检索结果-内蒙古大学图书馆

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Chandrasekhar Rao Katru Sathish Srinivasan Mohan Kumar T G Sunita Yadwad G. Satish Ramya Maranan Lead Software Engineer Indian Land SC USA Oracle Cloud Infrastructure Division Machine Learning & AI Development San Francisco Bay Area California USA Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru Karnataka Computer science and Engineering Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Post Limda Gujarat Department of Electrical and Electronics Engineering Sree Dattha Institute of Engineering and Science Sheriguda Telangana Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Cloud environments utilize availability and usage of resources as crucial components in order to produce scalability, reliability and low cost. Such resource capabilities require autonomous systems that can handle these resources dynamically in spite of fluctuating workloads and service delivery requirements. Static models of resource management suffer from scalability and inability to react on the fly and accurately predict the demand thus causing Service Level Agreement (SLA) breaches and affecting the Quality of Service (QoS) as well as energy consumption profile. Advanced and elaborative cloud workloads require an intelligent system that can analyse the temporal and spatial patterns without impacting the overall system's performance significantly. Inspired by these challenges, this research proposes a Causal Dilated Geometric Algebra Convolutional Transformer Network (CATNet) along with the Prairie-Dog Optimizer (P-DogO), referred to as CAT-DogNet to learn and predict the dynamic scalability. CATNet integrates Causal Dilated Convolutional Networks in time domain for temporal structure capturing and Geometric Algebra Transformer for spatial resource coding. P-DogO adjusts weight parameters and losses for resource allocation, enhancing them depending on a work environment. A set of comprehensive assessments demonstrate a 0.85% SLA violation rate, average response time of less than 10ms, and overall 12.3% less energy consumption than baseline methods. The system had favourable predictability rates over 99.4% for the resource demand estimate. CAT-DogN et presents a sound and agnostic architecture for autonomous resource allocation in cloud environment, which indeed extend the state of art by considering flexibility, power consumption and QoS compliance.

关键词： Cloud computing Energy consumption Algebra Scalability Quality of service Transformers Real-time systems Resource management Time factors Service level agreements

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Cryptographic Protocols for (IoT) Malware Defence

Benchmarking Cryptographic Protocols for (IoT) Malware Defen...

引用

International Symposium on Applied Machine Intelligence and Informatics (SAMI)

作者： Khalil Ben Khaled Dönìz Borsos Jozsef Katona Kandó Kalmán Faculty of Electrical Engineering Institute of Microelectronics and Technology Obuda University Budapest Hungary Kándó Kálmán Faculty of Electrical Engineering Institute of Electronics and Communication Systems Obuda University Budapest Hungary Department of Software Development and Application Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary GAMF Faculty of Engineering and Computer Science John Von Neumann University Kecskemet Hungary Department of Applied Quantitative Methods Faculty of Finance and Accountancy Budapest Business University Budapest Hungary

ISBN: (数字)9798350379365

ISBN: (纸本)9798350379372

This study presents a comprehensive benchmarking analysis of cryptographic protocols for Internet of Things (IoT) malware defense. The framework was specifically tailored to evaluate cryptographic protocols such as AES-128, AES-256, ChaCha20, RSA (1024-bit, 2048-bit, and 4096-bit), SHA256, SHA512, and HMAC-SHA256 were tested in both standalone and emulated environments. The primary objective was to evaluate the performance and resource consumption of these protocols, focusing on their encryption and hashing efficiency. Key innovations include the comparative analysis of resource consumption and performance efficiency across diverse cryptographic operations, under both real-world and emulated conditions. By identifying protocols like ChaCha20 for high efficiency and minimal resource usage, and RSA 4096-bit for enhanced security at higher computational costs, this study provides actionable insights into the trade-offs between security and performance. These findings offer a foundational reference for selecting optimized cryptographic protocols, advancing IoT malware defense strategies through informed decision-making.

关键词： Performance evaluation Technological innovation Benchmark testing Malware Encryption Internet of Things Reliability Informatics Machine intelligence Cryptographic protocols

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Distributed Collaborative Sensing and Spectrum Access Approach for Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Peng, Yuhuai Li, Yuan Guo, Yu Zhang, Dawei Khan, Fazlullah Alturki, Ryan Alshawi, Bandar Northeastern University College of Computer Science and Engineering Shenyang110819 China Zhiyuan Research Institute Xihu District Hangzhou China Zhengzhou University School of Computer and Artificial Intelligence Henan Zhengzhou450001 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Zhejiang Ningbo315104 China KKR and KSR Institute of Technology and Sciences Department of Computer Science and Engineering Andhra Pradesh Guntur India Division of Research and Development Lovely Professional University Phagwara India University Centre of Research and Development Chandigarh University Mohali India Umm Al-Qura University Department of Software Engineering College of Computing Makkah Saudi Arabia Umm Al-Qura University College of Computing Department of Computer and Network Engineering Makkah Saudi Arabia

