检索结果-内蒙古大学图书馆

FedSTDN: A Federated Learning-Enabled Spatial-Temporal Prediction Model for Wireless Traffic Prediction

IEEE Transactions on Mobile Computing 2025年

作者： Li, Zhenyu Fu, Yuchuan Tian, Mengqiu Li, Changle Yu, F. Richard Cheng, Nan Xidian University State Key Laboratory of Integrated Services Networks Shaanxi 710071 China Xidian University Research Institute of Smart Transportation Shaanxi Xi'an710071 China Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

Wireless Traffic Prediction (WTP) plays a significant role in achieving intelligent resource management for communication systems. However, WTP still faces challenges such as inaccurate prediction resulting from the complex spatial-temporal characteristics due to user mobility, high communication overhead caused by the complexity of the prediction model, and user privacy issues stemming from Centralized Learning (CL). To address the aforementioned issues, this paper proposes a WTP framework under the Federated Learning (FL) strategy called Federated Spatial-Temporal Dual-attention based Network (FedSTDN). Aiming at improving communication efficiency and simultaneously representing various wireless traffic patterns, a data augmentation-based clustering algorithm is adopted, which groups cells into different regions using a small augmented dataset, facilitating subsequent processing. To improve prediction performance, a local prediction model based on Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is proposed to capture the short- and long-term dependencies of traffic. Additionally, a novel Kolmogorov-Arnold Network (KAN) layer is introduced to replace the traditional Multi-Layer Perceptron (MLP) layer, further enhancing prediction performance. Simulations on two different real-world datasets verify the effectiveness and efficiency of FedSTDN. Compared to the well-performing baseline, the proposed FedSTDN achieves up to 32.83% and 24.30% improvements in Mean Square Error (MSE) and Mean Absolute Error (MAE) on the Milan dataset, respectively. For the Trentino dataset, FedSTDN achieves up to 17.25% and 5.86% improvements in MSE and MAE, respectively. © 2002-2012 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

SOK: EXPLORING HALLUCINATIONS AND SECURITY RISKS IN AI-ASSISTED SOFTWARE DEVELOPMENT WITH INSIGHTS FOR LLM DEPLOYMENT

arXiv

引用

arXiv 2025年

作者： Haque, Ariful Siddique, Sunzida Rahman, Md. Mahfuzur Hasan, Ahmed Rafi Das, Laxmi Rani Kamal, Marufa Masura, Tasnim Gupta, Kishor Datta Department of Cyber Physical Systems Clark Atlanta University AtlantaGA United States Department of Computer Science and Engineering Dhaka International University Dhaka Bangladesh Silicon Orchard Research and Analytics Lab Dhaka Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh

The integration of Large Language Models (LLMs) such as GitHub Copilot, ChatGPT, Cursor AI, and Codeium AI into software development has revolutionized the coding landscape, offering significant productivity gains, automation, and enhanced debugging capabilities. These tools have proven invaluable for generating code snippets, refactoring existing code, and providing real-time support to developers. However, their widespread adoption also presents notable challenges, particularly in terms of security vulnerabilities, code quality, and ethical concerns. This paper provides a comprehensive analysis of the benefits and risks associated with AI-powered coding tools, drawing on user feedback, security analyses, and practical use cases. We explore the potential for these tools to replicate insecure coding practices, introduce biases, and generate incorrect or non-sensical code (hallucinations). In addition, we discuss the risks of data leaks, intellectual property violations and the need for robust security measures to mitigate these threats. By comparing the features and performance of these tools, we aim to guide developers in making informed decisions about their use, ensuring that the benefits of AI-assisted coding are maximized while minimizing associated risks. © 2025, CC BY-SA.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Dynamic spectrum sharing in heterogeneous wireless networks using deep reinforcement learning

Internet of Things (The Netherlands)

引用

Internet of Things (The Netherlands) 2025年 32卷

作者： Adebayo, Sulaimon Oyeniyi Barnawi, Abdulaziz Sheltami, Tarek Felemban, Muhammad Computer Engineering Department King Fahd University of Petroleum and Minerals Dhahran 31261 Saudi Arabia Computer Engineering Department Interdisciplinary Research Center for Intelligent Secure Systems King Fahd University of Petroleum and Minerals Dhahran 31261 Saudi Arabia Computer Engineering Department Interdisciplinary Research Center of Smart Mobility and Logistics King Fahd University of Petroleum and Minerals Dhahran 31261 Saudi Arabia

