检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Lv, Qincheng Liu, Xiaofeng Li, Jie Ni, Rongrong Xue, Pujun Song, Siyang College of Information Science and Engineering Hohai University Changzhou China College of Artificial Intelligence and Automation Hohai University Changzhou China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China School of Microelectronics and Control Engineering Changzhou University Changzhou China School of Computer Science University of Exeter Exeter United Kingdom

ISBN: (纸本)9798350368741

Facial reactions convey crucial emotional information and coordinating interpersonal relationships in human dyadic interactions. While existing Multiple Appropriate Facial Reaction Generation (MAFRG) methods focus on generating multiple reasonable facial reactions, none of these approaches combines 2D and 3D facial behaviour information nor account for the influence of individuals' facial identities, leading to inconsistencies in the generated facial reactions and limited capability in capturing subtle variations in facial depth and expression dynamics. This paper proposes a novel Hierarchical Multimodal Decoupling-Fusion (HMDF) framework that decouples 3D facial identity from expression behaviors, eliminating identity-based interference in the reaction generation process, which are integrated with audio-visual features through a cross-attention mechanism. Experiments show that our framework achieved the enhanced diversity and synchrony in the generated facial reactions. © 2025 IEEE.

关键词： 2D 3D facial behaviour fusion Facial identity decoupling Multiple Appropriate Facial Reaction Generation

来源：评论

学校读者我要写书评

暂无评论

Lyapunov-Based Stochastic Resource Allocation for Integrated Satellite-Terrestrial Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Koutsioumpa, Vasiliki I. Mitsiou, Nikos A. Tegos, Sotiris A. Diamantoulakis, Panagiotis D. Sarigiannidis, Panagiotis G. Karagiannidis, George K. Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki54124 Greece University of Western Macedonia Department of Informatics and Telecommunications Engineering Kozani50100 Greece

The integration of a satellite network with a terrestrial network, supporting optimized network selection and service continuity, is essential to meet the requirements of sixth-generation (6 G) wireless networks. In a typical scenario with both terrestrial and satellite services, a subset, referred to as terrestrial users (t-users), can communicate only with the terrestrial base station (BS), while dual users (d-users) can transmit information to both the BS and an available LEO satellite. Thus, we focus on an integrated satellite-terrestrial uplink network, assuming that non-orthogonal multiple access (NOMA) is used in the terrestrial sub-network, which is motivated by the existence of non-line-of-sight channels between the BS and the users. We also investigate the use of two communication protocols for the satellite sub-network, considering both orthogonal multiple access (OMA) and NOMA. We define a utility function based on the achievable rates of the users and formulate an optimization problem to maximize the long-term utility of the network, taking into account constraints on the maximum capacity of the BS and the LEO satellite, as well as short- and long-term power consumption. We apply Lyapunov theory to decompose it into multiple single-time slot sub-problems, and finally transform it into convex form and solve it effectively. The network selection by the d-users as well as the optimal resource allocation for all users are also investigated. The simulation results show that d-users prefer to communicate with the LEO satellite rather than the BS. The probability of this selection is strongly influenced by the chosen communication scheme and the trajectory of the LEO satellite. Furthermore, there is an improvement in utility when the LEO satellite is close to its zenith position, while users achieve higher utility when the NOMA protocol is used in the satellite sub-network compared to the OMA counterpart. © 1967-2012 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

A Contend Node-Restricted Receiver-Initiated MAC Protocol With Consecutive Packet Transmission

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Liu, Yuxin Ota, Kaoru Dong, Mianxiong Wang, Ruoyu Changsha University College of Computer Science and Engineering Changsha410022 China Muroran Institute of Technology Department of Sciences and Informatics Japan Central South University School of Computer Science and Engineering Changsha410083 China

