检索结果-内蒙古大学图书馆

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 139-149页

作者： Wen, Jinbo Kang, Jiawen Niyato, Dusit Zhang, Yang Mao, Shiwen Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China Guangdong University of Technology School of Automation Guangzhou510006 China Nanyang Technological University College of Computing and Data Science Singapore639798 Singapore Auburn University Department of Electrical and Computer Engineering AuburnAL36849 United States

Industrial Cyber-Physical Systems (ICPSs) are an integral component of modern manufacturing and industries. By digitizing data throughout product life cycles, Digital Twins (DTs) in ICPSs enable a shift from current industrial infrastructures to intelligent and adaptive infrastructures. Thanks to data process capability, Generative Artificial Intelligence (GenAI) can drive the construction and update of DTs to improve predictive accuracy and prepare for diverse smart manufacturing. However, mechanisms that leverage Industrial Internet of Things (IIoT) devices to share sensing data for DT construction are susceptible to adverse selection problems. In this paper, we first develop a GenAI-driven DT architecture in ICPSs. To address the adverse selection problem caused by information asymmetry, we propose a contract theory model and develop a sustainable diffusion-based soft actor-critic algorithm to identify the optimal feasible contract. Specifically, we leverage dynamic structured pruning techniques to reduce parameter numbers of actor networks, allowing sustainability and efficient implementation of the proposed algorithm. Numerical results demonstrate the effectiveness of the proposed scheme and the algorithm, enabling efficient DT construction and updates to monitor and manage ICPSs. © 2023 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

FedDGA: Federated Multitask Learning Based on Dynamic Guided Attention

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 268-280页

作者： Sun, Haoyun Zhao, Hongwei Xu, Liang Zhang, Weishan Guan, Hongqing Yang, Su China University of Petroleum Qingdao266580 China Shandong Data Open Innovative Application Laboratory Qingdao266580 China WINDAKA Technology Company Ltd. Qingdao266580 China Beijing University of Science and Technology Beijing100083 China Swansea University Department of Computer Science Faculty of Science and Engineering SwanseaSA2 8PP United Kingdom

The proliferation of privacy-sensitive data has spurred the development of federated learning (FL), which is an important technology for state-of-the-art machine learning and responsible AI. However, most existing FL methods are constrained in their applicability and generalizability due to their narrow focus on specific tasks. This article presents a novel federated multitask learning (FMTL) framework that is capable of acquiring knowledge across multiple tasks. To address the challenges posed by non-IID data and task imbalance in FMTL, this study proposes a federated fusion strategy based on dynamic guided attention (FedDGA), which adaptively fine-tunes local models for multiple tasks with personalized attention. In addition, this article designed dynamic batch weight (DBW) to balance the task losses and improve the convergence speed. Extensive experiments were conducted on various datasets, tasks, and settings, and the proposed method was compared with state-of-the-art methods such as FedAvg, FedProx, and SCAFFOLD. The results show that our method achieves significant performance gains, with up to 11.1% increase in accuracy over the baselines. © 2020 IEEE.

关键词： Scaffolds

来源：评论

学校读者我要写书评

暂无评论

Explainable AI in Blockchain System for Decentralized Governance

Explainable AI in Blockchain System for Decentralized Govern...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Chahar, Suman Kaur, Kawaljit Kaswan, Kuldeep Singh Dhatterwal, Jagjit Singh University Institute of Computing Chandigarh University Mohali India Galgotias University Department of Computer Science and Engineering Greater Noida India Koneru Lakshmaiah Education Foundation Department of Artificial Intelligence and Data Science Andhra Pradesh India

