检索结果-内蒙古大学图书馆

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

作者： Neelamegam, G. Venkatesan, Rajaram Ramya, S.R. Ramya, R.S. Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak VSB College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Builders Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Tirupur India Dr NGP Institute of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Tamil Nadu Coimbatore India SRM Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Networking and Communications Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Chennai India

ISBN: (纸本)9798331523893

The ever-growing complexity of IoT networks ignited by their wide scale adoption in applications such as smart cities, the industrial automation, and health care, compelled to develop sophisticated yet resource efficient and scalable network management solution. Centralized systems are traditional in architecture, which leads to higher latency and bottlenecks, while decentralized systems can distribute workloads however the lack of adaptability to real time, along with the difficulty of extracting maximum resource usage, are limitations. In recent years, reinforcement learning (RL) based approaches have taken shape as a promising alternative to facilitate the automated learning and optimisation of task management. However, there are two challenges for existing RL based methods: slow convergence, inefficient priority assignment of tasks, and poor coordination amongst agents in the case of dynamic, large scale IoT environment. To solve these challenges, in this research we propose a distributed reinforcement learning based multi agent framework for managing IoT network. The framework also integrates a task prioritization mechanism to dynamically choose an optimal task allocation solution. Further validation was performed in a simulated IoT environment where real world inspired datasets were used. The proposed framework demonstrated 30% more task throughput than centralized, 25% less latency than decentralized, and 40% more energy efficiency than current RL based systems. The system was further validated using advanced visualizations such as anomaly detection maps and resource allocation efficiency graphs, demonstrating its capacity to manage dynamic load of tasks and resource allocation. The proposed framework addresses the critical limitations of current methods, through scalable, adaptive, and energy efficient framework for managing IoT network, and accordingly helps advancing the intelligent and autonomous IoT systems. © 2025 IEEE.

关键词： Distributed Reinforcement Learning IoT Network Management Multi-Agent Systems Resource Optimization

来源：评论

学校读者我要写书评

暂无评论

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration

引用

IEEE Symposium on High-Performance computer Architecture

作者： Yuzong Chen Ahmed F. AbouElhamayed Xilai Dai Yang Wang Marta Andronic George A. Constantinides Mohamed S. Abdelfattah Computer Systems Lab Cornell University Systems and Networking Research Group Microsoft Research Department of Electrical and Electronic Engineering Imperial College London

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Large language models (LLMs) have demonstrated remarkable performance across various machine learning tasks. Yet the substantial memory footprint of LLMs significantly hinders their deployment. In this paper, we improve the accessibility of LLMs through BitMoD 1 , an algorithm-hardware co-design solution that enables efficient LLM acceleration at low weight precision. On the algorithm side, BitMoD introduces fine-grained data type adaptation that uses a different numerical data type to quantize a group of (e.g., 128) weights. Through the careful design of these new data types, BitMoD is able to quantize LLM weights to very low precision (e.g., 4 bits and 3 bits) while maintaining high accuracy. On the hardware side, BitMoD employs a bitserial processing element to easily support multiple numerical precisions and data types; our hardware design includes two key innovations: First, it employs a unified representation to process different weight data types, thus reducing the hardware cost. Second, it adopts a bit-serial dequantization unit to rescale the per-group partial sum with minimal hardware overhead. Our evaluation on six representative LLMs demonstrates that BitMoD significantly outperforms state-of-the-art LLM quantization and acceleration methods. For discriminative tasks, BitMoD can quantize LLM weights to 4 -bit with < 0.5% accuracy loss on average. For generative tasks, BitMoD is able to quantize LLM weights to 3-bit while achieving better perplexity than prior LLM quantization scheme. Combining the superior model performance with an efficient accelerator design, BitMoD achieves an average of $1.69 \times$ and $1.48 \times$ speedups compared to prior LLM accelerators ANT and OliVe, respectively. 1 Code is available at: https://***/yc2367/BitMoD-HPCA-25

关键词： Technological innovation Quantization (signal) Accuracy Machine learning algorithms Costs Large language models Machine learning computer architecture Hardware Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Integrating Instruction-based Learning with Bidirectional LSTM for Autonomous Vehicle Pedestrian Detection

Integrating Instruction-based Learning with Bidirectional LS...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Shoba, B. Raghunathan, T. Peter, S.Sam Karthick, K. Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak Psn College of Engineering and Technology Department of Electronics and Communication Engineering Tirunelveli India Dr.NG.p.Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Sri Krishna College of Technology Department of Computer Science and Engineering Coimbatore India Sona College of Technology Department of Information Technology Salem India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Networking and Communications Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