The medium access control (MAC) protocol plays a crucial role in wireless communications, influencing key performance metrics, such as energy consumption, delay, collision, and throughput. This paper introduces the Contend Node Restricted Joint Consecutive Packet Transmissions Receiver-Initiated (CNR-CPT-RI) protocol, specifically designed to minimize collisions and reduce energy consumption in wake-up radio-enabled wireless sensor networks (WSNs). The CNR-CPT-RI protocol is an effective communication protocol that is mainly applied with nodes in the one-hop range of the sink. Since the sink has the ability to control each node, it becomes feasible to manage the nodes in a way that effectively reduces collisions and enhances network lifetime as well as throughput. Moreover, the CNR-CPT-RI protocol can adaptively adjust the number of nodes participating in channel contention, maintaining it within an optimal range to balance reduced collisions, decreased energy consumption, and sustained high throughput. Furthermore, the winning node in channel contention employs Consecutive Packet Transmissions (CPTs) method to further diminish competition. Comprehensive theoretical and experimental results demonstrate that the number of collisions of the CNR-CPT-RI protocol is only 42.4%, 35.9%, and 32.5% of the baseline protocol when the number of nodes is 10, 20, and 30, respectively. The energy consumption of the CNR-CPT-RI protocol is reduced by 5.7%, 15%, and 22.6%, and the delay is decreased by 6.7%, 16%, and 32%, respectively, compared with that of the existing protocol. © 2017 IEEE.

关键词： Internet protocols

来源：评论

学校读者我要写书评

暂无评论

AAL-based smart cane system with security and privacy features for blind and visually impaired individuals

引用

Microprocessors and Microsystems 2025年 114-115卷

作者： Tsantikidou, Kyriaki Delimpaltadakis, Grigorios Diasakos, Damianos Sklavos, Nicolas SCYTALE Group Computer Engineering and Informatics Department University of Patras Hellas Greece

Ambient Assisted Living (AAL) technologies aim at increasing the quality of life for people with impairments. Practicality, reliability, autonomy, ease-of-use, safety, and low cost are of the utmost importance and in some cases omitted or overlooked by the research community. In this paper, an AAL-based smart cane system with security and privacy features for blind and visually impaired individuals that aims at satisfying these requirements is proposed. Multiple services that facilitate the everyday life for both indoor and outdoor activities are implemented: obstacle detection for ground and head level via ultrasonic (US) sensors and vibrations, ascending and descending stair detection/recognition via computer vision, image processing through various sensors, an emergency button for additional safety, and a LoRa antenna with a security and privacy mechanism for safely communicating with the Health 4.0-based environment. The proposed system is implemented with an Arduino and Raspberry Pi Zero combination and provides more practical and economic services compared to other published related works, including head-level detection, an indoor-outdoor adjustment switch and security mechanisms that are in most cases dismissed. It achieves a 7.4 % accuracy increase for general obstacle detection and a 100 % consistent drop or wall detection accuracy compared to published works. The proposed system presents a 37.82 % increase of speed-adjusted recall and a 24.4 % performance increase in its stair detection feature compared to published works. It focuses on hardware efficiency, safety and real-world autonomy with cost efficient alternatives. The proposed architecture of the security mechanism achieves a small area consumption, minimum of 35.6 % decrease compared to published designs, and an efficient throughput, that is appropriate with the utilized antenna. © 2025 Elsevier B.V.

关键词： Assisted living

来源：评论

学校读者我要写书评

暂无评论

Identify spoofing attacks in Internet of Things (IoT) environments using machine learning algorithms

引用

Journal of High Speed Networks 2025年第1期31卷 61-70页

作者： Vajrobol, Vajratiya Saxena, Geetika Jain Pundir, Amit Singh, Sanjeev B. Gupta, Brij Gaurav, Akshat Rahaman, Mosiur Institute of Informatics and Communication University of Delhi New Delhi India Department of Electronics Maharaja Agrasen College University of Delhi New Delhi India Department of Computer Science and Information Engineering Asia University Taichung Taiwan Dehradun India UCRD Chandigarh University Chandigarh India Department of Computer Science Ronin Institute MontclairNJ United States International Center for AI and Cyber Security Research and Innovations Asia University Taichung Taiwan

