检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Ori Peleg Natalie Lang Stefano Rini Nir Shlezinger Kobi Cohen School of ECE Ben-Gurion University of the Negev Beer-Sheva Israel Department of ECE National Yang-Ming Chiao-Tung University (NYCU) Hsinchu Taiwan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated learning (FL) is a leading approach for iterative learning using possibly private data available at edge devices. The federated operation gives rise to challenges in privacy leakage, which accumulates in learning, and communication latency. These limitations are often individually mitigated by the introduction of privacy preserving noise and user-selection policies, typically at the cost of accuracy. In this work, we propose Privacy-aware Active User SElection (PAUSE), which balances the trade-off between privacy accumulation, communication latency, and optimization of the learned model, via dedicated user selection. This triplet is used to construct a reward (cost function), according to which a multi-armed bandit (MAB)-based algorithm dynamically chooses a subset of users in each round, while guaranteeing bounded accumulated privacy leakage. We establish a theoretical analysis, systematically showing that the reward growth rate of PAUSE follows the best-known rate in MAB literature. While the privacy guarantees hold by the construction of PAUSE, we numerically validate its associated improved latency and accuracy gains in different experimental settings of FL.

关键词： Privacy Accuracy Costs Federated learning Heuristic algorithms Noise signal processing algorithms Numerical models Iterative methods Speech processing

来源：评论

学校读者我要写书评

暂无评论

MULTIPLE SOURCE DF signal-processing - AN EXPERIMENTAL SYSTEM

引用

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION 1986年第3期34卷 281-290页

作者： SCHMIDT, RO FRANKS, RE TRW INC ESL495 JAVA DRSUNNYVALECA 94088

The multiple signal characterization (MUSIC) algorithm is an implementation of the signal subspace approach to compute parameter estimates of multiple point-source signals from the observed voltages received on an array of M antennas. In it, the solution to the multiple source direction finding (DF) problem is provided by the intersection of the signal subspace (obtained from the received data) and the array manifold (obtained via array calibration or prior knowledge of array directional characteristics). The MUSIC algorithm was implemented to experimentally verify the performance of the signal subspace approach to DF under very general scenarios and conditions which are regarded as difficult to impossible in traditional systems. The results of those experiments are described herein. The experimental system consisted of an eight-element antenna array 13 wavelengths in diameter, an eight-channel receiver and digitizer, and a minicomputer with disk storage to process the digitized data. With ideal instrumentation, the MUSIC algorithm provides performance that, as the amount of data collected increases without limit, is asymptotically ideal. However, with finite precision and finite data collection, the performance of even an ideal system can be a sensitive function of source and scenario parameters. Tests demonstrated the resolution of three sources all within one beamwidth (5 \deg ), even when the closer two were spaced less than 0.2 beamwidths. Sources that were polarized differently could be resolved at closer spacings. Experimental DF accuracy was limited by the oncalibrated scattering of source energy from the test range support tower and from the ground. The measured direction of arrival of one source changed by less than 0.01 beamwidths as the other two sources were switched on and off in all combinations. In general, results indicated that all parameters of a source can be measured and the signal waveform can be recovered as well in the presence of other sourc

关键词： signal processing signal processing algorithms Multiple signal classification Antenna arrays Receiving antennas Testing Energy resolution Array signal processing Parameter estimation Voltage

来源：评论

学校读者我要写书评

暂无评论

AdapFed: Adaptive Devices Training Strategy for Heterogeneous Federated Learning

AdapFed: Adaptive Devices Training Strategy for Heterogeneou...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Ziyang Chen Ying Zhou Fei Song School of Electronic and Information Engineering Beijing Jiaotong University Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated Learning has been widely adopted in privacy-sensitive distributed machine learning. However, in heterogeneous scenarios where significant differences exist in user data distribution, computational capabilities, or network conditions, existing models often underperform. This paper models key metrics such as communication delays and employs an integer programming approach to select participating devices for training intelligently. Additionally, an efficient federated learning algorithm, AdapFed, is proposed. In the early stages of training, AdapFed prioritizes updates from devices with rapidly changing gradients, while later rounds involve a broader range of diverse devices. The algorithm also incorporates a constraint on the average waiting time among device sets throughout the training process. Experimental results on three public datasets demonstrate that, compared to five baseline algorithms, the proposed framework improves model accuracy by 6.4% within the same number of training rounds and reduces the average waiting time among users by 71.4%.

