检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年

作者： He, Yifan Ding, Xi Tang, Yateng Guan, Jihong Zhou, Shuigeng Fudan University School of Computer Science Shanghai200433 China Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Tencent Weixin Group Guangzhou510308 China Tongji University Department of Computer Science and Technology Shanghai201804 China Ministry of Education Key Laboratory of Embedded System and Service Computing Tongji University Shanghai200092 China

Anomalies are usually regarded as data errors or novel patterns previously unseen, which are quite different from most observed data. Accurate detection of anomalies is crucial in various application scenarios. This paper focuses on unsupervised anomaly detection from Multivariate Time Series (MTS), as real-world data collected from sources such as wearable devices, medical equipment and industrial machines typically manifest as MTS and are often unlabeled. Anomaly detection in MTS represents a data-driven challenge that traditionally requires substantial centralized data for training models. However, in practice, data are frequently distributed among multiple institutions, with privacy concerns restricting unrestricted access. To address these issues, we introduce Feature Decoupling Federated Learning (FDFL), an approach designed to collaboratively train a representation learning network over multiple clients for unsupervised anomaly detection in MTS. Unlike previous methods that simply integrate MTS anomaly detection algorithms with federated learning strategies, FDFL specifically addresses heterogeneity among clients by decoupling the representation network into shared and private branches through a contrastive learning mechanism. This method aggregates shared parameters during each federated round while maintaining client-specific private parameters locally. Additionally, we develop a self-attention block that integrates the representations derived from both shared and private parameters to reconstruct MTS and identify anomalies based on reconstruction errors. Extensive experiments conducted on three publicly available datasets demonstrate that FDFL outperforms existing algorithms in most cases, highlighting the effectiveness and superiority of our proposed method in MTS anomaly detection. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

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

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

Directional Beamforming for High-Speed Railway Communications with Frequency Offset Precorrection

引用

Chinese Journal of Electronics 2025年第1期23卷 163-168页

作者： Yuan Cao Yinghong Wen Wei Xu Xin Xie School of Electronics and Information Engineering Beijing Jiaotong University National Engineering Research Center of Rail Transportation Operation and Control System Beijing China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China National Mobile Communications Research Lab. Southeast University Nanjing China

This paper considers a multi-antenna transmission strategy for high speed railway communications. In order to achieve better performance than conventional space-frequency block coding schemes, we propose a directional beamforming strategy for the High-speed railway (HSR) communication by exploiting some characteristic of the railway system including predetermined moving tracks and real-time positioning information. Moreover, for alleviating the effect of Doppler shift due to the moving train, a frequency offset precorrection method is also incorporated with direction beamforming. Theoretical Signal-to-noise ratio (SNR) gain of the proposed beamforming scheme over traditional HSR communication schemes is also derived for illustrating the performance enhancement. Numerical results verify the effectiveness of our proposed scheme even with some kind of imperfect position information available at the transmitter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RAFFCDNet: A diagnostic network based on adaptive feature fusion and class-distance-based loss function for occupational pneumoconiosis

引用

Biomedical Signal processing and control 2025年 109卷

作者： Zhao, Qian Guo, Yinan Gong, Dunwei School of Information and Control Engineering China University of Mining and Technology Jiangsu Xuzhou221008 China School of Mechanical Electronic and Information Engineering China University of Mining and Technology Beijing100083 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China College of Automation and Electronic Engineering Qingdao University of Science and Technology Shandong Qingdao266061 China

Pneumoconiosis, the most prevalent and severe occupational disease in China, is categorized into four stages based on the area of small lung shadows. Previous diagnostic methods have exhibited limited accuracy in identifying severity stages due to the complexity and diversity of pneumoconiosis lesions, as well as challenges in collecting rich X-ray images from patients. To address these issues, a diagnostic method based on adaptive feature fusion and class-distance-based loss function is proposed. First, the prototype network based on deep metric learning is introduced to establish a diagnostic model for pneumoconiosis with insufficient images, with the purpose of enhancing feature representations by analyzing the distance between features of various samples. Subsequently, the fusion modules of dual-path multi-channel and fine-grained multi-level features are proposed. These modules also utilize the mechanism of adaptive gating selection to efficiently integrate the most important features from different channels and levels. Finally, the class-distance-based loss function is designed to train the diagnostic model of occupational pneumoconiosis. The experimental results on a self-built dataset of chest X-ray radiographs demonstrate that our proposed method outperforms eight comparative methods in terms of comprehensive performance. © 2025 Elsevier Ltd