With the growing adoption of Internet of Things (IoT) devices, security concerns are becoming increasingly urgent. Protecting IoT systems from cyberattacks is crucial to safeguard sensitive information. Spoofing, particularly Domain Name System (DNS) and Address Resolution Protocol (ARP) spoofing, is a type of attack that can manipulate network traffic and compromise data integrity. DNS spoofing redirects users to fraudulent websites by altering domain name resolutions, while ARP spoofing tricks the network by associating a legitimate internet protocol address with a malicious MAC address, allowing attackers to intercept or modify communication. This study aims to develop an efficient method for detecting these types of spoofing attacks in IoT environments using machine learning techniques. The results show that the random forest algorithm outperforms other models, achieving remarkable performance with a 95.1% accuracy, a precision score of 95.2%, and a strong F1 score of 95.1%. A key contribution of this research is the simultaneous detection of both DNS and ARP spoofing within a unified framework, utilizing a comprehensive set of 46 features. These findings underscore the importance of ensuring robust protection against spoofing attacks to maintain the security and integrity of IoT systems. © The Author(s) 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Mamdani Fuzzy Inference System for Comprehensive Diabetes Risk Evaluation

A Mamdani Fuzzy Inference System for Comprehensive Diabetes ...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Tanjina Ahmed Tuly Tanjid Ahammed Shafin Md. Zahid Hasan Md. Hasan Imam Bijoy Mohammad Shamsul Arefin Mohammad Shorif Uddin Department of Computer Science and Engineering Health Informatics Research Lab Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering Chittagong University of Engineering and Technology Chattogram Bangladesh Department of Computer Science and Engineering Jahangirnagar University Savar Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Diabetes mellitus is a chronic condition characterized by insufficient insulin production and the inability to effectively utilize the insulin hormone, leading to elevated blood glucose levels. As diabetes is incurable and persists throughout a patient's lifetime, effective management requires early identification of risk factors to ensure continuous and feasible treatment. This study proposes a unique decision support system based on the Mamdani Fuzzy Inference System (MFIS) to predict diabetes risk. This study utilizes a publicly available diabetes dataset containing 442 data that includes nine key health metrics such as BMI, blood glucose, cholesterol levels, and blood pressure to predict the risk of diabetes. The dataset aims to support early diagnosis and better diabetes management by providing insights into individual risk factors. This resource contributes to the development of more accurate decision-support systems in healthcare. We identify key variables and establish a membership function to assess individual risk. The Fuzzy Inference System (FIS) is well-suited for handling complex and uncertain conditions, making it an effective tool for this application. The advantages of the MFIS include its ability to incorporate expert knowledge through linguistic variables and fuzzy rules. This system demonstrates the practical benefits of MFIS in developing intelligent decision-making tools, particularly in the domain of diabetes risk prediction.

关键词： Fuzzy logic Decision support systems Accuracy Uncertainty Predictive models Blood pressure Diabetes Glucose Insulin Blood

来源：评论

学校读者我要写书评

暂无评论

A unified approach to quasi-uniform completion: Bridging MacNeille, Dedekind and Doitchinov's theories with a new framework

引用

Topology and its Applications 2025年

作者： Andrikopoulos, Athanasios Gounaridis, Ioannis University of Patras Dept. of Computer Engineering and Informatics Patras 26504 Greece

In this paper, we present a comprehensive completion theory applicable to all quasi-uniform spaces, denoted as Λ-completion. An integral aspect of this completion theory lies in its incorporation of prerequisites articulated by Doitchinov, facilitating a natural extension of the classical theory of uniform completeness. Central to this approach is the concept of “cut of nets,” which emerges from the amalgamation of two fundamental notions: (1) The notion of a “Dedekind-MacNeille cut” within order theory, and (2) the concept of a D-“Cauchy net” as introduced by Doitchinov. Notably, in the realm of uniformity, the concept of cut of nets aligns with the well-established notion of an equivalence class of nets. This convergence enhances our understanding and provides a unifying framework for the completion theory, drawing from both order theory and the nuanced perspective of Doitchinov's D-Cauchy nets. © 2025 Elsevier B.V.