Pedestrian detection is a crucial aspect of autonomous vehicle (A V) safety, as it enables accurate identification and tracking of individuals in an A V environment. Effective pedestrian detection supports essential A V functions like braking, steering, and speed control to prevent accidents in urban settings. Traditional computer vision methods, such as Support Vector Machines and Random Forests, rely on pre-designed features like the Histogram of Oriented Gradients. While the existing techniques offer some performance, it face significant challenges in dynamic environments, especially under varying lighting conditions, occlusions, and diverse pedestrian poses. Traditional models also require extensive manual feature engineering and tuning, which limits scalability and adaptability. Recent advances in deep learning, particularly with Convolutional Neural Networks (CNNs), have allowed for automatic feature learning, yielding practical improvements over classical methods. However, CNNs can struggle in low light and when facing adversarial attacks, as they mainly capture spatial features. To address these limitations, this research proposes a new methodology combining CNNs for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks to capture temporal dependencies. This hybrid approach enhances detection capabilities by learning both static and dynamic patterns. Our proposed CNN-BiLSTM model achieves a 92 % detection accuracy and an F1 score of 88.5% across diverse conditions, outperforming existing models by up to 15%. By integrating temporal features, the model reduces missed detections and false positives by up to 20%, providing a more reliable and adaptable solution for pedestrian detection in autonomous vehicles. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization for Cooperative Service-Caching, Computation-Offloading, and Resource-Allocations Over EH/MEC 6G Ultra-Dense Mobile Networks

引用

IEEE Transactions on Wireless Communications 2025年

作者： Chen, Zhian Wang, Fei Zhang, Xi Southwest University College of Electronic and Information Engineering Chongqing400715 China Texas A&M University Networking and Information Systems Laboratory Department of Electrical and Computer Engineering College StationTX77843 United States

Service-caching, computation-offloading, and mobile edge-computing (MEC) have been widely recognized as three key 6G wireless technologies which can efficiently support implementing the ultra-dense networks (UDNs) with massive small-cell base stations (SBSs). But, these impose the new challenges for the UDNs to solely rely on grid power for energy supplying and to jointly optimize service-caching, computation-offloading, and resource-allocations. To overcome the above described difficulties, integrating energy-harvesting (EH) techniques with MEC-enabled 6G UDNs, we propose to develop the joint optimization schemes for cooperative service-caching, computation-offloading, and resource-allocations. In our considered UDNs, there exist a large number of EH-based stationary users (SUs) or mobile users (MUs), and a mixture of on-grid SBSs powered by electric grid and off-grid SBSs power-supplied by solar, radio frequency (RF) energy, etc. Specifically, first we formulate an energy minimization problem under a non-linear RF-energy EH model to minimize the sum of weighted energy consumption of users and off-grid SBSs. Second, for scenarios with SUs, we develop a two-timescale based joint cooperative service-caching, computation-offloading, and resource-allocations scheme using the hierarchical multi-agent deep reinforcement learning. We derive cooperative service-caching in each time frame, and then derive computation-offloading and resource-allocations in each time slot. Third, we extend our work to scenarios with MUs, where MUs can move with certain trajectories at low speeds. Finally, we validate and evaluate the performances of our proposed schemes through the extensive simulations. © 2002-2012 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Achievable Rate Analysis and Optimization of Double-RIS Assisted Spatially Correlated MIMO with Statistical CSI

引用

China Communications 2025年第1期22卷 139-157页

作者： Xu Kaizhe Guo Jiajia Zhang Jun Jin Shi Ma Shaodan Department of Communications and Networking Xi’an Jiaotong-Liverpool UniversitySuzhou 215123China State Key Laboratory of Internet of Things for Smart City University of MacaoMacao SARChina Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and TelecommunicationsNanjing 210003China National Mobile Communications Research Laboratory Southeast UniversityNanjing 210096China State Key Laboratory of Internet of Things for Smart City and the Department of Electrical and Computer Engineering University of MacaoMacao SARChina

Reconfigurable intelligent surface(RIS)is a novel meta-material which can form a smart radio environment by dynamically altering reflection directions of the impinging electromagnetic *** the prior literature,the inter-RIS links which also contribute to the performance of the whole system are usually neglected when multiple RISs are *** this paper we investigate a general double-RIS assisted multiple-input multiple-output(MIMO)wireless communication system under spatially correlated non line-of-sight propagation channels,where the cooperation of the double RISs is also *** design objective is to maximize the achievable ergodic rate based on full statistical channel state information(CSI).Specifically,we firstly present a closedform asymptotic expression for the achievable ergodic rate by utilizing replica method from statistical *** a full statistical CSI-enabled optimal design is proposed which avoids high pilot training overhead compared to instantaneous CSI-enabled *** further reduce the signal processing overhead and lower the complexity for practical realization,a common-phase scheme is proposed to design the double *** results show that the derived asymptotic ergodic rate is quite accurate even for small-sized antenna *** the proposed optimization algorithm can achieve substantial gain at the expense of a low overhead and ***,the cooperative double-RIS assisted MIMO framework is proven to achieve superior ergodic rate performance and high communication reliability under harsh propagation environment.

