Добірка наукової літератури з теми "Strongly supervised learning"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Strongly supervised learning".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Strongly supervised learning"
1
Lucas, Thomas, Philippe Weinzaepfel, and Gregory Rogez. "Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (June 28, 2022): 1881–89. http://dx.doi.org/10.1609/aaai.v36i2.20082.
Повний текст джерелаАнотація:
This paper tackles the problem of semi-supervised learning when the set of labeled samples is limited to a small number of images per class, typically less than 10, problem that we refer to as barely-supervised learning. We analyze in depth the behavior of a state-of-the-art semi-supervised method, FixMatch, which relies on a weakly-augmented version of an image to obtain supervision signal for a more strongly-augmented version. We show that it frequently fails in barely-supervised scenarios, due to a lack of training signal when no pseudo-label can be predicted with high confidence. We propose a method to leverage self-supervised methods that provides training signal in the absence of confident pseudo-labels. We then propose two methods to refine the pseudo-label selection process which lead to further improvements.The first one relies on a per-sample history of the model predictions, akin to a voting scheme. The second iteratively up-dates class-dependent confidence thresholds to better explore classes that are under-represented in the pseudo-labels. Our experiments show that our approach performs significantly better on STL-10 in the barely-supervised regime,e.g. with 4 or 8 labeled images per class.
2
She, Dongyu, Ming Sun, and Jufeng Yang. "Learning Discriminative Sentiment Representation from Strongly- and Weakly Supervised CNNs." ACM Transactions on Multimedia Computing, Communications, and Applications 15, no. 3s (January 22, 2020): 1–19. http://dx.doi.org/10.1145/3326335.
Повний текст джерела
3
Pan, Junwen, Qi Bi, Yanzhan Yang, Pengfei Zhu, and Cheng Bian. "Label-Efficient Hybrid-Supervised Learning for Medical Image Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (June 28, 2022): 2026–34. http://dx.doi.org/10.1609/aaai.v36i2.20098.
Повний текст джерелаАнотація:
Due to the lack of expertise for medical image annotation, the investigation of label-efficient methodology for medical image segmentation becomes a heated topic. Recent progresses focus on the efficient utilization of weak annotations together with few strongly-annotated labels so as to achieve comparable segmentation performance in many unprofessional scenarios. However, these approaches only concentrate on the supervision inconsistency between strongly- and weakly-annotated instances but ignore the instance inconsistency inside the weakly-annotated instances, which inevitably leads to performance degradation. To address this problem, we propose a novel label-efficient hybrid-supervised framework, which considers each weakly-annotated instance individually and learns its weight guided by the gradient direction of the strongly-annotated instances, so that the high-quality prior in the strongly-annotated instances is better exploited and the weakly-annotated instances are depicted more precisely. Specially, our designed dynamic instance indicator (DII) realizes the above objectives, and is adapted to our dynamic co-regularization (DCR) framework further to alleviate the erroneous accumulation from distortions of weak annotations. Extensive experiments on two hybrid-supervised medical segmentation datasets demonstrate that with only 10% strong labels, the proposed framework can leverage the weak labels efficiently and achieve competitive performance against the 100% strong-label supervised scenario.
4
Gui, Haitian, Tao Su, Zhiyong Pang, Han Jiao, Lang Xiong, Xinhua Jiang, Li Li, and Zixin Wang. "Diagnosis of Breast Cancer with Strongly Supervised Deep Learning Neural Network." Electronics 11, no. 19 (September 22, 2022): 3003. http://dx.doi.org/10.3390/electronics11193003.
Повний текст джерелаАнотація:
The strongly supervised deep convolutional neural network (DCNN) has better performance in assessing breast cancer (BC) because of the more accurate features from the slice-level precise labeling compared with the image-level labeling weakly supervised DCNN. However, manual slice-level precise labeling is time consuming and expensive. In addition, the slice-level diagnosis adopted in the DCNN system is incomplete and defective because of the lack of other slices’ information. In this paper, we studied the impact of the region of interest (ROI) and lesion-level multi-slice diagnosis in the DCNN auxiliary diagnosis system. Firstly, we proposed an improved region-growing algorithm to generate slice-level precise ROI. Secondly, we adopted the average weighting method as the lesion-level diagnosis criteria after exploring four different weighting methods. Finally, we proposed our complete system, which combined the densely connected convolutional network (DenseNet) with the slice-level ROI and the average weighting lesion-level diagnosis after evaluating the performance of five DCNNs. The proposed system achieved an AUC of 0.958, an accuracy of 92.5%, a sensitivity of 95.0%, and a specificity of 90.0%. The experimental results showed that our proposed system had a better performance in BC diagnosis because of the more precise ROI and more complete information of multi-slices.