关键词： Cauchy net Completeness Dedekind-MacNeille completion Embedding Quasi-uniform space Quasi-uniformity

来源：评论

学校读者我要写书评

暂无评论

Predicting Heat Stroke Risk: A Clinical Decision Support System using Fuzzy Association Mining Approach

Predicting Heat Stroke Risk: A Clinical Decision Support Sys...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Abdullah Al Noman Rinvi Jaman Riti Md. Zahid Hasan Md. Hasan Imam Bijoy Mohammad Shorif Uddin Mohammad Shamsul Arefin Department of Computer Science and Engineering Health Informatics Research Lab Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering Jahangirnagar University Savar Bangladesh Department of Computer Science and Engineering Chittagong University of Engineering and Technology Chattogram Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Heat stroke is a serious medical condition that requires immediate treatment and is exacerbated by intense heat and climate change. This paper introduces a Clinical Decision Support System (CDSS) for heat stroke risk assessment based on Fuzzy Association Rule Mining. The system evaluates key attributes extracted from the Stanford Bioengineering Senior Capstone Project dataset, including daily water intake, cardiovascular history, heat index, environmental and rectal temperatures, blood pressure, pulse rate, humidity, age, and sex. These attributes help identify detailed patterns associated with heat stroke risk. Using fuzzy logic, the CDSS addresses the inherent vagueness of medical information through a set of "if- then" rules designed for healthcare practitioners. The system is tested with historical data, demonstrating its effectiveness in recognizing critical parameters to provide personalized, timely attention to potential heat stroke cases. It aims to reduce heat- related illnesses and fatalities by enabling rapid data-driven decision-making in healthcare. Despite certain limitations, this study highlights the necessity of intelligent systems for proactive health management.

关键词： Decision support systems Climate change Fuzzy systems Risk management Predictive models Medical services Medical conditions

来源：评论

学校读者我要写书评

暂无评论

Learning to Deblur Polarized Images

引用

International Journal of computer Vision 2025年 1-16页

作者： Zhou, Chu Teng, Minggui Zhou, Xinyu Xu, Chao Sato, Imari Shi, Boxin National Institute of Informatics Tokyo Japan National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China National Key Laboratory of General AI School of Intelligence Science and Technology Peking University Beijing China

A polarization camera can capture four linear polarized images with different polarizer angles in a single shot, which is useful in polarization-based vision applications since the degree of linear polarization (DoLP) and the angle of linear polarization (AoLP) can be directly computed from the captured polarized images. However, since the on-chip micro-polarizers block part of the light so that the sensor often requires a longer exposure time, the captured polarized images are prone to motion blur caused by camera shakes, leading to noticeable degradation in the computed DoLP and AoLP. Deblurring methods for conventional images often show degraded performance when handling the polarized images since they only focus on deblurring without considering the polarization constraints. In this paper, we propose a polarized image deblurring pipeline to solve the problem in a polarization-aware manner by adopting a divide-and-conquer strategy to explicitly decompose the problem into two less ill-posed sub-problems, and design a two-stage neural network to handle the two sub-problems respectively. Experimental results show that our method achieves state-of-the-art performance on both synthetic and real-world images, and can improve the performance of polarization-based vision applications such as image dehazing and reflection removal. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep learning Image deblurring Polarization camera Polarized images

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to User Allocation in a 5th Generation Network 24

A Deep Learning Approach to User Allocation in a 5th Generat...

引用

Proceedings of the 28th Pan-Hellenic Conference on Progress in Computing and informatics

作者： Ioannis Konstantoulas Iliana Loi Kyriakos Sgarbas Apostolos Gkamas Christos Bouras Department of Electrical and Computer Engineering University of Patras Patras Greece Department of Chemistry University of Ioannina Ioannina Greece Computer Engineering and Informatics Department University of Patras Patras Greece

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：