检索结果-内蒙古大学图书馆

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： M. Manimaran A. Sasi Kumar N V S Natteshan K. Baranitharan R Mahaveerakannan K Sudhakar Department of Computer Science Sri Krishna Adithya College of Arts and Science Coimbatore Department of Cloud Technology & Data Science Institute of Engineering & Technology Srinivas University Mukka Surathkal Dakshina Kannada District Department of CSE S.A. Engineering College Chennai Department of CSE VSB Engineering College Department of Computer Science and Engineering Saveetha School of Engineering Chennai Tamil Nadu India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India

Approximately 962,000,000 persons worldwide are 60 or older. Despite the widespread adoption of techniques for human activity detection, there has been a dearth of study into the specific challenge of identifying the tasks performed by the elderly. Given the proliferation of wearable and mobile devices, the Internet of Healthcare Things is assuming a larger role in Human Activity Recognition (HAR). This article focuses on assisting the elderly by tracking their movements in both indoor and outdoor settings. The dataset includes human actions like sitting, walking, ascending and descending stairs, standing, and lying down. Here, how deep learning might improve HAR in Internet of Home Things settings has been examined. For better HAR results, a semi-supervised deep learning framework has been developed that makes effective use of the imperfectly labelled sensor data in order to fine-tune the classifier learning model. An intelligent auto-labelling system is built on top of Deep Q-Network to enhance learning performance in Internet of Things (IoT) environment and address the issue of insufficient labelled samples. Finally, real-world data is used in trial and evaluation to prove the method’s utility and efficacy.

关键词： Deep learning Performance evaluation Schedules Tracking Medical services Stairs Safety

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wound Care in Healthcare Systems with Logistic Regression for Infection Detection

Enhancing Wound Care in Healthcare Systems with Logistic Reg...

引用

Innovations in Communications, Electrical and computer engineering (ICICEC), International Conference on

作者： L. Ramalingam Raveendra N Amarnath V. Arun N. C. Sendhilkumar Rupavathy Ravi C. Srinivasan Department of Artificial Intelligence and Data Science Loyola Institute of Technology Chennai Tamil Nadu India Mphasis Corporation Melissa Texas USA Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Sri Indu College of Engineering and Technology Hyderabad India Department of Artificial Intelligence and Data Science Agni College of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376524

In healthcare systems, wound care management is essential for reducing infections and promoting faster recovery. To improve wound care, this paper proposes a data-driven method that combines machine learning (ML), more particularly, Logistic Regression (LR), with Internet of Things (IoT) sensors to identify early infections. The system provides real-time data streams to healthcare providers by continually monitoring important wound parameters, including temperature, moisture, pH levels, and exudate presence via IoT-enabled sensors. Using LR, the system predicts the potential of wound infections based on these physiological indicators, allowing for more effective patient care and early treatments. When tested for accuracy and dependability in infection prediction, the proposed model shows significant detection skills with few false positives. This approach optimizes clinical processes by reducing the need for manual wound examination, enhancing patient safety, and lowering the possibility of complications from infections. Wound care management might improve patient outcomes and expedite infection control measures in medical institutions.

关键词： Temperature measurement Temperature sensors Accuracy Medical services Wounds Predictive models Prediction algorithms Safety Sensors Monitoring

来源：评论

学校读者我要写书评

暂无评论

Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV Systems

arXiv

引用

arXiv 2025年

作者： Chen, Zheyi Huang, Sijin Min, Geyong Ning, Zhaolong Li, Jie Zhang, Yan College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian Key Laboratory of Network Fuzhou350002 China Computing and Intelligent Information Processing [Fuzhou University Fuzhou350116 China Department of Computer Science Faculty of Environment Science and Economy University of Exeter ExeterEX4 4QF United Kingdom School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Informatics University of Oslo Oslo0316 Norway

Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on prior knowledge and rarely consider efficient resource allocation during the service migration process, making it hard to reach optimal performance in dynamic IoV environments. To address these important challenges, we propose SR-CL, a novel mobility-aware seamless Service migration and Resource allocation framework via Convex-optimization-enabled deep reinforcement Learning in multi-edge IoV systems. First, we decouple the Mixed Integer Nonlinear Programming (MINLP) problem of service migration and resource allocation into two sub-problems. Next, we design a new actor-critic-based asynchronous-update deep reinforcement learning method to handle service migration, where the delayed-update actor makes migration decisions and the one-step-update critic evaluates the decisions to guide the policy update. Notably, we theoretically derive the optimal resource allocation with convex optimization for each MEC server, thereby further improving system performance. Using the real-world datasets of vehicle trajectories and testbed, extensive experiments are conducted to verify the effectiveness of the proposed SR-CL. Compared to benchmark methods, the SR-CL achieves superior convergence and delay performance under various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation

