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

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

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

Multiview Integration Network for Multitask Robotic Surgical Scene Analysis

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Shen, Wenting Wang, Yaonan Liu, Min Wang, Jiazheng Ding, Renjie Zhang, Zhe Meijering, Erik Hunan University College of Electrical and Information Engineering National Engineering Research Center of Robot Visual Perception and Control Technology International Scientific and Technological Innovation Cooperation Base for Biomedical Image Processing Hunan Changsha410082 China University of New South Wales School of Computer Science and Engineering SydneyNSW2052 Australia

Surgical scene analysis holds a pivotal role in robot-assisted surgery. However, existing methods often suffer from single or little views, leading to erroneous scene analysis conclusions. To address these issues, a novel Multiview Integration Network (MVINet) is proposed, which comprehensively analyzes the surgical scene by integrating effective information from multiple views, including global, local, dynamic, and static views. As a multitask scene analysis network, MVINet could simultaneously perform semantic segmentation of surgical instruments and detection of instrument-tissue interaction. By designing a unique Global-Local Spatial Feature Memory module (G-LSFM), the joint information from globally and locally analyzed views following graph analysis simultaneously enhances the accuracy of multitask scene analysis. The Dynamic-Static Visual Feature Memory module (D-SVFM) introduces an innovative approach by simultaneously incorporating temporal feature from consecutive frames and static feature from single frame into the node features of the interaction reasoning network. The multiscale perspective of both features further enhances the ability of the module to analyze the complex scenes. Experimental results on a public and a private dataset demonstrate that our method achieves superior performance compared to other state-of-the-art methods for two crucial tasks in surgical scene analysis. In the instrument segmentation task, MVINet outperforms the second-best method by 1.73% and 0.55% in terms of mIoU scores. For the interaction detection task, MVINet surpasses the second-best method by 10.14% and 5.47% in mAP scores. © 1963-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

MN-Net: Speech Enhancement Network via Modeling the Noise

引用

IEEE Transactions on Audio, Speech and Language processing 2025年 33卷 1208-1219页

作者： Ying Hu Qin Yang Wenbing Wei Li Lin Liang He Zhijian Ou Wenzhong Yang School of Computer Science and Technology Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China Xinjiang Institute of Electronics Research Shares Company Ltd. Urumqi China Department of Electrical Engineering Tsinghua University Beijing China Beijing National Research Center for information Science and Technology Department of Electronics Tsinghua University Beijing China

Currently, deep learning-based speech enhancement methods generally focus on target speech extraction while neglecting modeling the other sound sources in the mixture. These methods still can't distinguish the target speech from the interference well. In this paper, we present a monaural speech enhancement network via Modeling the Noise (MN-Net), which includes a shared Encoder and three separate Decoders for parallel modeling the magnitude and phase spectrogram of target speech, and the complex spectrogram of noise. Specifically, we propose a Multi-Branch Feature Extractor (MBFE) module to capture the richer contextual information in mixture, and a Spatial Reconstruction Unit (SRU) to remove the redundancy from extracted features. We compared our proposed MN-Net with 18 classical speech enhancement methods on the VoiceBank+DEMAND dataset, and with 9 ones on DNS-Challenge dataset for denoising task, and with 7 ones on the WHAMR! dataset for simultaneous denoising & de-reverberation task. Our proposed MBFE module was applied to two classical speech enhancement methods, DB-AIAT and CMGAN, replacing their DenseBlocks module. The results demonstrate that applying the MBFE module can boost their performances while keeping smaller model size. A series of visualization analysis intuitively verify that modeling the noise can enable the network to distinguish the target speech from noise and other interference more accurately.

关键词： Noise Feature extraction Spectrogram Speech enhancement Decoding Kernel Transformers Noise reduction Data mining Training

来源：评论

学校读者我要写书评

暂无评论

On homomorphic deconvolution of bandpass signals

引用

IEEE TRANSACTIONS ON signal processing 1997年第10期45卷 2499-2514页

作者： Marenco, AL Madisetti, VK Center for Signal and Image Processing (CSIP) Georgia Institute of Technology School of Electrical and Computer Engineering Atlanta GA USA

A convolution may be represented as x(.) = r(.)* w(.). The goal of deconvolution is to extract r(.) and w(.) from a knowledge of x(.) and finds numerous applications in digital signal processing, Of practical interest in oil exploration is the case where w(.) is a seismic pressure wavelet, x(.) is the observed seismic response, and, (.) is the reflectivity of the earth, A number of procedures have been proposed, including predictive, deterministic, and homomorphic deconvolution, Homomorphic deconvolution has been found to be particularly efficient for those cases where x(.) is known to be fullband. This paper presents a robust constructive procedure for efficient homomorphic deconvolution for those cases where x(.) is a bandpass signal, Extensive comparisons with other methods for deconvolving bandpass signals on measured seismic data traces (including the Novaya Zemlya event) illustrate the improvement in the deconvolution.

关键词： Deconvolution Convolution Reflection Digital signal processing Reflectivity Seismic measurements signal processing Pollution measurement Cepstral analysis Cepstrum

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal wavelet transforms for digital signal analysis

引用

signal processing 1997年第1期60卷 23-41页

作者： Leduc, JP Georgia Institute of Technology School of Electrical and Computer Engineering Center of Signal and Image Processing Atlanta GA 30332-0250 USA

The goal of this paper is to investigate spatio-temporal continuous wavelet transforms. A new wavelet family, called the Galilean wavelet, has been designed to tune to four main parameters, namely, scale, spatio-temporal position, spatial orientation, and velocity. The paper starts with the theory of motion-compensated wavelet filtering in the discrete realm of image processing. As a major difference from multi-dimensional homogeneous spaces, spatio-temporal signal involves motion that warps the signal along the trajectories. Modeling motion with 2-D affine transformations leads to spatio-temporal generalizations. Decomposition into elementary operators leads to developing transformation groups and exploiting the related representation theory. The construction of continuous spatio-temporal wavelets in R-n x R spaces is then handled with classical techniques of calculation. Close connections may then be established among all the spatio-temporal wavelet transforms through different sets of transformations. This approach generates a general framework for the study of future tools. Frames of wavelets are thereafter investigated to revisit discrete wavelet transforms in a more general way. Eventually, illustrations demonstrate the ability of Galilean wavelet transforms to analyze spatio-temporal signals. (C) 1997 Elsevier Science B.V.

关键词： wavelet transforms spatio-temporal signals image sequences motion analysis group of transformations regions of interest selective feature extraction

来源：评论

学校读者我要写书评

暂无评论

Sinusoidal modeling and modification of unvoiced speech

引用

IEEE TRANSACTIONS ON SPEECH AND AUDIO processing 1997年第6期5卷 557-560页

作者： Macon, MW Clements, MA Oregon Graduate Institute of Science and Technology Portland OR USA Center for Signal and Image Processing The Georgia Institute of Technology School of Electrical and Computer Engineering Atlanta GA USA

Although sinusoidal models have been shown to be useful for time-scale and pitch modification of voiced speech, objectionable artifacts often arise when such models are applied to unvoiced speech. This correspondence presents a sinusoidal model-based speech modification algorithm that preserves the natural character of unvoiced speech sounds after pitch and time-scale modification, eliminating commonly encountered artifacts. This advance is accomplished via a perceptually motivated modulation of the sinusoidal component phases that mitigates artifacts in the reconstructed signal after time-scale and pitch modification.

关键词： speech coding speech synthesis

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：