiological States." Applied Computational Intelligence and Soft Computing 2011 (2011): 1–8. http://dx.doi.org/10.1155/2011/135681.
Full textAbstract:
In EU-funded project HUMABIO, physiological signals are used as biometrics for security purposes. Data are collected via electrode sensors that are attached to the body of the subject and are obtrusive to some degree. In order to maximize the obtained information and the benefits from the use of obtrusive, physiological sensors, the collected data are processed to also detect abnormal physiology states that may endanger the subjects and those around them during critical operations. Three abnormal states are studied: drug and alcohol consumption and sleep deprivation. For the classification of the physiology, four state-of-the-art techniques were compared, support vector machines, fuzzy expert systems, neural networks, and Gaussian mixture models. The results reveal that there is significant potential on the automatic detection of potentially hazardous physiology states without the need for a human supervisor and that such a system could be included at installations such as nuclear factories to enhance safety by reducing the possibility of human operator related accidents.
28
Vinciková, Hana, Jan Procházka, and Jakub Brom. "Timely identification of agricultural crops in the Temelín NPP vicinity using satellite data in the event of radiation contamination." Journal of Agrobiology 27, no. 2 (December 1, 2010): 73–83. http://dx.doi.org/10.2478/s10146-009-0014-z.
Full textAbstract:
Timely identification of agricultural crops in the Temelín NPP vicinity using satellite data in the event of radiation contaminationThe study established the possibility of rapid evaluation of land cover structure and situation using as an example the Temelín NPP (Nuclear Power Plant) emergency zone. The composition, surface representation and spatial distribution of crop species in the area of interest were assessed on the basis of satellite data analysis (Landsat 5 TM).The supervised classification method of Landsat data yielded 92% accuracy of classification into the land cover classes. A comparison of satellite data classification and field investigation (farmers' and LPIS data) showed that the combination of both methods appears to be ideal for the classification of land cover. Analysis of the assessment of Landsat satellite data showed it was possible to process data in a few days. However, obtaining data was problematic; in our case it was 44 days. The results of the classification as well as other outputs (biomass growth model, expense-to-revenue ratio of measures, route network, LPIS database parcel structure, etc.) serve as a basis for the modelling of potential agricultural production contamination. The subsequent model is available for decision making and the selection of a suitable countermeasure in the event of potential radiation contamination.
29
Alevizos, Evangelos, and Jens Greinert. "The Hyper-Angular Cube Concept for Improving the Spatial and Acoustic Resolution of MBES Backscatter Angular Response Analysis." Geosciences 8, no. 12 (November 30, 2018): 446. http://dx.doi.org/10.3390/geosciences8120446.
Full textAbstract:
This study presents a novel approach, based on high-dimensionality hydro-acoustic data, for improving the performance of angular response analysis (ARA) on multibeam backscatter data in terms of acoustic class separation and spatial resolution. This approach is based on the hyper-angular cube (HAC) data structure which offers the possibility to extract one angular response from each cell of the cube. The HAC consists of a finite number of backscatter layers, each representing backscatter values corresponding to single-incidence angle ensonifications. The construction of the HAC layers can be achieved either by interpolating dense soundings from highly overlapping multibeam echo-sounder (MBES) surveys (interpolated HAC, iHAC) or by producing several backscatter mosaics, each being normalized at a different incidence angle (synthetic HAC, sHAC). The latter approach can be applied to multibeam data with standard overlap, thus minimizing the cost for data acquisition. The sHAC is as efficient as the iHAC produced by actual soundings, providing distinct angular responses for each seafloor type. The HAC data structure increases acoustic class separability between different acoustic features. Moreover, the results of angular response analysis are applied on a fine spatial scale (cell dimensions) offering more detailed acoustic maps of the seafloor. Considering that angular information is expressed through high-dimensional backscatter layers, we further applied three machine learning algorithms (random forest, support vector machine, and artificial neural network) and one pattern recognition method (sum of absolute differences) for supervised classification of the HAC, using a limited amount of ground truth data (one sample per seafloor type). Results from supervised classification were compared with results from an unsupervised method for inter-comparison of the supervised algorithms. It was found that all algorithms (regarding both the iHAC and the sHAC) produced very similar results with good agreement (>0.5 kappa) with the unsupervised classification. Only the artificial neural network required the total amount of ground truth data for producing comparable results with the remaining algorithms.
30
Du, Yang, Ke Yan, Zixiao Ren, and Weidong Xiao. "Designing Localized MPPT for PV Systems Using Fuzzy-Weighted Extreme Learning Machine." Energies 11, no. 10 (October 1, 2018): 2615. http://dx.doi.org/10.3390/en11102615.
Full textAbstract:
A maximum power point tracker (MPPT) should be designed to deal with various weather conditions, which are different from region to region. Customization is an important step for achieving the highest solar energy harvest. The latest development of modern machine learning provides the possibility to classify the weather types automatically and, consequently, assist localized MPPT design. In this study, a localized MPPT algorithm is developed, which is supported by a supervised weather-type classification system. Two classical machine learning technologies are employed and compared, namely, the support vector machine (SVM) and extreme learning machine (ELM). The simulation results show the outperformance of the proposed method in comparison with the traditional MPPT design.