Cognitive radio (CR) provides key technical support for the seamless communication of consumer electronic (CE) devices through distributed cooperative sensing and spectrum access. However, its openness and dynamic nature introduce potential security risks and challenges. Due to the openness of wireless communication, spectrum sensing and access are vulnerable to malicious attacks, and resource-constrained devices cannot effectively implement artificial intelligence (AI)-driven encryption and access control strategies. To address these limitations, this study proposes a blockchain-based distributed collaborative sensing method for CE devices. In the proposed method, after sensing, the smart contracts verify node legitimacy using the ring signature method. The malicious users are rejected by the outlier detection method, which improves the collaborative anti-interference ability. In addition, by using a centralized training and distributed execution architecture, a secure spectrum sensing strategy based on multi-agent reinforcement learning is designed. The proposed strategy ensures that each node makes independent decisions, which enhances the adaptability of the CE ecosystem. The proposed method is verified by extensive simulations, and the results show that it can maintain spectrum awareness of more than 95.72% and an access success rate of 91.19% under malicious attacks. Moreover, communication overhead is significantly reduced by approximately 93.53%. © 1975-2011 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Multi-Kernel Graph Learning for Autism Prediction and Biomarker Discovery

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 842-854页

作者： Jin Liu Junbin Mao Hanhe Lin Hulin Kuang Shirui Pan Xusheng Wu Shan Xie Fei Liu Yi Pan Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi China Hunan Province Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha China School of Science and Engineering University of Dundee Dundee U.K. School of Information and Communication Technology Griffith University Gold Coast QLD Australia Shenzhen Health Development Research and Data Management Center Shenzhen China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal integration and heterogeneous information extractions from graphs, we propose a novel method called Multi-modal Multi-Kernel Graph Learning (MMKGL). To solve the problem of negative impact among modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging Data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology.

关键词： Diseases Autism Random access memory Data mining Kernel Electronic mail Training Neuroimaging Graph convolutional networks Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Hybrid State-Space and GRU-based Graph Tokenization Mamba for Hyperspectral Image Classification

arXiv

引用

arXiv 2025年

作者： Ahmad, Muhammad Butt, Muhammad Hassaan Farooq Usama, Muhammad Mazzara, Manuel Distefano, Salvatore Khan, Adil Mehmood Hong, Danfeng Dipartimento di Matematica e Informatica—MIFT University of Messina Messina98121 Italy Institute of Artificial Intelligence School of Mechanical and Electrical Engineering Shaoxing University Shaoxing312000 China CFD Pakistan Institute of Software Development and Engineering Innopolis University Innopolis420500 Russia School of Computer Science University of Hull HullHU6 7RX United Kingdom Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

Hyperspectral image (HSI) classification plays a pivotal role in domains such as environmental monitoring, agriculture, and urban planning. However, it faces significant challenges due to the high-dimensional nature of the data and the complex spectral-spatial relationships inherent in HSI. Traditional methods, including conventional machine learning and convolutional neural networks (CNNs), often struggle to effectively capture these intricate spectral-spatial features and global contextual information. Transformer-based models, while powerful in capturing long-range dependencies, often demand substantial computational resources, posing challenges in scenarios where labeled datasets are limited, as is commonly seen in HSI applications. To overcome these challenges, this work proposes GraphMamba, a hybrid model that combines spectral-spatial token generation, graph-based token prioritization, and cross-attention mechanisms. The model introduces a novel hybridization of state-space modeling and Gated Recurrent Units (GRU), capturing both linear and nonlinear spatial-spectral dynamics. This approach enhances the ability to model complex spatial-spectral relationships while maintaining scalability and computational efficiency across diverse HSI datasets. Through comprehensive experiments, we demonstrate that GraphMamba outperforms existing state-of-the-art models, offering a scalable and robust solution for complex HSI classification tasks. © 2025, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Full-Coverage Mapping of Daily High-Resolution XCO2 across China from 2015 to 2020 by Deep Learning-Based Spatio-Temporal Fusion

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年

作者： Li, Yi Yan, Jining Zhong, Liheng Bao, De Sun, Leigang Li, Guangyu China University of Geosciences School of Computer Science Wuhan430074 China Ministry of Education Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software Wuhan430074 China Ant Group World Financial Center Beijing100020 China Hebei Academy of Sciences Institute of Geographical Sciences Shijiazhuang050011 China Hebei Technology Innovation Center for Geographic Information Application Shijiazhuang050011 China Environmental Development Center of the Ministry of Ecology and Environment China

