检索结果-内蒙古大学图书馆

Intelligent QV2X Routing for Traffic Management in Consumer IoV Using STGNN and Reinforcement Learning

IEEE Transactions on Consumer Electronics 2025年

作者： Jamal, Syed Saqib Muhammad, Afaq Song, Wang-Cheol Jeju National University Department of Electronic Engineering Jeju Korea Republic of College of Computing and Mathematics Computer Engineering Department and Interdisciplinary Research Center for Intelligent Secure Systems Dhahran Saudi Arabia

In the Consumer Internet of Vehicles (CIoV), reliable and timely data communication is essential for enhancing driver experience and safety. This paper introduces an innovative QV2X routing strategy that uses Spatio-Temporal Graph Neural Networks (STGNN) and Q-learning to optimize packet traffic in CIoV. By predicting network conditions and adapting to real-time data flows, our approach directly addresses consumer needs for efficient data transmission, reduced communication delays, and improved infotainment access. The integration of predictive models with adaptive learning mechanisms not only optimizes packet delivery but also minimizes latency and packet loss, critical for consumer applications like real-time navigation assistance and hazard warnings. Our key contribution is a dynamic packet traffic management system designed for consumer use, enhancing network reliability and efficiency for everyday vehicle users. Experimental results validate that our model surpasses existing benchmarks by improving packet delivery ratios by up to 15% and reducing end-to-end delays by up to 20% in urban traffic scenarios. This advancement demonstrates our strategy's effectiveness in enriching consumer experiences and safety in vehicular communications. © 1975-2011 IEEE.

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

GENSIMO - A Generic Framework for Modelling Social Insurance systems 25th

GENSIMO - A Generic Framework for Modelling Social Insuranc...

引用

25th International Workshop on Multi-Agent-Based Simulation, MABS 2024

作者： de Haan, Fjalar J. Thompson, Jason School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Parkville Australia Melbourne Centre for Data Science The University of Melbourne Parkville Australia Department of Psychiatry Faculty of Medicine Dentistry and Health Sciences The University of Melbourne Parkville Australia

ISBN: (纸本)9783031880162

We report on the design, development and prototype testing of gensimo (GENeric Social Insurance MOdeling), a free and open-source software framework for modelling and simulation of social insurance systems. We discuss the conceptual and software design considerations of the framework in general before demonstrating how it works in detail by setting it up to model a particular social insurance scheme. We then present how we used this prototype set up to model the impact of a policy intervention on the workload of the insurer. While gensimo is under active development and we are a while away from serious verification and validation, this prototype testing shows realistic results. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Agricultural Water Conservation through AI-Enhanced Solar IoT Networks 3

Agricultural Water Conservation through AI-Enhanced Solar Io...

引用

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

作者： Maniraj, S.P. Monisha, J. Amutha, R. Kavitha, R. Shriidhar, P.J. Srinivasan, C. Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems Kattankulathur Tamilnadu Chennai India Tamil Nadu Chennai India Ultra College of Engineering and Technology Department of Electrical and Electronics Engineering Tamil Nadu Madurai India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Vinayaka Missions Kirupananda Variyar Engineering College Department of Computer Science and Engineering Tamil Nadu Salem India Saveetha Universityi Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

With the increasing water shortage and climatic uncertainty, creative strategies for effective water management in agriculture are necessary. This research investigates the integration of Artificial Intelligence (AI), particularly Artificial Neural Networks (ANN), with solar-powered Internet of Things (IoT) networks to enhance water utilization in agricultural activities. The proposed system facilitates accurate irrigation scheduling using real-time data from soil moisture sensors, meteorological stations, and crop health monitoring devices. The ANN model analyses this data to predict ideal irrigation schedules and volumes, minimizing water waste while improving crop yields. The solar-powered IoT framework provides sustainability and reduces dependence on traditional energy sources. Field trials indicate that the AI-enhanced system may promote water saving by as much as 30% relative to traditional irrigation techniques. Moreover, using AI enables adaptive learning, enabling the system to enhance its irrigation tactics using historical and real-time data. This novel method conserves water resources and fosters sustainable agriculture practices, coinciding with global initiatives to address water shortages and assure food security. The findings underscore the potential of technology-based solutions to revolutionize agricultural water management for a sustainable future. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