5
Kasihmuddin, Mohd Shareduwan Mohd, Siti Zulaikha Mohd Jamaludin, Mohd Asyraf Mansor, Habibah A. Wahab, and Siti Maisharah Sheikh Ghadzi. "Supervised Learning Perspective in Logic Mining." Mathematics 10, no. 6 (March 13, 2022): 915. http://dx.doi.org/10.3390/math10060915.
Повний текст джерелаАнотація:
Creating optimal logic mining is strongly dependent on how the learning data are structured. Without optimal data structure, intelligence systems integrated into logic mining, such as an artificial neural network, tend to converge to suboptimal solution. This paper proposed a novel logic mining that integrates supervised learning via association analysis to identify the most optimal arrangement with respect to the given logical rule. By utilizing Hopfield neural network as an associative memory to store information of the logical rule, the optimal logical rule from the correlation analysis will be learned and the corresponding optimal induced logical rule can be obtained. In other words, the optimal logical rule increases the chances for the logic mining to locate the optimal induced logic that generalize the datasets. The proposed work is extensively tested on a variety of benchmark datasets with various performance metrics. Based on the experimental results, the proposed supervised logic mining demonstrated superiority and the least competitiveness compared to the existing method.
6
Ma, Jun, and Guolin Yu. "Lagrangian Regularized Twin Extreme Learning Machine for Supervised and Semi-Supervised Classification." Symmetry 14, no. 6 (June 9, 2022): 1186. http://dx.doi.org/10.3390/sym14061186.
Повний текст джерелаАнотація:
Twin extreme learning machine (TELM) is a phenomenon of symmetry that improves the performance of the traditional extreme learning machine classification algorithm (ELM). Although TELM has been widely researched and applied in the field of machine learning, the need to solve two quadratic programming problems (QPPs) for TELM has greatly limited its development. In this paper, we propose a novel TELM framework called Lagrangian regularized twin extreme learning machine (LRTELM). One significant advantage of our LRTELM over TELM is that the structural risk minimization principle is implemented by introducing the regularization term. Meanwhile, we consider the square of the l2-norm of the vector of slack variables instead of the usual l1-norm in order to make the objective functions strongly convex. Furthermore, a simple and fast iterative algorithm is designed for solving LRTELM, which only needs to iteratively solve a pair of linear equations in order to avoid solving two QPPs. Last, we extend LRTELM to semi-supervised learning by introducing manifold regularization to improve the performance of LRTELM when insufficient labeled samples are available, as well as to obtain a Lagrangian semi-supervised regularized twin extreme learning machine (Lap-LRTELM). Experimental results on most datasets show that the proposed LRTELM and Lap-LRTELM are competitive in terms of accuracy and efficiency compared to the state-of-the-art algorithms.
7
Liu, Yuzhuo, Hangting Chen, Jian Wang, Pei Wang, and Pengyuan Zhang. "Confidence Learning for Semi-Supervised Acoustic Event Detection." Applied Sciences 11, no. 18 (September 15, 2021): 8581. http://dx.doi.org/10.3390/app11188581.
Повний текст джерелаАнотація:
In recent years, the involvement of synthetic strongly labeled data, weakly labeled data, and unlabeled data has drawn much research attention in semi-supervised acoustic event detection (SAED). The classic self-training method carries out predictions for unlabeled data and then selects predictions with high probabilities as pseudo-labels for retraining. Such models have shown its effectiveness in SAED. However, probabilities are poorly calibrated confidence estimates, and samples with low probabilities are ignored. Hence, we introduce a confidence-based semi-supervised Acoustic event detection (C-SAED) framework. The C-SAED method learns confidence deliberately and retrains all data distinctly by applying confidence as weights. Additionally, we apply a power pooling function whose coefficient can be trained automatically and use weakly labeled data more efficiently. The experimental results demonstrate that the generated confidence is proportional to the accuracy of the predictions. Our C-SAED framework achieves a relative error rate reduction of 34% in contrast to the baseline model.
8
She, Dong-Yu, and Kun Xu. "Contrastive Self-supervised Representation Learning Using Synthetic Data." International Journal of Automation and Computing 18, no. 4 (May 11, 2021): 556–67. http://dx.doi.org/10.1007/s11633-021-1297-9.
Повний текст джерелаАнотація:
AbstractLearning discriminative representations with deep neural networks often relies on massive labeled data, which is expensive and difficult to obtain in many real scenarios. As an alternative, self-supervised learning that leverages input itself as supervision is strongly preferred for its soaring performance on visual representation learning. This paper introduces a contrastive self-supervised framework for learning generalizable representations on the synthetic data that can be obtained easily with complete controllability. Specifically, we propose to optimize a contrastive learning task and a physical property prediction task simultaneously. Given the synthetic scene, the first task aims to maximize agreement between a pair of synthetic images generated by our proposed view sampling module, while the second task aims to predict three physical property maps, i.e., depth, instance contour maps, and surface normal maps. In addition, a feature-level domain adaptation technique with adversarial training is applied to reduce the domain difference between the realistic and the synthetic data. Experiments demonstrate that our proposed method achieves state-of-the-art performance on several visual recognition datasets.
