检索结果-内蒙古大学图书馆

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Kokilepersaud, Kiran Kim, Seulgi Prabhushankar, Mohit Alregib, Ghassan Olives The Center for Signal and Information Processing Csip School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States

ISBN: (纸本)9798331510831

In this paper, we propose an algorithm that can be used on top of a wide variety of self-supervised (SSL) approaches to take advantage of hierarchical structures that emerge during training. SSL approaches typically work through some invariance term to ensure consistency between similar samples and a regularization term to prevent global dimensional collapse. Dimensional collapse refers to data representations spanning a lower-dimensional subspace. Recent work has demonstrated that the representation space of these algorithms gradually reflects a semantic hierarchical structure as training progresses. Data samples of the same hierarchical grouping tend to exhibit greater dimensional collapse locally compared to the dataset as a whole due to sharing features in common with each other. Ideally, SSL algorithms would take advantage of this hierarchical emergence to have an additional regularization term to account for this local dimensional collapse effect. However, the construction of existing SSL algorithms does not account for this property. To address this, we propose an adaptive algorithm that performs a weighted decomposition of the denominator of the InfoNCE loss into two terms: local hierarchical and global collapse regularization respectively. This decomposition is based on an adaptive threshold that gradually lowers to reflect the emerging hierarchical structure of the representation space throughout training. It is based on an analysis of the cosine similarity distribution of samples in a batch. We demonstrate that this hierarchical emergence exploitation (HEX) approach can be integrated across a wide variety of SSL algorithms. Empirically, we show performance improvements of up to 5.6% relative improvement over baseline SSL approaches on classification accuracy on imagenet with 100 epochs of training. © 2025 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Targeting Negative Flips in Active Learning using Validation Sets

Targeting Negative Flips in Active Learning using Validation...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Benkert, Ryan Prabhushankar, Mohit Alregib, Ghassan Georgia Institute of Technology Olives The Center for Signal and Information Processing Csip School of Electrical and Computer Engineering AtlantaGA United States

ISBN: (纸本)9798350362480

The performance of active learning algorithms can be improved in two ways. The often used and intuitive way is by reducing the overall error rate within the test set. The second way is to ensure that correct predictions are not forgotten when the training set is increased in between rounds. The former is measured by the accuracy of the model and the latter is captured in negative flips between rounds. Negative flips are samples that are correctly predicted when trained with the previous/smaller dataset and incorrectly predicted after additional samples are labeled. In this paper, we discuss improving the performance of active learning algorithms both in terms of prediction accuracy and negative flips. The first observation we make in this paper is that negative flips and overall error rates are decoupled and reducing one does not necessarily imply that the other is reduced. Our observation is important as current active learning algorithms do not consider negative flips directly and implicitly assume the opposite. The second observation is that performing targeted active learning on subsets of the unlabeled pool has a significant impact on the behavior of the active learning algorithm and influences both negative flips and prediction accuracy. We then develop ROSE - a plug-in algorithm that utilizes a small labeled validation set to restrict arbitrary active learning acquisition functions to negative flips within the unlabeled pool. We show that integrating a validation set results in a significant performance boost in terms of accuracy, negative flip rate reduction, or both. © 2024 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Supervised machine learning-based salp swarm algorithm for fault diagnosis of photovoltaic systems

引用

Journal of engineering and Applied Science 2024年第1期71卷 12页

作者： Hichri, Amal Hajji, Mansour Mansouri, Majdi Nounou, Hazem Bouzrara, Kais Research Unit Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kairouan Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar Laboratory of Automatic Signal and Image Processing National School of Engineers of Monastir University of Monastir Monastir5019 Tunisia

The diagnosis of faults in grid-connected photovoltaic (GCPV) systems is a challenging task due to their complex nature and the high similarity between faults. To address this issue, we propose a wrapper approach called the salp swarm algorithm (SSA) for feature selection. The main objective of SSA is to extract only the most important features from the raw data and eliminate unnecessary ones to improve the classification accuracy of supervised machine learning (SML) classifiers. Subsequently, the selected features are used to train supervised machine learning (SML) techniques in distinguishing between various operating modes. To evaluate the efficiency of the technique, we used healthy and faulty data from GCPV systems that have been injected with frequent faults, 20 different types of faults were introduced, including line-to-line, line-to-ground, connectivity faults, and those affecting the operation of bay-pass diodes. These faults present diverse conditions, such as simple and multiple faults in the PV arrays and mixed faults in both arrays. The performances of the developed SSA-SML are compared with those using principal component analysis (PCA) and kernel PCA (KPCA) based SML techniques through different criteria (i.e., accuracy, recall, precision, F1 score, and computation time). The experimental findings demonstrated that the proposed diagnosis paradigm outperformed the other techniques and achieved a high diagnostic accuracy (an average accuracy greater than 99%) while significantly reducing computation time. © 2023, The Author(s).