A new nano-scale authentication architecture for improving the security of human-computer interaction systems based on quantum computing

引用

Analog Integrated Circuits and Signal Processing 2025年第1期124卷 1-15页

作者： Ahmadpour, Seyed-Sajad Zohaib, Muhammad Navimipour, Nima Jafari Misra, Neeraj Kumar Rasmi, Hadi Salahov, Huseyn Avval, Danial Bakhshayeshi Navin, Ahmad Habibizad Hosseinzadeh, Mehdi Department of Computer Engineering Faculty of Engineering and Natural Sciences Kadir Has University Turkiye Istanbul Turkey Department of Electrical and Electronics Engineering Faculty of Engineering and Natural Sciences Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan School of Electronics Engineering VIT-AP University Andhra Pradesh Amaravathi522237 India Department of Computer Engineering Dezful Branch Islamic Azad University Dezful Iran Department of Information Systems Engineering Sakarya University Türkiye Sakarya Turkey Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz*** Iran Pattern Recognition and Machine Learning Laboratory School of Computing Gachon University Seongnam Korea Republic of

Human-Computer Interaction (HCI) is an interdisciplinary area of study focusing on the interaction of users and computers by scheming interactive computer interfaces. In addition, HCI systems need security to confirm user authentication, which is a crucial issue in these systems. Hence, user authentication is vital, allowing only authorized users to access data. Authentication is critical to the digital world since it provides security and safety for digital data. Moreover, a digital signature is an authentication method to confirm the accuracy and reliability of digital documents or communications. In addition, designing the circuit based on the complementary metal-oxide semiconductor (CMOS) technology can affect the security and safety of digital data due to the excessive heat dissipation of circuits. On the other hand, quantum-dot cellular automata (QCA) and reversible logic as alternative technologies to CMOS address these problems. Since QCA and reversible logic circuits have minimal energy dissipation, which is considered nearly zero, approaching these technologies proves extremely difficult for any hacker. This work presents an effective structure for the authenticator and human-computer interaction using QCA and IBM quantum computing with Qiskit simulations. The proposed structure has outperformed current circuits in terms of area, cell count, and latency. The paper demonstrates the QCA reversible logic layout of the proposed HCI authenticator and integrates IBM quantum computing simulations using Qiskit for validation. The implementation and testing of results are performed utilizing QCADesigner-2.0.3 and Qiskit simulation tools. The accuracy and efficiency of the proposed design are validated through simulation-derived comparison values, and energy dissipation simulations prove that the suggested circuit dissipates minimal energy. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Directed Brain Network Transformer for Psychiatric Diagnosis 27th

Directed Brain Network Transformer for Psychiatric Diagnosis

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhu, Xu Qi, Zhiwei Yue, Kun Su, Yunshan Duan, Liang School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China School of Education Yunnan University Kunming China Department of Radiology Affiliated Hospital of Yunnan University Kunming China

ISBN: (纸本)9783031781940

Human brain is a complex organ that consists of billions of neurons and trillions of connections among the neurons. To describe the correlations among the time series of the brain regions, we model the brain as a functional brain network to diagnose psychosis. However, traditional methods of functional brain network construction are usually noisy and do not consider the causal relationships among brain regions. To obtain the causal relationships and improve diagnosis interpretability, we propose a directed brain network Transformer (DBNT) for psychiatric diagnosis. First, the causal relationships in the blood-oxygen-level-dependent time series of brain regions are extracted to generate a directed brain network. Then, the feature encoding method is proposed to obtain local and global features of the brain networks by using the DBNT. Experimental results demonstrate that the accuracy of DBNT increases by 8.1% and 6.4% compared to state-of-the-art methods on two large-scale brain network datasets. DBNT also highlights the brain regions associated with psychosis and provides interpretation for diagnosis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Using Fitts' Law to Benchmark Assisted Human-Robot Performance 25

Using Fitts' Law to Benchmark Assisted Human-Robot Performan...