关键词： common reflection pattern double RISs large system analysis MIMO replica method

来源：评论

学校读者我要写书评

暂无评论

Intelligent Reflecting Surface-Assisted Millimeter Wave Communications: Cross Attention-aided Variational Autoencoder-based Precoding Design

引用

IEEE Transactions on Cognitive Communications and networking 2025年

作者： Wu, Meng-Hsun Chen, Hong-Yunn Yang, Ta-Wei Hsu, Chih-Chuan Huang, Chih-Wei Chou, Cheng-Fu National Taiwan University Department of Computer Science and Information Engineering Taipei Taiwan National Pingtung University Department of Computer Science and Information Engineering Pingtung Taiwan National Taiwan University Graduate Institute of Networking and Multimedia Taipei Taiwan National Taiwan University Department of Forestry and Resource Conservation Taipei Taiwan National Central University Department of Communication Engineering Taoyuan Taiwan

Sixth-generation technology, which surpasses 5G with faster speeds, lower latency, and increased capacity, highlights the pivotal intelligent reflecting surface (IRS) and optimizes wireless communication by precisely handling incoming radio waves, resulting in enhanced network coverage, capacity, and energy efficiency. In real-world scenarios, however, hybrid precoding in the IRS is affected by noise and interference. To address this, we propose DVAE-CATT-Precoding (variational denoising autoencoder model with cross attention precoding), in which cross attention enhances channel precoding by reevaluating the significance of the time domain. A variational autoencoder (VAE) is trained with reconstruction and regularization losses for parameter optimization, and its learned latent space facilitates feature capture for intra-channel precoding in both the frequency and spatial domains. We use an autoencoder to reconstruct the latent space, improving our analog precoding module's ability to capture global domain features. Additionally, a CNN models frequency and spatial domain intricacies for efficient channel precoding, reducing interference in the proposed digital precoding module. Numerical results show remarkable improvements in MSE, achievable rate, generalizability, and robustness compared to previous works. © 2015 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

A Dual-Modal Fusion Framework for Detection of Mild Cognitive Impairment Based on Autobiographical Memory

引用

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

作者： Chang, Ho-Ling Wai, Thiri Liao, Yu-Shan Lin, Sheng-Ya Chang, Yu-Ling Fu, Li-Chen National Taiwan University G.I. of Networking and Multimedia Taipei Taiwan National Taiwan University Department of Computer Science and Information Engineering Taipei Taiwan National Taiwan University Department of Psychology Taipei Taiwan

This paper introduces a dual-modal early cognitive impairment detection system based on autobiographical memory (AM) tests, and our approach is to automatically extract pre-defined acoustic features and self-designed embeddings to enhance linguistic representation of the spontaneous speech data. By integrating dual-modal data, we effectively enrich the features that aid in model learning, especially addressing the subtle symptoms exhibited by individuals with mild cognitive impairment (MCI), an intermediate stage between healthy individuals and those with Alzheimer's disease (AD). To account for spontaneous speech's unstructured and implicit nature, two additional embeddings, namely, speaker embedding and conversation embedding, are introduced to augment the information available for model learning, thus enriching the feature set for improving the model accuracy. The proposed dual-modal approach is tested on a self-collected Chinese spontaneous speech dataset due to the limited unstructured speech open-access dataset for MCI detection. The system's effectiveness is evaluated through a series of experiments, including ablation studies, to determine the impact of each module on overall performance. The proposed system achieved an average accuracy of 78% in detecting MCI, demonstrating its comparative effectiveness. Enhancements in our system are achieved by integrating a directional encoder tailored to capture temporal information across sequential visits. This addition leads to a 3% increase in detection accuracy within a subset of participants who have undergone multiple AM test sessions. Implementing such a longitudinal approach in analyzing unstructured speech data for MCI detection taps into a relatively underexplored area of research, offering new insights. © 2025 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Over-the-Air Computation for Federated Generative Model Fine-Tuning in Unmanned Vehicle-Assisted Disaster Relief

引用

IEEE Transactions on Cognitive Communications and networking 2025年

作者： Zhao, Yikun Feng, Lei Zhou, Fanqin Li, Wenjing Xiong, Zehui Du, Hongyang Wu, Celimuge Guo, Song Quek, Tony Q.S Han, Zhu State Key Laboratory of Networking and Switching Technology Beijing100876 China Singapore University of Technology and Design Information Systems Technology and Design Pillar Singapore487372 Singapore University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong University of Electro-Communications Meta-Networking Research Center Tokyo Japan Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong 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