The rapid expansion of wireless networks demands efficient spectrum allocation. Dynamic Spectrum Sharing (DSS) is a technology that allows multiple wireless networks to share the same frequency spectrum dynamically. It is an effective technique for optimizing spectrum use, particularly in heterogeneous environments where multiple wireless technologies with diverse spectrum access requirements coexist, often leading to interference challenges and increased spectrum competition. This research proposes an enhanced DSS technique based on Deep Reinforcement Learning (DRL). The proposed method enables an effective sharing of the available spectrum between two access technologies, namely Long Term Evolution (LTE) and Narrowband IoT (NB-IoT). The study optimizes throughput through DRL methods, including Deep Q-Networks (DQN), conducting experiments in three phases: LTE-DRL coexistence, NB-IoT-DRL coexistence, and LTE-NB-IoT coexistence. Results show that deep learning enhances the LTE-DRL system's convergence rate and throughput, achieving over 85% throughput with convergence times as low as 24 milliseconds (ms). The study highlights the trade-offs between parameters such as probabilities (arrival, successful transmission, and retransmission), packet expiry duration, learning rate, discount factor, fairness index, and the neural network architecture as well as the parameters’ impact on the overall system throughput. NB-IoT coexistence with DRL shows similar results with a slight decrement in throughput and negligibly longer convergence rate, while the coexistence of LTE and NB-IoT results in throughput of around 70% for each of the LTE and NB-IoT systems due to increased spectrum competition and increased complexity of the operating environment. This work offers insights into optimizing spectrum sharing using DRL and underscores the balance between various parameters for efficient spectrum management. © 2025 The Authors

关键词： Deep Reinforcement Learning (DRL) Dynamic Spectrum Sharing (DSS) Heterogenous Wireless Networks LTE NB-IoT

来源：评论

学校读者我要写书评

暂无评论

An online clustering-based optimal distributed damping controller design

引用

Electric Power systems research 2025年 247卷

作者： Atarodi, Azin Golpîra, Hêmin Bevrani, Hassan Power Systems Modeling & Simulation Lab. Department of Electrical Engineering University of Kurdistan Sanandaj15175-66177 Iran Smart/Micro Grids Research Center Department of Electrical Engineering University of Kurdistan Sanandaj15175-66177 Iran

Inter-area low-frequency oscillations with poor damping have long presented challenges in interconnected power systems, leading to the development of various damping control strategies. This paper introduces a novel method for designing Optimally Distributed Damping Control (ODDC) to enhance the damping ratios of critical inter-area modes while minimizing communication links, thereby increasing system stability. The non-convex nature of structural constraints adds complexity to identifying the optimal communication topology among control units in distributed frameworks. To address this, a computationally efficient Semi-Definite Programming (SDP) relaxation technique is applied to solve the non-convex ODDC problem. Additionally, a combined clustering framework is proposed to dynamically update controller coefficients based on mode identification using wide-area measurement data, ensuring effective damping of inter-area oscillations. The IEEE New England 39-bus system, simulated in MATlab, serves as the validation platform, demonstrating the ODDC method's effectiveness. Simulation results indicate that an optimal distributed configuration with a single communication link substantially enhances small-signal stability. Moreover, the adaptive updating module successfully provides new coefficients to restore adequate damping ratios when pre-designed controllers lose effectiveness under varying operating conditions. © 2025 Elsevier B.V.

关键词： Distributed parameter control systems

来源：评论

学校读者我要写书评

暂无评论

A Data-and-Model-Driven Acceleration Approach for Large-Scale Network-Constrained Unit Commitment Problem With Uncertainty

引用

IEEE Transactions on Sustainable Energy 2025年

作者： Zhou, Yuzhou Han, Zhihan Zhai, Qiaozhu Wu, Lei Cao, Xiaoyu Guan, Xiaohong Xi'an Jiaotong University Systems Engineering Institute MOEKLINNS Lab Xi'an710049 China Sichuan Digital Economy Industry Development Research Institute Sichuan Chengdu610037 China Xi'an Jiaotong University Systems Engineering Institute Xi'an710049 China Stevens Institute of Technology Department of Electrical and Computer Engineering Hoboken07030 United States Tsinghua University Department of Automation Center for Intelligent and Networked Systems Beijing100084 China

