检索结果-内蒙古大学图书馆

Mobility and Cost Aware inference Accelerating Algorithm for Edge Intelligence

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第3期24卷 1530-1549页

作者： Yuan, Xin Li, Ning Wei, Kang Xu, Wenchao Chen, Quan Chen, Hao Guo, Song Harbin Inst Technol Sch Ocean Engn Harbin 150001 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Peoples R China TheHong Kong Polytech Univ Dept Comp Hong Kong 999077 Peoples R China Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China

The edge intelligence (EI) has been widely applied recently. Splitting the model between device, edge server, and cloud can significantly improve the performance of EI. The model segmentation without user mobility has been investigated in detail in previous studies. However, in most EI use cases, the end devices are mobile. Few studies have been conducted on this topic. These works still have many issues, such as ignoring the energy consumption of mobile device, inappropriate network assumption, and low effectiveness on adapting user mobility, etc. Therefore, to address the disadvantages of model segmentation and resource allocation in previous studies, we propose mobility and cost aware model segmentation and resource allocation algorithm for accelerating the inference at edge (MCSA). Specifically, in the scenario without user mobility, the loop iteration gradient descent (Li-GD) algorithm is provided. When the mobile user has a large model inference task that needs to be calculated, it will take the energy consumption of mobile user, the communication and computing resource renting cost, and the inference delay into account to find the optimal model segmentation and resource allocation strategy. In the scenario with user mobility, the mobility aware Li-GD (MLi-GD) algorithm is proposed to calculate the optimal strategy. Then, the properties of the proposed algorithms are investigated, including convergence, complexity, and approximation ratio. The experimental results demonstrate the effectiveness of the proposed algorithms.

关键词： Servers Computational modeling inference algorithms Resource management Delays Costs Energy consumption Complexity theory Partitioning algorithms Mobile handsets Edge intelligence model segmentation inference accelerating mobility

来源：评论

学校读者我要写书评

暂无评论

Scene inference Using Saliency Graphs With Trust-Theoretic Semantic Information Encoding

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 256-260页

作者： Meena, Preeti Kumar, Himanshu Yadav, Sandeep Indian Inst Technol Jodhpur Discipline Elect Engn Jodhpur 342030 India

Scene inference refers to the identification of the scene from a given set of scene representations such as images. A saliency graph of a scene contains scene-defining objects along with semantic information between them in the graph representation. Existing methods consider the entire scene with uniform weighting to all semantic information for scene inference, resulting in a suboptimal performance. This letter presents an optimal edge weight estimation using the trust theoretic framework to encode semantic information effectively in saliency graphs. We have utilized the notion of converged global absolute trust in saliency scores of salient objects to compute the weighting of semantic information. Experimental results highlight the efficacy of the proposed method.

关键词： Peer-to-peer computing Semantics Estimation Symmetric matrices Image edge detection Signal processing algorithms inference algorithms Eigenvalues and eigenfunctions Visualization Accuracy Scene inference saliency graph semantic information trust graph P2P

来源：评论

学校读者我要写书评

暂无评论

Beyond the Cloud: Edge inference for Generative Large Language Models in Wireless Networks

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第1期24卷 643-658页

作者： Zhang, Xinyuan Nie, Jiangtian Huang, Yudong Xie, Gaochang Xiong, Zehui Liu, Jiang Niyato, Dusit Shen, Xuemin BUPT State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Singapore Univ Technol & Design Informat Syst Technol & Design ISTD Pillar Singapore 487372 Singapore Purple Mt Labs Nanjing 211111 Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore Univ Waterloo Dept Elect & Comp Engn Waterloo ON N2L 3G1 Canada

Generative Artificial Intelligenge (GAI) is revolutionizing the world with its unprecedented content creation ability. Large Language Model (LLM) is one of its most embraced branches. However, due to LLM's substantial size and resource-intensive nature, it is cloud-hosted, raising concerns about privacy, usage limitations, and latency. In this paper, we propose to utilize ubiquitous distributed wireless edge computing resources for real-time LLM inference. Specifically, we introduce a novel LLM edge inference framework, incorporating batching and model quantization to ensure high throughput inference on resource-limited edge devices. Then, based on the architecture of transformer decoder-based LLMs, we formulate an edge inference optimization problem which is NP-hard, considering batch scheduling and joint allocation of communication and computation resources. The solution is the optimal throughput under edge resource constraints and heterogeneous user requirements on latency and accuracy. To solve this NP-hard problem, we develop an OT-GAH (Optimal Tree-search with Generalized Assignment Heuristics) algorithm with reasonable complexity and 1/2-approximation ratio. We first design the OT algorithm with online tree-pruning for single-edge-node multi-user case, which navigates the inference request selection within the tree structure to miximize throughput. We then consider the multi-edge-node case and propose the GAH algorithm, which recrusively invokes the OT in each node's inference scheduling iteration. Simulation results demonstrate the superiority of OT-GAH batching over other benchmarks, revealing an over 45% time complexity reduction compared to brute-force searching.

