检索结果-内蒙古大学图书馆

Cross-Scenario Device-Free Wireless Sensing with A Free-Energy View

IEEE Internet of Things Journal 2025年第11期12卷 16610-16621页

作者： Chen, Bo Wang, Jie Liu, Xiaokai Gao, Qinghua Pan, Miao Fang, Yuguang Dalian Maritime University School of Information Science and Technology Dalian116026 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian116023 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States City University of Hong Kong Department of Computer Science Hong Kong Hong Kong

Device-free wireless sensing (DFWS) has gained significant attention due to its high accuracy and privacy-preserving capabilities. DFWS systems work by analyzing the influence pattern of targets on the surrounding wireless signals. However, changes in the sensing scenario can alter signal propagation patterns, causing deep learning models to lose effectiveness in cross-scenario applications. To address this problem, we analyze the information content of different samples from a free-energy view, and provide a new idea to guide the alignment of target scenario samples with source scenario samples based on free-energy. We find that free-energy can measure the degree of scenario knowledge contribution of the samples. Based on this observation, we first perform unsupervised coarse alignment by minimizing the free-energy deviation between scenarios. Next, we iteratively select a few number of high free-energy samples near the decision boundary to fine-Tune the network, achieving scenario fine alignment with a small labeling effort. Extensive experiments on two public datasets and one self-collected dataset show that our proposed method achieves high accuracy in cross-scenario human activity and gesture recognition tasks. © 2014 IEEE.

关键词： Labeling Sensors Wireless sensor networks Wireless communication Feature extraction Costs Internet of Things Gesture recognition Metalearning Training

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Clinical Decision Support Systems (CDSS): Challenges, Benefits, Applications, and Future Directions 2

AI-Powered Clinical Decision Support Systems (CDSS): Challen...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Yesankar, Prajyot Puri, Chetan Gote, Pradnyawant M. Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

AI-based Clinical Decision Support Systems are a revolutionary innovation in the healthcare sector, using artificial intelligence to improve diagnostic precision, optimize treatment planning, and enhance patient outcomes. This paper discusses the challenges, benefits, applications, and future directions of AI-driven CDSS. Some of the key challenges are data quality, integration with EHRs, ethical concerns, and explainability issues. Despite these challenges, benefits such as efficiency improvements, reduced clinician workload, and the possibility of tailored medicine are substantial. In addition, the paper depicts diverse applications across oncology, cardiology, and primary care. The paper further stresses the directions: validation of robustness, user-friendly interfaces, and equitable deployment to achieve maximal utilization of AI-CDSS in global health care systems. Besides this, the integration of multimodal data and improvement in predictive analytics will help to revolutionize preventive care. Moreover, ethical practices with AI will bring forth trust and adoption. Such an all-inclusive review signifies the pivotal role AI will play in shaping clinical decision-making for the future. © 2025 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Economical Camera-based Measuring Scheme for Roundabout Traffic

引用

Periodica Polytechnica Transportation engineering 2025年第2期53卷 235-241页

作者： Kovács, Tamás Kovács, Lóránt Department of Information Technology GAMF Faculty of Engineering and Computer Science John von Neumann University Izsáki út 10. KecskemétH-6000 Hungary

Counting the turning movements in a four-leg roundabout is a challenging task and often executed by vehicle recognition and tracking on traffic videos. In order to obtain accurately all the 12 flow values of the origin-destination (O-D) matrix we need to measure arbitrary chosen 12 linearly independent flow values. However, the larger the area to be observed the more cameras are needed because the good pixel resolution of the vehicles and the proper camera inclination angles are essential. Here we propose a novel measuring scheme, which observes only two roundabout legs instead of observing all the four, as a result obtaining all the 12 flow values requires a reduced number of cameras. The directly measured flow values and the mathematical method of determining the O-D matrix are given in details. © 2025 Budapest University of Technology and Economics. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Telugu Language Analysis with XLM-RoBERTa: Enhancing Parts of Speech Tagging for Effective Natural Language Processing

引用

SN computer science 2025年第2期6卷 1-13页

作者： Bharathi Mohan, G. Prasanna Kumar, R. Krishna Jayanth, K. Doss, Srinath Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Faculty of Engineering and Technology Botho University Gaborone Botswana