arXiv

引用

arXiv 2023年

作者： Xue, Ye Lau, Vincent Shenzhen Research Institute of Big Data Shenzhen China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Low-rank model compression is a widely used technique for reducing the computational load when training machine learning models. However, existing methods often rely on relaxing the low-rank constraint of the model weights using a regularized nuclear norm penalty, which requires an appropriate hyperparameter that can be difficult to determine in practice. Furthermore, existing compression techniques are not directly applicable to efficient over-the-air (OTA) aggregation in federated learning (FL) systems for distributed Internet-of-Things (IoT) scenarios. In this paper, we propose a novel manifold optimization formulation for low-rank model compression in FL that does not relax the low-rank constraint. Our optimization is conducted directly over the low-rank manifold, guaranteeing that the model is exactly low-rank. We also introduce a consensus penalty in the optimization formulation to support OTA aggregation. Based on our optimization formulation, we propose an alternating Riemannian optimization algorithm with a precoder that enables efficient OTA aggregation of low-rank local models without sacrificing training performance. Additionally, we provide convergence analysis in terms of key system parameters and conduct extensive experiments with real-world datasets to demonstrate the effectiveness of our proposed Riemannian low-rank model compression scheme compared to various state-of-the-art baselines. © 2023, CC BY-NC-ND.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Scalable Federated Learning for Privacy-Preserving Credit Card Fraud Detection

Scalable Federated Learning for Privacy-Preserving Credit Ca...

引用

International Carnahan Conference on Security Technology

作者： Kyle D'souza Sia Puthusseri Aiden Gigi Samuel Computer Engineering Department Fr. Conceicao Rodrigues College of Engineering Mumbai India Artificial Intelligence & Data Science Department Fr. Conceicao Rodrigues College of Engineering Mumbai India

ISBN: (数字)9798350315875

ISBN: (纸本)9798350315882

In the modern digital landscape, credit card fraud remains a persistent threat, posing significant challenges to both individuals and banks, leading to privacy breaches. This study introduces an innovative approach by integrating federated learning into credit card fraud detection. Unlike traditional methods relying on centralized data collection, federated learning allows several banks to work together in training a fraud detection model while safeguarding individual transaction privacy through secure aggregation and differential privacy techniques. Experimental results with real-world data show that this approach achieves comparable performance to centralized methods, offering an effective and privacy-preserving solution to combat credit card fraud, enhance financial security, and protect sensitive data. This research provides a practical and secure means for banks to collectively identify credit card fraud and provide data privacy for both banks and cardholders.

关键词： Training Differential privacy Federated learning data collection Credit cards Privacy breach data models Fraud Security

来源：评论

学校读者我要写书评

暂无评论

Empirical Privacy Variance

arXiv

引用

arXiv 2025年

作者： Hu, Yuzheng Wu, Fan Xian, Ruicheng Liu, Yuhang Zakynthinou, Lydia Kamath, Pritish Zhang, Chiyuan Forsyth, David Siebel School of Computing and Data Science University of Illinois Urbana-Champaign United States Institute of Automation Chinese Academy of Sciences China Department of Electrical Engineering and Computer Science University of California Berkeley United States Google Research United States

We propose the notion of empirical privacy variance and study it in the context of differentially private fine-tuning of language models. Specifically, we show that models calibrated to the same (Ε, δ)-DP guarantee using DP-SGD with different hyperparameter configurations can exhibit significant variations in empirical privacy, which we quantify through the lens of memorization. We investigate the generality of this phenomenon across multiple dimensions and discuss why it is surprising and relevant. Through regression analysis, we examine how individual and composite hyperparameters influence empirical privacy. The results reveal a no-free-lunch trade-off: existing practices of hyperparameter tuning in DP-SGD, which focus on optimizing utility under a fixed privacy budget, often come at the expense of empirical privacy. To address this, we propose refined heuristics for hyperparameter selection that explicitly account for empirical privacy, showing that they are both precise and practically useful. Finally, we take preliminary steps to understand empirical privacy variance. We propose two hypotheses, identify limitations in existing techniques like privacy auditing, and outline open questions for future research. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Advancements in Chatbot Technology: Enhancing User Experience through AI and NL

Advancements in Chatbot Technology: Enhancing User Experienc...

引用

Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), International Conference on

作者： Yojna Arora Ajeet Singh Abhay Sharma Nitin Aggarwal Nidhi Bansal Department of Computer Science & Engineering Sharda University Greater Noida India Department of Computer Science & Engineering Moradabad Institute of Technology Moradabad Uttar Pradesh India Department of IoT & IS School of Computing and Intelligent System Manipal University Jaipur Jaipur Rajasthan Supervisor Oracle Development Database Admin Data Science PA USA Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

A chatbot is an AI-powered software or application designed to communicate with people. This technology can perform a variety of tasks, including providing instant responses and answers to users, delivering information, assisting with purchasing products, and enhancing customer service. In my paper, I present the fundamental principles and essential concepts of computing related to chatbots and its applications various sectors like Education, E commerce, Entertainment, Healthcare, Telecommunication, Customer Service etc. The paper also mentions detailed literature explain the contribution by various researchers in this fields. Architecture and step wise approach of creating a chatbot is presented lately.

