检索结果-南通市图书馆

Optimized Binary Neural Networks for Road Anomaly Detection:A TinyML Approach on Edge Devices

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第7期80卷 527-546页

作者： Amna Khatoon Weixing Wang Asad Ullah Limin Li Mengfei Wang school of information engineering Chang’an UniversityXi’an710064China school of information engineering Xi’an Eurasia UniversityXi’an710065China school of Electrical and electronic engineering Wenzhou UniversityWenzhou325035China

Integrating Tiny Machine Learning(TinyML)with edge computing in remotely sensed images enhances the capabilities of road anomaly detection on a broader *** devices efficiently implement a Binary Neural Network(BNN)for road feature extraction,utilizing quantization and compression through a pruning *** modifications resulted in a 28-fold decrease in memory usage and a 25%enhancement in inference speed while only experiencing a 2.5%decrease in *** showcases its superiority over conventional detection algorithms in different road image *** constrained by computer resources and training datasets,our results indicate opportunities for future research,demonstrating that quantization and focused optimization can significantly improve machine learning models’accuracy and operational *** Cortex-M0 gives practical feasibility and substantial benefits while deploying our optimized BNN model on this low-power device:Advanced machine learning in edge *** analysis work delves into the educational significance of TinyML and its essential function in analyzing road networks using remote sensing,suggesting ways to improve smart city frameworks in road network assessment,traffic management,and autonomous vehicle navigation systems by emphasizing the importance of new technologies for maintaining and safeguarding road networks.

关键词： Edge computing remote sensing TinyML optimization BNNs road anomaly detection quantization model compression

Masked Autoencoders as Single Object Tracking Learners

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第7期80卷 1105-1122页

作者： Chunjuan Bo XinChen Junxing Zhang school of information and Communication engineering Dalian Minzu UniversityDalian116600China school of information and Communication engineering Dalian University of TechnologyDalian116024China

Significant advancements have beenwitnessed in visual tracking applications leveragingViT in recent years,mainly due to the formidablemodeling capabilities of Vision Transformer(ViT).However,the strong performance of such trackers heavily relies on ViT models pretrained for long periods,limitingmore flexible model designs for tracking *** address this issue,we propose an efficient unsupervised ViT pretraining method for the tracking task based on masked autoencoders,called *** pretraining,we employ two shared-parameter ViTs,serving as the appearance encoder and motion encoder,*** appearance encoder encodes randomly masked image data,while the motion encoder encodes randomly masked pairs of video ***,an appearance decoder and a motion decoder separately reconstruct the original image data and video frame data at the pixel *** this way,ViT learns to understand both the appearance of images and the motion between video frames *** results demonstrate that ViT-Base and ViT-Large models,pretrained with TrackMAE and combined with a simple tracking head,achieve state-of-the-art(SOTA)performance without additional ***,compared to the currently popular MAE pretraining methods,TrackMAE consumes only 1/5 of the training time,which will facilitate the customization of diverse models for *** instance,we additionally customize a lightweight ViT-XS,which achieves SOTA efficient tracking performance.

关键词： Visual object tracking vision transformer masked autoencoder visual representation learning

Improved PSO-Extreme Learning Machine Algorithm for Indoor Localization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第5期21卷 113-122页

作者： Qiu Wanqing Zhang Qingmiao Zhao Junhui Yang Lihua school of information engineering East China Jiaotong UniversityNanchang 330013China school of electronic and information engineering Beijing Jiaotong UniversityBeijing 100044China

Wi Fi and fingerprinting localization method have been a hot topic in indoor positioning because of their universality and location-related *** basic assumption of fingerprinting localization is that the received signal strength indication(RSSI)distance is accord with the location ***,how to efficiently match the current RSSI of the user with the RSSI in the fingerprint database is the key to achieve high-accuracy *** this paper,a particle swarm optimization-extreme learning machine(PSO-ELM)algorithm is proposed on the basis of the original fingerprinting ***,we collect the RSSI of the experimental area to construct the fingerprint database,and the ELM algorithm is applied to the online stages to determine the corresponding relation between the location of the terminal and the RSSI it ***,PSO algorithm is used to improve the bias and weight of ELM neural network,and the global optimal results are ***,extensive simulation results are *** is shown that the proposed algorithm can effectively reduce mean error of localization and improve positioning accuracy when compared with K-Nearest Neighbor(KNN),Kmeans and Back-propagation(BP)algorithms.