This research investigates the efficacy of XLM-RoBERTa, a potent deep learning architecture rooted in transformer networks, for Part-of-Speech (POS) tagging—a foundational task in Natural Language Processing (NLP). The study narrows its focus to address the formidable UCD Telugu dataset, renowned for its intricate morphological characteristics that pose challenges to accurate tagging. Through meticulous fine-tuning of the pre-trained XLM-RoBERTa model. This study adeptly discerns and exploit intricate syntactic and semantic patterns underpinning the interplay between lexical elements and their respective POS tags. The rigorous evaluation regimen, complemented by a comprehensive statistical comparison with the Multilingual BERT model, conclusively establishes XLM-RoBERTa’s superiority. This advanced model attains a remarkable accuracy score of 91%, decisively surpassing the Multilingual BERT model, which achieves an accuracy of 88%. These findings not only underscore XLM-RoBERTa’s prowess in precise POS tagging, especially in the context of morphologically rich languages like Telugu, but also carry significant implications for the broader NLP community. This research unlocks valuable insights and positions XLM-RoBERTa as an exemplar of reliability and robustness in POS tagging. Furthermore, it extends an invitation for further exploration and innovation in deep learning architectures within the NLP domain. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bert Multilingual Bert NLP Parts-of-speech tagging Telugu XLM-RoBERTa

来源：评论

学校读者我要写书评

暂无评论

Research on Image Encryption Algorithm Based on Four-Dimensional Hyperchaotic System and Mandelbrot Set

Research on Image Encryption Algorithm Based on Four-Dimensi...

引用

作者： Sun, Yanling Jiang, Tianjiao Liu, Baoxing Li, Yingqi Xiao, Mingkun Su, Qun Faculty of Science Shenyang Jianzhu University Shenyang China School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China

In view of the problems of small key space and poor key sensitivity in classical image encryption algorithm, the characteristics of chaotic system and M set are analyzed, and a new image encryption algorithm is proposed in this paper. The parameter values generated by SHA-256 algorithm are substituted into the hyper-chaotic Lorenz system to form the initial values of the input plaintext image. Then pseudo-random sequences are generated by hyper-chaotic Lorenz system, and the sequences are scrambled and diffused. The image matrix is generated according to Mandelbrot set, and the image is scrambled again with the sequence generated by different iteration times, and the encrypted image is finally obtained by XOR operation. The experimental results show that the proposed image encryption algorithm has good performance in various evaluation criteria, the key space value of the algorithm is large enough, high key sensitivity and the correlation of adjacent pixels is significantly reduced, and the information entropy is close to the ideal value. Thus this paper proposes image encryption algorithm has good security, can satisfy the requirements of the digital image encryption technology. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

The Evolving Role of Telemedicine in Expanding Access to Healthcare: Benefits, Barriers, and Future Directions 2

The Evolving Role of Telemedicine in Expanding Access to Hea...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Talvekar, Shreya Khonde, Tanvi Hajbe, Janhavi Patle, Sneha Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

Telemedicine, the remote delivery of medical treatment via digital technology has become essential, particularly for rural and disadvantaged populations. The benefits of telemedicine are reviewed in this research, including increased access to care, lower costs, and better chronic illness management. Although the COVID-19 pandemic's acceleration guaranteed continuity of care, technological constraints, legal concerns, and data privacy considerations hindered the full potential from being achieved. The article addresses the barriers to wider adoption and examines research showing the benefits of telemedicine. It ends with suggestions for infrastructure investments and legislative modifications to broaden the use of telemedicine and lessen healthcare inequities. © 2025 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Assessment of Fuzzy Rule-based Systems for Heart Attack Prediction 2

A Comprehensive Assessment of Fuzzy Rule-based Systems for H...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Ugale, Om Puri, Chetan Gote, Pradnyawant M. Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

Heart disease is a leading global cause of death, highlighting the need for accurate and efficient risk assessment methods. Traditional models often fail to address the uncertainty and vagueness in medical data. A Fuzzy Rule-Based System (FRBS) offers a solution by leveraging fuzzy logic to handle imprecise inputs like age, blood pressure, and lifestyle factors. The system uses fuzzification to convert crisp inputs into fuzzy sets, applies expert-defined IF-THEN rules through an inference engine, and translates outputs into interpretable risk scores via defuzzification. FRBS provides a flexible and patient-centric approach, accommodating linguistic variables and ambiguous data. Applications include real-time monitoring through wearable devices and telemedicine platforms, enhancing preventive care and empowering early detection of heart disease. This innovative system bridges the gap between medical uncertainty and actionable insights, improving healthcare © 2025 IEEE.