Carbon neutrality has become a global priority, and high spatio-temporal resolution data on the column-average dry-air mole fraction carbon dioxide (XCO2) is essential for tracking progress and guiding policy adjustments. However, satellite-derived XCO2 exhibits significant temporal and spatial gaps due to influences such as orbital dynamics and cloud cover. Additionally, the low spatial resolution of CarbonTracker (CT) is insufficient to meet the current demands for fine-scale monitoring. Current XCO2 assessment methods often rely solely on single-pixel data, overlooking the spatio-temporal correlations. In this article, we introduce a deep learning-based spatio-temporal model (DSTM) that extracts features from multiple data sources related to atmospheric transport, carbon emissions, and carbon sinks, enabling fine-scale XCO2 assessments. Additionally, XCO2 data from the Orbiting Carbon Observatory-2 (OCO-2) and CT were fused at a 0.1° spatial resolution to generate training labels with broader coverage and more samples, serving as fitting labels. Our approach produced daily, full-coverage 0.1° resolution XCO2 maps for China from 2015 to 2020, and analyzed changes in XCO2 growth trends over this period. Numerical results show that our model outperforms traditional deep learning methods. Model validation using data from four ground-based observation sites of the Total Carbon Column Observing Network (TCCON) achieved an average R2 of 0.86 and an RMSE of 2.67 ppm. The extraction and fusion of spatio-temporal features from multiple data sources provide a novel approach for reconstructing missing XCO2 data. © 1980-2012 IEEE.

关键词： Atmospheric movements

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to ‘Device-to-device communication in 5G heterogeneous network based on game-theoretic approaches: A comprehensive survey’ [J. Netw. Comput., Volume 238, June 2025, 104152] (Journal of Network and Computer Applications (2025) 238, (S1084804525000499), (10.1016/***.2025.104152))

引用

Journal of Network and Computer Applications 2025年 239卷

作者： Ahmad, Rana Zeeshan Rizwan, Muhammad Yousuf, Muhammad Jehanzaib Khan, Mohammad Bilal Almadhor, Ahmad Gadekallu, Thippa Reddy Abbas, Sidra Department of Information Technology University of Sialkot Sialkot Pakistan College of Science and Engineering University of Derby United Kingdom Software Research Institute Athlone Institute of Technology Ireland School of Electronic Engineering Xidian University Xidian China Department of Computer Engineering and Networks College of Computer and Information Science Jouf University Sakaka Saudi Arabia The College of Mathematics and Computer Science Zhejiang A&F University Hangzhou311300 China Division of Research and Development Lovely Professional University Phagwara India Centre of Research Impact and Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India Department of Computer Science COMSATS University Islamabad Sahiwal Pakistan

The authors regret the mistake in affiliation of Author Sidra Abbas. The correct affiliation is as follows: Sidra AbbasDepartment of Computer Science, COMSATS University Islamabad, Sahiwal, Pakistansidraabbas@***:sidr...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emergency Vehicle Navigation in Connected Autonomous Systems Using Enhanced Traffic Management System

引用

IEEE Internet of Things Journal 2025年

作者： Raja, Gunasekaran Anbalagan, Sudha Gurumoorthy, Sugeerthi Jegathesan, Darshini Girivel, Niveditha Subramanian Sundaram, Varsha Mani Shanmuga Khowaja, Sunder Ali Dev, Kapal Anna University NGNLab Department of Computer Technology MIT Campus Chennai600044 India Vellore Institute of Technology Chennai Centre for Smart Grid Technologies School of Computer Science and Engineering Chennai600127 India Citicorp Services Private Ltd Software Development Chennai600113 India Dublin City University School of Computing Faculty of Engineering and Computing Glasnevin Campus DublinD09 V209 Ireland Munster Technological University Department of Computer Science Bishopstown CorkT12 P928 Ireland University of Johannesburg Department of Institute of Intelligent Systems Johannesburg2006 South Africa Chitkara University Institute of Engineering and Technology Centre for Research Impact Outcome Chitkara University Punjab Rajpura140401 India

Autonomous Vehicle (AV) usage has become predominant in the rapidly evolving landscape of urban transportation. Integrating AVs and non-AVs in the existing traffic infrastructure has significantly increased the complexity of traffic patterns. This research work primes the enhanced Traffic Management System (e-TMS), a solution implemented to expedite Emergency Vehicle (EV) travel in the context of Connected AVs (CAVs) and ensured secured communication employing Public Key Infrastructure (PKI) among the Internet of Vehicles (IoV) framework. When an EV is detected, the IoV system verifies the EV's signal using PKI, ensuring its authenticity and integrity by encrypting the communication between the EV and Road Side Units (RSUs). Further, the e-TMS activates the platooning process where CAVs in the EV's lane shift to the adjacent lanes and dynamically form platoons to create a dedicated lane for the EV. To further optimize the platooning process, an Adaptive Smart Leader Selection (ASLS) algorithm is employed to select a leader vehicle spontaneously among the AVs based on the proximity to the EV, communication reliability, and lane position. Radio Detection and Ranging devices aid this platooning process by providing distance and target velocity, which are needed to maintain the required distance between the AVs and ensure safe platoon formation. The e-TMS enhances EV response times and overall traffic flow efficiency and resulted in 27.8% increase in mean speed compared to the traditional methods. © 2014 IEEE.

