检索结果-内蒙古大学图书馆

Automation and Computation (AUTOCOM), International Conference on

作者： Bhupendra Ku. Gupta Shreya Ghosal Subbulakshmi Ganesan T. Sudhakar Awakash Mishra Neelesh Pandey Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Sciences Chemistry and Biochemistry JAIN (Deemed to be University) Bangalore Karnataka India Department of Biomedical Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Self-powered body-worn sensors are considered one of the potential candidates for health and fitness monitoring in wireless body area networks. Sensors extract energy from the human body or its environment to power themselves, making them self-contained with no external power supply, thus improving portability and wear ability. According to this, energy harvesting methods are essential for developing selfpowered body-worn sensors in WBANs. This technical paper reviews different methods of energy harvesting used for bodyworn sensors, such as Body heat, motion, ambient light harvesting, etc. It also discusses some drawbacks and limitations, such as low energy production and inconsistent energy sources. It also features some of the latest blasting techniques and technologies concerning energy recovery. Using self-powered body-worn sensors can lead to various applications and advantages in WBANs. Such uses included continuous & non-invasive health monitoring, data collection for medical research and sports performance tracking. Self-powered sensors reduce the frequency of maintenance and minimize environmental pollution caused by battery disposal.

关键词： Wireless communication Wireless sensor networks Electric potential Reviews Body area networks Sensors Batteries Energy harvesting Monitoring Sports

来源：评论

学校读者我要写书评

暂无评论

VFLMonitor: Defending One-Party Hijacking Attacks in Vertical Federated Learning

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4828-4843页

作者： Xiangrui Xu Yiwen Zhao Yufei Han Yongsheng Zhu Zhen Han Guangquan Xu Bin Wang Shouling Ji Wei Wang School of Information Science and Technology Qingdao University of Science and Technology Qingdao China Thomas Lord Department of Computer Science University of Southern California Los Angeles CA USA INRIA Rennes Brittany France Institute of Computing Technologies China Academy of Railway Sciences Corporation Ltd. Beijing China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University Beijing China Tianjin Key Laboratory of Advanced Networking (TANK) College of Intelligence and Computing Tianjin University Tianjin China Zhejiang Key Laboratory of Artificial Intelligence of Things (AIoT) Network and Data Security Hangzhou China College of Computer Science and Technology Zhejiang University Zhejiang China Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China

Vertical Federated Learning (VFL) is susceptible to various one-party hijacking attacks, such as Replay and Generation attacks, where a single malicious client can manipulate the model to produce attacker-specified results, thereby compromising its reliability in real-world deployments. In this paper, we first uncover the underlying mechanisms of these attacks and observe that successful attacks induce significant discrepancies in the embedding-label associations across different clients. We establish a theoretical framework demonstrating how these discrepancies can serve as reliable indicators for detecting hijacking attempts. Building upon this insight, we propose VFLMonitor, a robust defense mechanism that leverages these embedding-label discrepancies to detect and mitigate hijacking attacks. Specifically, VFLMonitor identifies suspicious queries by analyzing differences in label estimations from multiple clients and applies a majority voting rule to correct or filter out these malicious queries. Moreover, VFLMonitor introduces a novel regularization strategy during training to reduce intra-class variance in embeddings, thereby enhancing their discriminative power and improving defense effectiveness. Extensive experiments were conducted on 5 real-world datasets against 2 different attack types under 3 attack scenarios. The results demonstrate that VFLMonitor can effectively identify and exclude potential hijacked requests in all types of one-party hijacking attacks, while maintaining a meager false positive rate for legitimate queries.

关键词： Training Servers Electronic mail Artificial intelligence Reliability theory Predictive models Federated learning Data models Computational modeling Collaboration

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Protecting Privacy in Big Data Networks