Numerous binary variables and constraints greatly affect the computation of large-scale network-constrained unit commitment (NCUC) problems. With the integration of massive renewable energy and distributed loads, binary variables and network power flows face more frequent changes to cope with uncertainties. How to ensure the calculation efficiency and accuracy of NCUC problems against uncertainties and frequent changes becomes a common challenge for academia and industry. Inspired by data-driven and model-driven technologies, this paper presents a hybrid reduction approach for variables and constraints to accelerate the solving of large-scale NCUC problems, which achieves "one plus one much greater than two" effect. Specifically, an offline database of nodal net load clusters and the corresponding NCUC solutions is established, which also captures the impacts of changes in renewables, loads, topology, etc. on UC solutions. With this database, a data-and-modeldriven reduction method is proposed to fix binary variables and reduce constraints, while considering the changes of prices and net loads in online NCUC instances. Moreover, the reduction method was further developed to accelerate various NCUC problems, including scenario-based methods, robust optimization methods, etc. Thus, the computation burden of online large-scale NCUC problems is greatly mitigated while ensuring good solution quality. Numerical tests implemented on IEEE 24-bus system, 118-bus system, and Polish 2383-bus system illustrate the efficiency of the proposed approach. © 2025 IEEE. All rights reserved.

关键词： Mendelevium

来源：评论

学校读者我要写书评

暂无评论

Language Fusion for Parameter-Efficient Cross-lingual Transfer

arXiv

引用

arXiv 2025年

作者： Borchert, Philipp Vulić, Ivan Moens, Marie-Francine De Weerdt, Jochen Research Centre for Information Systems Engineering KU Leuven Belgium IESEG School of Management France Language Technology Lab University of Cambridge United Kingdom Department of Computer Science KU Leuven Belgium

Limited availability of multilingual text corpora for training language models often leads to poor performance on downstream tasks due to undertrained representation spaces for languages other than English. This ‘under-representation’ has motivated recent cross-lingual transfer methods to leverage the English representation space by e.g. mixing English and ‘non-English’ tokens at the input level or extending model parameters to accommodate new languages. However, these approaches often come at the cost of increased computational complexity. We propose Fusion for Language Representations (FLARE) in adapters, a novel method that enhances representation quality and downstream performance for languages other than English while maintaining parameter efficiency. FLARE integrates source and target language representations within low-rank (LoRA) adapters using lightweight linear transformations, maintaining parameter efficiency while improving transfer performance. A series of experiments across representative crosslingual natural language understanding tasks, including natural language inference, question-answering and sentiment analysis, demonstrate FLARE’s effectiveness. FLARE achieves performance improvements of 4.9% for Llama 3.1 and 2.2% for Gemma 2 compared to standard LoRA fine-tuning on question-answering tasks, as measured by the exact match metric.1 © 2025, CC BY.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on smart Glasses

arXiv

引用

arXiv 2025年

作者： Cai, Runze Janaka, Nuwan Kim, Hyeongcheol Chen, Yang Zhao, Shengdong Huang, Yun Hsu, David Synteraction Lab School of Computing National University of Singapore Singapore Synteraction Lab Smart Systems Institute National University of Singapore Singapore Synteraction Lab National University of Singapore Singapore College of Design and Engineering National University of Singapore Singapore Synteraction Lab School of Creative Media Department of Computer Science City University of Hong Kong Hong Kong China School of Information Sciences University of Illinois at Urbana-Champaign Champaign IL United States School of Computing Smart Systems Institute National University of Singapore Singapore