9
Waspada, Indra, Adi Wibowo, and Noel Segura Meraz. "SUPERVISED MACHINE LEARNING MODEL FOR MICRORNA EXPRESSION DATA IN CANCER." Jurnal Ilmu Komputer dan Informasi 10, no. 2 (June 30, 2017): 108. http://dx.doi.org/10.21609/jiki.v10i2.481.
Повний текст джерелаАнотація:
The cancer cell gene expression data in general has a very large feature and requires analysis to find out which genes are strongly influencing the specific disease for diagnosis and drug discovery. In this paper several methods of supervised learning (decisien tree, naïve bayes, neural network, and deep learning) are used to classify cancer cells based on the expression of the microRNA gene to obtain the best method that can be used for gene analysis. In this study there is no optimization and tuning of the algorithm to test the ability of general algorithms. There are 1881 features of microRNA gene epresi on 25 cancer classes based on tissue location. A simple feature selection method is used to test the comparison of the algorithm. Expreriments were conducted with various scenarios to test the accuracy of the classification.
10
Zhao, Zhen, Luping Zhou, Lei Wang, Yinghuan Shi, and Yang Gao. "LaSSL: Label-Guided Self-Training for Semi-supervised Learning." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 8 (June 28, 2022): 9208–16. http://dx.doi.org/10.1609/aaai.v36i8.20907.
Повний текст джерелаАнотація:
The key to semi-supervised learning (SSL) is to explore adequate information to leverage the unlabeled data. Current dominant approaches aim to generate pseudo-labels on weakly augmented instances and train models on their corresponding strongly augmented variants with high-confidence results. However, such methods are limited in excluding samples with low-confidence pseudo-labels and under-utilization of the label information. In this paper, we emphasize the cruciality of the label information and propose a Label-guided Self-training approach to Semi-supervised Learning (LaSSL), which improves pseudo-label generations from two mutually boosted strategies. First, with the ground-truth labels and iteratively-polished pseudo-labels, we explore instance relations among all samples and then minimize a class-aware contrastive loss to learn discriminative feature representations that make same-class samples gathered and different-class samples scattered. Second, on top of improved feature representations, we propagate the label information to the unlabeled samples across the potential data manifold at the feature-embedding level, which can further improve the labelling of samples with reference to their neighbours. These two strategies are seamlessly integrated and mutually promoted across the whole training process. We evaluate LaSSL on several classification benchmarks under partially labeled settings and demonstrate its superiority over the state-of-the-art approaches.
Дисертації з теми "Strongly supervised learning"
1
Gardner, Angelica. "Stronger Together? An Ensemble of CNNs for Deepfakes Detection." Thesis, Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-97643.
Повний текст джерелаАнотація:
Deepfakes technology is a face swap technique that enables anyone to replace faces in a video, with highly realistic results. Despite its usefulness, if used maliciously, this technique can have a significant impact on society, for instance, through the spreading of fake news or cyberbullying. This makes the ability of deepfakes detection a problem of utmost importance. In this paper, I tackle the problem of deepfakes detection by identifying deepfakes forgeries in video sequences. Inspired by the state-of-the-art, I study the ensembling of different machine learning solutions built on convolutional neural networks (CNNs) and use these models as objects for comparison between ensemble and single model performances. Existing work in the research field of deepfakes detection suggests that escalated challenges posed by modern deepfake videos make it increasingly difficult for detection methods. I evaluate that claim by testing the detection performance of four single CNN models as well as six stacked ensembles on three modern deepfakes datasets. I compare various ensemble approaches to combine single models and in what way their predictions should be incorporated into the ensemble output. The results I found was that the best approach for deepfakes detection is to create an ensemble, though, the ensemble approach plays a crucial role in the detection performance. The final proposed solution is an ensemble of all available single models which use the concept of soft (weighted) voting to combine its base-learners’ predictions. Results show that this proposed solution significantly improved deepfakes detection performance and substantially outperformed all single models.
2
Maicas, Suso Gabriel. "Pre-hoc and Post-hoc Diagnosis and Interpretation of Breast Magnetic Resonance Volumes." Thesis, 2018. http://hdl.handle.net/2440/120330.
