检索结果-内蒙古大学图书馆

Innovations in High Speed Communication and Signal Processing (IHCSP), International Conference on

作者： Digantkumar N Parmar Sudharshan Putha Renato R. Maaliw Bhavani Prasad Kasaraneni Faheem Ahmad Reegu Haewon Byeon Department of Computer Engineering Silver Oak University Independent Researcher and Senior Software Developer at Salesforce USA College of Engineering Southern Luzon State University Lucban Philippines Independet Researcher USA Department of Electrical and Electronics Engineering College of Engineering and Computer Science Jazan University Ksa Department of AI and Software Inje University Gimhae Republic of Korea

ISBN: (数字)9798350368949

ISBN: (纸本)9798350368956

AI and blockchain can make companies safer and more trustworthy. AI can handle massive quantities of data and make complicated judgments, but its lack of clarity and reliance on centralized data present safety, accountability, and openness concerns. Blockchain ensures data is accurate, clear, and simple to track with its decentralized and unchangeable record. Blockchain can improve AI systems by making decision-making more open and safer for AI data. Blockchain protects AI model data from unauthorized changes. This prevents illicit alterations and improves AI accuracy. Blockchain's autonomy lets parties independently verify AI decision-making, which fosters confidence. This study examines blockchain's primary AI protections. These include open data storage, validated AI models, and trustworthy smart contracts that make decisions automatically. Real-world examples from healthcare, finance, and supply chain management show how blockchain-enhanced AI could address data breaches, algorithmic bias, and machine accountability. These findings demonstrate that adding blockchain to AI systems increases their trustworthiness and makes AI use in modern organizations safer and more open.

关键词： Accuracy Supply chain management Decision making Smart contracts Medical services Data models Blockchains Security Reliability Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

SCS: A Secure Cloud Storage Framework with Enhanced Integrity and Auditability Using Consortium Blockchain System

SCS: A Secure Cloud Storage Framework with Enhanced Integrit...

引用

IEEE International Conference on Smart Internet of Things (SmartIoT)

作者： Aguru Aswani Devi Erukala Suresh Babu Mekala Srinivasa Rao Rajesh Kaluri Thippa Reddy Gadekallu Department of Computer Science & Engineering SRM University AP Amaravati Andhra Pradesh India Department of Computer Science & Engineering National Institute of Technology Warangal India Department of Computer Science & Engineering Lakireddy Bali Reddy College of Engineering India Department of Software and Systems Engineering Vellore Institute of Technology Vellore India The College of Mathematics and Computer Science Zhejiang A&F University Hangzhou China Division of Research and Development Lovely Professional University Phagwara India

ISBN: (数字)9798350366440

ISBN: (纸本)9798350366457

The widespread adoption of cloud storage enables users to remotely access resources through a self-service model. Utilizing pay-per-use storage services provided by cloud service providers (CSPs) requires users to commit financially to their resources. This paper introduces a Secure Cloud Storage (SCS) framework, offering a secure architecture for cloud storage using a consortium blockchain network to address trust issues. This framework substitutes the third-party auditor with peers of a consortium blockchain network, which handles the role of data storage and verification. Storage space is divided into uncommitted and committed segments. Uncommitted storage is used for storing unverified documents, while committed storage is reserved for documents that have been validated through a consensus mechanism. In contrast, committed storage is des-ignated for the storage of committed documents. Documents validated by a consensus threshold of peer nodes are moved from uncommitted to committed storage. The implementation of the SCS framework is conducted using Hyperledger Fabric, a modular blockchain platform optimized for permissioned networks. The security analysis demonstrates that SCS effectively protects cloud storage against attacks, including unauthorized access attacks, data integrity attacks, and malicious server attacks, while maintaining data integrity and auditability. The performance evaluation shows that document upload and retrieval times, block acceptance, execution times, and latency are all improved compared to state-of-the-art cloud storage techniques.