31
Tarunamulia, Tarunamulia, Jesmond Sammut, and Akhmad Mustafa. "PERBAIKAN METODE IDENTIFIKASI POTENSI PENGEMBANGAN LAHAN UNTUK TAMBAK AIR PAYAU SISTEM EKSTENSIF LEWAT INTEGRASI LOGIKA SAMAR DAN PENGINDERAAN JAUH." Jurnal Riset Akuakultur 5, no. 2 (November 25, 2016): 317. http://dx.doi.org/10.15578/jra.5.2.2010.317-323.
Full textAbstract:
Tersedianya data potensi lahan tambak yang cepat, akurat dan lengkap untuk kebutuhan pengelolaan kawasan pengembangan perikanan budidaya air payau harus didukung oleh metode identifikasi yang efektif dan efisien. Penelitian ini bertujuan untuk mengupayakan peningkatan kualitas metode klasifikasi multispektral dalam penginderaan jauh dalam mengidentifikasi potensi lahan tambak ekstensif dengan mengintegrasikan logika samar dalam proses klasifikasi citra. Citra landsat-7 ETM+ (30 m), data elevasi digital dan data pengecekan lapang untuk wilayah pantai (kawasan tambak ekstensif/tradisional) Kecamatan Kembang Tanjung, Pidie, Nangroe Aceh Darussalam (NAD) digunakan sebagai bahan utama dalam penelitian ini. Klasifikasi multispektral standar secara terbimbing diperbaiki melalui pengambilan data training secara cermat, yang diikuti dengan uji keterpisahan objek, pemrosesan pasca-klasifikasi dan analisis tingkat ketelitian. Hasil klasifikasi dengan tingkat ketelitian terbaik dari berbagai algoritma yang diujikan untuk tiga saluran selanjutnya dibandingkan dengan hasil klasifikasi dengan menggunakan logika samar. Dari hasil penelitian diketahui bahwa klasifikasi multispektral standar dengan algoritma Maximum Likelihood mampu menghasilkan informasi penutup lahan yang cukup lengkap dan rinci pada wilayah pertambakan dengan ketelitian yang cukup baik (>86%). Tingkat ketelitian yang sama juga masih dijumpai walaupun hanya melibatkan kombinasi 3 saluran terbaik (5,4, dan 3) yang dipilih berdasarkan analisis statistik nilai kecerahan piksel. Dengan membandingkan hasil terbaik dari metode klasifikasi standar yang berbasis logika biner (boolean) dengan hasil klasifikasi citra dengan logika samar dalam pengklasifikasian wilayah tambak, diketahui bahwa klasifikasi citra dengan logika samar mampu memperlihatkan hasil klasifikasi yang sangat baik untuk menentukan batas wilayah tambak yang tidak bisa dilakukan secara langsung bahkan oleh metode standar dengan algoritma terbaik. Dan dengan penambahan satu variabel kunci untuk tambak ekstensif seperti elevasi dalam klasifikasi, klasifikasi dengan logika samar dapat digunakan untuk memprediksi potensi pengembangan lahan budidaya tambak ekstensif dan kemungkinan tumpang tindih dengan penggunaan lahan lainnya.The availability of immediate, accurate and complete data on potential pond area as a baseline data for land management of brackishwater aquaculture must be supported by effective and efficient identification methods. The objective of this study was to explore the possibility of improving the quality of multispectral image classification methods in identifying potential areas for extensive brackishwater aquaculture through the integration of fuzzy logic and classification of remotely sensed data. 2002 Landsat-7 Enhanced Thematic Mapper Data (30-m pixels), digital elevation data, and groundtruthing of training data (region of interest/ROI) of Kembang Tanjung coastal areas (Pidie, NAD) were used as the primary data in this study. Standard supervised multispectral classification methods were enhanced by collecting appropriate and unbiased training data, applying separability measures of ROI pairs, employing post-classification analysis, and assessing the accuracy of classification results. Different types of standard supervised classification algorithms were evaluated and a classification output with the highest accuracy was selected to be compared with the result from fuzzy logic classification. The study showed that a supervised classification method based on maximum likelihood analysis produced the best classification output of land use-cover over the coastal region (overall accuracy > 86%). The accuracy remained at the same level although it involved only the best composite of 3 bands (5,4, and 3) determined by a rigorous statistical analysis of brightness values of pixels. It was clear that the fuzzy-based classification method was more effective in identifying potential extensive brackishwater pond areas compared to the best standard image classification based on binary logic (maximum likelihood). Also, by integrating elevation data as another key variable to determine the suitability of land for extensive brackishwater aquaculture, the fuzzy classification can be used to more accurately predict potential area suited for brackishwater aquaculture ponds and any possible overlapping activity with other land uses.
32
Katkovsky, Leonid, Boris Beliaev, Volha Siliuk, Mikhail Beliaev, Erik Sarmin, and Yurii Davidovich. "Remote spectral methods for detecting stress coniferous." E3S Web of Conferences 223 (2020): 02004. http://dx.doi.org/10.1051/e3sconf/202022302004.