Повний текст джерелаАнотація:
Breast cancer is among the leading causes of death in women. Aiming at reducing the number of casualties, breast screening programs have been implemented to diagnose asymptomatic cancers due to the correlation of higher survival rates with earlier tumour detection. Although these programs are normally based on mammography, magnetic resonance imaging (MRI) is recommended for patients at high-risk. The interpretation of such MRI volumes is timeconsuming and prone to inter-observer variability, leading to missed cancers and a relatively high number of false positives provoking unnecessary biopsies. Consequently, computeraided diagnosis systems are being designed to help improve the efficiency and the diagnosis outcomes of radiologists in breast screening programs. Traditional automated breast screening systems are based on a two-stage pipeline consisting of the localization of suspicious regions of interest (ROIs) and their classification to perform the diagnosis (i.e. decide about their malignancy). This process is typically ineffective due to the usual expensive inference involved in the exhaustive search for ROIs and the employment of non-optimal hand-crafted features in both stages. These issues have been partially addressed with the introduction of deep learning methods that unfortunately need large strongly annotated training datasets (voxel-wise labelling of each lesion), which tend to be expensive to acquire. Alternatively, the use of weakly labelled datasets (i.e volume-level labels) allows diagnosis to become a supervised classification problem, where a malignancy probability is estimated after examining the entire volume. However, large weakly labelled training sets are still required. Additionally, to facilitate the adoption of such weakly trained systems in clinical practice, it is desirable that they are capable of providing the localization of lesions that justifies the automatically produced diagnosis for the whole volume. Nonetheless, current methods lack the precision required for the problem of weakly supervised lesion detection. Motivated by these limitations, we propose a number of methods that address these deficiencies. First, we propose two strongly supervised deep learning approaches that not only can be trained with relatively small datasets, but are efficient in the localization of suspicious tissue. In particular, we propose: 1) the global minimization of an energy functional containing information from the semantic segmentation produced by a deep learning model for lesion segmentation, and 2) a reinforcement learning model for suspicious region detection. Diagnosis is performed by classifying suspicious regions yielded by the reinforcement learning model. Second, aiming to reduce the burden associated to strongly annotating datasets, we propose a novel training methodology to improve the diagnosis performance on systems trained with weakly labelled datasets that contain a relatively small number of training samples. We further propose a novel 1-class saliency detector to automatically localize lesions associated with the diagnosis outcome of this model. Finally, we present a comparison between both of our proposed approaches for diagnosis and lesion detection. Experiments show that whole volume analysis with weakly labelled datasets achieves better performance for malignancy diagnosis than the strongly supervised methods. However, strongly supervised methods show better accuracy for lesion detection.Thesis (Ph.D.) -- University of Adelaide, School of Computer Science, 2018
Частини книг з теми "Strongly supervised learning"
1
He, Qinyuan, and Hualong Yu. "Optimal Decision Threshold-Moving Strategy for Skewed Gaussian Naive Bayes Classifier." In Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications, 837–43. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-2456-9_85.
Повний текст джерелаАнотація:
AbstractGaussian Naive Bayes (GNB) is a popular supervised learning algorithm to address various classification issues. GNB has strong theoretical basis, however, its performance tends to be hurt by skewed data distribution. In this study, we present an optimal decision threshold-moving strategy for helping GNB to adapt imbalanced classification data. Specifically, a PSO-based optimal procedure is conducted to tune the posterior probabilities produced by GNB, further repairing the bias on classification boundary. The proposed GNB-ODTM algorithm presents excellent adaptation to skewed data distribution. Experimental results on eight class imbalance data sets also indicate the effectiveness and superiority of the proposed algorithm.
2
Batina, Lejla, Milena Djukanovic, Annelie Heuser, and Stjepan Picek. "It Started with Templates: The Future of Profiling in Side-Channel Analysis." In Security of Ubiquitous Computing Systems, 133–45. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-10591-4_8.
Повний текст джерелаАнотація:
AbstractSide-channel attacks (SCAs) are powerful attacks based on the information obtained from the implementation of cryptographic devices. Profiling side-channel attacks has received a lot of attention in recent years due to the fact that this type of attack defines the worst-case security assumptions. The SCA community realized that the same approach is actually used in other domains in the form of supervised machine learning. Consequently, some researchers started experimenting with different machine learning techniques and evaluating their effectiveness in the SCA context. More recently, we are witnessing an increase in the use of deep learning techniques in the SCA community with strong first results in side-channel analyses, even in the presence of countermeasures. In this chapter, we consider the evolution of profiling attacks, and subsequently we discuss the impacts they have made in the data preprocessing, feature engineering, and classification phases. We also speculate on the future directions and the best-case consequences for the security of small devices.
3
Lien, Yen-Chieh, Rongting Zhang, F. Maxwell Harper, Vanessa Murdock, and Chia-Jung Lee. "Leveraging Customer Reviews for E-commerce Query Generation." In Lecture Notes in Computer Science, 190–98. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-99739-7_22.