关键词： Performance evaluation Cloud computing Data integrity Memory Peer-to-peer computing Servers Security Internet of Things Secure storage Self-service

来源：评论

学校读者我要写书评

暂无评论

Enhanced Breast Cancer Relapse Prediction using Ensemble Learning Techniques

Enhanced Breast Cancer Relapse Prediction using Ensemble Lea...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： Mukesh Kumar Tripathi Meka Ananya V.N.L.N Murthy Tumma Shashank Jale Subash Reddy Kaushal Attaluri Department of Computer Science & Engineering Vardhaman college of Engineering Hyderabad Department of Information Technology Vardhaman college of Engineering Hyderabad Software Engineer (Machine Learning/AI Team) Pegasystems Worldwide India Pvt Ltd Hyderabad

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Breast cancer remains a significant health concern for women, and accurate prediction of recurrence is vital for effective treatment and improved outcomes. This research investigates the application of advanced ensemble learning techniques to enhance the reliability of breast cancer recurrence predictions. By combining Deep Neural Networks (DNN) and Artificial Neural Networks (ANN) with traditional machine learning methods, the proposed approach demonstrates significant improvements in accuracy, precision, sensitivity, specificity, F1-scores, and areas under the curve (AVCs). The study utilizes two breast cancer relapse datasets, UMCIO and WPBC, to evaluate the performance of the ensemble learning models. The results highlight the effectiveness of the proposed approach in accurately predicting breast cancer recurrence. This research contributes to the advancement of breast cancer diagnosis and treatment by providing a valuable tool for clinicians to assess the risk of recurrence and tailor treatment plans accordingly.

关键词： Deep learning Accuracy Sensitivity Artificial neural networks Predictive models Prediction algorithms Breast cancer Robustness Ensemble learning Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection 39

Look Inside for More: Internal Spatial Modality Perception f...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liang, Hanzhe Xie, Guoyang Hou, Chengbin Wang, Bingshu Gao, Can Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Audencia Financial Technology Institute Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Intelligent Manufacturing CATL Ningde China School of Computing and Artificial Intelligence Fuyao University of Science and Technology Fuzhou China School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (纸本)157735897X

3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we introduce a straightforward method named Internal Spatial Modality Perception (ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine (SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction module for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further aligning precise spatial structure. Extensive experiments validate the effectiveness of our proposed method, achieving object-level and pixel-level AUROC improvements of 4.2% and 13.1%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and is verified in both classification and segmentation tasks. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Enabling Collaborative and Green Generative AI Inference in Edge Networks

Enabling Collaborative and Green Generative AI Inference in ...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Meng Tian Zhicheng Liu Chao Qiu Xiaofei Wang Dusit Niyato Victor C. M. Leung College of Intelligence and Computing Tianjin University Tianjin China College of Computing and Data Science Nanyang Technological University Singapore College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Recent advances in the diffusion model mark a significant leap in AI-generated image technology while extending its application to the Internet of Things (IoT). However, deploying these models on resource-constrained edge devices presents considerable challenges, primarily due to their high computational energy demands and stringent quality requirements. In response to these challenges, we introduce a collaborative inference system tailored for green edge networks. First, we propose a multi-exit U-ViT model that achieves the balance between inference quality and processing speed by allowing adaptive selection of exit points during diffusion for efficient processing. Next, we develop a novel generative AI-assisted reinforcement learning algorithm that controls the exit selections and offloading decisions of the device to achieve maximum global gain. Furthermore, we design a novel policy network incorporating an attention-based state-embedded policy network to enhance the algorithm’s ability to perceive and make decisions about the state of the environment. Experimental results demonstrate that our system achieves energy-efficient inference while ensuring the quality of the generated content.