Unlike the free exploration of childhood, the demands of daily life reduce our motivation to explore our surroundings, leading to missed opportunities for informal learning. Traditional tools for knowledge acquisition are reactive, relying on user initiative and limiting their ability to uncover hidden interests. Through formative studies, we introduce AiGet, a proactive AI assistant integrated with AR smart glasses, designed to seamlessly embed informal learning into low-demand daily activities (e.g., casual walking and shopping). AiGet analyzes real-time user gaze patterns, environmental context, and user profiles, leveraging large language models to deliver personalized, context-aware knowledge with low disruption to primary tasks. In-lab evaluations and real-world testing, including continued use over multiple days, demonstrate AiGet’s effectiveness in uncovering overlooked yet surprising interests, enhancing primary task enjoyment, reviving curiosity, and deepening connections with the environment. We further propose design guidelines for AI-assisted informal learning, focused on transforming everyday moments into enriching learning experiences. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Pseudo-labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic- like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. Firstly, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic- like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. The source code will be made publicly available. ©1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Elastic smart Contracts in Blockchains

引用

IEEE/CAA Journal of Automatica Sinica 2021年第12期8卷 1901-1912页

作者： Schahram Dustdar Pablo Fernández JoséMaría García Antonio Ruiz-Cortés Distributed Systems Group Vienna University of TechnologyWien 1040Austria Smart Computer Systems Research and Engineering Lab Research Institute of Computer EngineeringUniversity of SevillaSevilla 41012Spain

In this paper,we deal with questions related to blockchains in complex Internet of Things(IoT)-based *** ecosystems are typically composed of IoT devices,edge devices,cloud computing software services,as well as people,who are decision makers in scenarios such as smart *** decisions related to analytics can be based on data coming from IoT sensors,software services,and ***,they are typically based on different levels of abstraction and *** poses a number of challenges when multiple blockchains are used together with smart *** work proposes to apply our concept of elasticity to smart contracts and thereby enabling analytics in and between multiple blockchains in the context of *** propose a reference architecture for Elastic smart Contracts and evaluate the approach in a smart city scenario,discussing the benefits in terms of performance and self-adaptability of our solution.

关键词： Blockchain elasticity Internet of Things(IoT) smart cities smart contracts virtual chains

来源：评论

学校读者我要写书评

暂无评论

Learning 6-DoF Fine-grained Grasp Detection Based on Part Affordance Grounding

引用

IEEE Transactions on Automation Science and engineering 2025年 22卷 15200-15214页

作者： Song, Yaoxian Sun, Penglei Jin, Piaopiao Ren, Yi Zheng, Yu Li, Zhixu Chu, Xiaowen Zhang, Yue Li, Tiefeng Gu, Jason Zhejiang University Center for X-Mechanics School of Aeronautics and Astronautics Zhejiang Hangzhou China Information Hub Data Science and Analytics Thrust Guangdong China Huawei Technologies Advanced Manufacturing Lab Guangdong Shenzhen China UBTECH Robotics Inc Research Institute Guangdong Shenzhen China Renmin University of China School of Information School of Smart Governance Beijing China Westlake University Institute of Advanced Technology Westlake Institute for Advanced Study School of Engineering Zhejiang Hangzhou China Dalhousie University Department of Electrical and Computer Engineering HalifaxB3H 4R2 Canada

Robotic grasping is a fundamental ability for a robot to interact with the environment. Current methods focus on how to obtain a stable and reliable grasping pose in object level, while little work has been studied on part (shape)-wise grasping which is related to fine-grained grasping and robotic affordance. Parts can be seen as atomic elements to compose an object, which contains rich semantic knowledge and a strong correlation with affordance. However, lacking a large part-wise 3D robotic dataset limits the development of part representation learning and downstream applications. In this paper, we propose a new large Language-guided SHape grAsPing datasEt (named LangSHAPE) to promote 3D part-level affordance and grasping ability learning. From the perspective of robotic cognition, we design a two-stage fine-grained robotic grasping framework (named LangPartGPD), including a novel 3D part language grounding model and a partaware grasp pose detection model, in which explicit language input from human or large language models (LLMs) could guide a robot to generate part-level 6-DoF grasping pose with textual explanation. Our method combines the advantages of humanrobot collaboration and LLMs’ planning ability using explicit language as a symbolic intermediate. To evaluate the effectiveness of our proposed method, we perform 3D part grounding and fine-grained grasp detection experiments on both simulation and physical robot settings, following language instructions across different degrees of textual complexity. Results show our method achieves competitive performance in 3D geometry fine-grained grounding, object affordance inference, and 3D part-aware grasping tasks. © 2004-2012 IEEE.

关键词： Visual languages

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：