Повний текст джерелаАнотація:
AbstractCustomer reviews are an effective source of information about what people deem important in products (e.g. “strong zipper” for tents). These crowd-created descriptors not only highlight key product attributes, but can also complement seller-provided product descriptions. Motivated by this, we propose to leverage customer reviews to generate queries pertinent to target products in an e-commerce setting. While there has been work on automatic query generation, it often relied on proprietary user search data to generate query-document training pairs for learning supervised models. We take a different view and focus on leveraging reviews without training on search logs, making reproduction more viable by the public. Our method adopts an ensemble of the statistical properties of review terms and a zero-shot neural model trained on adapted external corpus to synthesize queries. Compared to competitive baselines, we show that the generated queries based on our method both better align with actual customer queries and can benefit retrieval effectiveness.
4
Marcher, Thomas, Georg Erharter, and Paul Unterlass. "Capabilities and Challenges Using Machine Learning in Tunnelling." In Theory and Practice on Tunnel Engineering [Working Title]. IntechOpen, 2021. http://dx.doi.org/10.5772/intechopen.97695.
Повний текст джерелаАнотація:
Digitalization changes the design and operational processes in tunnelling. The way of gathering geological data in the field of tunnelling, the methods of rock mass classification as well as the application of tunnel design analyses, tunnel construction processes and tunnel maintenance will be influenced by this digital transformation. The ongoing digitalization in tunnelling through applications like building information modelling and artificial intelligence, addressing a variety of difficult tasks, is moving forward. Increasing overall amounts of data (big data), combined with the ease to access strong computing powers, are leading to a sharp increase in the successful application of data analytics and techniques of artificial intelligence. Artificial Intelligence now arrives also in the fields of geotechnical engineering, tunnelling and engineering geology. The chapter focuses on the potential for machine learning methods – a branch of Artificial Intelligence - in tunnelling. Examples will show that training artificial neural networks in a supervised manner works and yields valuable information. Unsupervised machine learning approaches will be also discussed, where the final classification is not imposed upon the data, but learned from it. Finally, reinforcement learning seems to be trendsetting but not being in use for specific tunnel applications yet.
5
Khan, Muhammad Taimoor, and Shehzad Khalid. "Sentiment Analysis for Health Care." In Big Data, 676–89. IGI Global, 2016. http://dx.doi.org/10.4018/978-1-4666-9840-6.ch031.
Повний текст джерелаАнотація:
Sentiment analysis for health care deals with the diagnosis of health care related problems identified by the patients themselves. It takes the patients opinions into perspective to make policies and modifications that could directly address their problems. Sentiment analysis is used with commercial products to great effect and has outgrown to other application areas. Aspect based analysis of health care, not only recommend the services and treatments but also present their strong features for which they are preferred. Machine learning techniques are used to analyze millions of review documents and conclude them towards an efficient and accurate decision. The supervised techniques have high accuracy but are not extendable to unknown domains while unsupervised techniques have low accuracy. More work is targeted to improve the accuracy of the unsupervised techniques as they are more practical in this time of information flooding.
6
Anderson, Raymond A. "Segmentation." In Credit Intelligence & Modelling, 687–704. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780192844194.003.0022.
Повний текст джерелаАнотація:
Segmentation identifies subgroups better served if treated separately, especially for risk-heterogeneous populations. Trade-offs occur between the resulting extra lift and the extra costs and complexities. It provides little where risk-homogeneity is enforced by strong filtering mechanisms. (1) Overview—i) drivers—operational, strategic, feedstock or interactional; ii) inhibitors—limits on the number of segments {insufficient data, costs of development, implementation, monitoring}; iii) mitigators—steps to reduce model count {interaction characteristics, alternative transformation and development methodologies}. (2) Analysis—i) learning types—supervised and unsupervised; ii) finding interactions—how to measure interactions for binary targets; iii) segment mining—comparing multiple options; iv) boundary analysis—assessing the impact for cases that switch segments. (3) Presentation—tabular and graphic means of presenting comparisons of different options, especially against having a single model. It includes performance within and across segments, drill-downs into segments and strategy curves showing differences in Accept and Bad rates.
7
Teodor, Stefanut, Dorian Gorgan, Eleni Kaldoudi, Nikolas Dovrolis, and Stefan Dietze. "Creating Educational Resources for Medical Education in the Web2.0/Web3.0 Era." In Advances in Business Information Systems and Analytics, 275–94. IGI Global, 2013. http://dx.doi.org/10.4018/978-1-4666-4062-7.ch015.