关键词： Computational modeling Quantization (signal) Accuracy inference algorithms Throughput Wireless networks Transformers Resource management Optimization Chatbots Generative AI edge inference wireless networks multiuser edge computing

来源：评论

学校读者我要写书评

暂无评论

A Rapid Concrete Crack Detection Method Based on Improved YOLOv8

引用

IEEE ACCESS 2025年 13卷 59227-59243页

作者： Wang, Yongzhen He, Jiacong China Univ Min & Technol Sch Mech & Elect Engn Xuzhou 221116 Peoples R China

An improved YOLOv8 (You Only Look Once version 8) model is proposed to tackle the challenges of low detection accuracy and slow speed resulting from the complex background and shape diversity of concrete cracks. Firstly, a lightweight feature fusion module, GE_Conv, is designed by integrating the Ghost Module and Efficient Channel Attention in series. This module is embedded into the neck network to preserve more feature information during downsampling and accelerate the model's inference speed. Secondly, the DBB_Bottleneck is introduced into the C2f module, combining the lightweight GE_Conv with the structurally re-parameterized Diverse Branch Block, enhancing the model's multi-scale feature extraction capability. Furthermore, the introduction of the GF_Detect detection head significantly reduces the number of model parameters while improving detection performance. Finally, the WIoUv3 loss function is employed to dynamically assign anchor boxes of varying qualities, thereby enhancing the accuracy of anchor box positioning. Experimental results demonstrate that the proposed model achieves a detection precision of 92.9% and a mAP@50 (mean average precision at an Intersection over Union threshold of 0.5) of 77.8%. Compared to state-of-the-art algorithms such as Faster R-CNN, SSD, RetinaNet, YOLOv5s, YOLOv7-tiny, and the original YOLOv8s, the proposed model exhibits superior performance in both detection accuracy and generalization capability. Additionally, the model achieves an average detection time of 10.20 ms per image, demonstrating its practical feasibility. This study not only improves the accuracy and speed of crack detection but also significantly reduces the computational complexity of the model, advancing the development of lightweight and practical crack detection algorithms. The proposed model can be widely applied to crack inspection tasks for roads, bridges, coal mine shafts, and other scenarios, providing efficient and reliable technical support for cra

关键词： Accuracy Feature extraction YOLO Image edge detection Computational modeling Neck inference algorithms Image segmentation Convolution Standards Concrete cracks object detection lightweight module wise intersection over union you only look once version 8

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv7 Tiny Algorithm for Vehicle and Pedestrian Detection with Occlusion in Autonomous Driving

引用

Chinese Journal of Electronics 2025年第1期34卷 282-294页

作者： Jian Su Fang Wang Wei Zhuang Nanjing University of Information Science and Technology

Future transportation is advancing in the direction of intelligent transportation systems, where an essential part is vehicle and pedestrian detection. Due to the complex urban traffic environment, vehicles and pedestrians in road monitoring have different forms of occlusion problems, resulting in the missed detection of objects. We design an improved you only look once version 7(YOLOv7) tiny algorithm for vehicle and pedestrian detection under occlusion, with the following four main improvements. In order to locate the object more accurately, 1 × 1 convolution and identity connection are added to the 3 × 3 convolution, and convolution reparameterization is used to enhance the inference speed of the network model. In view of the complex road background and more interference, the coordinate attention was added to the connection part of backbone and neck to enhance the network's capacity to detect the object and lessen interference from other targets. At the same time, before being sent to the detection head, global attention mechanism is added to improve the accuracy of model detection by capturing three-dimensional features. Considering the issue of imbalanced training samples, we propose focal complete intersection over union(CIOU) loss instead of CIOU loss to become the bounding box regression loss, so that the regression process attention to high-quality anchor boxes. Experiments show that the improved YOLOv7 tiny algorithm achieves 82.2% map@ 0.5 in pattern analysis, statistical modelling and computational learning visual object classes dataset, which is 2.8% higher than before the improvement. The performance of map @ 0.5:0.95 is 5.2% better than the previous improvement. The proposed improved algorithm can availably to detect partial occlusion objects.

