检索结果-内蒙古大学图书馆

Fast and Accurate Video Analysis and Visualization of Classroom Activities Using Multiobjective Optimization of Extremely Low-Parameter Models

引用

IEEE Access 2025年 13卷 81143-81166页

作者： Jatla, Venkatesh Teeparthi, Sravani Egala, Ugesh Celedón-Pattichis, Sylvia Pattichis, Marios S. The University of New Mexico Image and Video Processing and Communications Laboratory Department of Electrical and Computer Engineering AlbuquerqueNM87131 United States The University of Texas at Austin Department of Curriculum and Instruction AustinTX78712 United States

The paper considers the problem of video activity recognition in real-life collaborative classroom learning environments. Video analysis of real-life collaborative classroom learning environments faces significant challenges not encountered in current, advanced video recognition datasets. In collaborative learning environments, students are arranged in small groups where they interact within their group. Video analysis needs to deal with long-term activity recognition (of one hour or more session videos), detect multiple simultaneous activities, rapid transitions between activities, occlusions, and numerous individuals performing similar activities in the background that are not part of the group being analyzed. Developing ground truth datasets for analyzing complex video datasets is prohibitively expensive. We dramatically reduce the requirement for large ground truth datasets by creating separate, custom datasets for object detection and video activity recognition. We then introduce a separable, extremely low-parameter system for video activity recognition that can be optimally trained using the derived datasets without the need for transfer learning from larger systems trained on large datasets. We further develop an interactive WebApp for visualizing the results over long video sessions. Overall, the extremely low-parameter activity classification model uses just 18.7K parameters for each activity, requiring 136.32 MB of memory. On a moderate GPU (RTX 5000), the activity classification model runs at an impressive 4,620 ( 154 x 30 ) frames per second. Our approach uses at least 1,000 fewer parameters than several well-established methods for video recognition. Our extremely low-parameter classifiers can process 90 minutes of video in just 26 seconds. Furthermore, our models are much easier to train, they are much faster, and outperform comparable methods. © 2013 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning Using Nonlinear Dependence

arXiv

引用

arXiv 2025年

作者： Sepanj, M. Hadi Ghojogh, Benyamin Fieguth, Paul Vision and Image Processing Group Systems Design Engineering University of Waterloo ON Canada Department of Electrical and Computer Engineering University of Waterloo ON Canada

Self-supervised learning has gained significant attention in contemporary applications, particularly due to the scarcity of labeled data. While existing SSL methodologies primarily address feature variance and linear correlations, they often neglect the intricate relations between samples and the nonlinear dependencies inherent in complex data. In this paper, we introduce Correlation-Dependence Self-Supervised Learning (CDSSL), a novel framework that unifies and extends existing SSL paradigms by integrating both linear correlations and nonlinear dependencies, encapsulating sample-wise and feature-wise interactions. Our approach incorporates the Hilbert-Schmidt Independence Criterion (HSIC) to robustly capture nonlinear dependencies within a Reproducing Kernel Hilbert Space, enriching representation learning. Experimental evaluations on diverse benchmarks demonstrate the efficacy of CDSSL in improving representation quality. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-modal signal integration for enhanced sleep stage classification: Leveraging EOG and 2-channel EEG data with advanced feature extraction

引用

Artificial Intelligence in Medicine 2025年 166卷 103152-103152页

作者： Samaee, Mahdi Yazdi, Mehran Massicotte, Daniel Signal and Image Processing Laboratory School of Electrical and Computer Engineering Shiraz University Shiraz Iran Laboratory of Signal and System Integration Department of Electrical and Computer Engineering Université du Québec à Trois-Rivières Trois-Rivières Canada

This paper introduces an innovative approach to sleep stage classification, leveraging a multi-modal signal integration framework encompassing Electrooculography (EOG) and two-channel electroencephalography (EEG) data. We explore the utility of various feature extraction techniques, including Short-Time Fourier Transform (STFT), Wavelet Transform, and raw signal processing, alongside the utilization of neural networks as feature extractors. This unique combination allows us to harness the benefits of traditional feature extraction methods while capitalizing on the power of neural networks to enhance classification performance. Our comprehensive classifier evaluation encompasses a range of models, including Long Short-Term Memory (LSTM) networks and XGBoost. Remarkably, our results reveal exceptional performance with the XGBoost classifier, achieving an overall accuracy of 84.57 % and a macro-F1 score of 78.21 % on the Sleep-EDF expanded dataset, and an overall accuracy of 86.02 % and a macro-F1 score of 81.96 % on the ISRUC-Sleep dataset. Class-specific accuracies highlight its proficiency, particularly in detecting wake and N2 stages, solidifying its superiority among the classifiers tested. This amalgamation of feature sets, complemented by Principal Component Analysis (PCA) for dimensionality reduction, underscores its significance in yielding top-tier classification outcomes. The integration of traditional feature extraction methods with neural networks as feature extractors creates a robust and comprehensive system for sleep stage classification, offering the advantages of both approaches to enhance the accuracy and reliability of the results. © 2025

