检索结果-内蒙古大学图书馆

An Online Algorithm for inference Service Scheduling Using Combinations of Server-Based and Serverless Instances in Cloud Environments

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第8期12卷 11153-11165页

作者： Liu, Siyuan Pan, Li Liu, Shijun Qi, Kaiyuan Shandong Univ Sch Software Jinan 250101 Peoples R China Jinan Inspur Data Technol Co Ltd Jinan 250101 Peoples R China

With the continuous development in the field of machine learning, there is an increasing demand for the cloud-based machine learning inference services, which are latency-sensitive tasks, such as the service requests from the Internet of Things (IoT) devices. These inference services are generally accompanied by fluctuations and uncertainties, so they often require vastly varied numbers of servers at different time spots. As a result, how to dynamically and rationally schedule cloud servers for inference services has become an important issue. Alibaba Cloud currently provides its serverless instances called elastic container instance (ECI), and due to the advantages of pay-as-you-go billing and second-level elasticity, they are well-suited for handling bursty or fluctuating workloads. At the same time, Alibaba Cloud's subscription-based elastic compute service (ECS) instances can be used for steady-state workloads. Our objective is to dynamically combine these two types of instances to deal with inference service requests. In this article, we propose a deterministic online algorithm that can rationally schedule these two types of instances to optimize costs without requiring knowledge of future workloads. We prove that the proposed online algorithm achieves a competitive ratio of no more than 2 compared to the optimal offline algorithm. Through simulation experiments, we demonstrate that our algorithm outperforms three benchmarks, which are all-reserved algorithm, all-on-demand algorithm, and traditional online algorithms that only use ECS instances. Our algorithm exhibits superiority across various workloads and can significantly reduces costs in most cases.

关键词： Cloud computing Costs Pricing inference algorithms Servers Optimization Machine learning Internet of Things Scheduling Prediction algorithms competitive analysis cost management inference service online algorithm

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

MIS-YOLOv8: An Improved Algorithm for Detecting Small Objects in UAV Aerial Photography Based on YOLOv8

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Tao, Sun Shengqi, Yang Haiying, Liu Jason, Gu Lixia, Deng Lida, Liu Qilu Univ Technol Shandong Acad Sci Sch Informat & Automat Engn Jinan 250353 Peoples R China Dalhousie Univ Sch Elect & Comp Engn Halifax NS B3J 1Z1 Canada Shandong Runyi Intelligent Technol Co Ltd Jinan 250002 Peoples R China

Small objects' detection from a drone's perspective has always been a challenging issue in the field of object detection. To address the problems of low recognition accuracy and information loss in small object detection, this article proposed MIS-YOLOv8 algorithm, primarily aimed at resolving the issue of small object loss during the detection process of the classic YOLOv8s algorithm. First, a multilevel feature extraction (MFE) module was designed for enriching the feature representation capabilities capable of extracting objects from different scales. Second, a small object detection mechanism was incorporated for improving the detection ability. Finally, the integration of depthwise atrous flexible convolutions is introduced, enabling a rich capture of information from spatial to depth dimensions, thereby reducing the loss of small objects. The improved MIS-YOLOv8 algorithm validation was conducted on the VisDrone2019 dataset, where MIS-YOLOv8 demonstrated a 9% and 6.2% increase in mAP@0.5 and mAP@0.5:0.95, respectively, compared with YOLOv8s. The experimental results indicated that the improved model exhibits superior performance in small object detection for drones.

关键词： Feature extraction Computational modeling YOLO Training Accuracy Computational efficiency Drones inference algorithms Deep learning Autonomous aerial vehicles small object detection unmanned aerial vehicle (UAV) YOLOv8s

来源：评论

学校读者我要写书评

暂无评论

Counterfactual Data Generation Method for Fault Diagnosis of Complex Electromechanical Systems

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Wang, Chong Liu, Jie Cao, Junwei Chen, Xi Chen, Lihua Ji, Yindong Tsinghua Univ Dept Automat Beijing 100190 Peoples R China Beihang Univ Sch Reliabil & Syst Engn Beijing 100191 Peoples R China Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol Beijing 100190 Peoples R China Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 610032 Sichuan Peoples R China

The high reliability and maintainability of complex electromechanical systems make the collection of representative fault data difficult in routine operations. This issue poses significant challenges to data-driven models, hindering their ability to accurately capture system fault mechanisms. Generating simulated fault samples is a popular and effective approach to augment fault data. However, state-of-the-art data generation methods can only produce synthetic data with respect to the distribution of the collected data and may violate the actual fault mechanisms. To address this, this article proposes a counterfactual data generation method grounded in causality, aiming to simulate the intrinsic generation process of monitoring data and thereby obtain counterfactual data that conforms to the system's fault mechanisms. In the proposed method, a priori-constrained causal discovery method is designed to uncover the causalities among the monitoring variables in complex electromechanical systems. A graph decoupling network is designed to disentangle causal mechanisms and extract decoupled features representing different uncertainty sources of the monitoring data. Finally, a causal-based generative adversarial network (CGAN) is proposed to generate counterfactual monitoring data that satisfies the mined causalities. The experimental results show that the generalizability and stability of fault diagnosis models can be enhanced with the counterfactual data.

关键词： Monitoring Electromechanical systems Data collection Cause effect analysis Fault diagnosis inference algorithms Training Roads Generative adversarial networks Data models Causality counterfactual data generation decoupling causal representation electromechanical systems fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Hybrid Attention for Robust RGB-T Pedestrian Detection in Real-World Conditions

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第1期10卷 319-326页

作者： Rathinam, Arunkumar Pauly, Leo Shabayek, Abd El Rahman Rharbaoui, Wassim Kacem, Anis Gaudilliere, Vincent Aouada, Djamila Univ Luxembourg Interdisciplinary Ctr Secur Reliabil & Trust SnT L-1855 Kirchberg Luxembourg Univ Luxembourg Interdisciplinary Ctr Secur Reliabil & Trust SnT L-4365 Esch Sur Alzette Luxembourg Univ Poitiers XLIM Inst F-87060 Limoges France Univ Lorraine CNRS Inria Loria F-54000 Nancy France

Multispectral pedestrian detection has gained significant attention in recent years, particularly in autonomous driving applications. To address the challenges posed by adversarial illumination conditions, the combination of thermal and visible images has demonstrated its advantages. However, existing fusion methods rely on the critical assumption that the RGB-Thermal (RGB-T) image pairs are fully overlapping. These assumptions often do not hold in real-world applications, where only partial overlap between images can occur due to sensors configuration. Moreover, sensor failure can cause loss of information in one modality. In this letter, we propose a novel module called the Hybrid Attention (HA) mechanism as our main contribution to mitigate performance degradation caused by partial overlap and sensor failure, i.e. when at least part of the scene is acquired by only one sensor. We propose an improved RGB-T fusion algorithm, robust against partial overlap and sensor failure encountered during inference in real-world applications. We also leverage a mobile-friendly backbone to cope with resource constraints in embedded systems. We conducted experiments by simulating various partial overlap and sensor failure scenarios to evaluate the performance of our proposed method. The results demonstrate that our approach outperforms state-of-the-art methods, showcasing its superiority in handling real-world challenges.

关键词： Sensors Pedestrians Feature extraction Thermal sensors Cameras Robustness inference algorithms Sensor fusion Lighting Image sensors Deep learning for visual perception multi-modal perception for HRI sensor fusion human detection and tracking computer vision for transportation

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：