Federated Learning for Protecting Privacy in Big Data Networ...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Binod Kumar Pattanayak Bhavuk Samrat Shaji Thomas F V Jaya Sudha Deeksha Choudhary Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India School of Mangement - PG Management JAIN (Deemed to be University) Bangalore Karnataka Department of Electronics and Communication Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Due to the big data era, the use of cloud computing and Internet of Things devices has increased tremendously, which has resulted in the mass collection of personal data. This caused major privacy protection and safety issues, as sensitive personal data could be exploited and misused. Data encryption and similar techniques have largely needed to be improved as a privacy-protecting solution. A new approach to overcome the privacy and security issues in big data networks is federated learning. Federated Learning is a distributed approach to learning in which machine learning models are trained locally on each device (e.g., phone), and the raw data never leaves the local devices to reach a central server. With this device, however, only model updates are sent while the private data continues to be stored locally on the devices for privacy protection. FL has several benefits compared to normal privacy protection methods, such as reducing the risks of data breaches and minimizing computational and communication costs. In addition, FL allows better data management and greater control over personal data as users are involved in training. FL can be an important building block for privacy and security in large data networks, and it has been adopted by most of the major technology companies as part of their applications. They still have to solve problems like efficient convergence of the model, heterogeneous data and so on. FL is still being prepared for practical use in big data networks and needs more research based on its development to protect privacy.

关键词： Training Data privacy Differential privacy Federated learning Big Data Data models Encryption Servers Security Protection

来源：评论

学校读者我要写书评

暂无评论

LMS-Net: A Learned Mumford-Shah Network For Few-Shot Medical Image Segmentation

arXiv

引用

arXiv 2025年

作者： Zhang, Shengdong Jia, Fan Li, Xiang Zhang, Hao Shi, Jun Ma, Liyan Ying, Shihui Department of Mathematics School of Science Shanghai University Shanghai200444 China Institute University of Utah Salt Lake CityUT84102 United States School of Computer Science and Technology East China Normal University Shanghai China School of Communication and Information Engineering Shanghai University Shanghai200444 China School of Computer Engineering and Science Shanghai University Shanghai200444 China School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai200444 China Shanghai Institute of Applied Mathematics and Mechanics The School of Mechanics and Engineering Science Shanghai University Shanghai200072 China

Few-shot semantic segmentation (FSS) methods have shown great promise in handling data-scarce scenarios, particularly in medical image segmentation tasks. However, most existing FSS architectures lack sufficient interpretability and fail to fully incorporate the underlying physical structures of semantic regions. To address these issues, in this paper, we propose a novel deep unfolding network, called the Learned Mumford-Shah Network (LMSNet), for the FSS task. Specifically, motivated by the effectiveness of pixel-to-prototype comparison in prototypical FSS methods and the capability of deep priors to model complex spatial structures, we leverage our learned Mumford-Shah model (LMS model) as a mathematical foundation to integrate these insights into a unified framework. By reformulating the LMS model into prototype update and mask update tasks, we propose an alternating optimization algorithm to solve it efficiently. Further, the iterative steps of this algorithm are unfolded into corresponding network modules, resulting in LMS-Net with clear interpretability. Comprehensive experiments on three publicly available medical segmentation datasets verify the effectiveness of our method, demonstrating superior accuracy and robustness in handling complex structures and adapting to challenging segmentation scenarios. These results highlight the potential of LMS-Net to advance FSS in medical imaging applications. Our code will be available at: https:// ***/SDZhang01/LMSNet Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Policy-to-Language: Train LLMs to Explain Decisions with Flow-Matching Generated Rewards

arXiv

引用

arXiv 2025年

作者： Yang, Xinyi Zeng, Liang Dong, Heng Yu, Chao Wu, Xiaoran Yang, Huazhong Wang, Yu Tambe, Milind Wang, Tonghan Department of Electronic Engineering Tsinghua University Beijing China Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Harvard John A. Paulson School of Engineering and Applied Sciences Harvard University Cambridge United States

As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain their policies in natural language will be vital for reliable coexistence. In this paper, we build a model-agnostic explanation generator based on an LLM. The technical novelty is that the rewards for training this LLM are generated by a generative flow matching model. This model has a specially designed structure with a hidden layer merged with an LLM to harness the linguistic cues of explanations into generating appropriate rewards. Experiments on both RL and LLM tasks demonstrate that our method can generate dense and effective rewards while saving on expensive human feedback;it thus enables effective explanations and even improves the accuracy of the decisions in original tasks. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MSEMG: Surface Electromyography Denoising with a Mamba-based Efficient Network

MSEMG: Surface Electromyography Denoising with a Mamba-based...