关键词： Energy consumption Adaptation models Generative AI Computational modeling Image edge detection Green products Collaboration Inference algorithms Energy efficiency Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Inducing Individual Students’ Learning Strategies through Homomorphic POMDPs

arXiv

引用

arXiv 2024年

作者： Gao, Huifan Zeng, Yifeng Pan, Yinghui Department of Automation Xiamen University Xiamen China Department of Computer & Information Sciences Northumbria University United Kingdom College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Optimizing students’ learning strategies is a crucial component in intelligent tutoring systems. Previous research has demonstrated the effectiveness of devising personalized learning strategies for students by modelling their learning processes through partially observable Markov decision process (POMDP). However, the research holds the assumption that the student population adheres to a uniform cognitive pattern. While this assumption simplifies the POMDP modelling process, it evidently deviates from a real-world scenario, thus reducing the precision of inducing individual students’ learning strategies. In this article, we propose the homomorphic POMDP (H-POMDP) model to accommodate multiple cognitive patterns and present the parameter learning approach to automatically construct the H-POMDP model. Based on the H-POMDP model, we are able to represent different cognitive patterns from the data and induce more personalized learning strategies for individual students. We conduct experiments to show that, in comparison to the general POMDP approach, the H-POMDP model demonstrates better precision when modelling mixed data from multiple cognitive patterns. Moreover, the learning strategies derived from H-POMDPs exhibit better personalization in the performance evaluation. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-based Service Chains Scheduling for Medical Emergency in Healthcare 7

Artificial Intelligence-based Service Chains Scheduling for ...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Soni, Mukesh Rusho, Maher Ali Byeon, Haewon Alghamdi, Azzah Hannan, Shaikh Abdul Dave, Parth Rameshchandra Dr. D. Y. Patil School of Science & Technology Tathawade Dr. D. Y. Patil Vidyapeeth Marashtra Pune India University of Colorado Department of Lockheed Martin Engineering Management BoulderCO80309 United States Inje University Department of Ai and Software & Medical Big Data Research Centre Gimhae50834 Korea Republic of Imam Abdalrhman Bin Faisal University College of Computer Science and Information Technology Computer Information Systems Department Khobar Saudi Arabia AlBaha University Faculty of Computing and Information AlBaha Saudi Arabia L. D. College of Engineering Department of Computer Engineering Gujarat Ahmedabad India

ISBN: (纸本)9798350350067

This study analyses the weekly scheduling challenge of health and medical information network service function chains to meet medical emergency categorization and grading needs. Emergency services are divided into four sorts by urgency and service area, with priorities and weights. The health and medical information network architecture, service model, and operation method are built accordingly. To reduce weighted completion time, a service function chain scheduling model is created. The function chain scheduling scheme is solved by matching game and Q -learning reinforcement learning algorithms for different issue scales. Finally, simulation studies demonstrate that this approach can accomplish graded medical emergency service, build health and medical information networks, and progress smart healthcare. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Maximizing the Social Welfare of Decentralized Knowledge Inference Through Evolutionary Game

Maximizing the Social Welfare of Decentralized Knowledge Inf...

引用

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Yuanfang Chi Qiyue Zhang Jiaxiang Sun Wei Cai Z. Jane Wang Victor C.M. Leung Department of Electrical and Computer Engineering The University of British Columbia Vancouver BC Canada College of Computer Science and Software Engineering Shenzhen University Guangdong China School of Science and Engineering The Chinese University of Hong Kong Shenzhen Guangdong China

ISBN: (数字)9798350384475

ISBN: (纸本)9798350384482

To broaden their domain knowledge coverage, large language models (LLMs) increasingly incorporate extensive cor-pus data from various industries. These heterogeneous datasets are often maintained by different stakeholders, where issues of data heterogeneity, privacy, and the network cost of data transmission have attracted much attention. To address these challenges, researchers have studied the integration of LLMs with knowledge graphs to manage data heterogeneity and with edge computing to ensure data privacy and transmission efficiency. In this work, we introduce a reputation system and a spot-check mechanism for a decentralized knowledge inference system in which edge nodes can collaborate with others for knowledge sharing while preserving their data privacy. We then use an evolutionary game model to study the dynamic decision-making between requestors and workers. Moreover, we show that higher reward values and higher model quality accelerate the maximization of social welfare.