引用

ACM/IEEE International Conference on Human-Robot Interaction (HRI)

作者： Jiahe Pan Jonathan Eden Denny Oetomo Wafa Johal Department of Mechanical Engineering The University of Melbourne Melbourne Australia School of Computing and Information Systems The University of Melbourne Melbourne Australia

ISBN: (数字)9798350378931

ISBN: (纸本)9798350378948

Shared control systems aim to combine human and robot abilities to improve task performance. However, achieving optimal performance requires that the robot's level of assistance adjusts the operator's cognitive workload in response to the task difficulty. Understanding and dynamically adjusting this balance is crucial to maximizing efficiency and user satisfaction. In this paper, we propose a novel benchmarking method for shared control systems based on Fitts' Law to formally parameterize the difficulty level of a target-reaching task. With this we systematically quantify and model the effect of task difficulty (i.e. size and distance of target) and robot autonomy on task performance and operators' cognitive load and trust levels. Our empirical results (N=24) not only show that both task difficulty and robot autonomy influence task performance, but also that the performance can be modelled using these parameters, which may allow for the generalization of this relationship across more diverse setups. We also found that the users' perceived cognitive load and trust were influenced by these factors. Given the challenges in directly measuring cognitive load in real-time, our adapted Fitts' model presents a potential alternative approach to estimate cognitive load through determining the difficulty level of the task, with the assumption that greater task difficulty results in higher cognitive load levels. We hope that these insights and our proposed framework inspire future works to further investigate the generalizability of the method, ultimately enabling the benchmarking and systematic assessment of shared control quality and user impact, which will aid in the development of more effective and adaptable systems.

关键词： Adaptation models Teleoperators Systematics Human-robot interaction Benchmark testing Cognitive load Control systems Real-time systems Robots Load modeling

来源：评论

学校读者我要写书评

暂无评论

Cardiac MRI Segmentation of Ventricular Structures and Myocardium Using U-Net Variants

Cardiac MRI Segmentation of Ventricular Structures and Myoca...

引用

Advanced Research in computing (ICARC), International Conference on

作者： Chinthalanka B. Wijesinghe Dulani Meedeniya Pratheepan Yogarajah Department of Computer Science and Engineering University of Moratuwa Sri Lanka School of Computing Engineering and Intelligent Systems Ulster University Londonderry United Kingdom

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

Accurate segmentation of the ventricular structures and myocardium from Cardiac Magnetic Resonance (CMR) images is essential to diagnose and manage cardiovascular diseases. This study systematically evaluates the performance of five U-Net variants in cardiac MRI segmentation using the Automated Cardiac Diagnosis Challenge (ACDC) dataset and a hybrid loss function combining Cross-Entropy and dice losses. Among the variants, the Feature Pyramid U-Net achieved the best performance, with Dice coefficients of 0.9388 (Left Ventricle), 0.8759 (Right Ventricle), and 0.8426 (Myocardium), showcasing its superior ability to capture multi-scale features and segment complex anatomical structures. The comprehensive and standardized evaluation conducted in this study provides valuable insights into the strengths and limitations of these architectures for cardiac segmentation.

关键词： Deep learning Image segmentation Magnetic resonance imaging Computational modeling Magnetic resonance Computer architecture Myocardium Cardiovascular diseases Artificial intelligence Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Robust speech perception and classification-driven deep convolutional neural network with natural language processing

引用

Alexandria engineering Journal 2025年 123卷 358-368页

作者： Alshammari, Alya Alzaidi, Muhammad Swaileh A. Alrusaini, Othman Alshuhail, Asma Allafi, Randa Yafoz, Ayman Alsini, Raed Khadidos, Alaa O. Department of Applied Linguistics College of Languages Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of English Language College of Language Sciences King Saud University P. O. Box 145111 Riyadh Saudi Arabia Department of Engineering and Applied Sciences Applied College Umm Al-Qura University Makkah Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Department of Computer Science College of Sciences Northern Border University Arar Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