引用

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

作者： Yu-Tung Liu Kuan-Chen Wang Rong Chao Sabato Marco Siniscalchi Ping-Cheng Yeh Yu Tsao Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University Taiwan Research Center for Information Technology Innovation Academic Sinica Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Department of Computer Science and Information Engineering National Taiwan University Taiwan University of Palermo Italy

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Surface electromyography (sEMG) recordings can be contaminated by electrocardiogram (ECG) signals when the monitored muscle is closed to the heart. Traditional signal processing-based approaches, such as high-pass filtering and template subtraction, have been used to remove ECG interference but are often limited in their effectiveness. Recently, neural network-based methods have shown greater promise for sEMG denoising, but they still struggle to balance both efficiency and effectiveness. In this study, we introduce MSEMG, a novel system that integrates the Mamba state space model with a convolutional neural network to serve as a lightweight sEMG denoising model. We evaluated MSEMG using sEMG data from the Non-Invasive Adaptive Prosthetics database and ECG signals from the MIT-BIH Normal Sinus Rhythm Database. The results show that MSEMG outperforms existing methods, generating higher-quality sEMG signals using fewer parameters.

关键词： Adaptation models Databases Computational modeling Surface contamination Noise reduction Interference Electrocardiography Electromyography Speech processing Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Low Thermal Conductivity Plaster – Perlite Microsphere Composites as Potential Thermal Insulation Materials in Building Construction

引用

International Journal of Thermophysics 2025年第7期46卷 1-18页

作者： Viskadourakis, Z. Angelopoulos, P. M. Orfanou, M. Drymiskianaki, Α. Manousaki, A. Koudoumas, E. Taxiarchou, M. Kenanakis, G. Foundation for Research and Technology – Hellas (FORTH) Institute of Electronic Structure and Laser (IESL) Heraklion Greece School of Mining and Metallurgical Engineering National Technical University of Athens Athens Greece Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Greece Department of Materials Science and Technology University of Crete Heraklion Crete Greece National Institute for R&D in Microtechnologies - IMT Bucharest Bucharest Romania

In the current study plaster − expanded perlite microsphere composites, were investigated regarding their thermal insulation properties. In this context commercially available plaster powder was mixed with expanded perlite microspheres, of various grain size distribution and bulk density, aiming the investigation of the effect of ultrafines in the aggregates on the mechanical properties of the composites. The mixing procedure resembles that of making plaster mortars, in building construction. Thermal conductivity of composites was found to be sizably lower than that of pure plaster, and was further decreased with increasing filler loading. Moreover, filler density seems to affect thermal insulation performance, at high loading concentrations. Slight increase of the mechanical properties was identified when aggregates include ultrafine particles. Thermal insulation performance experiments indicate that plaster − expanded perlite microsphere composites clearly exhibit better thermal insulation properties, in comparison to pure plaster. Overall, expanded plaster − expanded perlite microsphere composites seem to be efficient insulation materials for potential applications in buildings’ construction, toward reducing their energy footprint.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Dimensional Material Based Photodetector for Near Infrared Detection

arXiv

引用

arXiv 2025年

作者： Larki, Farhad Dehzangi, Arash Abedini, Alam Buyong, Muhamad Ramdzan Tavakol, Hossein Kameli, Parviz Salamati, Hadi Laye Rooyan Part Isfahan Science and Technology Isfahan Iran Department of Physics Isfahan University of Technology Isfahan84156 Iran Universiti Kebangsaan Malaysia Selangor Bangi Malaysia Department of Electrical and Computer Engineering University of Texas at Dallas RichardsonTX United States Department of Chemistry Isfahan University of Technology Isfahan Iran

Implementing new materials as alternative to silicon for application in photonic devices has been the center of attention in the scientific community. Two-Dimensional (2D) materials have shown a great capacity to be next alternative to remedy this impediment. Graphene due to its unique properties such as high mobility and optical transparency, in addition to flexibility, robustness and environmental stability is amongst 2D materials to shine in photonics and optoelectronics. Several graphene-based photodetectors with ability to integrate with various energy thermoelectric, electromagnetic and piezoelectric devices is reported. However, pristine graphene is not suitable to detect reasonable signals in infrared region, due to its bandgap limitation. In this work, a graphene based near infrared detection is demonstrated using graphene/metal intercalated graphene photodetector. The intercalated graphene was grown using chemical vapor deposition (CVD) on Cu substrate and wet transfer of the layers to the Si/SiO2 substrate. A tapered aluminum microelectrode has been used for the electrical contacts to improve the detection of photogenerated carriers during the illumination. The infrared detection was demonstrated, responsivity and quantum efficiency was tested at room temperature and the mechanism of photogeneration was explained. © 2025, CC BY-NC-ND.