The utilization of emergent generative artificial intelligence (GAI) within the realm of unmanned vehicles (UVs) can boost edge intelligence and potentially enhance the efficiency and effectiveness of rescue operations. However, to facilitate specialized generative edge intelligence in dynamic UV networks, GAI models need to tap into local data and conduct online fine-tuning, and the dispersed distribution of UVs makes distributed fine-tuning paradigms crucial. Although the federated generative model fine-tuning brings a potential solution, the large number of parameter transmissions involved in its fine-tuning process are often constrained by communication bottlenecks, which are more pronounced for resource-constrained UV networks. To cope with these challenges, we introduce an energy-efficient GAI model fine-tuning framework for the hierarchical UV networks, which employs over-the-air technology to save computational resource costs for unmanned aerial vehicle (UAV) during federated aggregation within a federated learning paradigm. Thereafter, we study the resource allocation problem in the fine-tuning process of the generative model and formulate a joint optimization problem for the bandwidth allocation, power control, computation resource allocation, and denoising factor control, aiming to minimize the system energy consumption. Then, we decouple the original problem into four tractable subproblems, and propose a block coordinate descent algorithm to solve them iteratively. Particularly, we derive a closed-form solution for the denoising factor to minimize the local model uploading transmission energy consumption under a specific AirComp communication error threshold. Simulation based on the state-of-the-art generative models shows that our AirComp-assisted federated generative model fine-tuning scheme can achieve satisfactory customized field-of-view image generation capability compared with the traditional fine-tuning scheme in an energy-efficient way. © 2015 I

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimizing Forest Fire Detection Systems: A Deep Learning Approach with UAVs and Binary Sand Cat Swarm Optimization

Optimizing Forest Fire Detection Systems: A Deep Learning Ap...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： T. Rajesh Kumar K Komala Devi P. Subramanian Mahaveerakannan R Balamanigandan R. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of ISE CMR Institute of Technology Bengaluru India Department of Networking Institute of CSE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Devastating forest fires are an international environmental crisis that endangers both people and their valuable natural resources. Forest fires are becoming more common and more destructive, leading to significant depletion of natural resources. A combination of human interference with natural processes and the effects of climate alteration have contributed to a recent uptick in the frequency of wildfires. Combating this issue requires firefighters to respond swiftly and identify fires from early smoke so they can prevent the fires from spreading. An efficient system for detecting and monitoring fires is essential for reducing this risk. The purpose of this study is to investigate and assess the state of the art in forest fire detection and monitoring with the use of deep learning algorithms and drones or unmanned aerial vehicles (UAVs). An efficient and economical way to monitor in real-time and detect fires early is to use drones that are outfitted with specialised sensors and cameras. Using the suggested customised Convolutional Neural Network models, the datasets were tested. Deep Q learning (DQL) is used to extract features, which enhances the accuracy of classification. When compared to other transfer learning methods, such as VGG16, Xception, ResNet50, DenseNet121, Inception ResnetV2, besides Inception V3, their outcomes are evaluated. To analyse and solve the optimal parameter selection problem, the authors suggest using Binary Sand Cat Swarm Optimisation (bSCSO) to fine-tune the parameters of the prototypical. The suggested custom VGG16 model outstripped state-of-the-art models by a significant margin (98.14%), which was measured by its ability to generalise to unknown images.

关键词： Natural resources Wildfires Accuracy Q-learning Biological system modeling Forestry Feature extraction Real-time systems Particle swarm optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Multi-Controller Architecture Design and Features in Software - Defined networking (SDN)

Multi-Controller Architecture Design and Features in Softwar...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： V. Prabhu P. Balamurugan Department of Computer Science and Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chengalpattu Tamilnadu India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chengalpattu Tamilnadu India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

networking paradigm known as “Software-Defined networking” (SDN) offers more flexibility with network management and is fast gaining popularity. Separating the control plane from the data plane is largely responsible for this success. In SDN-enabled networks, a centralized controller is used to translate high-level network application requirements into low-level directives that are issued to the forwarding devices. Such the controller requires limited ability to react to the request for flow processing generated by forwarding devices. Whenever an SDN-enabled network expands in terms of size or as a network traffic rises, flow processing demands can't be able to fulfill by a single centralized controller. This causes a controller's performance to decline, which eventually results in a malfunctioning SDN-enabled network. Implementing a multi-controller architecture, in which a number of controllers cooperate to manage a sizable amount of network traffic and flow processing requirements, would be a successful strategy. The introduction of a multi-controller architecture and a consideration of the problems with its scalability, coherence as well as accessibility make up the core contribution of this study. Additionally, it identifies areas where study in this area could still be done.

关键词： Performance evaluation Scalability Process control computer architecture Telecommunication traffic Coherence Software Reliability Software defined networking Mobile computing

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：