关键词： Industries Data privacy Large language models Instruments Games Knowledge graphs Reliability theory

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT-Based Smart Farming Security with a Hybrid GRU Intrusion Detection System 3

Enhancing IoT-Based Smart Farming Security with a Hybrid GRU...

引用

3rd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2025

作者： Nagarajan, Sivakumar Vijay, S. Karthi, S. Praveen, R.V.S. Ramesh Vijaya Babu, K. Naresh, Burri I & I Software Inc Baglyos Circle Suite B-32 Bethlehem United States Sacred Heart College (Autonomous) Department of Data Science Tamilnadu India V.S.B. Engineering College Department of Computer Science and Engineering Tamilnadu Karur India LTIMindtree Limited M/s. Divija Commercial Properties The Skyview-Building No. 20 Telangana Hyderabad India Srkr Engineering College Andhra Pradesh Bhimavaram India Cvr College of Engineering Department of Cse - Cyber Security Telangana Hyderabad India

ISBN: (纸本)9798331521691

The growing use of IoT devices in smart agriculture makes the industry vulnerable to several cyber risks. This study introduces an innovative hybrid Intrusion Detection System (IDS) utilising Gated Recurrent Units (GRUs) to improve the security of IoT-enabled smart agriculture. compared to current LSTM and CNN-based intrusion detection systems, the proposed model effectively incorporates sequential data dependencies, hence minimising false positives and enhancing detection accuracy. Experimental findings indicate that the suggested model surpasses conventional techniques, with an accuracy of 97.5%, an F1 score of 0.96, and a recall of 0.97. These developments create a strong, efficient, and scalable solution for safeguarding IoT-based agricultural systems from cyber-attacks. © 2025 IEEE.

关键词： Anomaly Detection CNN Cybersecurity GRU Intrusion Detection System IoT Security LSTM Sequential Data Analysis Smart Farming

来源：评论

学校读者我要写书评

暂无评论

Fashion Recommendation System for E-Commerce using Deep Learning Algorithms

Fashion Recommendation System for E-Commerce using Deep Lear...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： M S Arunkumar R Gopinath M Chandru R Suguna S Deepa V Omprasath Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu Department of Computer Science and Engineering K. S. Rangasamy College of Technology Tiruchgode Department of Computer Science VET-Institute of Arts and Science (Co-Education) College Erode Department of Computer science and Engineering Bannari Amman Institute of Technology Sathyamangalam Department of Computer Technology - PG Kongu Engineering College Perundurai Erode Tamilnadu M.Sc (Software Systems) Kongu Engineering College Perundurai Erode Tamilnadu

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

In the increasingly competitive outlook of ecommerce, personalized recommendation systems have emerged as pivotal tools to enhance user experience and drive sales. This paper proposes a novel Fashion Recommendation System (FRS) leveraging deep learning techniques to offer personalized fashion suggestions to users. The system utilizes a combination of convolutional neural networks (CNNs) for image feature extraction. Through a comprehensive analysis of user interactions and preferences, the FRS generates tailored recommendations that align with individual style preferences and current trends. The work proposes a novel approach that utilizes the ResNet50 algorithm to analyze images of fashion items, extracting meaningful features that capture the essence of style, color, and texture. By training the ResNet50 model on vast datasets of fashion images, thereby enhancing its ability to make accurate recommendations. Through the integration of user preferences and historical data, this system can generate personalized fashion recommendations tailored to each user’s unique style and preferences, thus enhancing user satisfaction and engagement. By harnessing the power of deep learning and the ResNet50 algorithm, fashion retailers can offer personalized shopping experiences, increase customer retention, and drive sales.

关键词： Deep learning Training Image color analysis Feature extraction Market research User experience Electronic commerce Convolutional neural networks Recommender systems Residual 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：