关键词： Occupational diseases

来源：评论

学校读者我要写书评

暂无评论

Modality Unified Attack for Omni-Modality Person Re-Identification

引用

IEEE Transactions on information Forensics and Security 2025年

作者： Bian, Yuan Liu, Min Yi, Yunqi Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning based person re-identification (re-id) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial examples (AEs), leaving the robustness of multi-modality re-id models unexplored. Due to the lack of knowledge about the specific type of model deployed in the target black-box surveillance system, we aim to generate modality unified AEs for omni-modality (single-, cross- and multi-modality) re-id models. Specifically, we propose a novel Modality Unified Attack method to train modality-specific adversarial generators to generate AEs that effectively attack different omni-modality models. A multi-modality model is adopted as the surrogate model, wherein the features of each modality are perturbed by metric disruption loss before fusion. To collapse the common features of omnimodality models, Cross Modality Simulated Disruption approach is introduced to mimic the cross-modality feature embeddings by intentionally feeding images to non-corresponding modality-specific subnetworks of the surrogate model. Moreover, Multi Modality Collaborative Disruption strategy is devised to facilitate the attacker to comprehensively corrupt the informative content of person images by leveraging a multi modality feature collaborative metric disruption loss. Extensive experiments show that our MUA method can effectively attack the omni-modality re-id models, achieving 55.9%, 24.4%, 49.0% and 62.7% mean mAP Drop Rate, respectively. © 2005-2012 IEEE.

关键词： Modality unified attack Multi Modality Collaborative Disruption Omni-Modality re-id

来源：评论

学校读者我要写书评

暂无评论

In-situ Monitoring of Maximum and Average Chip Junction Temperature within Multichip IGBT Power Modules Using Kelvin Emitter Voltage

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Yang, Jianxiong Ran, Li Che, Yanbo Du, Mingxing Tianjin University of Technology Tianjin Key Laboratory of Control Theory and Applications in Complicated System Tianjin300384 China Chongqing University State Key Laboratory of Power Transmission Equipment and System Security and New Technology School of Electrical Engineering Chongqing400044 China University of Warwick School of Engineering CoventryCV4 7AL United Kingdom Tianjin University Key Laboratory of Smart Grid of Ministry of Education School of Electrical and Information Engineering Tianjin300072 China

Parallel configurations of power chips within a multichip IGBT power module (M-IGBT-PM) are employed to meet the required current and power ratings. When the internal chips of an M-IGBT-PM experience uneven temperature distributions and package aging, it becomes challenging to determine the maximum and average temperatures of the chips within the module. This paper investigates the relationship between four transient thermal-sensitive electrical parameters (T-TSEPs) derived from the Kelvin emitter voltage and the chip junction temperature, while establishing relevant mathematical models. It compares the sensitivity and linearity of these four T-TSEPs, and also assesses the influence of external gate resistance, bus voltage, and load current on each of them. A key innovation in this paper is the proposal of a method for monitoring the maximum and average temperatures across the chips within the M-IGBT-PM, which is not influenced by the load current. The experimental results suggest that the temperature derived from the quasi-turn-on delay time is a good approximation of the maximum chip temperature, whereas the temperatures predicted by the other T-TSEPs are nearer to the average temperature. © 2025 IEEE.

关键词： Insulated gate bipolar transistors (IGBT)

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Anomalous Driving Behavior Detection With Adaptive Masking

引用

Concurrency and Computation: Practice and Experience 2025年第12-14期37卷

作者： Zeng, Kun Peng, Zhonghua Li, Zuoyong Chen, Yun Chen, Feng Wu, Nanbing Fujan Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Data Science Minjiang University Fuzhou China Fujian Communications Planning & Design Institute Co. LTD Fuzhou China Fujian Provincial Highway Development Center Fuzhou China

Intelligent Transportation systems are tasked with enhancing road safety, a crucial challenge given that approximately 1.35 million fatalities occur globally each year, with 15%–27% of these deaths attributed to Anomalous Driving Behaviors (ADBs). Detecting these behaviors in real time is vital for preventing accidents and improving traffic safety. However, the complexity of driving environments, characterized by diverse scenarios, drivers, and vehicle conditions, makes ADB detection a challenging task. This article proposes a novel approach for ADB detection, leveraging the advantages of multimodal data, adaptive masking, and multihead self-attention mechanisms. The proposed method first employs an adaptive masking technique based on the Softmax function to sparsify input features, effectively reducing the influence of irrelevant information. By focusing on key features, the model becomes more resilient to noise, such as background clutter or irrelevant driver actions, which might otherwise interfere with the detection of abnormal behaviors. To further enhance feature integration across different data modalities (e.g., visual, infrared, and depth data), a multihead self-attention mechanism is incorporated. This mechanism enables the model to prioritize important information from various sensor inputs, fostering more effective multimodal fusion and better decision-making for behavior classification. In addition, a supervised contrastive learning strategy is utilized to mitigate memory usage, a common challenge in real-time systems where computational resources are limited. This approach ensures efficient learning by emphasizing the distinction between normal and abnormal behaviors while minimizing the memory footprint of the model. Extensive experiments on two benchmark datasets, 3MDAD and DAD, demonstrate the proposed method's superior performance in detecting ADBs. The results indicate a significant improvement in detection accuracy and robustness, highlighting th

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

Pathological axonal enlargement in connection with amyloidosis,lysosome destabilization,and bleeding is a major defect in Alzheimer’s disease