Speech recognition systems use computer algorithms to interpret and process spoken words and translate them into text. Speech-to-text, or Speech detection, is the proficiency of a program or machine to find spoken words aloud and translate them into plain text. Speech detection systems are the most common complex systems that use wide-ranging research in computer engineering, linguistics, and computer science. In today's significant data era, several machine learning (ML) approaches for processing raw, unlabelled speech data still need to be improved. Deep learning (DL) models, on the other hand, with their powerful modelling ability for extensive data, are capable of directly processing unlabelled data and have become a crucial area of research in the domain of automated speech recognition. The DL model has recently gained popularity for voice disorders and automated speech detection. DL is an ML that exploits artificial neural networks (ANN) to gain meaningful insights from data. The DL approach demonstrated great success and achieved significant attention in different fields comprising speech processing, computer vision (CV), and natural language processing (NLP). Therefore, this article develops a Deep Learning with Natural Language Processing based Robust Speech Detection (DLNLP-RSD) technique. The DLNLP-RSD technique derives features from the mel-frequency cepstral coefficient (MFCC) technique. Followed by the DLNLP-RSD technique employs a one-dimensional deep convolutional neural network (CNN) approach for the detection and classification of speech. Moreover, the parameter tuning model uses the grasshopper fractals optimization algorithm (GOA) approach. The performance evaluation of the proposed technique highlights its significant performance over other models concerning distinct measures. An extensive simulation analysis is executed to examine the improved results of the DLNLP-RSD model. The experimental validation of the DLNLP-RSD technique portrayed a sup

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

TraffiCoT-R: A framework for advanced spatio-temporal reasoning in large language models

引用

Alexandria engineering Journal 2025年 128卷 464-475页

作者： Tariq Alsahfi Kaleem Ullah Qasim Department of Information Systems and Technology College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia School of Computing and Artificial Intelligence Southwest Jiaotong University China

Spatio-temporal prediction investigates dynamic patterns in urban areas, including traffic flow, population movement, and infrastructure development and change. Most of the existing methods, however, require massive historical labeled data to train domain-specific models for a particular area of interest, which leads to inefficiency and reduced generalizability across different real-world environments. Such constraints call for models with high generalizability across different spatio-temporal applications. In this study, we introduce TraffiCoT-R, a prompt-based method that models the spatio-temporal relationships efficiently with LLMs. TraffiCoT-R integrates Spatio-Temporal Feature Importance Rotation (ST-FIR), a feature selection method, with a Feature Definition Module to enable contextualized reasoning and a multi-step iteration framework to enhance prediction. Such developments enable robust performance in zero-shot and few-shot configurations. Experiments on PeMS, NYCTaxi, NYCBike, and CHITaxi demonstrate that TraffiCoT-R outperforms state-of-the-art baselines on all the above-mentioned datasets in zero-shot configurations. These results show the potential of unifying LLMs with spatio-temporal frameworks for data-efficient, scalable city analysis.

关键词： Traffic flow prediction Prompt engineering Modular reasoning Spatio-temporal dependencies Feature reranking Token efficiency

来源：评论

学校读者我要写书评

暂无评论

Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Zhang, Xiyue Xue, Xiaoyong Du, Xiaoning Xie, Xiaofei Liu, Yang Sun, Meng University of Oxford Department of Computer Science United Kingdom Peking University Department of Information and Computing Science School of Mathematical Science China Monash University Department of Software Systems and Cybersecurity Australia Singapore Management University School of Computing and Information Systems Singapore Nanyang Technological University School of Computer Science and Engineering Singapore

Federated learning (FL), as a powerful learning paradigm, trains a shared model by aggregating model updates from distributed clients. However, the decoupling of model learning from local data makes FL highly vulnerable to backdoor attacks, where a single compromised client can poison the shared model. While recent progress has been made in backdoor detection, existing methods face challenges with detection accuracy and runtime effectiveness, particularly when dealing with complex model architectures. In this work, we propose a novel approach to detecting malicious clients in an accurate, stable, and efficient manner. Our method utilizes a sampling-based network representation method to quantify dissimilarities between clients, identifying model deviations caused by backdoor injections. We also propose an iterative algorithm to progressively detect and exclude malicious clients as outliers based on these dissimilarity measurements. Evaluations across a range of benchmark tasks demonstrate that our approach outperforms state-of-the-art methods in detection accuracy and defense effectiveness. When deployed for runtime protection, our approach effectively eliminates backdoor injections with marginal overheads. © 2025 IEEE.

关键词： Federated learning

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：