ISBN: (纸本)9798331508685

Decentralized governance is going through radical changes due to the innovative use of blockchain which allows decisions to be made in a transparent, secure and more im- portantly, immutable way, without the authority of a single individual or party. Thus, the introduction of artificial intelligence (AI) in blockchain governing systems complicates such thing as transparency and trust, especially in the case of deep AI systems. But more on this later - this is where Explainable AI or XAI comes into the picture. XAI methods enable understanding of the reasons behind the choices made by AI models and solves the "black box"problem that is predominant in machine learn- ing. When applied to decentralised governance, XAI provides clarifications of AI's decision making in such areas as voting, resource distribution and the enactment of smart contracts. This way, the stakeholders are confident that the decision-making is fair and impartial and this is made possible by the use of XAI. This paper aims to find out more about the applicability of XAI concept in blockchain -based governance systems in terms of bias and fairness in automated decisions and explanation of the decisions made. The reasons why interpretability plays the crucial role in decentralized systems are explained with the help of the comparison between the classical artificial intelligence and the Xin Intelligent. The study also looks at various use cases such as, Decentralized Autonomous Organizations (DAOs), and voting systems implemented on blockchain platforms and how XAI can enhance the performance of the governance systems. As this study shows, XAI is vital in building trust, improving responsibility, and guaranteeing balanced majorities in decentralized blockchain governance structures. © 2025 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Unveiling Hidden Water Resources: Deep Learning and Remote Sensing for Subsurface Hydrology for Environmental Health

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 352-364页

作者： Babu, Jampani Satish G, Dinesh Suganya, R. Radhakrishnan, P. Sutar, Anand S, Alex David Rao, L. Malleswara Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur AP Vaddeswaram India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur (KTR) Chennai India Department of Computer Science and Engineering (Data Science) New Horizon College of Engineering Karnataka Bengaluru India Department of ECE Tagore Engineering College Chennai India Department of Electronics and Telecommunication Bharati Vidyapeeth College of Engineering Navi Mumbai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & d Institute of Science and Technology Chennai India Department of Physics Sri Y N College (A) West Godavari District Andhra Pradesh Narsapur India

Water scarcity in arid regions necessitates innovative solutions to uncover and manage subsurface water resources for environmental health. This study explores the potential of GeoHydroNet, a specialized deep learning framework, in identifying hidden water resources within arid regions. Utilizing remote sensing data such as multispectral and hyperspectral imagery, geological maps, and soil moisture datasets, GeoHydroNet combines graph neural Networks (GNNs), AutoEncoders, and generative adversarial networks (GANs) to address challenges in subsurface hydrology. The model achieved an accuracy of 93.5%, surpassing traditional models like CNNs (85.4%), LSTMs (88.1%), and RNNs (82.6%). GeoHydroNet demonstrates significant precision (0.88), recall (0.87), and sensitivity to data imbalance (0.91). Its physics-informed learning approach incorporates hydrological principles, ensuring realistic predictions. By analyzing subsurface water patterns, recharge zones, and geological influences, the model not only enhances prediction accuracy but also aids in sustainable groundwater management. GeoHydroNet’s performance in identifying groundwater levels, with minimal errors ranging from 0.62 to 3.07%, indicates its robustness in tackling water scarcity challenges in data-constrained environments. These findings highlight its transformative role in hydrological modeling and sustainable water resource management in arid regions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Aquifers Arid regions Deep learning Generative adversarial networks GeoHydroNet Physics-informed learning Remote sensing Subsurface hydrology Sustainable water management

来源：评论

学校读者我要写书评

暂无评论

Monkeypox Disease Classification from Skin Lesion Images using Deep Convolution Neural Network 3

Monkeypox Disease Classification from Skin Lesion Images usi...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Thangaraj, Rajasekaran Vadivel, Balasubramaniam Kumar, S. Manoj Sadesh, S. Karunakaran, P. Prakash, P. Nandha Engineering College Department of Computer Science and Engineering Erode India Sri Ramakrishna Institute of Technology Department of Computer Science and Engineering Coimbatore India KPR Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Velalar College of Engineering and Technology Department of Artificial Intelligence and Data Science Erode India Nandha Engineering College Department of Artificial Intelligence and Data Science Erode India Velalar College of Engineering and Technology Department of Information Technology Erode India

ISBN: (纸本)9798331523893

Recently monkeypox outbreak has raised concerns due to its increasing number of cases and diverse dermatological symptoms in 2024, which can complicate early diagnosis due to similarities with other viral infections such as measles and chickenpox. To enhance diagnostic accuracy, transfer learning models and artificial intelligence (AI) have been explored as effective tools. Pre-trained models such as VGG16, VGG19, ResNet50V2, and MobileNetV2 have been employed for monkeypox detection, each with distinct trade-offs in terms of computational efficiency and diagnostic precision. MobileNetV2 offers superior efficiency, but this comes at the cost of reduced accuracy. VGG models provide higher accuracy but require much more computational *** these models, DenseNet121 stands out by achieving 99% accuracy while requiring 37% less computational power, making it the model optimized choice for efficient and accurate monkeypox classification. © 2025 IEEE.