Full textAbstract:
The article presents investigation of the possibility of drying coniferous forest areas detecting by multispectral satellite data in the visible and NIR spectral range with low spatial resolution, obtained by the imaging systems of three satellites - the Belarusian spacecraft (BS), Landsat 8 and Sentinel 2. A forest area in the south of Belarus was considered as a test site. High-resolution multispectral airborne data and, in part, ground measurements were used as reference ground data by which training samples were formed. Most of the known classical methods of supervised classification have been tested, the maximum likelihood method turned out to be the best for this task. In order to improve the accuracy of identifying the drying areas of coniferous forests on multispectral images, parametric transformations of images in the spectral space are proposed, which should lead to an increase in initial small spectral differences. The methodological issues of assessing the accuracy of the satellite images classification are considered using the result of the classification of airborne image with high spatial resolution as a ground truth image. The assessment of the classification accuracy, both visually and using the obtained confusion matrices, allows us to conclude that the images of the BS, Landsat 8 and Sentinel 2 can be used to detect drying area of coniferous forests as well as the expediency of carrying out the proposed transformations of the original images.
33
Saeed, Sawza Saadi, and Raghad Zuhair Yousif. "A Slantlet based Statistical Features Extraction for Classification of Normal, Arrhythmia, and Congestive Heart Failure in Electrocardiogram." UHD Journal of Science and Technology 5, no. 1 (June 10, 2021): 71–81. http://dx.doi.org/10.21928/uhdjst.v5n1y2021.pp71-81.
Full textAbstract:
Intelligent and automated systems for diagnosing heart disease play a key role in treatment of heart disease and hence mitigating the possibility of heart disease, heart failure or sudden death. Thus, a Computer-Aided Design CAD system can provide a doctors with a clue about the category of patient heart disease, which might be Normal Sinus Rhythm, Abnormal Arrhythmia (ARR), and Congestive Heart Failure (CHF) electrocardiogram (ECG) signal. In this work a novel Slantlet transform (SLT) statistical features have been extracted and selected for 900 ECG segments taken from MIT-BIH ARR Database equally from three classes mentioned above for heart dieses classification through ECG signals. Based on the superiority of SLT in time localization as compared to the traditional wavelet transform, 12 out of 14 statistical features have been successfully passed the ANOVA test with P-value of 10−3. Then after, the relevant features are provided to three well-known classifiers (Support Vector Machine [SVM], K-nearest neighbor, and Naive Bayes). The performance tests show that Attaining 99.254% classification average AUC it can be achieved using SLT transform based features along with SVM classifier, which is a set of related supervised machine learning algorithm used for regression and classification with high generalization ability. It performs classification on two group problems. SVM classifier determines the best hyperplane which distinguishes between each positive and negative training sample.
34
Sarkar, Jyotirmoy, Kartik Bhatia, Snehanshu Saha, Margarita Safonova, and Santonu Sarkar. "Postulating exoplanetary habitability via a novel anomaly detection method." Monthly Notices of the Royal Astronomical Society 510, no. 4 (December 13, 2021): 6022–32. http://dx.doi.org/10.1093/mnras/stab3556.
Full textAbstract:
ABSTRACT A profound shift in the study of cosmology came with the discovery of thousands of exoplanets and the possibility of the existence of billions of them in our Galaxy. The biggest goal in these searches is whether there are other life-harbouring planets. However, the question which of these detected planets are habitable, potentially-habitable, or maybe even inhabited, is still not answered. Some potentially habitable exoplanets have been hypothesised, but since Earth is the only known habitable planet, measures of habitability are necessarily determined with Earth as the reference. Several recent works introduced new habitability metrics based on optimisation methods. Classification of potentially habitable exoplanets using supervised learning is another emerging area of study. However, both modelling and supervised learning approaches suffer from drawbacks. We propose an anomaly detection method, the multi-stage memetic algorithm (MSMA), to detect anomalies and extend it to an unsupervised clustering algorithm multi-stage multi-version memetic clustering algorithm to use it to detect potentially habitable exoplanets as anomalies. The algorithm is based on the postulate that Earth is an anomaly, with the possibility of existence of few other anomalies among thousands of data points. We describe an MSMA-based clustering approach with a novel distance function to detect habitable candidates as anomalies (including Earth). The results are cross-matched with the Planetary Habitability Laboratory-habitable exoplanet catalogue (PHL-HEC) of the PHL with both optimistic and conservative lists of potentially habitable exoplanets.
35
Acharki, Siham, Mina Amharref, Pierre-Louis Frison, and Abdes Samed Bernoussi. "CARTOGRAPHIE DES CULTURES DANS LE PÉRIMÈTRE DU LOUKKOS (MAROC) : APPORT DE LA TÉLÉDÉTECTION RADAR ET OPTIQUE." Revue Française de Photogrammétrie et de Télédétection, no. 222 (November 26, 2020): 15–29. http://dx.doi.org/10.52638/rfpt.2020.481.