关键词： Emergency vehicles

来源：评论

学校读者我要写书评

暂无评论

The role of GPT in promoting inclusive higher education for people with various learning disabilities: a review

引用

PeerJ Computer Science 2025年 11卷 e2400-e2400页

作者： Gadekallu, Thippa Reddy Yenduri, Gokul Kaluri, Rajesh Rajput, Dharmendra Singh Lakshmanna, Kuruva Fang, Kai Chen, Junxin Wang, Wei Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon School of Computer Science Engineering and Information Systems Vellore Institute of Technology University Tamil Nadu India Zhongda Group Jiaxing China College of Information Science and Engineering Jiaxing University Jiaxing China Division of Research and Development Lovely Professional University Phagwara India School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati India School of Mathematics and Computer Science Zhejiang Agricultural and Forestry University Hangzhou China School of Software Dalian University of Technology Dalian China Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen China School of Medical Technology Beijing Institute of Technology Beijing China

The generative pre-trained transformer (GPT) is a notable breakthrough in the field of artificial intelligence, as it empowers machines to effectively comprehend and engage in interactions with humans. The GPT exhibits the capacity to enhance inclusivity and accessibility for students with learning disabilities in the context of higher education, hence potentially facilitating substantial advancements in the field. GPT can provide personalized and diverse solutions that successfully cater to the distinct requirements of students with learning disabilities. This motivated us to conduct an extensive review to assess the effectiveness of GPT in enhancing accessibility and inclusivity in higher education for students with learning disabilities. This review offers a comprehensive analysis of the GPT and its significance for enhancing inclusivity in the field of higher education. In this research, we also examined the possible challenges and constraints associated with the integration of GPT into inclusive higher education, along with potential solutions. Overall, this review is intended for educators, students with and without learning disabilities, policymakers, higher education institutes, researchers, and educational technology developers. This review aims to provide a comprehensive understanding of GPT in promoting inclusive higher education for people with various learning disabilities, its impacts on inclusive higher education, emerging challenges, and potential solutions. Copyright 2025 Gadekallu et al.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

GPT-Based Automated Induction: Vulnerability Detection in Medical software

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Deng, Liangjun Lei, Hang Khan, Fazlullah Srivastava, Gautam Chen, Jingxue Haque, Mainul University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China University of Nottingham Ningbo China School of Computer Science and the Next-Generation Internet of Everything Laboratory Faculty of Science and Engineering Zhejiang Ningbo315104 China Lovely Professional University Division of Research and Development Phagwara India Chandigarh University University Centre of Research and Development Mohali India Brandon University Department of Math and Computer Science BrandonMBR7A 6A9 Canada China Medical University Research Centre for Interneural Computing Taichung40402 Taiwan Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact & Outcome Punjab Rajpura140401 India University of Nottingham Ningbo China Department of Mathematics Faculty of Science and Engineering Zhejiang Ningbo315104 China

Integrating Natural Language Processing (NLP) with Generative Pre-trained Transformer (GPT) models plays a pivotal role in enhancing the accuracy and efficiency of healthcare software, which is essential for patient safety and providing high-quality care. The precision of healthcare software is fundamental to protecting the well-being of the patient. In addition, it can ensure the delivery of superior care, maintain the integrity of healthcare systems, and promote trust and cost-effectiveness. It is necessary to emphasize the importance of software reliability in its development and deployment. Symbolic execution serves as a vital technology in automated vulnerability detection. However, symbolic execution often faces problems such as path explosion, which seriously affects efficiency. Although there have been several studies to reduce the number of computational paths in symbolic execution, this problem remains a major obstacle. Therefore, more efficient solutions are urgently needed to ensure the software security. This paper proposes a large-scale language model(LLM) induction method mitigating path explosion applied to symbolic execution engines. In contrast to traditional symbolic execution engines, which often result in timeout or out-of-memory detection, our approach achieves the task of detecting vulnerabilities in seconds. Furthermore, our proposal improves the scalability of symbolic execution, allowing more extensive and complex programs to be analyzed without significant increases in computational resources or time. This scalability is crucial to tackling modern software systems and improving the efficiency and effectiveness of automated defect verification in healthcare software. © 2025 IEEE. All rights reserved,

关键词： Scalability

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：