关键词： Deep Learning Disease Classification Monkeypox Detection Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation 31

Extending LLMs to New Languages: A Case Study of Llama and P...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Sani, Samin Mahdizadeh Sadeghi, Pouya Vu, Thuy-Trang Yaghoobzadeh, Yadollah Haffari, Gholamreza Department of Electrical and Computer Engineering University of Tehran Iran Tehran Institute for Advanced Studies Khatam University Iran Department of Data Science & AI Monash University Australia

ISBN: (纸本)9798891761964

Large language models (LLMs) have made great progress in classification and text generation tasks. However, they are mainly trained on English data and often struggle with low-resource languages. In this study, we explore adding a new language, i.e., Persian, to Llama (a model with a limited understanding of Persian) using parameter-efficient fine-tuning. We employ a multi-stage approach involving pretraining on monolingual Persian data, aligning representations through bilingual pretraining and instruction datasets, and instruction-tuning with task-specific datasets. We evaluate the model's performance at each stage on generation and classification tasks. Our findings suggest that incorporating the Persian language, through bilingual data alignment, can enhance classification accuracy for Persian tasks, with no adverse impact and sometimes even improvements on English tasks. Additionally, the results highlight the model's initial strength as a critical factor when working with limited training data, with cross-lingual alignment offering minimal benefits for the low-resource language. Knowledge transfer from English to Persian has a marginal effect, primarily benefiting simple classification tasks. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Defending data Inference Attacks Against Machine Learning Models by Mitigating Prediction Distinguishability

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 2687-2704页

作者： Yang, Ziqi Zhu, Yiran Wan, Jie Xiang, ChuXiao Tang, Tong Wang, Yilin Xu, Ruite Wang, Lijin Zhang, Fan Xu, Jiarong Qin, Zhan Zhejiang University State Key Laboratory of Blockchain and Data Security Hangzhou310027 China Institute of Blockchain and Data Security Hangzhou310027 China Zhejiang University College of Computer Science and Technology Hangzhou310027 China Fudan University Department of Information Management and Business Intelligence Shanghai200437 China

Neural networks are vulnerable to data inference attacks, including the membership inference attack, the model inversion attack, and the attribute inference attack. In this paper, we propose PURIFIER to defend against membership inference attacks by quantifying the differences between dataset members and non-members in three dimensions: individual shape, statistical distribution, and prediction label. PURIFIER involves transforming the confidence scores produced by the target classifier, resulting in purified confidence scores that are indistinguishable across the dimensions above. We conduct experiments on widely-used datasets and models. The results show that Purifier offers robust defense against membership inference attacks with superior efficacy compared to prior defense techniques while maintaining minimal utility degradation (e.g., less than 0.7% classification accuracy drop of most datasets). Additionally, our extended experiments explore the effectiveness of PURIFIER in defending against the model inversion attack and the attribute inference attack. © 2004-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating Inductive Reasoning Capabilities of Large Language Models With The One Dimensional Abstract Reasoning Corpus 3rd

Evaluating Inductive Reasoning Capabilities of Large Langua...

引用

3rd International Workshop on Hybrid Models for Coupling Deductive and Inductive Reasoning, HYDRA 2024

作者： Mesnage, Cédric Wang, Xiaoyang Dong, Hang Aishwaryaprajna Institute for Data Science and Artificial Intelligence University of Exeter Exeter United Kingdom Department of Computer Science University of Exeter Exeter United Kingdom

