检索结果-内蒙古大学图书馆

Decentralized Unlearning for Trustworthy AI-Generated Content (AIGC) Services

IEEE Network 2025年第3期39卷 285-292页

作者： Lin, Yijing Du, Hongyang Gao, Zhipeng Yao, Jing Jiang, Bingting Niyato, Dusit Li, Ruidong Zhang, Ping Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China The University of Hong Kong Department of Electrical and Electronic Engineering Pokfulam Hong Kong Central South University School of Computer Science and Engineering Changsha410083 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore Kanazawa University Institute of Science and Engineering Kanazawa920-1192 Japan

The widespread adoption of AI-Generated Content (AIGC) has captured remarkable interests from academia and industry. However, this advancement brings forth challenges in data ownership, as emphasized by the General data Protection Regulation’s right to be forgotten. The right to be forgotten allows participants to erase their data contributions from well-trained AIGC models. Training AIGC models demands an extensive amount of data and computations, often surpassing the capabilities of individual participants. As a solution, Federated Learning (FL) is employed to collaboratively train an AIGC model without sharing raw data directly. To protect the right to be forgotten in FL, "federated unlearning" has been introduced to eradicate the data contributions of unlearning participants from fully trained AIGC models, achieved by deleting historical model updates. However, given that historical updates are distributed among various participants, they may still hold contributions from the unlearning participants. This presents a challenge to the trustworthiness of federated unlearning. In this paper, we first provide an overview of both centralized and federated learning and unlearning methods. We survey relevant works and classify four main categories for federated unlearning. Subsequently, we introduce a comprehensive decentralized unlearning architecture designed for trustworthy AIGC services. To address the challenge of participants retaining historical contributions from unlearning participants, we integrate a coded computing-based interaction mechanism, ensuring both scalability and security. We further present a case study using NanoGPT to demonstrate the effectiveness of the proposed framework for decentralized unlearning. We conclude by identifying potential future research directions. © 1986-2012 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Autoencoder based Temporal Convolutional Network for Anomaly Detection in data Streams 1

Autoencoder based Temporal Convolutional Network for Anomaly...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Tamilselvan, K. Riadhwsein, Ramee Sundaram, S. Meenakshi Vigneshwaran, K.S. Abhinaya, S. Avs Engineering College Department of Information Technology Salem India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Data Science Bengaluru India New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering Chennai India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Computer Science and Engineering Mamallapuram India

ISBN: (纸本)9798331529246

Nowadays, the rapid growth of data stream from different sources has needed the development of effective Anomaly Detection (AD) methods. The existing unsupervised Deep Learning (DL) approaches learnt various patterns and relationships in data streams without labeled data. However, detecting anomalies in data streams led to significant challenges such as handling high-dimensional data and capturing temporal dependencies. Hence, this research proposes an Autoencoder based Temporal Convolutional Network (AE-TCN) for AD in data streams. Initially, the input data is collected from Numenta Anomaly Benchmark (NAB) repository and further preprocessed with Regression Imputation (RI) to handle missing values and logarithmic scaling to normalize the data respectively. After that, Robustly Optimized Bidirectional Encoder Representation from Transformer approach (RoBERTa) is employed to extract the semantic features. Finally, AE-TCN is introduced to identify the anomalies in data streams by extracting temporal features from reconstructed nominal patterns. From the results, the proposed AE-TCN established high results in terms of Accuracy (Acc), F1-score, and Area Under Curve (AUC) of 99.89%, 94.06%, and 99.85% respectively when compared with existing Deep Autoencoder Neural Network with Adamax Optimization (DANN-AO). © 2025 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

An Analytical Review of Large Language Models Leveraging KDGI Fine-Tuning, Quantum Embedding’s, and Multimodal Architectures

引用

computers, Materials and Continua 2025年第3期83卷 4031-4059页

作者： Uddagiri Sirisha Chanumolu Kiran Kumar Revathi Durgam Poluru Eswaraiah G Muni Nagamani Department of Computer Science and Engineering Prasad V Potluri Siddhartha Institute of Technology Vijayawada 520007 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram 522302 India Department of Computer Science and Engineering (Data Science) AVN Institute of Engineering and Technology Hyderabad 501510 India Department of Computer Science and Engineering (Data Science) Vignan’s Institute of Management and Technology for Women Hyderabad 501301 India Department of Computer Science and Engineering Andhra Loyola Institute of Engineering and Technology Vijayawada 520008 India

A complete examination of Large Language Models’ strengths, problems, and applications is needed due to their rising use across disciplines. Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance, strengths, and weaknesses. This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies. In this research, 50 studies on 25+ LLMs, including GPT-3, GPT-4, Claude 3.5, DeepKet, and hybrid multimodal frameworks like ContextDET and GeoRSCLIP, are thoroughly reviewed. We propose LLM application taxonomy by grouping techniques by task focus—healthcare, chemistry, sentiment analysis, agent-based simulations, and multimodal integration. Advanced methods like parameter-efficient tuning (LoRA), quantum-enhanced embeddings (DeepKet), retrieval-augmented generation (RAG), and safety-focused models (GalaxyGPT) are evaluated for dataset requirements, computational efficiency, and performance measures. Frameworks for ethical issues, data limited hallucinations, and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted. The investigation’s scope, mad, and methods are described, but the primary results are not. The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings perform better for context-heavy applications. In medical text normalization, ChatGPT-4 outperforms previous models, while two multimodal frameworks, GeoRSCLIP, increase remote sensing. Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance, demonstrating the necessity for adaptive models in multiple domains. To discover the optimum domain-specific models, explain domain-specific fine-tuning, and present quantum and multimodal LLMs to address scalability and cross-domain issues. The framework helps academics and practitioners identify, a