Повний текст джерелаАнотація:
The accelerated development of the networked society throughout the last few years had a strong impact on the teaching and learning activities from the medical related domains. E-learning applications have become very popular and encouraged the shift from traditional training activities – having the teacher as a mediator, towards self-guided ones where the teacher is rather a supervisor. These changes imposed the creation of new, more complex and more interactive teaching resources, with high quality standards, that could fulfill the requirements of the new approach. At present, the lack of specialized development tools requires the involvement of both medical and IT specialists in the resources creation process, consequently, generating higher production costs. In this chapter, the authors present two specialized tools – MetaMorphosis+ and eGLE – together with a new resources development methodology based on the repurposing approach and the blend of social networks activities with semantic web functionalities. In addition, the authors describe the user evaluation activities performed over the MetaMorphosis+ application and the results obtained.
8
Salhi, Dhai Eddine, Abelkamel Tari, and Mohand Tahar Kechadi. "Using E-Reputation for Sentiment Analysis." In Research Anthology on Implementing Sentiment Analysis Across Multiple Disciplines, 1384–400. IGI Global, 2022. http://dx.doi.org/10.4018/978-1-6684-6303-1.ch071.
Повний текст джерелаАнотація:
In a competitive world, companies are looking to gain a positive reputation through these clients. Electronic reputation is part of this reputation mainly in social networks, where everyone is free to express their opinion. Sentiment analysis of the data collected in these networks is very necessary to identify and know the reputation of a companies. This paper focused on one type of data, Twits on Twitter, where the authors analyzed them for the company Djezzy (mobile operator in Algeria), to know their satisfaction. The study is divided into two parts: The first part was the pre-processing phase, where this research filtered the Twits (eliminate useless words, use the tokenization) to keep the necessary information for a better accuracy. The second part was the application of machine learning algorithms (SVM and logistic regression) for a supervised classification since the results are binary. The strong point of this study was the possibility to run the chosen algorithms on a cloud in order to save execution time; the solution also supports the three languages: Arabic, English, and French.
9
Rahim, Rahila, Aamir S Ahanger, Sajad M Khan, and Faheem Masoodi. "Analysis of IDS using Feature Selection Approach on NSL-KDD Dataset." In SCRS CONFERENCE PROCEEDINGS ON INTELLIGENT SYSTEMS, 475–81. Soft Computing Research Society, 2021. http://dx.doi.org/10.52458/978-93-91842-08-6-45.
Повний текст джерелаАнотація:
Due to the increased use of the internet, cyber-attacks are becoming more prominent causing major difficulty in achieving and preventing security risks and threats in the network. There have been a variety of attacks (both passive and aggressive) used to compromise network security and privacy. As a result, network security is becoming an increasingly important aspect in safe guarding and maintaining network data and resources to ensure dependable, secure access and protection against vulnerabilities. For detecting such attacks quickly and accurately, a strong Intrusion Detection System is required which is a valuable means for detecting intrusions in a network or system by extensively inspecting each packet in the network in real-time, preventing any harm to the user or system resources. In this paper, we proposed a statistical method to train the model with the training data to understand complicated patterns in the dataset and to make intelligent decisions or predictions whenever it comes across new or previously unseen data instances. For the classification of data, we used five machine learning classifiers such as Support Vector Machine, Decision Tree, Random Forest, AdaBoost, and Logistic Regression. To properly grasp complicated patterns in data, machine learning models require a large amount of data, which is why NSL-KDD was utilized to develop and validate supervised machine learning models. Initially, the dataset is pre-processed to remove any unnecessary or undesired dataset features. Feature selection (extra-treeclassifier) were used which combines the qualities of both filter and wrapper methods to provide features based on their importance as a result, the dataset dimensionality is reduced, lowering the processing complexity. Finally, the overall classification accuracy of the various machine learning classifiers was evaluated to find the best optimal algorithm for detecting intrusions.
Тези доповідей конференцій з теми "Strongly supervised learning"
1
Wang, Jiajie, Jiangchao Yao, Ya Zhang, and Rui Zhang. "Collaborative Learning for Weakly Supervised Object Detection." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/135.
Повний текст джерелаАнотація:
Weakly supervised object detection has recently received much attention, since it only requires image-level labels instead of the bounding-box labels consumed in strongly supervised learning. Nevertheless, the save in labeling expense is usually at the cost of model accuracy.In this paper, we propose a simple but effective weakly supervised collaborative learning framework to resolve this problem, which trains a weakly supervised learner and a strongly supervised learner jointly by enforcing partial feature sharing and prediction consistency. For object detection, taking WSDDN-like architecture as weakly supervised detector sub-network and Faster-RCNN-like architecture as strongly supervised detector sub-network, we propose an end-to-end Weakly Supervised Collaborative Detection Network. As there is no strong supervision available to train the Faster-RCNN-like sub-network, a new prediction consistency loss is defined to enforce consistency of predictions between the two sub-networks as well as within the Faster-RCNN-like sub-networks. At the same time, the two detectors are designed to partially share features to further guarantee the model consistency at perceptual level. Extensive experiments on PASCAL VOC 2007 and 2012 data sets have demonstrated the effectiveness of the proposed framework.