关键词： extreme learning machine fingerprinting localization indoor localization machine learning particle swarm optimization

Deployment of Edge Computing Nodes in IoT:Effective Implementation of Simulated Annealing Method Based on User Location

在线全文

学校读者我要写书评

暂无评论

China Communications 2024年第1期21卷 279-296页

作者： Junhui Zhao Ziyang Zhang Zhenghao Yi Xiaoting Ma Qingmiao Zhang school of electronic and information engineering Beijing Jiaotong UniversityBeijing 100044China school of information engineering East China Jiaotong UniversityNanchang 330013China

Edge computing paradigm for 5G architecture has been considered as one of the most effective ways to realize low latency and highly reliable communication,which brings computing tasks and network resources to the edge of *** deployment of edge computing nodes is a key factor affecting the service performance of edge computing *** this paper,we propose a method for deploying edge computing nodes based on user *** the combination of Simulation of Urban Mobility(SUMO)and Network Simulator-3(NS-3),a simulation platform is built to generate data of hotspot areas in Io T *** effectively using the data generated by the communication between users in Io T scenario,the location area of the user terminal can be *** this basis,the deployment problem is expressed as a mixed integer linear problem,which can be solved by Simulated Annealing(SA)*** analysis of the results shows that,compared with the traditional method,the proposed method has faster convergence speed and better performance.

关键词： deployment problem edge computing internet of things machine learning

CMMCAN:Lightweight Feature Extraction and Matching Network for Endoscopic Images Based on Adaptive Attention

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第8期80卷 2761-2783页

作者： Nannan Chong Fan Yang school of electronic and information engineering Hebei University of TechnologyTianjin300401China school of information and Intelligence engineering Tianjin Renai CollegeTianjin301636China

In minimally invasive surgery,endoscopes or laparoscopes equipped with miniature cameras and tools are used to enter the human body for therapeutic purposes through small incisions or natural ***,in clinical operating environments,endoscopic images often suffer from challenges such as low texture,uneven illumination,and non-rigid structures,which affect feature observation and *** can severely impact surgical navigation or clinical diagnosis due to missing feature points in endoscopic images,leading to treatment and postoperative recovery issues for *** address these challenges,this paper introduces,for the first time,a Cross-Channel Multi-Modal Adaptive Spatial Feature Fusion(ASFF)module based on the lightweight architecture of ***,a novel lightweight feature extraction and matching network based on attention mechanism is *** network dynamically adjusts attention weights for cross-modal information from grayscale images and optical flow images through a dual-branch Siamese *** extracts static and dynamic information features ranging from low-level to high-level,and from local to global,ensuring robust feature extraction across different widths,noise levels,and blur *** and local matching are performed through a multi-level cascaded attention mechanism,with cross-channel attention introduced to simultaneously extract low-level and high-level *** ablation experiments and comparative studies are conducted on the HyperKvasir,EAD,M2caiSeg,CVC-ClinicDB,and UCL synthetic *** results demonstrate that the proposed network improves upon the baseline EfficientViT-B3 model by 75.4%in accuracy(Acc),while also enhancing runtime performance and storage *** compared with the complex DenseDescriptor feature extraction network,the difference in Acc is less than 7.22%,and IoU calculation results on specific datasets outperform complex dense ***

关键词： Feature extraction and matching lightweighted network medical images endoscopic attention

Flight Time Minimization of UAV for Cooperative Data Collection in Probabilistic LoS Channel

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第2期21卷 210-226页

作者： Yan Li Shaoyi Xu Yunpu Wu Dongji Li school of electronic and information engineering Beijing Jiaotong UniversityBeijing 100044China school of Electrical engineering and electronic information Xihua UniversityChengdu 610039China

This paper investigates the data collection in an unmanned aerial vehicle(UAV)-aided Internet of Things(IoT) network, where a UAV is dispatched to collect data from ground sensors in a practical and accurate probabilistic line-of-sight(LoS) channel. Especially, access points(APs) are introduced to collect data from some sensors in the unlicensed band to improve data collection efficiency. We formulate a mixed-integer non-convex optimization problem to minimize the UAV flight time by jointly designing the UAV 3D trajectory and sensors’ scheduling, while ensuring the required amount of data can be collected under the limited UAV energy. To solve this nonconvex problem, we recast the objective problem into a tractable form. Then, the problem is further divided into several sub-problems to solve iteratively, and the successive convex approximation(SCA) scheme is applied to solve each non-convex subproblem. Finally,the bisection search is adopted to speed up the searching for the minimum UAV flight time. Simulation results verify that the UAV flight time can be shortened by the proposed method effectively.