关键词： Training Adaptation models Accuracy Federated learning Heuristic algorithms Computational modeling signal processing algorithms signal processing Mathematical models Speech processing

来源：评论

学校读者我要写书评

暂无评论

Calculating Singular Integrals with Cauchy Kernels in Digital processing of Gastroenterological Medical signals

Calculating Singular Integrals with Cauchy Kernels in Digita...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Latif Ya. Xuramov Shahnoza Xafizova Muhammad Mustaffaqulov Samarkand State University named after Sharof Rashidov Samarkand Uzbekistan Urgut branch of Samarkand State University named after Sharof Rashidov Samarkand Uzbekistan

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

This article within the framework of the research work is devoted to the study of the problem of integrals. Singular integrals are usually encountered in the deep analysis of biomedical signals, which are characterized by sharp changes in continuity and discontinuity. Efficient and accurate evaluation of this type of integral is of great importance in the diagnostic process, especially in spectral analysis and identification of specific signals in gastrointestinal diseases. In this article, I have extensively discussed the mathematical foundations of the use of Cauchy kernels for the approximate calculation of singular integrals and their algorithmic methods. In this regard, modern methods are proposed to further improve the accuracy of signal detection, noise suppression and accuracy in the diagnostic process, since the complexity of gastrointestinal signals and the negative impact of noise and interference on performance are also considered in this study. The proposed method simplifies the interpretation of complex signals, increases the accuracy of spectral analysis results, and automates medical procedures. These methods, in addition to increasing diagnostic accuracy, create new ways to correctly assess the patient's condition using medical markers. The relevance of the research to the development of algorithmic solutions adapted to data processing and biomedical interpretation processes increases its relevance. Therefore, the application of modern technology in medicine largely depends on this research.

关键词： Accuracy Noise Noise reduction signal processing algorithms Interference Gastrointestinal tract Kernel Medical diagnostic imaging Spectral analysis signal detection

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-Driven Bearing-Fault Detection in Induction Motor and Drives using Graph Sampling and Aggregation Network

Digital Twin-Driven Bearing-Fault Detection in Induction Mot...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Haraprasad Badajena Suryanarayan Majhi Bivash Chakraborty Mamata Jenamani Aurobinda Routray Ronit Dutta Advanced Technology Development Centre Indian Institute of Technology Kharagpur India Industrial and Systems Engineering Indian Institute of Technology Kharagpur India Dept. of Electrical Engineering Indian Institute of Technology Kharagpur India

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Bearing fault diagnosis is crucial for ensuring the reliability and safety of industrial systems, particularly in preventing operational failures and maintaining product quality. Traditional signal processing methods and deep learning algorithms, while useful, often overlook the complex structural relationships within sensor data, limiting their diagnostic effectiveness. To address this, we present a novel Digital Twin-Driven Fault Diagnosis Framework that integrates graph-based learning techniques with advanced signal analysis. Our approach employs XGBoost and GraphSAGE embeddings to capture both spatial and temporal correlations within the current signals. The raw sensor data is then processed using a sliding window technique and time-frequency domain features are extracted then transformed into a graph structure that represents the intricate relationship in the signal. GraphSAGE is then applied to these graph structures, generating embeddings that enhance fault detection accuracy. Additionally, XGBoost is utilized for classification, improving the overall robustness of the system. The proposed method, deployed on edge devices, delivers real-time diagnostics, providing a scalable and efficient solution for industrial applications. Experimental results using real-world datasets demonstrate that our method significantly outperforms state-of-the-art algorithms, improving detection accuracy and Area under the curve (AUC) scores up to 97% and 99%, respectively.

关键词： Fault diagnosis Time-frequency analysis Accuracy Correlation Fault detection Image edge detection signal processing algorithms Feature extraction Real-time systems Speech processing

来源：评论

学校读者我要写书评

暂无评论

Noise-Resilient Unlimited Sampling and Recovery of Sparse signals

Noise-Resilient Unlimited Sampling and Recovery of Sparse Si...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Geethu Joseph Signal Processing Systems Group Delft University of Technology Delft Netherlands

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we investigate the use of modulo-ADCs in compressed sensing to handle the issue of the limited dynamic range of standard ADCs. The current state-of-the-art algorithm for modulo-compressed sensing uses an ℓ 1 -norm-based approximation of the sparsity constraint, resulting in a computationally demanding mixed-integer linear optimization. Handling noisy measurements further complicates the problem, requiring mixed-integer quadratic programming, a problem known to be NP-hard. We present an alternative iterative hard-thresholding approach to address this issue. Our solution is computationally simpler and capable of handling noisy measurements. Additionally, we provide theoretical guarantees that the algorithm can successfully recover sparse vectors if the sampling operator satisfies the integer augmented-restricted isometry property, which holds when the number of measurements is sufficiently large.

关键词： signal processing algorithms Acoustic measurements Vectors Sensors Noise measurement Iterative methods Sparse matrices Quadratic programming Speech processing Standards

来源：评论

学校读者我要写书评

暂无评论

Analysis on UAV Sensing with Sparse Array in ISAC System

Analysis on UAV Sensing with Sparse Array in ISAC System

引用

IEEE Conference on Wireless Communications and Networking

作者： Min Huang Mingxi Yin Hao Xu Qualcomm Wireless Communication Technologies (China) Limited China Qualcomm International Inc. USA

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

In integrated sensing and communication (ISAC) systems, the increasing demand for higher sensing resolution necessitates the use of more antenna elements and greater radio resource consumption when employing traditional uniform antenna arrays and uniform pilot placement. This paper addresses these challenges by leveraging sparse arrays in ISAC system design to reduce costs while maintaining sensing performance. Specifically, the application of sparse antenna arrays and sparse pilot placement is investigated in the context of device-free unmanned aerial vehicle (UAV) sensing. To accommodate the distinct characteristics of sparse patterns in the spatial, frequency and time domains, two types of sparse array signal processing algorithms are designed. These algorithms are based on subspace analysis or correlation in difference coarray (DCA) domain, and applied for direction of arrival (DoA) estimation with sparse antenna arrays or for distance/velocity estimation with sparse resource patterns. Additionally, to analyze the sensibility condition of multi-target sensing scenarios, an Uncorrelation Criterion associated with multi-target geometrical characteristics is proposed. Simulation results demonstrate that sparse arrays offer similar performance to full uniform arrays for single-target scenarios but provide only coarse sensing in multi-target scenarios.