Full textAbstract:
Dans cet article, nous analysons la possibilité d’amélioration de la classification des cultures dans un périmètre irrigué du nord du Maroc en se basant sur la combinaison des données multi-temporelles de deux satellites (Sentinel-1 et Sentinel-2) avec l’inclusion de neuf indices. Le périmètre concerné (Loukkos), en plus de sa position stratégique, se caractérise par un climat méditerranéen avec une forte valeur écologique. Il présente une intense activité agricole avec une grande diversité des cultures dont le fonctionnement pourrait être affecté par le changement climatique. Afin de quantifier les besoins en eau, nous avons utilisé les séries d’images satellitaires acquises pour la période du 09/2017 au 08/2018. Les cartes produites pour trois niveaux de classification illustrent notre approche. L’étude a montré que les 10 canaux optiques, à 10 et 20 m de résolution spatiale, des données acquises par Sentinel-2 permettent d'obtenir de bonnes performances, avec un indice de kappa > 85% pour les sous-classes et une précision globale > 86%. Ces performances sont supérieures à celles obtenues avec des données radar acquises par Sentinel-1, avec des écarts de F-score inférieurs de 9% en moyenne, et pouvant aller jusqu'à 29% (sur le chêne-liège/Niveau SSC). Ni l'ajout d'indices radiométriques optiques, ni la combinaison des données optiques et radar n'apportent d'amélioration significative aux performances obtenues avec les données Sentinel-2. Afin d’exploiter les données obtenues, les travaux à venir se focaliseraient sur l’étude des profils temporels de chaque type de culture.Mots-clés : Sentinel-1, Sentinel-2, Classification supervisée, Forêt aléatoire, Cultures, Loukkos
36
Gómez, Catalina, Mauricio Neira, Marcela Hernández Hoyos, Pablo Arbeláez, and Jaime E. Forero-Romero. "Classifying image sequences of astronomical transients with deep neural networks." Monthly Notices of the Royal Astronomical Society 499, no. 3 (October 2, 2020): 3130–38. http://dx.doi.org/10.1093/mnras/staa2973.
Full textAbstract:
ABSTRACT Supervised classification of temporal sequences of astronomical images into meaningful transient astrophysical phenomena has been considered a hard problem because it requires the intervention of human experts. The classifier uses the expert’s knowledge to find heuristic features to process the images, for instance, by performing image subtraction or by extracting sparse information such as flux time-series, also known as light curves. We present a successful deep learning approach that learns directly from imaging data. Our method models explicitly the spatiotemporal patterns with deep convolutional neural networks and gated recurrent units. We train these deep neural networks using 1.3 million real astronomical images from the Catalina Real-Time Transient Survey to classify the sequences into five different types of astronomical transient classes. The TAO-Net (for Transient Astronomical Objects Network) architecture outperforms the results from random forest classification on light curves by 10 percentage points as measured by the F1 score for each class; the average F1 over classes goes from $45{{\ \rm percent}}$ with random forest classification to $55{{\ \rm percent}}$ with TAO-Net. This achievement with TAO-Net opens the possibility to develop new deep learning architectures for early transient detection. We make available the training data set and trained models of TAO-Net to allow for future extensions of this work.
37
Pham, Dang, and Lisa Kaltenegger. "Color classification of Earth-like planets with machine learning." Monthly Notices of the Royal Astronomical Society 504, no. 4 (April 23, 2021): 6106–16. http://dx.doi.org/10.1093/mnras/stab1144.
Full textAbstract:
ABSTRACT Atmospheric characterization of directly imaged exoplanets is currently limited to Giant planets and Mini-Neptunes. However, upcoming ground-based Extremely Large Telescopes (ELTs) and space-based concepts such as Origins, HabEx, and LUVOIR are designed to characterize rocky exoplanets. But spectroscopy of Earth-like planets is time-intensive even for upcoming telescopes; therefore, initial photometry has been discussed as a promising avenue to faster classify and prioritize exoplanets. Thus, in this article we explore whether photometric flux – using the standard Johnson filters – can identify the existence of surface-life by analysing a grid of 318 780 reflection spectra of nominal terrestrial planets with 1 Earth radius, 1 Earth mass, and modern Earth atmospheres for varying surface compositions and cloud coverage. Because different kinds of biota change the reflection spectra, we assess the sensitivity of our results to six diverse biota samples including vegetation, representative of modern Earth, a biofilm as a way for microbes to survive extreme environments, and UV radiation resistant biota. We test the performance of several supervised machine-learning algorithms in classifying planets with biota for different signal-to-noise ratios: Machine-learning methods can detect the existence of biota using only the photometric flux of Earth-like planets’ reflected light with a balanced accuracy between 50 per cent and up to 75 per cent. These results assess the possibility that photometric flux could be used to initially identify biota on Earth-like planets and the trade-off between two critical results when classifying biota: false-positive and false-negative rates. Our spectra library is available online and can easily be used to test different filter combinations for upcoming missions and mission designs.
38
Alcaras, E., P. P. Amoroso, C. Parente, and G. Prezioso. "REMOTELY SENSED IMAGE FAST CLASSIFICATION AND SMART THEMATIC MAP PRODUCTION." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVI-4/W5-2021 (December 23, 2021): 43–50. http://dx.doi.org/10.5194/isprs-archives-xlvi-4-w5-2021-43-2021.