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Effective uncertain fault diagnosis technique for wind conversion systems using improved ensemble learning algorithm

引用

Energy Reports 2023年 10卷 3113-3124页

作者： Attouri, Khadija Dhibi, Khaled Mansouri, Majdi Hajji, Mansour Bouzrara, Kais Nounou, Mohamed Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kasserine1200 Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Qatar Chemical Engineering Program Texas A&M University at Qatar Qatar Laboratory of Automatic Signal and Image Processing National Engineering School of Monastir University of Monastir 5019 Tunisia

This paper introduces a pioneering fault diagnosis technique termed Interval Ensemble Learning based on Sine Cosine Optimization Algorithm (IEL- SCOA), tailored to tackle uncertainties prevalent in wind energy conversion (WEC) systems. The approach unfolds in three integral phases. Firstly, the establishment of interval centers and ranges, employing upper and lower bounds, effectively manages the inherent uncertainties arising from noise and measurement errors intrinsic to the wind system. Subsequently, the dataset undergoes processing via the Sine-Cosine Optimization Algorithm (SCOA), enabling the extraction of the most pertinent attributes. The culmination of predictive precision and classification performance is achieved through the integration of the refined dataset into an ensemble learning paradigm, harmonizing bagging, boosting techniques, and an artificial neural network classifier. The principal aim of the IEL-SCOA approach is to discern the spectrum of operational conditions within WEC systems, encompassing a healthy mode alongside six distinct faulty modes. These anomalies, encompassing short circuits, open circuits, and wear-out incidents, are deliberately induced at diverse locations and facets of the system, notably the generator and grid sides. Empirical results underscore the robustness and efficiency of the proposed methodology, showcasing an exceptional accuracy rate of 99.76 %. These outcomes definitively establish the IEL-SCOA approach as a potent and efficacious tool for precise fault diagnosis in uncertain WEC systems. © 2023

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

FOCAL: A Cost-Aware Video Dataset for Active Learning

FOCAL: A Cost-Aware Video Dataset for Active Learning

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Kokilepersaud, Kiran Logan, Yash-Yee Benkert, Ryan Zhou, Chen Prabhushankar, Mohit Alregib, Ghassan Corona, Enrique Singh, Kunjan Parchami, Mostafa Georgia Institute of Technology Olives at the Center for Signal and Information Processing Csip School of Electrical and Computer Engineering AtlantaGA United States Ford Motor Company DearbornMI United States

ISBN: (纸本)9798350324457

In this paper, we introduce the FOCAL (Ford-OLIVES Collaboration on Active Learning) dataset which enables the study of the impact of annotation-cost within a video active learning setting. Annotation-cost refers to the time it takes an annotator to label and quality-assure a given video sequence. A practical motivation for active learning research is to minimize annotation-cost by selectively labeling informative samples that will maximize performance within a given budget constraint. However, previous work in video active learning lacks real-time annotation labels for accurately assessing cost minimization and instead operates under the assumption that annotation-cost scales linearly with the amount of data to annotate. This assumption does not take into account a variety of real-world confounding factors that contribute to a nonlinear cost such as the effect of an assistive labeling tool and the variety of interactions within a scene such as occluded objects, weather, and motion of objects. FOChL addresses this discrepancy by providing real annotation-cost labels for 126 video sequences across 69 unique city scenes with a variety of weather, lighting, and seasonal conditions. These videos have a wide range of interactions that are at the intersection of infrastructure-assisted autonomy and autonomous vehicle communities. We show through a statistical analysis of the FOChL dataset that cost is more correlated with a variety of factors beyond just the length of a video sequence. We also introduce a set of conformal active learning algorithms that take advantage of the sequential structure of video data in order to achieve a better trade-off between annotation-cost and performance while also reducing floating point operations (FLOPS) overhead by at least 77.67%. We show how these approaches better reflect how annotations on videos are done in practice through a sequence selection framework. We further demonstrate the advantage of these approaches by introducing two

关键词： active learning labeling cost sequential video

来源：评论

学校读者我要写书评

暂无评论

EEG based stress classification by using difference plots of variational modes and machine learning

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第12期14卷 16347-16360页

作者： Salankar, Nilima Qaisar, Saeed Mian School of Computer Science University of Petroleum and Energy Studies Dehradun India Persistent System Limited IT Park Maharashtra Nagpur India Department of Electrical and Computer Engineering EFfat University Jeddah22332 Saudi Arabia Communication and Signal Processing Lab Energy and Technology Research Center Effat University Jeddah22332 Saudi Arabia

The recent trend in healthcare is to use the automated biomedical signals processing for an augmented and precise diagnosis. In this context, an original approach is presented for categorization of stress and non-stress classes by processing the multichannel Electroencephalogram (EEG) signals. The EEG signals are decomposed by using the "Empirical Mode Decomposition" (EMD) and "Variational Mode Decomposition" (VMD), respectively render the "Intrinsic Mode Functions" (IMFs) and Modes. The Second Order Difference Plots (SODPs) are traced for each IMF and Mode. Shapes of SODPs are used to discriminate the two intended categories. The feature space includes areas, Central Tendency Measures (CTMs) and means of SODPs. It is derived from first 7 IMFs and Modes. The identification of stress and non-stress categories is performed by using the robust machine learning algorithms namely, the Support Vector Machine (SVM), Boosting with Random Forest (RF) and Multilayer Perceptron Neural Network (MLPNN). The applicability is tested by using a publicly available EEG signals dataset, recorded during mental arithmetic test. A detailed evaluation is carried out at the subset, individual channel and lobes wise. Noteworthy highest accuracies of subset wise 99.89%, channel wise 98.89% and lobe wise 99.99% are obtained respectively. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Enhanced fault diagnosis of wind energy conversion systems using ensemble learning based on sine cosine algorithm