关键词： Large language models quantum embeddings fine-tuning techniques multimodal architectures ethical AI scenarios

来源：评论

学校读者我要写书评

暂无评论

Hybrid AI-Electronic Systems for Real-Time Edge Processing in IoT Networks 3

Hybrid AI-Electronic Systems for Real-Time Edge Processing i...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Sweety Prasanna Kiruba, G. Esakki Madura, E. Kumar, Bura Vijay Kavitha, M. Reddy, T. Srinivas Athiraja, A. Bannari Amman Institute of Technology Department of Computer Technology Tamil Nadu Sathyamangalam India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Sathyamangalam India School of Computer Science and Artificial Intelligence Sr University Warangal India Kathir College of Engineering Department of Artificial Intelligence and Data Science Neelambur Coimbatore India Malla Reddy Engineering College Department of Ece Main Campus Maisammaguda Telangana Medchal India Hyderabad India

ISBN: (纸本)9798331515911

Real-time data processing is facing many issues as a result of the Internet of Things' rapid expansion, especially at the network's edge where latency, bandwidth, and compute resources are limited. The creation of hybrid AI-electronic systems for real-time edge processing is investigated as a solution to these problems. To improve the effectiveness and precision of data processing in Internet of Things contexts, the research combines machine learning algorithms with sophisticated electronic circuits. The techniques include creating a brand-new hybrid framework that blends edge computing and AI models and focuses for low latency and low power consumption. When compared to conventional edge processing systems, extensive simulations and real-world research show a 25% reduction in processing latency and a 15% gain in data categorization accuracy. According to the findings, the suggested hybrid AI-electronic system can successfully handle the requirements of contemporary IoT networks and offer a scalable real-time edge processing solution. This strategy has potential for use in smart city applications, industrial automation, and other fields in the future. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Augmented Evolutionary Strategies for Intelligent Global Optimization

引用

IEEE Access 2025年 13卷 70138-70178页

作者： Ezugwu, Absalom El-Shamir Oyelade, Olaide Nathaniel Agushaka, Jeffrey Ovre Saha, Apu Kumar Unit for Data Science and Computing North-West University Potchefstroom2520 South Africa School of Electronics Electrical Engineering and Computer Science Queen’s University BelfastBT9 5BN United Kingdom Department of Computer Science Federal University of Lafia Lafia950101 Nigeria Department of Mathematics National Institute of Technology Agartala Tripura Agartala799046 India

This paper introduces the Susceptible-Infected-Removed Optimizer (SIRO), a novel learned heuristic inspired by biological systems and deep learning techniques. SIRO models its search process after the SIR epidemiological compartmental model, predicting the susceptibility, infection, and recovery dynamics of solutions. SIRO integrates deep learning into its initialization and parameter setting to enhance its efficiency, enabling intelligent and adaptive behavior. This hybridization improves solution quality, accelerates convergence, enhances robustness, and reduces computational costs. The algorithm’s performance was evaluated using CEC 2017 benchmark functions, demonstrating superior results in hybrid functions (C1-C28) despite moderate performance on traditional CEC1-CEC14 functions. Friedman’s test ranked SIRO 4th overall, with SSA as the top-performing algorithm. Additionally, SIRO was tested on real-world optimization problems, including mechanical engineering design, hyperparameter tuning, and feature selection for medical image classification. In the classification task, SIRO-enhanced CNN achieved an accuracy of 0.86 at the 5th epoch, outperforming CNN (0.66), CNN-GA (0.76), and CNN-WOA (0.75). Furthermore, SIRO reported a precision of 0.96, recall of 1.0, and F1-score of 0.98, highlighting its effectiveness. These results validate the benefits of integrating a learning mechanism into SIRO, yielding superior precision, computational efficiency, and performance over conventional optimization approaches. © 2013 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning at the service of metaheuristics for solving numerical optimization problems