Full textAbstract:
Abstract. Apps available for Smartphone, as well as software for GNSS/GIS devices, permit to easily mapping the localization and shape of an area by acquiring the vertices coordinates of its contour. This option is useful for remote sensing classification, supporting the detection of representative sample sites of a known cover type to use for algorithm training or to test classification results. This article aims to analyse the possibility to produce smart maps from remotely sensed image classification in rapid way: the attention is focalized on different methods that are compared to identify fast and accurate procedure for producing up-to-date and reliable maps. Landsat 8 OLI multispectral images of northern Sicily (Italy) are submitted to various classification algorithms to distinguish water, bare soil and vegetation. The resulting map is useful for many purposes: appropriately inserted in a larger database aimed at representing the situation in a space-time evolutionary scenario, it is suitable whenever you want to capture the variation induced in a scene, e.g. burnt areas identification, vegetated areas definition for tourist-recreational purposes, etc. Particularly, pixel-based classification approaches are preferred, and experiments are carried out using unsupervised (k-means), vegetation index (NDVI, Normalized Difference Vegetation Index), supervised (minimum distance, maximum likelihood) methods. Using test sites, confusion matrix is built for each method, and quality indices are calculated to compare the results. Experiments demonstrate that NDVI submitted to k-means algorithm allows the best performance for distinguishing not only vegetation areas but also water bodies and bare soils. The resulting thematic map is converted for web publishing.
39
Baur, Tobias, Alexander Heimerl, Florian Lingenfelser, Johannes Wagner, Michel F. Valstar, Björn Schuller, and Elisabeth André. "eXplainable Cooperative Machine Learning with NOVA." KI - Künstliche Intelligenz 34, no. 2 (January 19, 2020): 143–64. http://dx.doi.org/10.1007/s13218-020-00632-3.
Full textAbstract:
Abstract In the following article, we introduce a novel workflow, which we subsume under the term “explainable cooperative machine learning” and show its practical application in a data annotation and model training tool called NOVA. The main idea of our approach is to interactively incorporate the ‘human in the loop’ when training classification models from annotated data. In particular, NOVA offers a collaborative annotation backend where multiple annotators join their workforce. A main aspect is the possibility of applying semi-supervised active learning techniques already during the annotation process by giving the possibility to pre-label data automatically, resulting in a drastic acceleration of the annotation process. Furthermore, the user-interface implements recent eXplainable AI techniques to provide users with both, a confidence value of the automatically predicted annotations, as well as visual explanation. We show in an use-case evaluation that our workflow is able to speed up the annotation process, and further argue that by providing additional visual explanations annotators get to understand the decision making process as well as the trustworthiness of their trained machine learning models.
40
di Donato, Francesca, and Luciano Nieddu. "Corporate failure: Bankruptcy prediction for Italian SMEs based on a longitudinal case study from 2000 to 2011." Corporate Ownership and Control 17, no. 3 (2020): 27–33. http://dx.doi.org/10.22495/cocv17i3art2.
Full textAbstract:
We investigate the case of Small-Medium Enterprises (SMEs) in Italy trying to understand if key performance indicators obtained from the financial statement are able to predict possible distress in a company with enough time to take some corrective actions. In order to test the hypotheses, a nonparametric supervised classification algorithm has been applied to a random sample of 100 non-listed SMEs, considering 50 companies that filed for bankruptcy during the period 2000-2011 and 50 companies still active on the market at the end of 2011. Results describe the Italian picture for SMEs during an economic crisis period. They show that, for the Italian case, it is possible to predict with enough time (4-5 years prior to failure) a distress situation in a firm through classification methods. Anyway, these methods are not predicting the health of a company but the possibility of the firm to access the credit system. The results are limited to the Italian SMEs context which is quite particular if compared with other countries in Europe. The dataset is limited in size but has been chosen to be representative of non-listed Italian companies.
41
Harris, Patricia M., Raymond Gingerich, and Tiffany A. Whittaker. "The “Effectiveness” of Differential Supervision." Crime & Delinquency 50, no. 2 (April 2004): 235–71. http://dx.doi.org/10.1177/0011128703258939.
Full textAbstract:
This article presents an evaluation of the Client Management Classification System (CMC), a method for assessment and differential supervision of offenders that embodies the principle of responsivity. As in prior evaluations of the CMC, probationers whose officers were trained in CMC techniques experienced lower rates of revocation compared with regularly supervised subjects. However, the experimental group incurred similar or higher rates of rules violations and arrests. Of particular interest, the study found that supervision of experimental subjects did not conform to recommended CMC strategies. In combination, these results suggest the possibility that training in CMC successfully heightened officers’ understanding of offender motivations and needs, leading them to view probationer misconduct in a more lenient and flexible context—and thereby producing the appearance of favorable outcomes. The findings have implications for the design of evaluations of efforts to implement principles of effective offender treatment in community corrections agencies.
42
Kubus, Mariusz. "The Problem of Redundant Variables in Random Forests." Acta Universitatis Lodziensis. Folia Oeconomica 6, no. 339 (February 13, 2019): 7–16. http://dx.doi.org/10.18778/0208-6018.339.01.
Full textAbstract:
Random forests are currently one of the most preferable methods of supervised learning among practitioners. Their popularity is influenced by the possibility of applying this method without a time consuming pre‑processing step. Random forests can be used for mixed types of features, irrespectively of their distributions. The method is robust to outliers, and feature selection is built into the learning algorithm. However, a decrease of classification accuracy can be observed in the presence of redundant variables. In this paper, we discuss two approaches to the problem of redundant variables. We consider two strategies of searching for best feature subset as well as two formulas of aggregating the features in the clusters. In the empirical experiment, we generate collinear predictors and include them in the real datasets. Dimensionality reduction methods usually improve the accuracy of random forests, but none of them clearly outperforms the others.