引用

Journal of engineering and Applied Science 2023年第1期70卷 56页

作者： Attouri, Khadija Dhibi, Khaled Mansouri, Majdi Hajji, Mansour Bouzrara, Kais Nounou, Hazem Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kasserine1200 Tunisia Chemical Engineering Program Texas A&M University at Qatar 23874 Doha Qatar Electrical and Computer Engineering Program Texas A&M University at Qatar 23874 Doha Qatar Laboratory of Automatic Signal and Image Processing National Engineering School of Monastir University of Monastir Monastir5019 Tunisia

This paper investigates the problem of incipient fault detection and diagnosis (FDD) in wind energy conversion systems (WECS) using an innovative and effective approach called the ensemble learning-sine cosine optimization algorithm (EL-SCOA). The evolved strategy involves two primary steps: first, a sine-cosine algorithm is used to extract and optimize features in order to only select the most descriptive ones. Second, to further improve the capability, thereby providing the highest accuracy performance, the newly gathered dataset is introduced as input to an ensemble learning paradigm, which merges the benefits of boosting and bagging techniques with an artificial neural network classifier. The essential goal of the developed proposal is to discriminate between the diverse operating conditions (one healthy and six faulty conditions). Three potential and frequent types of faults that can affect the system behaviors including short-circuit, open-circuit, and wear-out are considered and thereby injected at diverse locations and sides (grid and generator sides) in order to evaluate the availability and performance of the proposed technique when compared to the conventional FDD methods. The diagnosis performance is analyzed in terms of accuracy, recall, precision, and computation time. The acquired outcomes demonstrate the efficiency of the suggested diagnostic paradigm compared to conventional FDD techniques (accuracy rate has been successfully achieved 98.35%). © 2023, This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms

HEX: Hierarchical Emergence Exploitation in Self-Supervised ...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Kiran Kokilepersaud Seulgi Kim Mohit Prabhushankar Ghassan AlRegib OLIVES at the Center for Signal and Information Processing CSIP School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

关键词： Training Measurement computer vision Accuracy Semantics Data visualization Adaptive algorithms Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Intelligent Multi-View Test Time Augmentation

Intelligent Multi-View Test Time Augmentation

引用

IEEE International Conference on image processing

作者： Efe Ozturk Mohit Prabhushankar Ghassan AlRegib School of Electrical and Computer Engineering OLIVES at the Center for Signal and Information Processing CSIP Georgia Institute of Technology Atlanta GA USA

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

In this study, we introduce an intelligent Test Time Augmentation (TTA) algorithm designed to enhance the robustness and accuracy of image classification models against viewpoint variations. Unlike traditional TTA methods that indiscriminately apply augmentations, our approach intelligently selects optimal augmentations based on predictive uncertainty metrics. This selection is achieved via a two-stage process: the first stage identifies the optimal augmentation for each class by evaluating uncertainty levels, while the second stage implements an uncertainty threshold to determine when applying TTA would be advantageous. This methodological advancement ensures that augmentations contribute to classification more effectively than a uniform application across the dataset. Experimental validation across several datasets and neural network architectures validates our approach, yielding an average accuracy improvement of 1.73% over methods that use single-view images. This research underscores the potential of adaptive, uncertainty-aware TTA in improving the robustness of image classification in the presence of viewpoint variations, paving the way for further exploration into intelligent augmentation strategies. The code is available at: https://***/olivesgatech/Intelligent-Multi-View-TTA

关键词： Measurement Uncertainty Accuracy image processing Neural networks Machine learning Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Explaining Representation Learning With Perceptual Components

Explaining Representation Learning With Perceptual Component...

引用

IEEE International Conference on image processing

作者： Yavuz Yarici Kiran Kokilepersaud Mohit Prabhushankar Ghassan AlRegib School of Electrical and Computer Engineering OLIVES at the Center for Signal and Information Processing CSIP Georgia Institute of Technology Atlanta GA USA

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Self-supervised models create representation spaces that lack clear semantic meaning. This interpretability problem of representations makes traditional explainability methods ineffective in this context. In this paper, we introduce a novel method to analyze representation spaces using three key perceptual components: color, shape, and texture. We employ selective masking of these components to observe changes in representations, resulting in distinct importance maps for each. In scenarios, where labels are absent, these importance maps provide more intuitive explanations as they are integral to the human visual system. Our approach enhances the interpretability of the representation space, offering explanations that resonate with human visual perception. We analyze how different training objectives create distinct representation spaces using perceptual components. Additionally, we examine the representation of images across diverse image domains, providing insights into the role of these components in different contexts.

关键词： Training Representation learning Analytical models Shape image color analysis Semantics Visual perception

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：