关键词： Fuzzy rules

来源：评论

学校读者我要写书评

暂无评论

Assessing the Effectiveness of Machine Learning Algorithms in Vehicle Insurance Fraud Prediction: A Comparative Approach 3

Assessing the Effectiveness of Machine Learning Algorithms i...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Satone, Aditya P. Daronde, Subodh Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Biomedical Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331509675

Due to the wealth of information accessible on many insurance issues, including travel and auto insurance, individuals are becoming more and more impacted by these kinds of insurance in today's society. But this tendency also makes room for dishonest practices. Insurance fraud is harmful and unlawful, regardless of who commits it - the vendor or the customer. Fraud can come from both the customer and the vendor. The consumer may commit fraud by filing exaggerated claims or using out-of-date policies, while the vendor may market insurance from phoney firms or neglect to submit premiums. This paper presents a comparative analysis of various classification algorithms, including Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Linear Regression (LR), and Polynomial Regression, for detecting insurance fraud. The performance of these algorithms is evaluated using key metrics such as Precision, Recall, and F1-Score. The analysis reveals that the bestperforming model is the Random Forest, with a Mean Squared Error (MSE) of 6.50, outperforming the other techniques. © 2025 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Enhancing Organizational Performance: Synergy of Cyber-Physical Systems, Cloud Services, and Crowdsensing

引用

International Journal of Crowd science 2025年第1期9卷 44-55页

作者： Al-Qerem, Ahmad Ali, Ali Mohd Nabot, Ahmad Jebreen, Issam Alauthman, Mohammad Alangari, Someah Aburub, Faisal Aldweesh, Amjad Computer Science Department Faculty of Information Technology Zarqa University Zarqa13110 Jordan Communications and Computer Engineering Department Faculty of Engineering Al-Ahliyya Amman University Amman19328 Jordan Department of Information Security University of Petra Amman11196 Jordan Department of Computer Science College of Science and Humanities Dawadmi Shaqra University Shaqra11911 Saudi Arabia Department of Business Intelligence and Data Analytics University of Petra Amman11196 Jordan College of Computing and Information Technology Shaqra University Shaqra11911 Saudi Arabia

In the contemporary business landscape, software has evolved into a strategic asset crucial for organizations seeking sustainable competitive advantage. The imperative of ensuring software quality becomes evident as low-quality software systems pose formidable challenges to organizational performance. This study delves into the profound impact of three key dimensions of information system quality on organizational performance—information quality (IQ), quality of service (QoS), and software quality (SQ). Anchored in the DeLone and McLean information system (IS) success model, a quantitative questionnaire was administered to 360 industry experts and academics. Rigorous data analysis, employing exploratory factor analysis (EFA), confirmatory factor analysis (CFA), and structural equation modeling (SEM), revealed significant positive effects of all three quality dimensions on organizational performance. Among these dimensions, software quality emerged as the most influential, showcasing substantial total effects, closely followed by information and service qualities. The study underscores the tangible value derived from strategic investments in enhancing software, information, and service quality. Elevating these facets manifests as a catalyst for improved organizational performance, empowering decision-makers with accurate and timely information while enhancing user satisfaction with the system. This research contributes significantly to the IS success literature by empirically validating the synergistic relationship between information quality, service quality, software quality, and organizational outcomes. The systematic analysis offered in this study goes beyond theoretical validation, providing actionable insights for managers. The findings guide the prioritization of quality initiatives and resource allocation, enabling organizations to maximize competitive advantage. As a future research direction, investigating moderator influences and exploring alternate qualit

关键词： Data quality

来源：评论

学校读者我要写书评

暂无评论

AI-Progressions in Automated Facial Paralysis Evaluation: A Comprehensive Survey of Traditional to Deep Learning Approaches 4

AI-Progressions in Automated Facial Paralysis Evaluation: A ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Kiruthiga, S. Anbuananth, C. Dhilipkumar, V. Annamalai University Faculty of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India

ISBN: (纸本)9798331523923

Deep learning mechanisms allow computers to solve complex real-time problems with complex neural networks, it employs a vital role in health sector, for assisting the medical practitioners with quick and accurate decision making. Various studies on this research area proves that deep learning approaches are more effective in detecting facial paralysis, a common visible symptom of acute stroke. The sealing sign of stroke is facial weakness which destroys the newline muscle movements in the face on one or both sides of the nerves in the brain stream. Accurate and timely detection is most important and need of the golden hour, to patients effectively. Human assessment and traditional diagnostic methods have demonstrated poor inter rated reliability, demanding improved diagnostic tools. By analysing facial asymmetry and other relevant features like Face feature analysis, extracting characteristics such as eye shape, movement, and wrinkles from static images to detect facial weakness is done using various deep learning techniques. This work encompass the real-time challenges such as curating datasets, ethical concerns and data privacy of patients. The objective of this paper is to review the potentiality of various traditional to deep learning algorithms in automising the facial paralysis detection for accurate stroke diagnosis in patients. AI models can provide objective assessments that enhance the reliability of stroke detection. © 2025 IEEE.

关键词： Convolutional neural networks

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：