关键词： Training Pedestrians Attention mechanisms Convolution Roads Transportation Object detection Interference inference algorithms Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Balancing Complexity and Accuracy: Trajectory-Enhanced Fingerprinting Localization With a Realistic Simulation Framework for 5G

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第4期74卷 6548-6560页

作者： Deng, Jie Xiao, Fu Nanjing Univ Posts & Telecommun Sch Comp Sci Nanjing 210003 Jiangsu Peoples R China

This paper underscores the critical role of outdoor localization in wireless network operations and Internet of Things (IoT) applications. While Global Navigation Satellite Systems (GNSS), such as GPS, provide meter-level accuracy, their limitations in urban environments and high power consumption make them unsuitable for many use cases. Consequently, fingerprint-based localization methods leveraging existing sensor infrastructures have emerged as viable alternatives. This study investigates both traditional fingerprint-based algorithms and advanced deep learning techniques, noting their potential to enhance accuracy alongside challenges in data processing and collection. To address these issues, we propose a novel probabilistic model that enhances Received Signal Strength Indicator (RSSI)-based user location inference by incorporating user trajectories. This approach mitigates the effects of noise and signal fading. We further developed a comprehensive algorithm integrating this probabilistic model with system-level parameters to accommodate diverse real-world deployment scenarios. Performance evaluations demonstrate that our trajectory-enhanced method achieves accuracy improvements of 10% to 35% in urban environments compared to RSSI-only, Weighted k-Nearest Neighbor (WKNN), and neural network-based approaches. These enhancements rely solely on User Equipment (UE) signal strength from the serving cell and benefit from rapid training processes. Additionally, we introduce a simulation framework build on top of OMNet++, Veins, and Simu5G platforms, enabling realistic and generic validation of localization algorithms. This framework allows researchers and telecommunications operators to efficiently evaluate algorithm performance across diverse scenarios, reducing costs and deployment efforts by eliminating the need for extensive hardware resources.

关键词： Location awareness Fingerprint recognition Accuracy Hidden Markov models Trajectory Probabilistic logic Global navigation satellite system Roads Nearest neighbor methods inference algorithms 5G cell deployment cellular based positioning outdoor positioning probabilistic trajectory model

来源：评论

学校读者我要写书评

暂无评论

Intelligence-Based Reinforcement Learning for Dynamic Resource Optimization in Edge Computing-Enabled Vehicular Networks

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第3期24卷 2394-2406页

作者： Wang, Yuhang He, Ying Yu, F. Richard Wu, Kaishun Chen, Shanzhi Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Carleton Univ Sch Informat Technol Ottawa ON K1S 5B6 Canada Hong Kong Univ Sci & Technol GZ Hong Kong Peoples R China State Key Lab Wireless Mobile Commun Beijing 100083 Peoples R China China Informat & Commun Technol Grp Co Ltd CICT Beijing 100079 Peoples R China

Intelligent transportation systems demand efficient resource allocation and task offloading to ensure low-latency, high-bandwidth vehicular services. The dynamic nature of vehicular environments, characterized by high mobility and extensive interactions among vehicles, necessitates considering time-varying statistical regularities, especially in scenarios with sharp variations. Despite the widespread use of traditional reinforcement learning for resource allocation, its limitations in generalization and interpretability are evident. To overcome these challenges, we propose an Intelligence-based Reinforcement Learning (IRL) algorithm. This algorithm utilizes active inference to infer the real world and maintain an internal model by minimizing free energy. Enhancing the efficiency of active inference, we incorporate prior knowledge as macro guidance, ensuring more accurate and efficient training. By constructing an intelligence-based model, we eliminate the need for designing reward functions, aligning better with human thinking, and providing a method to reflect the learning, information transmission and intelligence accumulation processes. This approach also allows for quantifying intelligence to a certain extent. Considering the dynamic and uncertain nature of vehicular scenarios, we apply the IRL algorithm to environments with constantly changing parameters. Extensive simulations confirm the effectiveness of IRL, significantly improving the generalization and interpretability of intelligent models in vehicular networks.

关键词： Reinforcement learning Vehicle dynamics Heuristic algorithms Resource management Biological system modeling Adaptation models Decision making Transportation inference algorithms Dynamic scheduling Active inference prior knowledge reinforcement learning resource allocation

来源：评论

学校读者我要写书评

暂无评论

On-Device Training of Fully Quantized Deep Neural Networks on Cortex-M Microcontrollers

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2025年第4期44卷 1250-1261页

作者： Deutel, Mark Hannig, Frank Mutschler, Christopher Teich, Juergen Friedrich Alexander Univ Erlangen Nurnberg Dept Comp Sci D-91058 Erlangen Germany Fraunhofer Inst Integrated Circuits IIS Fraunhofer IIS D-91058 Erlangen Germany