关键词： Location awareness Time-frequency analysis Direction-of-arrival estimation Array signal processing Adaptive arrays Estimation signal processing algorithms Parallel processing Autonomous aerial vehicles Integrated sensing and communication

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model for Weakly-Supervised Speech Dereverberation

A Hybrid Model for Weakly-Supervised Speech Dereverberation

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Louis Bahrman Mathieu Fontaine Gaël Richard LTCI Télécom Paris Institut Polytechnique de Paris Palaiseau France

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This paper introduces a new training strategy to improve speech dereverberation systems using minimal acoustic information and reverberant (wet) speech. Most existing algorithms rely on paired dry/wet data, which is difficult to obtain, or on target metrics that may not adequately capture reverberation characteristics and can lead to poor results on non-target metrics. Our approach uses limited acoustic information, like the reverberation time (RT60), to train a dereverberation system. The system’s output is resynthesized using a generated room impulse response and compared with the original reverberant speech, providing a novel reverberation matching loss replacing the standard target metrics. During inference, only the trained dereverberation model is used. Experimental results demonstrate that our method achieves more consistent performance across various objective metrics used in speech dereverberation than the state-of-the-art.

关键词： Measurement Training Weak supervision signal processing algorithms Predictive models signal processing Probabilistic logic Reverberation Speech processing Standards

来源：评论

学校读者我要写书评

暂无评论

EfficientSleepNet: A Novel Lightweight End-to-End Model for Automated Sleep Staging on Single-Channel EEG

EfficientSleepNet: A Novel Lightweight End-to-End Model for ...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Fei Wang Zekun Zheng BangShun Hu Xiaodong Yang Maolin Tang Haiyun Huang School of Artificial Intelligence South China Normal University Foshan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Sleep staging is critical for evaluating sleep quality and regulating sleep patterns. While deep learning has shown potential for automatically scoring sleep stages from raw signals, many existing models are overly complex, computationally intensive, and rely on future information, limiting their use in real-time monitoring and widespread applications. To address these challenges, we propose EfficientSleepNet, a lightweight architecture for sleep staging based on single-channel EEG. EfficientSleepNet integrates depthwise separable convolutions, grouped convolutions, channel reordering, and a novel channel attention mechanism. Compared to previous models, EfficientSleepNet significantly reduces both parameter count and complexity. We conducted extensive evaluations on two public datasets, SleepEDF-20 and SleepEDF-78, achieving accuracies of 84.4% and 80.8%, respectively, with only 83.8K parameters. These findings demonstrate that EfficientSleepNet substantially reduces model complexity and parameter count, offering strong potential for real-time sleep staging applications.

关键词： Sleep Convolution Computational modeling signal processing algorithms Computer architecture Brain modeling Feature extraction Electroencephalography Real-time systems Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Robust Supervised Graph Embedding Method For EEG-Based Brain Network Emotion Recognition

Robust Supervised Graph Embedding Method For EEG-Based Brain...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Pengcheng Zhu Cunbo Li Peiyang Li Fali Li Dezhong Yao Peng Xu School of Life Science and Technology University of Electronic Science and Technology of China Chengdu China School of Life Health Information Science and Engineering Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Emotion recognition based on brain networks has attracted increasing research attention due to its ability to reveal the information interactions between brain regions under different emotional states. However, there are still two challenges in practical applications: 1) The high dimensionality of brain networks can lead to issues of feature redundancy, overfitting, and high computational costs; 2) Electroencephalography (EEG) signals are susceptible to outlier noise, and label noise caused by mismatches between the stimuli labels used to induce emotions and the individuals’ actual emotional responses can significantly impact emotion recognition. To address these challenges, we propose a supervised graph embedding algorithm based on the L1-norm space (L1-SGE). This method leverages the local structure and class information of the original data for discriminative subspace learning, achieving a low-dimensional representation of high-dimensional networks. Additionally, the constraints of the L1-norm space enable the method to effectively suppress outliers and label noise. The performance on publicly available emotional EEG databases has successfully validated the effectiveness of the proposed method in low-dimensional feature representation and noise suppression. Furthermore, this method not only offers a powerful tool for research in affective brain-computer interfaces but also provides a potential solution for pattern recognition tasks facing similar challenges in the field of artificial intelligence.

关键词： Emotion recognition Noise Redundancy Noise reduction signal processing algorithms Speech recognition Electroencephalography Emotional responses Speech processing Overfitting

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：