关键词： data collection flight time probabilistic line-of-sight channel unlicensed band unmanned aerial vehicle

A Review of NILM Applications with Machine Learning Approaches

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 2971-2989页

作者： Maheesha Dhashantha Silva Qi Liu school of electronic and information engineering Nanjing University of Information Science and TechnologyNanjing210044China

In recent years,Non-Intrusive LoadMonitoring (NILM) has become an emerging approach that provides affordableenergy management solutions using aggregated load obtained from a single smart meter in the power ***, by integrating Machine Learning (ML), NILM can efficiently use electrical energy and offer less ofa burden for the energy monitoring process. However, conducted research works have limitations for real-timeimplementation due to the practical issues. This paper aims to identify the contribution of ML approaches todeveloping a reliable Energy Management (EM) solution with NILM. Firstly, phases of the NILM are discussed,along with the research works that have been conducted in the domain. Secondly, the contribution of machinelearning approaches in three aspects is discussed: Supervised learning, unsupervised learning, and *** highlights the limitations in the applicability of ML approaches in the field. Then, the challenges in the realtimeimplementation are concerned with six use cases: Difficulty in recognizing multiple loads at a given time,cost of running the NILM system, lack of universal framework for appliance detection, anomaly detection andnew appliance identification, and complexity of the electricity loads and real-time demand side ***, options for selecting an approach for an efficientNILMframework are suggested. Finally, suggestionsare provided for future research directions.

关键词： Non-intrusive load monitoring transfer learning machine learning feature extraction

Joint Communication-Caching-Computing Resource Allocation for Bidirectional Data Computation in IRS-Assisted Hybrid UAV-Terrestrial Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of electronics 2024年第4期33卷 1093-1103页

作者： Yangzhe LIAO Lin LIU Yuanyan SONG Ning XU school of information engineering Wuhan University of Technology

Joint communication-caching-computing resource allocation in wireless inland waterway communications enables resource-constrained unmanned surface vehicles(USVs) to provision computation-intensive and latencysensitive tasks forward beyond fifth-generation(B5G) and sixth-generation(6G) era. The power of such resource allocation cannot be fully studied unless bidirectional data computation is properly managed. A novel intelligent reflecting surface(IRS)-assisted hybrid UAV-terrestrial network architecture is proposed with bidirectional tasks. The sum of uplink and downlink bandwidth minimization problem is formulated by jointly considering link quality, task execution mode selection, UAVs trajectory, and task execution latency constraints. A heuristic algorithm is proposed to solve the formulated challenging problem. We divide the original challenging problem into two subproblems, i.e., the joint optimization problem of USVs offloading decision, caching decision and task execution mode selection, and the joint optimization problem of UAVs trajectory and IRS phase shift-vector design. The Karush–Kuhn–Tucker conditions are utilized to solve the first subproblem and the enhanced differential evolution algorithm is proposed to solve the latter one. The results show that the proposed solution can significantly decrease bandwidth consumption in comparison with the selected advanced algorithms. The results also prove that the sum of bandwidth can be remarkably decreased by implementing a higher number of IRS elements.

关键词： Wireless communication Heuristic algorithms Bandwidth Network architecture Downlink Trajectory Resource management

Formal Modeling of Frame Selection in Asynchronous TSN Communications

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of electronics 2024年第2期33卷 549-563页

作者： Ershuai LI Xuan ZHOU Jinjing SUN Huagang XIONG Feng HE school of electronic and information engineering Beihang University

The asynchronous time-sensitive networking(TSN) based on IEEE 802.1Qcr is expected to be a promising solution for the asynchronous transmissions of safety-critical flows without the support of clock *** the asynchronous traffic shaping(ATS) mechanism is adopted to meet the deadline requirements for transmissions of safety-critical flow, it is necessary to formally verify the real-time properties and corresponding network ***, it is still unclear how to build an efficient formal model to evaluate different frame selection methods during the ATS scheduling process, which originate from the dominations of priority or eligibility time. In this paper, we present a formal modeling framework to compare the impacts of different frame selection on transmission sequence under the ATS mechanism. According to the priority level(p ATS) or eligibility time(e ATS) for flows, two transmission selection methods in ATS are modeled and compared. Then, we verify the real-time properties of ATS. The result shows that the shaping-for-free property can be satisfied with the p ATS method but can not be fulfilled with the e ATS method. Besides, the timing analysis results illustrate that the e ATS method can provide more fairness than the p ATS method for the transmission of low-priority flows in TSN networks.

关键词： System recovery Real-time systems Delays Synchronization