检索结果-内蒙古大学图书馆

Distributed data-privacy preserving federated learning method for sleep stage classification

Biomedical Signal Processing and Control 2025年 109卷

作者： Li, Hongjin Zhao, Xiaohui Liu, Hang Wang, Ziyi Cai, Yukai Yang, Chuanshuai Cong, Fengyu School of Biomedical Engineering Faculty of Medicine Dalian University of Technology Dalian China Liaoning Key Laboratory of Integrated Circuit and Biomedical Electronic System Dalian University of Technology Dalian China Department of Respiratory and Critical Care Medicine The Affiliated Central Hospital of Dalian University of Technology Dalian China Faculty of Information Technology University of Jyväskylä Jyväskylä Finland

Artificial intelligence and big data have great promise for promoting sleep medicine assistance. However, obstacles such as data privacy restrictions occur when enough data are collected from different data centers to develop classification models with better performance. Federated learning (FL), a collaborative machine learning approach, aims to address problems by acquiring models rather than directly accessing data from multiple clients. In this work, we utilize federated learning to increase model performance and preserve data privacy when deploying automatic sleep staging methods with insufficient data. And we construct a CNN-Transformer model and design an anti-class ratio (ACR) weighted loss function to complete the classification task with class imbalanced data. We evaluate our model and ACR using Sleep-EDF database and achieve better overall and N1 classification performance. To clearly show the efficiency of FL, we set three different data volume experiments with three independent heterogeneous public sleep databases. The experimental results are compared with two benchmark methods, traditional local learning and data-centralized learning. The results suggest that federated learning method outperforms the local learning approach in classification performance and achieves comparable results with data-centralized learning. As a result, we argue that federated learning is a promising alternative for multiple clients developing sleep staging algorithms especially with insufficient data because it adds benefits in terms of model performance and data privacy protection. © 2025 Elsevier Ltd

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Novel 1T-APS Using 22 nm FD-SOI technology with Record High Tunable Sensitivity Range

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2025年

作者： Xie, Hui Wang, Zehua He, Rongshan Wang, Haihua Cao, Jingya Zhou, Peng Tang, Xiao-Lan Jiang, Yu-Long Xu, Yong Wan, Jing Fudan University College of Integrated Circuits and Micro-Nano Electronics Shanghai200433 China Nanjing University of Posts and Telecommunications College of Integrated Circuit Science and Engineering Nanjing210023 China Shaoxin Laboratory Shaoxing312000 China Gannan University of Science and Technology School of Information Engineering Ganzhou341000 China Guangdong Greater Bay Area Institute of Integrated Circuit and System Guangzhou510300 China

A novel one transistor active pixel sensor (1T-APS) with extraordinary tunable sensitivity range is experimentally demonstrated using 22 nm fully depleted silicon-on-insulator (FD-SOI) technology. The proposed device enables independent control of both full well capacity and sensitivity. Two electrodes are connected to the substrate, with one used to form the depletion region beneath the buried oxide (BOX) and the other to tune the movement of photoelectrons. The experimental results show a record high tunable sensitivity range of 340000%, varying from 4 mV/(μJ/cm2) to 13.6 V/(μJ/cm2). With tunable sensitivity, the dynamic range is expanded from 51.5 dB to 101.5 dB, making it promising for high-dynamic-range imaging applications. © 1980-2012 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

MambaRF: A Bi-directional Mamba Structure for Radio Frequency Signal Classification of Unmanned Aerial Vehicle

MambaRF: A Bi-directional Mamba Structure for Radio Frequenc...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Mufeng Yao Chao Liu Lexu Xie Mingmin Chi School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China School of Computer Science Fudan University Zhengzhou Zhongke Institute of Integrated Circuit and System Application Shanghai China Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The rapid development of Unmanned Aerial Vehicle (UAV) technology has facilitated the widespread use of UAVs in daily life, this advancement brings huge regulatory demand for UAVs. Automatic identification of UAVs using radio frequency (RF) signals can effectively reduce regulatory costs. Previous studies first extracts spectrogram features from raw RF signals using short-time Fourier transform, and then use neural networks to classify the spectrograms. These studies are mainly based on local convolution, ignoring the long-range dependence of the spectrograms, and thus are limited in terms of UAV classification accuracy. In addition, these works also focus only on classifying UAV types without identifying flight states (e.g., hovering, flying, and switch on). To this end, we propose MambaRF, which employs a bi-directional selective scanning mechanism to capture long-range information of spectrograms from two different directions. MambaRF also jointly classifies UAV types and flight states by using two decoupled classification heads, which has not been addressed in previous studies. Experiments on two publicly available datasets show that our proposed MambaRF outperforms VMamba and other previous studies in both type classification and flight state classification.