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Efficient Fault Detection in Nonlinear Industrial Process: A Reduced Kernel PCA-Based Spectral Clustering Approach

Efficient Fault Detection in Nonlinear Industrial Process: A...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Khadija Attouri Majdi Mansouri Mansour Hajji Kais Bouzrara Laboratory of Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir Tunisia

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

The challenges posed by nonlinearities in industrial systems necessitate innovative techniques that outperform the limitations of traditional methods such as principal component analysis (PCA). While Kernel Principal Component Analysis (KPCA) offers a robust solution to handle nonlinear data, its computational requirements are a significant issue, especially for large-sized datasets. In this work, we propose a novel technique, namely, reduced kernel principal component analysis-based spectral clustering (RKPCA SpC ), to monitor and detect faults in the benchmark Tennessee Eastman process. The suggested approach addresses the complexity associated with KPCA by reducing data size during the model training phase. This reduction involves retaining only the principal components, preserving informative features, and selecting pertinent samples without compromising the original data's content. The efficacy of the proposed method is evaluated through key performance metrics, including false alarm rate (FAR), missed detection rate (MDR), detection time delay (DTD), and computation time (CT). Additionally, gained execution time (GET), gained storage space (GSP), and loss function (LF) are considered, providing a comprehensive assessment of the developed paradigms' effectiveness. The results demonstrate the promising capabilities of our proposed scheme.

关键词： Training Measurement Technological innovation Fault detection Delay effects Computational modeling Complexity theory Kernel Monitoring Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Short-Term Photovoltaic Power Forecasting-Based Kernel Ridge Regression

Short-Term Photovoltaic Power Forecasting-Based Kernel Ridge...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Manel Marweni Majdi Mansouri Mansour Hajji Mohamed Faouzi Mimouni Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman Laboratory of Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kasserine Tunisia

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

The modern energy landscape is undergoing a seismic change from traditional, finite energy sources and toward cleaner, renewable alternatives. The restrictions faced by traditional sources, which are not only finite but increasingly shrink in the face of burgeoning global energy demands driven by population increase and industrial expansion, are driving this change. Although promising, renewable energy poses complications, particularly the reliance on climatic conditions. An important aspect of addressing these difficulties is effective energy management within distribution systems, which includes forecasting and optimization phases. This research focuses on forecasting using an advanced machine learning (ML) approach. Accurately forecasting renewable energy generation over time is critical for improving energy management. This technique is evaluated using a variety of performance indicators, including Mean Error (ME), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R 2 ). Empirical studies support the method's usefulness, demonstrating noteworthy performance with low error rates.

关键词： Photovoltaic systems Renewable energy sources Technological innovation Accuracy Machine learning Predictive models Forecasting Kernel Energy management Optimization

来源：评论

学校读者我要写书评

暂无评论

A Parallel Read-Write Circuit With Fast Amplitude-Adaptive Matching Scheme to Memristor Crossbar Array

引用

IEEE Transactions on Circuits and Systems I: Regular Papers 2025年

作者： Jiang, Ningye Jiang, Mingxuan Huang, Haoen Yang, Le Huang, Yi Zeng, Zhigang Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan430074 China Wuhan Institute of Technology School of Electrical and Information Engineering Wuhan430205 China University of Massachusetts Amherst Department of Electrical and Computer Engineering AmherstMA01003 United States

Memristor crossbar array (MCA) is a computing-in-memory (CIM) module for computational acceleration. However, conventional read-write (R-W) circuits for MCA rely heavily on external components and have shortcoming in long writing times. To address these issues, we propose a parallel R-W circuit with a fast amplitude-adaptive matching (AAM) scheme. The fast AAM scheme is designed to accelerate time of writing memristors in MCA by adaptively adjusting the writing voltage to match an optimal amplitude. The architecture of parallel R-W circuit are outlined with the implementation of R-W processes. The design principles of parallel R-W unit, fast AAM unit, and associated control logic are described for analyzing their functions within the circuit. By integrating the parallel R-W circuit with MCA, a computing block is leveraged in a neural network for classification tasks. The experimental results demonstrate that the neural network with multiple computing blocks maintains high accuracy across various datasets (over 80%). Furthermore, the proposed AAM scheme achieves an average 54% reduction in writing time compared to that one without AAM scheme. Compared to the pulse-width scheme, the parallel R-W circuit exhibits an average 3.05× speedup in adjusting a 5×5 MCA, and the speedup efficiency is higher as the increases of MCA size. © 2025 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