关键词： Quantum computing Customer services Education Medical services computer architecture Chatbots User experience Software Artificial intelligence Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Tensor Network Structure Search Using Program Synthesis

arXiv

引用

arXiv 2025年

作者： Guo, Zheng Deshpande, Aditya Kiedrowski, Brian Wang, Xinyu Gorodetsky, Alex Michigan Institute for Data & AI in Society University of Michigan United States Electrical Engineering and Computer Science Department University of Michigan United States Aerospace Engineering Department University of Michigan United States Neuclear Engineering & Radiological Sciences Department University of Michigan United States

Tensor networks provide a powerful framework for compressing multi-dimensional data. The optimal tensor network structure for a given data tensor depends on both the inherent data properties and the specific optimality criteria, making tensor network structure search a crucial research problem. Existing solutions typically involve sampling and validating numerous candidate structures;this is computationally expensive, limiting their practical applications. We address this challenge by formulating tensor network structure search as a program synthesis problem and proposing a highly efficient validation method that is based on constraint solving. Specifically, we design a domain specific language: it builds the correspondence between programs and network structures, and uses a novel idea of output-directed splits to compress the search space without hindering the expressiveness. We then propose a synthesis algorithm that can prioritize promising candidates through constraint solving. Experimental results show that our approach improves search speed by 10× and achieves compression ratios by 1.5× to 3× better than state-of-the-art. Notably, our approach scales to larger tensors that are out of reach by prior work. Finally, we demonstrate that the discovered topologies generalize to data from the same source, achieving compression ratios up to 2.4× better than hierarchical Tuckers while maintaining the runtime around 110 seconds. © 2025, CC BY.

关键词： data compression ratio

来源：评论

学校读者我要写书评

暂无评论

Heuristic Solution to Joint Deployment and Beamforming Design for STAR-RIS Aided Networks

arXiv

引用

arXiv 2024年

作者： Yan, Bai Zhao, Qi Zhang, Jin Zhang, J. Andrew Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Global Big Data Technologies Centre University of Technology SydneyNSW2007 Australia

This paper tackles the deployment challenges of Simultaneous Transmitting and Reflecting Reconfigurable Intelligent Surface (STAR-RIS) in communication systems. Unlike existing works that use fixed deployment setups or solely optimize the location, this paper emphasizes the joint optimization of the location and orientation of STAR-RIS. This enables searching across all user grouping possibilities and fully boosting the system’s performance. We consider a sum rate maximization problem with joint optimization and hybrid beamforming design. An offline heuristic solution is proposed for the problem, developed based on differential evolution and semi-definite programming methods. In particular, a point-point representation is proposed for characterizing and exploiting the user-grouping. A balanced grouping method is designed to achieve a desired user grouping with low complexity. Numerical results demonstrate the substantial performance gains achievable through optimal deployment design. Copyright © 2024, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Intelligent Gen: An Efficient On-Demand Access Protocol in MANETs using Network Simulator - 2

Intelligent Gen: An Efficient On-Demand Access Protocol in M...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： T. Ganesan N. Murali S. Palani Murugan M. Chandrakumar Peter P. Anand Raj S. Manikandan Department of Computer Science & Engineering E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of Artificial Intelligence & Data Science E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of Software Engineering Periyar Maniammai Institute of Science & Technology Thanjavur Tamil Nadu India Department of Computer Science and Business Systems E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of Information Technology E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India

Mobile Ad-Hoc network is a self-configuring and multi-hop collection of mobile devices for making successful communication. The wireless and mobile communication process are encountered based on bandwidth, process control and energy conception. Energy conception is considered and dynamically changed to rely on life time of batteries and power. The life time of battery get exhausted very quickly the nodes are moved and changed rapidly across the network. This paper noticed the problem of life time of power, batteries and energy consumption problem in various routing stages. The proposed Intelligent Gen Algorithm is used to get optimal solution for ensuring high robustness, flexibility and Energy consumption factor. It presents a common framework to balance various routing requirements in MANETs dynamically. The following are the main contributions includes, i. introducing Intelligent GEN Algorithms to classify the throughout bandwidth, delay, data ratio. ii. Various routing performance are evaluated and viewed by speed, packetize and simulation time. The comparison evaluated by select routing algorithm using NS-2. The simulation results are recorded and the performance is monitored by using on demand access protocl. The result clearly demonstrated the proposed Intelligent Gen algorithm used in self-organized manner by wireless channel.

关键词：

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：