On-device training of deep neural networks (DNNs) allows models to adapt and fine tune to newly collected data or changing domains while deployed on microcontroller units (MCUs). However, DNN training is a resource-intensive task, making the implementation and execution of DNN training algorithms on MCUs challenging due to low processor speeds, constrained throughput, limited floating-point support, and memory constraints. In this work, we explore on-device training DNNs for different sized Cortex-M MCUs (Cortex-M0+, Cortex-M4, and Cortex-M7). We present a method that enables efficient training of DNNs completely in place on the MCU using fully quantized training (FQT) and dynamic partial gradient updates. We demonstrate the feasibility of our approach on multiple vision and time-series datasets and provide insights into the tradeoff between training accuracy, memory overhead, energy, and latency on real hardware. The results show that compared to related work, our approach requires 34.8% less memory and has a 49.0% lower latency per training sample, with dynamic partial gradient updates allowing a speedup of up to 8.7 compared to fully updating all weights.

关键词： Training Memory management Tensors Artificial neural networks Random access memory Quantization (signal) Design automation Servers Microcontrollers inference algorithms Efficient AI embedded machine learning microcontrollers on-device training TinyML

来源：评论

学校读者我要写书评

暂无评论

Extending Causal Discovery to Live 5G NR Network With Novel Proportional Fair Scheduler Enhancements

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第1期12卷 288-296页

作者： Polaganga, Roopesh Kumar Liang, Qilian T Mobile US Inc Access Network Dev Bellevue WA 98012 USA Univ Texas Arlington Dept Elect Engn Arlington TX 76010 USA

Understanding the cause-and-effect connections in intricate systems like telecommunication networks is essential for enhancing and optimizing their performance. This article, in its novelty, extends causal discovery to the context of 5G new radio (NR) Networks by leveraging established technique of the greedy equivalent search (GES) algorithm to real-world 5G network data. Our research uncovers causal relations among several network characteristics represented in the form of a directed acyclic graph (DAG). A specific causal link between latency and downlink throughput is further analyzed unveiling a robust correlation between network utilization and latency, manifesting the factors of packet loss and retransmissions especially when the network infrastructure becomes overwhelmed. Building on these findings, the second significant contribution of our study involves the introduction of a novel enhancement to the NR proportional fair (PF) scheduling algorithm. This enhancement incorporates retransmission considerations to improve network resource utilization. Our experimental results show notable gains in network efficiency and resource allocation, highlighting the potential for real-world enhancements based on the causal insights uncovered in our research. This research broadens the horizons of causal discovery within 5G NR networks and presents a tangible pathway for enhancing network performance and resource allocation, with implications for the broader field of network optimization.

关键词： 5G mobile communication Cause effect analysis Germanium inference algorithms Correlation Bayes methods Reliability 5G new radio (NR) networks causal discovery causality greedy equivalent Search (GES) proportional fair (PF) scheduler

来源：评论

学校读者我要写书评

暂无评论

A Mutual Information Constrained Multitask Learning Method for Very High-Resolution Building Segmentation

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 9230-9243页

作者： Wu, Yongchuang Wang, Yingchun Yang, Hui Zhang, Peng Wu, Yanlan Wang, Biao Anhui Univ Sch Artificial Intelligence Hefei 230601 Peoples R China Anhui Prov Geomatic Ctr Hefei 230031 Peoples R China Anhui Univ Inst Phys Sci & Informat Technol Hefei 230601 Peoples R China Anhui Univ Sch Resources & Environm Engn Hefei 230601 Peoples R China

Accurately extracting building footprints from remote sensing imagery is essential for urban management. Multitask learning (MTL) has shown its potential on improving segmentation accuracy with shared network weights to simultaneously capture various building-related features. However, due to the lack of adaptive context information balancing and effective knowledge transfer mechanisms between tasks, current MTL methods often obtain incomplete and irregular delineations of buildings. To address these issues, we propose a mutual information constrained multitask learning network (MIMNet) for precise building segmentation from remote sensing imagery. The MIMNet introduces a contextual information parallel perception structure to capture both global and local building features. In addition, it incorporates a fourier mutual information balancing module to promote the interaction and fusion of multiscale contextual information. The MIMNet simultaneously segments building mask and boundary utilizing the MTL strategy, and employs a mutual information loss function to enhance information exchange between the two tasks. Experimental evaluations demonstrate that the proposed MIMNet framework achieves state-of-the-art performance across three benchmark datasets, obtaining intersection over union scores of 91.49% on the WHU aerial dataset, 76.43% on the Massachusetts building dataset, and 83.54% on the Inria aerial dataset.

关键词： Buildings Feature extraction Mutual information Multitasking Image segmentation Correlation Semantics Remote sensing Knowledge transfer inference algorithms Boundary optimization building segmentation fourier transform multitask learning (MTL) mutual information (MI)

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：