1.5V resistive fuse for image smoothing and segmentation

引用

ELECTRONICS LETTERS 1997年第10期33卷 851-852页

作者： Athreya, JKV Gregson, PH Department of Electrical Engineering Computer Vision and Image Processing Laboratory Technical University of Nova Scotia Halifax Canada

A 1.5V resistive fuse for image smoothing and segmentation using bulk-driven MOSFETs is presented. The circuit switches on only if the differential voltage applied across its input terminals is less than a set voltage;it switches off if the differential voltage is higher than the set value. The useful operation range of the circuit is 0.4V with a supply voltage of 1.5V and threshold voltages of V-Tn = 0.828V and V-Tp = -0.56V for n and g channel MOSFETs, respectively.

关键词： image processing segmentation (image processing)

来源：评论

学校读者我要写书评

暂无评论

Texture segmentation using hierarchical wavelet decomposition

引用

PATTERN RECOGNITION 1995年第12期28卷 1819-1824页

作者： Salari, E Ling, Z Computer Vision and Image Processing Laboratory Department of Electrical Engineering University of Toledo Toledo OH 43606 U.S.A.

This paper presents a texture segmentation algorithm based on a hierarchical wavelet decomposition. Using Daubechies' four-tap filter, an original image is decomposed into three detail images and one approximate image. The decomposition can be recursively applied to the approximate image to generate a lower resolution of the pyramid. The segmentation starts at the lowest resolution using the K-means clustering scheme and textural features obtained from various sub-bands. The result of segmentation is propagated through the pyramid to a higher resolution with continuously improving the segmentation. The lower resolution levels help to build the contour of the segmented texture, while higher levels refine the process, and correct possible errors.

关键词： Texture segmentation Wavelet transform Clustering algorithm Multiresolution segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Palmprint Recognition-A Comprehensive Survey

arXiv

引用

arXiv 2025年

作者： Gao, Chengrui Yang, Ziyuan Jia, Wei Leng, Lu Zhang, Bob Teoh, Andrew Beng Jin College of Computer Science Sichuan University Chengdu610065 China Singapore School of Computer and Information Hefei University of Technology Hefei China Jiangxi Provincial Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China Pattern Analysis and Machine Intelligence Group Department of Computer and Information Science University of Macau Taipa China School of Electrical and Electronic Engineering College of Engineering Yonsei University Seoul Korea Republic of

Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on researchers' prior knowledge. Deep learning (DL) has been introduced to address this limitation, leveraging its remarkable successes across various domains. While existing surveys focus narrowly on specific tasks within palmprint recognition-often grounded in traditional methodologies-there remains a significant gap in comprehensive research exploring DL-based approaches across all facets of palmprint recognition. This paper bridges that gap by thoroughly reviewing recent advancements in DL-powered palmprint recognition. The paper systematically examines progress across key tasks, including region-of-interest segmentation, feature extraction, and security/privacy-oriented challenges. Beyond highlighting these advancements, the paper identifies current challenges and uncovers promising opportunities for future research. By consolidating state-of-the-art progress, this review serves as a valuable resource for researchers, enabling them to stay abreast of cutting-edge technologies and drive innovation in palmprint recognition. Copyright © 2025, The Authors. All rights reserved.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

ZERO CROSSINGS, BANDWIDTH COMPRESSION, AND RESTORATION OF NONLINEARLY DISTORTED BAND-LIMITED SIGNALS

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS image SCIENCE AND vision 1986年第5期3卷 651-654页

作者： MARVASTI, F JAIN, AK Computer Vision and Image Processing Laboratory Department of Electrical and Computer Engineering University of California at Davis Davis California 95616 USA

This paper discusses the relationship between the zero crossings or zeros of band-limited signals and their nonlinear transformations. It is proved that the bandwidth of a signal can be compressed by a ratio of 1/ n if and only if the signal has n th-order zero crossings or zeros (if complex). Also, a monotonic nonlinearity in the observation of a band-limited signal can be identified from the zero crossings (or zeros) of the derivative of the observed signal. (The results are for one-dimensional signals. Extensions to two-dimensional signals remain to be addressed.)

关键词： Coherent systems Distortion Electronic imaging Imaging systems Modulation Phase shift

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：