2
Liu, Meng, Nate Veldt, Haoyu Song, Pan Li, and David F. Gleich. "Strongly Local Hypergraph Diffusions for Clustering and Semi-supervised Learning." In WWW '21: The Web Conference 2021. New York, NY, USA: ACM, 2021. http://dx.doi.org/10.1145/3442381.3449887.
Повний текст джерела
3
Wang, Yuhui, Xin Jin, and Xiaoyang Tan. "Pornographic image recognition by strongly-supervised deep multiple instance learning." In 2016 IEEE International Conference on Image Processing (ICIP). IEEE, 2016. http://dx.doi.org/10.1109/icip.2016.7533195.
Повний текст джерела
4
Du, Yu, Yongkang Wong, Wenguang Jin, Wentao Wei, Yu Hu, Mohan Kankanhalli, and Weidong Geng. "Semi-Supervised Learning for Surface EMG-based Gesture Recognition." In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/225.
Повний текст джерелаАнотація:
Conventionally, gesture recognition based on non-intrusive muscle-computer interfaces required a strongly-supervised learning algorithm and a large amount of labeled training signals of surface electromyography (sEMG). In this work, we show that temporal relationship of sEMG signals and data glove provides implicit supervisory signal for learning the gesture recognition model. To demonstrate this, we present a semi-supervised learning framework with a novel Siamese architecture for sEMG-based gesture recognition. Specifically, we employ auxiliary tasks to learn visual representation; predicting the temporal order of two consecutive sEMG frames; and, optionally, predicting the statistics of 3D hand pose with a sEMG frame. Experiments on the NinaPro, CapgMyo and csl-hdemg datasets validate the efficacy of our proposed approach, especially when the labeled samples are very scarce.
5
Pardo, Alejandro, Mengmeng Xu, Ali Thabet, Pablo Arbelaez, and Bernard Ghanem. "BAOD: Budget-Aware Object Detection." In LatinX in AI at Computer Vision and Pattern Recognition Conference 2021. Journal of LatinX in AI Research, 2021. http://dx.doi.org/10.52591/lxai202106254.
Повний текст джерелаАнотація:
We study the problem of object detection from a novel perspective in which annotation budget constraints are taken into consideration, appropriately coined Budget Aware Object Detection (BAOD). When provided with a fixed budget, we propose a strategy for building a diverse and informative dataset that can be used to optimally train a robust detector. We investigate both optimization and learning-based methods to sample which images to annotate and what type of annotation (strongly or weakly supervised) to annotate them with. We adopt a hybrid supervised learning framework to train the object detector from both these types of annotation. We conduct a comprehensive empirical study showing that a handcrafted optimization method outperforms other selection techniques including random sampling, uncertainty sampling and active learning. By combining an optimal image/annotation selection scheme with hybrid supervised learning to solve the BAOD problem, we show that one can achieve the performance of a strongly supervised detector on PASCAL-VOC 2007 while saving 12.8% of its original annotation budget. Furthermore, when 100% of the budget is used, it surpasses this performance by 2.0 mAP percentage points.
6
Lang, Xiao, Da Wu, and Wengang Mao. "Benchmark Study of Supervised Machine Learning Methods for a Ship Speed-Power Prediction at Sea." In ASME 2021 40th International Conference on Ocean, Offshore and Arctic Engineering. American Society of Mechanical Engineers, 2021. http://dx.doi.org/10.1115/omae2021-62395.
Повний текст джерелаАнотація:
Abstract The development and evaluation of energy efficiency measures to reduce air emissions from shipping strongly depends on reliable description of a ship’s performance when sailing at sea. Normally, model tests and semi-empirical formulas are used to model a ship’s performance but they are either expensive or lack accuracy. Nowadays, a lot of ship performance-related parameters have been recorded during a ship’s sailing, and different data driven machine learning methods have been applied for the ship speed-power modelling. This paper compares different supervised machine learning algorithms, i.e., eXtreme Gradient Boosting (XGBoost), neural network, support vector machine, and some statistical regression methods, for the ship speed-power modelling. A worldwide sailing chemical tanker with full-scale measurements is employed as the case study vessel. A general data pre-processing method for the machine learning is presented. The machine learning models are trained using measurement data including ship operation profiles and encountered metocean conditions. Through the benchmark study, the pros and cons of different machine learning methods for the ship’s speed-power performance modelling are identified. The accuracy of various algorithms based models for ship performance during individual voyages is also investigated.
7
Pagé Fortin, Mathieu, and Brahim Chaib-draa. "Continual Semantic Segmentation Leveraging Image-level Labels and Rehearsal." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/177.