引用

Neural Regeneration Research 2026年第2期21卷 790-799页

作者： Hualin Fu Jilong Li Chunlei Zhang Guo Gao Qiqi Ge Xinping Guan Daxiang Cui Institute of Nano Biomedicine and Engineering School of Sensing Science and EngineeringSchool of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghaiChina Institute of Marine Equipment Shanghai Jiao Tong UniversityShanghaiChina National Center for Translational Medicine Shanghai Jiao Tong UniversityShanghaiChina Department of Automation Shanghai Jiao Tong UniversityShanghaiChina The Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina

Alzheimer’s disease is a multi-amyloidosis disease characterized by amyloid-βdeposits in brain blood vessels,microaneurysms,and senile *** amyloid-βdeposition affects axon pathology has not been examined *** used immunohistochemistry and immunofluorescence staining to analyze the forebrain tissue slices of Alzheimer’s disease *** axonal amyloidosis with distinctive axonal enlargement was observed in patients with Alzheimer’s *** average,amyloid-β-positive axon diameters in Alzheimer’s disease brains were 1.72 times those of control brain ***,axonal amyloidosis was associated with microtubule-associated protein 2 reduction,tau phosphorylation,lysosome destabilization,and several blood-related markers,such as apolipoprotein E,alpha-hemoglobin,glycosylated hemoglobin type A1C,and *** destabilization in Alzheimer’s disease was also clearly identified in the neuronal soma,where it was associated with the co-expression of amyloid-β,Cathepsin D,alpha-hemoglobin,actin alpha 2,and collagen type *** suggests that exogenous hemorrhagic protein intake influences neural lysosome ***,the data showed that amyloid-β-containing lysosomes were 2.23 times larger than control ***,under rare conditions,axonal breakages were observed,which likely resulted in Wallerian *** summary,axonal enlargement associated with amyloidosis,micro-bleeding,and lysosome destabilization is a major defect in patients with Alzheimer’s *** finding suggests that,in addition to the well-documented neural soma and synaptic damage,axonal damage is a key component of neuronal defects in Alzheimer’s disease.

关键词： Alzheimer’s disease amyloid-β amyloidosis axonal enlargement hemoglobin hemorrhage lysosome destabilization neuropil thread tau Wallerian degeneration

来源：评论

学校读者我要写书评

暂无评论

SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis

arXiv

引用

arXiv 2025年

作者： Chen, Yi Deng, Tianchen Zhao, Wentao Wang, Xiaoning Xi, Wenqian Chen, Weidong Wang, Jingchuan Department of Automation Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200030 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200030 China Ruijin Hospital Shanghai Jiao Tong University School of Medicine China Renji hospital Shanghai Jiao Tong University School of Medicine China

Recent research has begun exploring novel view synthesis (NVS) for LiDAR point clouds, aiming to generate realistic LiDAR scans from unseen viewpoints. However, most existing approaches do not reconstruct semantic labels, which are crucial for many downstream applications such as autonomous driving and robotic perception. Unlike images, which benefit from powerful segmentation models, LiDAR point clouds lack such large-scale pre-trained models, making semantic annotation time-consuming and labor-intensive. To address this challenge, we propose SN-LiDAR, a method that jointly performs accurate semantic segmentation, high-quality geometric reconstruction, and realistic LiDAR synthesis. Specifically, we employ a coarse-to-fine planar-grid feature representation to extract global features from multi-frame point clouds and leverage a CNN-based encoder to extract local semantic features from the current frame point cloud. Extensive experiments on SemanticKITTI and KITTI-360 demonstrate the superiority of SN-LiDAR in both semantic and geometric reconstruction, effectively handling dynamic objects and large-scale scenes. Codes will be available on https://***/dtc111111/SN-Lidar. © 2025, CC BY-NC-SA.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Performance-Aware control of Modular Batteries For Fast Frequency Response

arXiv

引用

arXiv 2025年

作者： He, Yutong Ruan, Guangchun Zhong, Haiwang State Key Laboratory of Power System Operation and Control Department of Electrical Engineering Tsinghua University Beijing100084 China Lab for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States

Modular batteries can be aggregated to deliver frequency regulation services for power grids. Although utilizing the idle capacity of battery modules is financially attractive, it remains challenging to consider the heterogeneous module-level characteristics such as dynamic operational efficiencies and battery degradation. In addition, real-time decision making within seconds is required to enable fast frequency response. In order to address these issues, this paper proposes a performance-aware scheduling approach for battery modules to deliver fast frequency response (FFR) support. In particular, the conduction loss and switching loss of battery packs as well as converters are captured within a mix-integer quadratic constrained program (MIQCP). The cycle-based aging model identifies the aging cost of battery modules during frequent cycling by introducing the aging subgradient calculation and linearization. Case studies based on real-world battery data show that the proposed scheduling approach can effectively reduce power loss cost by nearly 28%-57% and battery aging cost by 4%-15% compared to conventional methods, which can also enhance the SoC balance. Copyright © 2025, The Authors. All rights reserved.

关键词： Battery management systems

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：