43
Shimizu, Ayame, and Kei Wakabayash. "Effect of Label Redundancy in Crowdsourcing for Training Machine Learning Models." Journal of Data Intelligence 3, no. 3 (August 2022): 301–15. http://dx.doi.org/10.26421/jdi3.3-1.
Full textAbstract:
Crowdsourcing is widely utilized for collecting labeled examples to train supervised machine learning models, but the labels obtained from workers are considerably noisier than those from expert annotators. To address the noisy label issue, most researchers adopt the repeated labeling strategy, where multiple (redundant) labels are collected for each example and then aggregated. Although this improves the annotation quality, it decreases the amount of training data when the budget for crowdsourcing is limited, which is a negative factor in terms of the accuracy of the machine learning model to be trained. This paper empirically examines the extent to which repeated labeling contributes to the accuracy of machine learning models for image classification, named entity recognition and sentiment analysis under various conditions of budget and worker quality. We experimentally examined four hypotheses related to the effect of budget, worker quality, task difficulty, and redundancy on crowdsourcing. The results on image classification and named entity recognition supported all four hypotheses and suggested that repeated labeling almost always has a negative impact on machine learning when it comes to accuracy. Somewhat surprisingly, the results on sentiment analysis using pretrained models did not support the hypothesis which shows the possibility of remaining utilization of multiple-labeling.
44
Olago, Victor, Mazvita Muchengeti, Elvira Singh, and Wenlong C. Chen. "Identification of Malignancies from Free-Text Histopathology Reports Using a Multi-Model Supervised Machine Learning Approach." Information 11, no. 9 (September 21, 2020): 455. http://dx.doi.org/10.3390/info11090455.
Full textAbstract:
We explored various Machine Learning (ML) models to evaluate how each model performs in the task of classifying histopathology reports. We trained, optimized, and performed classification with Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Adaptive Boosting (AB), Decision Trees (DT), Gaussian Naïve Bayes (GNB), Logistic Regression (LR), and Dummy classifier. We started with 60,083 histopathology reports, which reduced to 60,069 after pre-processing. The F1-scores for SVM, SGD KNN, RF, DT, LR, AB, and GNB were 97%, 96%, 96%, 96%, 92%, 96%, 84%, and 88%, respectively, while the misclassification rates were 3.31%, 5.25%, 4.39%, 1.75%, 3.5%, 4.26%, 23.9%, and 19.94%, respectively. The approximate run times were 2 h, 20 min, 40 min, 8 h, 40 min, 10 min, 50 min, and 4 min, respectively. RF had the longest run time but the lowest misclassification rate on the labeled data. Our study demonstrated the possibility of applying ML techniques in the processing of free-text pathology reports for cancer registries for cancer incidence reporting in a Sub-Saharan Africa setting. This is an important consideration for the resource-constrained environments to leverage ML techniques to reduce workloads and improve the timeliness of reporting of cancer statistics.
45
Zhang, Hao, Haifeng Sun, Ling Wang, Shun Wang, Wei Zhang, and Jiandong Hu. "Near Infrared Spectroscopy Based on Supervised Pattern Recognition Methods for Rapid Identification of Adulterated Edible Gelatin." Journal of Spectroscopy 2018 (December 20, 2018): 1–9. http://dx.doi.org/10.1155/2018/7652592.
Full textAbstract:
The aim of this work is to identify the adulteration of edible gelatin using near-infrared (NIR) spectroscopy combined with supervised pattern recognition methods. The spectral data obtained from a total of 144 samples consisting of six kinds of adulterated gelatin gels with different mixture ratios were processed with multiplicative scatter correction (MSC), Savitzky–Golay (SG) smoothing, and min-max normalization. Principal component analysis (PCA) was first carried out for spectral analysis, while the six gelatin categories could not be clearly distinguished. Further, linear discriminant analysis (LDA), soft independent modelling of class analogy (SIMCA), backpropagation neural network (BPNN), and support vector machine (SVM) were introduced to establish discrimination models for identifying the adulterated gelatin gels, which gave a total correct recognition rate of 97.44%, 100%, 97.44%, and 100%, respectively. For the SIMCA model with significant level α = 0.05, sample overlapping clustering appeared; thus, the SVM model presents the best recognition ability among these four discrimination models for the classification of edible gelatin adulteration. The results demonstrate that NIR spectroscopy combined with unsupervised pattern recognition methods can quickly and accurately identify edible gelatin with different adulteration levels, providing a new possibility for the detection of industrial gelatin illegally added into food products.
46
Campos, Sérgio, Edson Luís Piroli, Célia Regina Lopes Zimback, and João Batista Tolentino Rodrigues. "AVALIAÇÃO DO USO DA TERRA EM MICROBACIA UTILIZANDO UMA MATRIZ DE PARTIÇÃO FUZZY." IRRIGA 12, no. 2 (August 10, 2007): 216–24. http://dx.doi.org/10.15809/irriga.2007v12n2p216-224.