Повний текст джерелаАнотація:
Despite the remarkable progress of deep learning models for semantic segmentation, the success of these models is strongly limited by the following aspects: 1) large datasets with pixel-level annotations must be available and 2) training must be performed with all classes simultaneously. Indeed, in incremental learning scenarios, where new classes are added to an existing framework, these models are prone to catastrophic forgetting of previous classes. To address these two limitations, we propose a weakly-supervised mechanism for continual semantic segmentation that can leverage cheap image-level annotations and a novel rehearsal strategy that intertwines the learning of past and new classes. Specifically, we explore two rehearsal technique variants: 1) imprinting past objects on new images and 2) transferring past representations in intermediate features maps. We conduct extensive experiments on Pascal-VOC by varying the proportion of fully- and weakly-supervised data in various setups and show that our contributions consistently improve the mIoU on both past and novel classes. Interestingly, we also observe that models trained with less data in incremental steps sometimes outperform the same architectures trained with more data. We discuss the significance of these results and propose some hypotheses regarding the dynamics between forgetting and learning.
8
Wolff, Sascha, Jan-Simon Schäpel, and Rudibert King. "Application of Artificial Neural Networks for Misfiring Detection in an Annular Pulsed Detonation Combustor Mockup." In ASME Turbo Expo 2016: Turbomachinery Technical Conference and Exposition. American Society of Mechanical Engineers, 2016. http://dx.doi.org/10.1115/gt2016-56007.
Повний текст джерелаАнотація:
An annular pulsed detonation combustor basically consists of a number of detonation tubes which are firing in a predetermined sequence into a common downstream annular plenum. Fluctuating initial conditions and fluctuating environmental parameters strongly affect the detonation. Operating such a set-up without misfiring is delicate. Misfiring of individual combustion tubes will significantly lower performance or even stop the engine. Hence, an operation of such an engine requires a misfiring detection. Here, a supervised data driven machine learning approach is used for the misfiring detection. The features used as inputs for the classifier are extracted from measurements incorporating physical knowledge about the given set-up. To this end, a neural network is trained based on labeled data which is then used for classification purposes, i.e., misfiring detection. A surrogate, non-reacting experimental set-up is considered in order to develop and test these methods.
9
Hu, Yazhe, and Tomonari Furukawa. "A Self-Supervised Learning Technique for Road Defects Detection Based on Monocular Three-Dimensional Reconstruction." In ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers, 2019. http://dx.doi.org/10.1115/detc2019-98135.
Повний текст джерелаАнотація:
Abstract This paper presents a self-supervised learning technique for road surface defects detection using a monocular camera. The uniqueness of the proposed technique relies on its self-supervised learning structure which is achieved by combining physics-driven three-dimensional (3D) reconstruction with data-driven Convolutional Neural Network (CNN). Only images from one camera are needed as the inputs to the model without human labeling. The 3D point cloud are reconstructed from input images based on a near-planar road 3D reconstruction process to self-supervise the learning process. During testing, the network receives images and predicts the images as defect or non-defect. A refined class prediction is produced by combining the 3D road surface data with the network output when the belief of original network prediction is not strong enough to conclude the classification. Experiments are conducted on real road surface images to find the optimal parameters for this model. The testing results demonstrate the robustness and effectiveness of the proposed self-supervised road surface defects detection technique.
10
Rahman, M. Shafiqur, Jonathan Ciaccio, and Uttam K. Chakravarty. "A Machine Learning Approach for Predicting Melt-Pool Dynamics of Ti-6Al-4V Alloy in the Laser Powder-Bed Fusion Process." In ASME 2021 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2021. http://dx.doi.org/10.1115/imece2021-71348.
Повний текст джерелаАнотація:
Abstract This paper presents a supervised machine learning (ML) model to predict the melt-pool geometries of Ti-6Al-4V alloy in the laser powder-bed fusion (L-PBF) process. The ML model is developed based on the normalized values of the five key features (i.e., the laser and material parameters) — laser power, scanning speed, spot size, powder layer thickness, and powder porosity. The two target variables are the melt-pool width and depth, which define the melt-pool geometry and strongly correlate the geometry with the melt-pool dynamics. Information about the features and the corresponding target variables are compiled from an extensive literature survey. A trained data set is created with the melt-pool evolution data collected from experiments. The data set is divided into training and testing sets before any feature engineering, visualization, and analysis, to prevent any data leakage. The k-fold cross-validation technique is applied to minimize the error and find the best performance. Multiple regression methods are trained and tested to find the best model to predict the melt-pool geometry data. Extra trees regressor is found to be the model with the least amount of error using the mean absolute error function. The verification of the ML model is performed by comparing its results with the experimental and CFD modeling results for the melt-pool geometry at a given combination of the processing parameters in the L-PBF process. The melt-pool geometry outputs obtained for the ML model are consistent with the experimental and CFD modeling results.