关键词： Microelectrodes

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Cellular VR: Online Learning and Dynamic Caching

arXiv

引用

arXiv 2025年

作者： Tharakan, Krishnendu S. Dahrouj, Hayssam Kouzayha, Nour ElSawy, Hesham Al-Naffouri, Tareq Y. The School of Computing Queen's University Kingston Canada The Department of Electrical Engineering University of Sharjah Sharjah United Arab Emirates The Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

Delivering an immersive experience to virtual reality (VR) users through wireless connectivity offers the freedom to engage from anywhere at any time. Nevertheless, it is challenging to ensure seamless wireless connectivity that delivers real-time and high-quality videos to the VR users. This paper proposes a field of view (FoV) aware caching for mobile edge computing (MEC)-enabled wireless VR network. In particular, the FoV of each VR user is cached/prefetched at the base stations (BSs) based on the caching strategies tailored to each BS. Specifically, decentralized and personalized federated learning (DP-FL) based caching strategies with guarantees are presented. Considering VR systems composed of multiple VR devices and BSs, a DP-FL caching algorithm is implemented at each BS to personalize content delivery for VR users. The utilized DP-FL algorithm guarantees a probably approximately correct (PAC) bound on the conditional average cache hit. Further, to reduce the cost of communicating gradients, one-bit quantization of the stochastic gradient descent (OBSGD) is proposed, and a convergence guarantee of O(1/√T) is obtained for the proposed algorithm, where T is the number of iterations. Additionally, to better account for the wireless channel dynamics, the FoVs are grouped into multicast or unicast groups based on the number of requesting VR users. The performance of the proposed DP-FL algorithm is validated through realistic VR head-tracking dataset, and the proposed algorithm is shown to have better performance in terms of average delay and cache hit as compared to baseline algorithms. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-Enabled Real-Time Optimization System for Traffic and Power Grid Management in 6G-Driven Smart Cities

引用

IEEE Internet of Things Journal 2025年

作者： Prathiba, Sahaya Beni Krishnamoorthy, Sri Ram Kannan, Karuna Soundari Selvaraj, Arikumar K. Ranganayakulu, Dhanalakshmi Fang, Kai Gadekallu, Thippa Reddy Vellore Institute of Technology Centre for Cyber Physical Systems School of Computer Science and Engineering Chennai600127 India Vellore Institute of Technology School of Electronics Engineering Chennai600127 India College of Engineering and Technology Department of Data Science and Business Systems Kattankulathur603 203 India Zhejiang A and F University College of Mathematics and Computer Science Hangzhou311300 China Zhejiang A and F University Division of Research and Development Lovely Professional University College of Mathematics and Computer Science Hangzhou Phagwara311300 India Chitkara University Center of Research Impact and Outcome Punjab Rajpura140401 India

The advent of 6G-enabled Internet of Everything(IoE) technologies is set to revolutionize urban infrastructures by providing fast, consistent, and low-delay capabilities for communication. 6G connectivity will integrate traffic and power grids for adaptive urban management. However, current traffic networks and power grids face critical challenges such as fragmented data processing, delayed responses, and outdated resource management leading to inefficiencies like traffic congestion and power outages. In 6G-enabled smart grid cities, system complexity and interdependence demand dynamic, real-time solutions, further exacerbating inefficiencies. To address these issues, this study introduces Digital Twin-enabled Real-time Optimization System (DT-ROS), a dynamic framework designed to optimize urban traffic and power grid systems. DT-ROS integrates a dual-tier Digital Twin (DT) and an advanced scheduling framework based on Priority Age of Information Deep Q Scheduler (PAoI-QS). The dual-tier framework builds an elementary and Integrated Digital Twin (IDT) with Auto-Regressive Integrated Moving Average (ARIMA)-based forecasting for accurate real-time traffic and energy demand predictions. The advanced scheduling framework minimizes the Age of Information (AoI), ensuring decision-making relies on the most current and relevant data. By continuously monitoring and processing real-time data, DT-ROS creates virtual models to simulate system behavior and dynamically allocate resources. Simulation results demonstrate the effectiveness of DT-ROS, achieving a 30% reduction in traffic congestion and a 25% improvement in power grid stability compared to existing methods. To create effective, robust, and sustainable urban systems for future smart cities, DT-ROS addresses traffic and electricity problems. © 2014 IEEE.

关键词： Smart power grids

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：