Full textAbstract:
AVALIAÇÃO DO USO DA TERRAEM MICROBACIA UTILIZANDO UMAMATRIZ DE PARTIÇÃO FUZZY Sérgio Campos1; Edson Luís Piroli2; Célia Regina Lopes Zimback3; João Batista Tolentino Rodrigues31Departamento de Engenharia Rural, Faculdade de Ciências Agronômicas, Universidade Estadual Paulista, Botucatu, SP, seca@fca.unesp.br2Campus Experimental de Rosana, Universidade Estadual Paulista, Rosana, SP3Departamento de Ciências do Solo, Faculdade de Ciências Agronômicas, Universidade Estadual Paulista, Botucatu, SP 1 RESUMO A evolução da informática oferece, hoje, a possibilidade de desenvolvimento de novas técnicas e metodologias para elaboração de trabalhos em todas as áreas do conhecimento humano. Aliado a isto, a capacidade de manuseio de grande volume de dados dos computadores pessoais atuais, facilita a criação e aplicação de novas ferramentas para análise de informações. Neste trabalho objetivou-se a aplicação de uma matriz de partição fuzzy para análise os dados obtidos pelo sensor TM do satélite Landsat 5, visando elaborar a classificação supervisionada do uso da terra na microbacia hidrográfica do Arroio das Pombas, no Município de Botucatu, SP. A atribuição de pesos no momento da criação das assinaturas, possibilitou que uma simples área de treinamento oferecesse entrada em mais de uma classe de cobertura. Constatou-se, também, uma modificação no resultado da classificação quando comparada com a classificação por máxima verossimilhança, principalmente com relação à maior homogeneidade e melhor definição das bordas das classes. UNITERMOS: matrix de partição fuzzy, classificação supervisionada, imagem de satélite. CAMPOS, S., PIROLI, E.L., ZIMBACK, C.R.L., RODRIGUES, J.B.T.ANALYSIS OF SOIL USE IN A MICROBASIN USING A FUZZY PARTITION MATRIX 2 ABSTRACT Informatics evolution presently offers the possibility of new technique and methodology development for studies in all human knowledge areas. In addition, the present personal computer capacity of handling a large volume of data makes the creation and application of new analysis tools easy. This paper aimed the application of a fuzzy partition matrix to analyze data obtained from the Landsat 5 TMN sensor, in order to elaborate the supervised classification of land use in Arroio das Pombas microbasin, in Botucatu,SP,Brazil. It was possible that one single training area present input in more than one covering class due to weight attribution at the signature creation moment. A change in the classification result was also observed when compared to maximum likelihood classification, mainly when related to bigger uniformity and better class edges classification.KEYWORDS: fuzzy partition matrix, supervised classification, satellite image.
47
Herrera-Alcántara, Oscar, Ari Barrera-Animas, Miguel González-Mendoza, and Félix Castro-Espinoza. "Monitoring Student Activities with Smartwatches: On the Academic Performance Enhancement." Sensors 19, no. 7 (April 3, 2019): 1605. http://dx.doi.org/10.3390/s19071605.
Full textAbstract:
Motivated by the importance of studying the relationship between habits of students and their academic performance, daily activities of undergraduate participants have been tracked with smartwatches and smartphones. Smartwatches collect data together with an Android application that interacts with the users who provide the labeling of their own activities. The tracked activities include eating, running, sleeping, classroom-session, exam, job, homework, transportation, watching TV-Series, and reading. The collected data were stored in a server for activity recognition with supervised machine learning algorithms. The methodology for the concept proof includes the extraction of features with the discrete wavelet transform from gyroscope and accelerometer signals to improve the classification accuracy. The results of activity recognition with Random Forest were satisfactory (86.9%) and support the relationship between smartwatch sensor signals and daily-living activities of students which opens the possibility for developing future experiments with automatic activity-labeling, and so forth to facilitate activity pattern recognition to propose a recommendation system to enhance the academic performance of each student.
48
CABRERA CABAÑAS, REINIER, FRANCISCO LUNA ROSAS, JULIO CESAR MARTINEZ ROMO, CLAUDIO FRAUSTRO REYES, and Marco Antonio Hernandez Vargas. "ADAPTATIVE NEURO-FUZZY INFERENCE SYSTEM (ANFIS) APPLIED ON RAMAN SPECTROSCOPY SIGNALS TO DECIPHER AND CLASSIFY HEALTHY AND DAMAGED BREAST CANCER TISSUE." DYNA NEW TECHNOLOGIES 9, no. 1 (September 22, 2022): [13P.]. http://dx.doi.org/10.6036/nt10557.