ISBN: (纸本)9783031893650

We present an initial automated test to evaluate LLMs’ capacity to perform inductive reasoning tasks. We use the GPT-3.5 and GPT-4 models to create a system which generates Python code as hypotheses for inductive reasoning to transform sequences of the One Dimensional Abstract Reasoning Corpus (1D-ARC) challenge. We experiment with three prompting techniques, namely standard prompting, Chain of Thought (CoT), and direct feedback. We provide results and an analysis of cost-to-success rate and benefit-cost ratio. Our best result is an overall 25% success rate with our CoT prompting on GPT-4, significantly surpassing the standard prompting approach. We discuss potential avenues to improve our experiments and test other strategies, and combine deductive reasoning with LLM-based inductive reasoning. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Abstract Reasoning Corpus Inductive Reasoning Large Language Models Prompt Engineering

来源：评论

学校读者我要写书评

暂无评论

Traffic flow prediction based on graph convolutional networks with a parallel attention network and stacked gate recurrent units

引用

Multimedia Tools and Applications 2025年第15期84卷 14329-14358页

作者： Xia, Dawen Ao, Yuce Wei, Xiaoduo Li, Yunsong Chen, Yan Hu, Yang Li, Yantao Li, Huaqing College of Data Science and Information Engineering Guizhou Minzu University Guiyang550025 China Department of Automotive Engineering Guizhou Traffic Technician and Transportation College Guiyang550008 China College of Computer Science Chongqing University Chongqing400044 China College of Electronic and Information Engineering Southwest University Chongqing400715 China

Accurate traffic flow prediction is essential to address traffic issues and assist traffic managers make informed decisions in intelligent transportation systems. Extracting potential features from traffic data is challenging due to the complex topology of urban road networks and the time-varying traffic flow. To capture the global spatiotemporal characteristics of traffic flow, we propose a novel model based on graph convolutional networks with a parallel attention network and stacked gated recurrent units (PAGCN-SGRU). First, the parallel attention (PA) network enhances the feature representation of global traffic road nodes and road segments. Then, the graph convolutional networks (GCN) are designed to extract spatial characteristics. Next, the stacked gate recurrent units (SGRU) are employed to capture temporal features. Finally, PAGCN-SGRU discovers global spatiotemporal features for traffic flow prediction. The experimental results demonstrate that the accuracy of PAGCN-SGRU under the SZ-dataset is improved by 9.76%, 72.54%, 5.76%, 16.07%, 2.07%, 1.82%, 3.35%, and 6.59%, respectively, compared to that of HA, ARIMA, SVR, GCN, T-GCN, A3T-GCN, ST-GCN, and DCRNN. In the Los-dataset, the accuracy values increase by 7.11%, 8.94%, 6.66%, 7.77%, 3.43%, 2.45%, 2.28%, and 4.09%, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Interference-Based Reliability and Capacity Analysis for IEEE 802.11 Broadcast Ad-Hoc Networks on the Highway 11

Interference-Based Reliability and Capacity Analysis for IEE...

引用

11th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2025

作者： Li, Zhijuan Wu, Xintong Li, Xiaokun Ma, Xiaomin Department of Computer and Big Data Heilongjiang University Harbin150080 China Postdoctoral Program of Heilongjiang Hengxun Technology Co. Ltd. Harbin150090 China School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China College of Science and Engineering Oral Roberts University TulsaOK74171 United States

ISBN: (纸本)9789897587450

Interference is a critical factor that degrades wireless network performance. In IEEE 802.11 wireless broadcast networks, hidden terminals and concurrent transmissions are the primary sources of interference due to the carrier sense multiple access (CSMA) mechanism. Therefore, analyzing the signal-to-interference-plus-noise ratio (SINR) distribution is essential for evaluating network performance, whose derivation relates to the transmission probabilities of hidden terminals and concurrent transmissions. In this study, we utilize the existing semi-markov process (SMP) model to calculate these transmission probabilities. Subsequently, we employ the Laplace transform to analyze the SINR distribution in IEEE 802.11 broadcast ad-hoc networks on highways. Based on the derived SINR distribution, we further evaluate the reliability and capacity. This approach can be readily extended to two-dimensional (2D) or three-dimensional (3D) scenarios by employing d-dimensional (1 ≤ d ≤ 3, dD) point process. Experimental results demonstrate that the proposed model achieves high accuracy under small to medium interference ranges. Additionally, the analysis remains highly accurate for receivers within 70 meters, even in scenarios with large interference ranges. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Markov processes

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：