引用

Neural Computing and Applications 2025年 1-36页

作者： Oyelade, Olaide N. Ezugwu, Absalom E. Saha, Apu K. Thieu, Nguyen V. Gandomi, Amir H. School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Bangladesh Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom2520 United States Department of Mathematics National Institute of Technology Agartala Tripura Agartala799046 India Faculty of Computer Science Phenikaa University Yen Nghia Hanoi Ha Dong12116 Viet Nam Department of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Integrating deep learning methods into metaheuristic algorithms has gained attention for addressing design-related issues and enhancing performance. The primary objective is to improve solution quality and convergence speed within solution search spaces. This study investigates the use of deep learning methods as a generative model to learn historical content, including global best and worst solutions, solution sequences, function evaluation patterns, solution space characteristics, population modification trajectories, and movement between local and global search processes. An LSTM-based architecture is trained on dynamic optimization data collected during the metaheuristic optimization process. The trained model generates an initial solution space and is integrated into the optimization algorithms to intelligently monitor the search process during exploration and exploitation phases. The proposed deep learning-based methods are evaluated on 55 benchmark functions of varying complexities, including CEC 2017 and compared with 13 biology-based, evolution-based, and swarm-based metaheuristic algorithms. Experimental results demonstrate that all the deep learning-based optimization algorithms achieve high-quality solutions, faster convergence rates, and significant performance improvements. These findings highlight the critical role of deep learning in addressing design issues, enhancing solution quality, trajectory, and performance speed in metaheuristic algorithms. © The Author(s) 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial Computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Optimal hybrid energy-saving cluster head selection for wireless sensor networks: an empirical study

引用

Peer-to-Peer Networking and Applications 2025年第4期18卷 1-17页

作者： Lonkar, Bhupesh Kuthe, Annaji Charde, Pallavi Dehankar, Archana Kolte, Roshan Department of Computer Engineering Cummins College of Engineering for Women Nagpur India Department of Computer Science and Engineering KDK College of Engineering Nagpur India Department of Artificial Intelligence and Data Science Priyadarshini College of Engineering Nagpur India Department of Computer Technology Priyadarshani College of Engineering Nagpur India Department of Information Technology KDK College of Engineering Nagpur India

Wireless sensor networks (WSNs) are gaining attention in modern technology, and are valued for their affordability and versatility. However, energy efficiency is a still major challenge, especially since sensor nodes are often deployed in remote areas where replacing or recharging batteries is difficult. While clustering algorithms and cluster head (CH) selection methods have been recognized as key strategies for extending network lifetime, existing studies often lack a comprehensive evaluation of hybrid CH selection techniques. This paper addresses these gaps by presenting a detailed analysis of clustering algorithms aimed at optimizing energy consumption in WSNs and evaluating various hybrid CH selection procedures. A key contribution of this work is the development of a framework that compares these methods across multiple performance metrics, including Packet Delivery Ratio (PDR), energy consumption, delay, network lifetime, and routing efficiency, using robust simulation tools. The findings demonstrate that hybrid CH selection techniques can significantly enhance energy efficiency while maintaining or improving network performance. By providing a thorough quantitative analysis and actionable insights, this research advances the state of the art in WSN energy management and offers practical implications for designing more sustainable and efficient sensor networks. The proposed methodologies and findings can serve as a foundation for future studies and real-world deployments, addressing critical challenges in resource-constrained environments.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

AI-Based Image Classification for Indian Temple Iconography: A CNN-Based Approach

AI-Based Image Classification for Indian Temple Iconography:...

引用

Artificial Intelligence and data engineering (AIDE), International Conference on

作者： Vanishree Kavi Mahesh Lubna Ansari Aprna Tripathi Department of Computer Science and Engineering Mangalayatan University Department of Data Science and Engineering Manipal University Jaipur

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

India is a country that encompasses a vast and diverse cultural and historical legacy, including numerous architecturally significant sculptures in temples. Analyzing and identifying entities in temple sculptures is a highly challenging and complex task. Digital archives with images, videos, books, interviews, and other resources can significantly accelerate iconographic research by building on past studies. This study explores image classification techniques applied to archives to enhance iconographic study. The findings contribute to the broader discourse on Indian art and culture, providing valuable insights into the intricate iconographic representations found in temple architecture.

关键词： Image recognition Art Convolution data engineering data models Cultural differences Artificial intelligence Interviews Image classification Videos

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Driven Precise Automobile Insurance Claim Predictions 15th

Machine Learning Driven Precise Automobile Insurance Claim P...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Logeswaran, K. Savitha, S. Sree Harshan, A.S. Suganraj, S. Dinesh Kumar, M. Prasanna Kumar, K.R. Gunasekar, M. Rajdevi, R. Department of Artificial Intelligence and Data Science Kongu Engineering College Perundurai India Department of Computer Science and Engineering K.S.R College of Engineering Tiruchengode India Department of Information Technology Kongu Engineering College Perundurai India

ISBN: (纸本)9783031810855

New techniques are required to effectively manage vehicle insurance claims due to the rising trend in claim severity and volume. One approach to resolving this issue is machine learning (ML).Car insurance firms have started implementing Machine Learning to boost the efficient interpretation of client data, greater knowledge of client demands to enhance customer service. With the help of Machine Learning algorithm, one can predict the car insurance claim. This is done in an effort to better serve their customers. This study examines how auto insurance firms use machine learning within their organizations and investigates how ML models may be used with large-scale insurance data. To forecast the recurrence of a claim, a variety of ML techniques is used, including Naive Bayes, KNN, Decision Tree, Random Forest, logistic regression, and XGBoost. The performances of these models are also assessed and contrasted. The outcomes demonstrated that Random Forest had superior accuracy than other approaches. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Automobile Insurance Decision Tree Insurance Claim Logistic Regression Random Forest XGBoost

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：