Full textAbstract:
Abstract: One of the most notable causes of death in the world is cancer. We know that some of these variants can be eliminated with some method such as surgery or chemotherapy. In this paper we present an optimized method which is responsible for classifying breast tissue into healthy and damaged. After getting the spectra one of the main challenges in this process is the elimination of spectral noise composed of (a) fluorescence background and (b) high frequency noise; we used Adaptative Neuro-Fuzzy Inference System (ANFIS) in combination with moving averages filter to eliminate these disturbances. When employing multicore technology to the set of biological spectra (data parallelism), we can clearly observe the significant reduction in processing time with a gain of approximately 59.67% compared to sequential process. We highlight the advantages of applying a supervised learning algorithm like ANFIS on the principal components to perform the classification of healthy and damaged tissue and the results are compared with the well-known linear regression methods and vector support machines using testing table and k fold cross validation recording Mean Square Error values of 0.00458 and 0.002254 respectively. Based on the results obtained with this method, we consider that it would be an important clinical tool for specialists for a rapid and efficient automatic detection of breast cancer and consider the possibility of being applicable to other kinds of cancer, e.g., lung, prostate, stomach. Keywords: ANFIS, Breast Cancer, Raman Spectroscopy, Automatic Detection. We highlight the advantages of applying a supervised learning algorithm like ANFIS applied on the principal components from the point cloud to perform the classification of healthy and damaged tissue and the results are compared with the well-known linear regression methods and vector support machines. We highlight the advantages of using testing table method applied on ANFIS obtaining a considerable decrease in the Mean Square Error factor with a value of 0.00458, when we used cross validation The MSE decrease to 0.002254. Based on the results obtained with this method, we consider that it would be an important clinical tool for specialists for a rapid and efficient automatic detection of breast cancer and consider the possibility of being applicable to other kinds of cancer, e.g., lung, prostate, stomach. Keywords: ANFIS, Breast Cancer, Raman Spectroscopy, Automatic Detection.
49
Martinez, Beatriz, Raquel Leon, Himar Fabelo, Samuel Ortega, Juan F. Piñeiro, Adam Szolna, Maria Hernandez, et al. "Most Relevant Spectral Bands Identification for Brain Cancer Detection Using Hyperspectral Imaging." Sensors 19, no. 24 (December 12, 2019): 5481. http://dx.doi.org/10.3390/s19245481.
Full textAbstract:
Hyperspectral imaging (HSI) is a non-ionizing and non-contact imaging technique capable of obtaining more information than conventional RGB (red green blue) imaging. In the medical field, HSI has commonly been investigated due to its great potential for diagnostic and surgical guidance purposes. However, the large amount of information provided by HSI normally contains redundant or non-relevant information, and it is extremely important to identify the most relevant wavelengths for a certain application in order to improve the accuracy of the predictions and reduce the execution time of the classification algorithm. Additionally, some wavelengths can contain noise and removing such bands can improve the classification stage. The work presented in this paper aims to identify such relevant spectral ranges in the visual-and-near-infrared (VNIR) region for an accurate detection of brain cancer using in vivo hyperspectral images. A methodology based on optimization algorithms has been proposed for this task, identifying the relevant wavelengths to achieve the best accuracy in the classification results obtained by a supervised classifier (support vector machines), and employing the lowest possible number of spectral bands. The results demonstrate that the proposed methodology based on the genetic algorithm optimization slightly improves the accuracy of the tumor identification in ~5%, using only 48 bands, with respect to the reference results obtained with 128 bands, offering the possibility of developing customized acquisition sensors that could provide real-time HS imaging. The most relevant spectral ranges found comprise between 440.5–465.96 nm, 498.71–509.62 nm, 556.91–575.1 nm, 593.29–615.12 nm, 636.94–666.05 nm, 698.79–731.53 nm and 884.32–902.51 nm.
50
Lang, Frederique, Diego Chavarro, and Yuxian Liu. "Can Automatic Classification Help to Increase Accuracy in Data Collection?" Journal of Data and Information Science 1, no. 3 (September 1, 2017): 42–58. http://dx.doi.org/10.20309/jdis.201619.
Full textAbstract:
AbstractPurposeThe authors aim at testing the performance of a set of machine learning algorithms that could improve the process of data cleaning when building datasets.Design/methodology/approachThe paper is centered on cleaning datasets gathered from publishers and online resources by the use of specific keywords. In this case, we analyzed data from the Web of Science. The accuracy of various forms of automatic classification was tested here in comparison with manual coding in order to determine their usefulness for data collection and cleaning. We assessed the performance of seven supervised classification algorithms (Support Vector Machine (SVM), Scaled Linear Discriminant Analysis, Lasso and elastic-net regularized generalized linear models, Maximum Entropy, Regression Tree, Boosting, and Random Forest) and analyzed two properties: accuracy and recall. We assessed not only each algorithm individually, but also their combinations through a voting scheme. We also tested the performance of these algorithms with different sizes of training data. When assessing the performance of different combinations, we used an indicator of coverage to account for the agreement and disagreement on classification between algorithms.FindingsWe found that the performance of the algorithms used vary with the size of the sample for training. However, for the classification exercise in this paper the best performing algorithms were SVM and Boosting. The combination of these two algorithms achieved a high agreement on coverage and was highly accurate. This combination performs well with a small training dataset (10%), which may reduce the manual work needed for classification tasks.Research limitationsThe dataset gathered has significantly more records related to the topic of interest compared to unrelated topics. This may affect the performance of some algorithms, especially in their identification of unrelated papers.Practical implicationsAlthough the classification achieved by this means is not completely accurate, the amount of manual coding needed can be greatly reduced by using classification algorithms. This can be of great help when the dataset is big. With the help of accuracy, recall, and coverage measures, it is possible to have an estimation of the error involved in this classification, which could open the possibility of incorporating the use of these algorithms in software specifically designed for data cleaning and classification.Originality/valueWe analyzed the performance of seven algorithms and whether combinations of these algorithms improve accuracy in data collection. Use of these algorithms could reduce time needed for manual data cleaning.