关键词： Accuracy Convolution RF signals Bidirectional control Switches Autonomous aerial vehicles Feature extraction Speech processing Spectrogram Radiofrequency identification

来源：评论

学校读者我要写书评

暂无评论

Crystal orientation-modulated ferroelectric and dielectric properties in Hf0.5Zr0.5O2 thin films

引用

Science China(Information Sciences) 2025年第06期 204-212页

作者： Yu-Chun LI Xiao-Xi LI Zhongshan XU Zi-Ying HUANG Yingguo YANG Xiao-Na ZHU Ming LI David Wei ZHANG Hong-Liang LU State Key Laboratory of Application-Specific Integrated Circuit and System Shanghai Institute of Intelligent Electronics and Systems School of Microelectronics Fudan University Zhangjiang Fudan International Innovation Center National Integrated Circuit Innovation Center Wide Bandgap Semiconductor Technology Disciplines State Key Laboratory School of Microelectronics Xidian University Jiashan Fudan Institute School of Integrated Circuits Peking University

Hafnium oxide（HfO2） is a promising ferroelectric material because of its robust electric dipoles at the *** HfO2is an oxygen-displacement-induced ferroelectric material, a comprehensive understanding of the intricate relationship between its electrical performance and oxygen-related processes is still limited. This study delves into the ferroelectric and dielectric properties of Zr-doped HfO2(Hf0.5Zr0.5O2, HZO) thin films, unveiling a reliance on the oxygen dose during the atomic layer deposition process. A superior remanent polarization（2Pr） of 58 μC/cm2and a high dielectric constant of 52.7 are obtained in the HZO capacitors with 10 and 1 s oxygen plasma durations, respectively. Our work establishes that the enhanced ferroelectricity observed in samples with longer oxygen dose time is attributed to the gradual out-of-plane orientation of the polar c-axis, as indicated by grazing incidence wide-angle X-ray scattering analysis. Meanwhile,the larger dielectric constant observed in samples with the shortest oxygen dose time（1 s） originates from the out-of-plane tilt of the b-axis in an orthorhombic-phase cell. These new insights into the controlled crystal orientation through oxygen dose modulation open avenues for optimizing the performance of the HfO2-based devices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Segmentation Model Integrating Deep Residual Shrinkage and Lightweight Transformer Encoding Technique

引用

Laser and Optoelectronics Progress 2025年第10期62卷

作者： Li, Hongxu Lu, Yitao Chi, Ronghua Li, Shiyu Yang, Zhenbo School of Electronics and Information Engineering Nanjing University of Information Science and Technology Jiangsu Nanjing210044 China Jiangsu Province Engineering Research Center of Integrated Circuit Reliability Technology and Testing System Wuxi University Jiangsu Wuxi214105 China

The existing point cloud segmentation techniques can neither easily and effectively eliminate invalid noise points in the feature-extraction stage nor adequately capture key global and local features. Therefore, this study proposes an improved point cloud feature extraction network based on the PointGroup segmentation model, which is named deep residual shrinkage Transformer U-Net (DRST-UNet). The proposed network combines the deep residual shrinkage attention module and lightweight Transformer encoding, which removes invalid noise points by soft thresholding to shrinkage the residual block, combines with the attention mechanism such that the network prioritizes the important features, and utilizes the Transformer to capture the long-distance dependency and high-level interactions between point samples, thus enhancing the accuracy and efficiency of feature extraction. Experimental results show that the DRST-UNet is superior to existing methods in terms of segmentation accuracy based on ScanNetV2 and S3DIS datasets, in particularly for cases involving complex indoor scenes. The maximum average precision when the intersection ratio threshold is 50% (AP50) of the proposed method is 66. 4% on the ScanNetV2 dataset, which is an improvement by 2. 8 percentage points compared with the result of the baseline model, and the added module incurs almost no time cost. The maximum AP50 on the S3DIS dataset is 61. 7%, which is an improvement by 3. 9 percentage points compared with the result of the baseline model. © 2025 Universitat zu Koln. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery

arXiv

引用

arXiv 2025年

作者： Li, Yansheng Wu, Yuning Cheng, Gong Tao, Chao Dang, Bo Wang, Yu Zhang, Jiahao Zhang, Chuge Liu, Yiting Tang, Xu Ma, Jiayi Zhang, Yongjun Information and computing science from Shandong University Weihai China Pattern recognition and intelligent system from the Huazhong University of Science and Technology Wuhan China Computer science and technology from Wuhan University Wuhan China Xidian University Xi’an China Pattern recognition and intelligent systems from Northwestern Polytechnical University Xi’an China School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan China Institute for Pattern Recognition and Artificial Intelligence Huazhong China University of Science and Technology Remote sensing science and technology from Wuhan University Wuhan China School of Remote Sensing and Information Engineering Wuhan University Wuhan China Electronic circuit and system from Xidian University Xi’an China University of Colorado at Boulder BoulderCO United States Control science and engineering from the Huazhong University of Science and Technology Wuhan China Geodesy and photography from Wuhan University Wuhan China

Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples. This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios. To address this limitation, we introduce the Million-scale finE-grained geospatial scEne classification dataseT (MEET), which contains over 1.03 million zoom-free remote sensing scene samples, manually annotated into 80 fine-grained categories. In MEET, each scene sample follows a scene-in-scene layout, where the central scene serves as the reference, and auxiliary scenes provide crucial spatial context for fine-grained classification. Moreover, to tackle the emerging challenge of scene-in-scene classification, we present the Context-Aware Transformer (CAT), a model specifically designed for this task, which adaptively fuses spatial context to accurately classify the scene samples. CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes. Based on MEET, we establish a comprehensive benchmark for fine-grained geospatial scene classification, evaluating CAT against 11 competitive baselines. The results demonstrate that CAT significantly outperforms these baselines, achieving a 1.88% higher balanced accuracy (BA) with the Swin-Large backbone, and a notable 7.87% improvement with the Swin-Huge backbone. Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping. The source code and dataset will be publicly available at https://***/project/***. Copyright © 2025, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Real-Time Blind Calibration for Frequency Response Mismatches in Two-Channel TI-ADCs 13

Real-Time Blind Calibration for Frequency Response Mismatche...

引用

2017 13th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)

作者： Liu Guiqing Wang Yinan Liu Husheng Diao Jietao Department of Circuit and System National University of Defense Technology

ISBN: (纸本)9781509050369;9781509050352

This paper introduces a real-time blind calibration algorithm for frequency response mismatch in two-channel time-interleaved(TI) ADCs. By adding an offset calibration algorithm before frequency response calibration algorithm, we can compensate offset, gain, timing and bandwidth mismatches. The offset calibration algorithm is low complexity and very efficient, which consume only several adders. In addition, we replace Fx LMS with Signed-Fx LMS to reduce resource consumption and improve clocking performance. In order to achieve superior clocking performance, the whole algorithm is designed to a full-pipelined form. Finally, we demonstrate the efficiency of the calibration algorithm by XILINX ISIM.

关键词： TIADC real-time blind calibration frequency response mismatch

来源：评论

学校读者我要写书评

暂无评论

A Ray-Tracing Approach for Simulating Recognition Abilities of Active Infrared Sensor Arrays

A Ray-Tracing Approach for Simulating Recognition Abilities ...

引用

First IEEE International Conference on Sensors - IEEE Sensors 2002

作者： Iske, Burkhard Jäger, Björn Rückert, Ulrich System and Circuit Technology Paderborn University Paderborn Germany

This paper deals with the simulation and evaluation of the recognition abilities of active infrared sensor arrays for autonomous systems. The simulation is based on a Monte Carlo algorithm, which uses ray-tracing to calculate the impulse response of a receiving element. The emphasis lies in an efficient computation, which means that the rays sent should ideally contribute maximally to the final result and that different sender and receiver characteristics should easily be calculable. Extensive experiments were carried out with the simulation mostly taking less than a minute on an Athlon 650MHz computer and simulated values being a good approximation of the measured values.

关键词： Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Finding an optimal set of breakpoint locations in a control flow graph

Finding an optimal set of breakpoint locations in a control ...

引用

9th International Multi-Conference on systems, Signals and Devices, SSD 2012

作者： Langer, Jan Rößler, Marko Heinkel, Ulrich Circuit and System Design Chemnitz University of Technology Chemnitz Germany

ISBN: (纸本)9781467315906

With the advance of high-level synthesis methodologies it has become possible to transform software tasks, typically running on a processor, to hardware tasks running on a FPGA device. Furthermore, dynamic reconfiguration techniques allow dynamic scheduling of hardware tasks on an FPGA area at runtime. Combining these techniques allows dynamic scheduling across the hardware-software boundary. However, to interrupt and resume a task, its context has to be identified and stored. We propose a method to find an optimal set of breakpoints in the control flow of a hardware task, such that the introduced resource overhead for context access is minimized and a maximum latency between interrupt request and the end of the context storing is guaranteed. This set of breakpoints allows the context to be restricted to the essential subset of data. Our method opens the door to flexible task scheduling not only on one reconfigurable device but also between different devices and even software instances of the same task. © 2012 IEEE.

关键词： High level synthesis

来源：评论

学校读者我要写书评

暂无评论

Camera-based climbing analysis for a therapeutic training system

Camera-based climbing analysis for a therapeutic training sy...

引用

作者： Richter, Julia Beltrán, Raul Beltrán Heinkel, Ulrich Circuit and System Design Chemnitz University of Technology Chemnitz Germany

In view of therapeutic applications, climbing motion analysis has gained increased importance to avoid movements that are prone to cause injuries and to motivate the climber by means of gamification. To date, there remains need to investigate analysis methods for feedback generation that do not require body contact and that can be easily integrated in the climbing setup. Therefore, this study proposes an camera-based approach for contact-less motion analysis that localises the climber's centre of mass (COM) and derives relevant parameters, such as fluency, force and distance to the wall, from the temporal COM analysis. © 2020 Julia Richter et al., published by De Gruyter, Berlin/Boston 2020.

关键词： Computer vision

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：