检索结果-内蒙古大学图书馆

FPGA-based acceleration for binary neural networks in edge computing

Journal of Electronic Science and technology 2023年第2期21卷 65-77页

作者： Jin-Yu Zhan An-Tai Yu Wei Jiang Yong-Jia Yang Xiao-Na Xie Zheng-Wei Chang Jun-Huan Yang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China School of Automation Chengdu University of Information TechnologyChengdu610225China State Grid Sichuan Electric Power Research Institute Chengdu610095China Department of Information Sciences and Technology George Mason UniversityFairfaxVA22030USA

As a core component in intelligent edge computing,deep neural networks(DNNs)will increasingly play a critically important role in addressing the intelligence-related issues in the industry domain,like smart factories and autonomous *** to the requirement for a large amount of storage space and computing resources,DNNs are unfavorable for resource-constrained edge computing devices,especially for mobile terminals with scarce energy *** of DNN has become a promising technology to achieve a high performance with low resource consumption in edge ***-programmable gate array(FPGA)-based acceleration can further improve the computation efficiency to several times higher compared with the central processing unit(CPU)and graphics processing unit(GPU).This paper gives a brief overview of binary neural networks(BNNs)and the corresponding hardware accelerator designs on edge computing environments,and analyzes some significant studies in *** performances of some methods are evaluated through the experiment results,and the latest binarization technologies and hardware acceleration methods are *** first give the background of designing BNNs and present the typical types of *** FPGA implementation technologies of BNNs are then *** comparison with experimental evaluation on typical BNNs and their FPGA implementation is further ***,certain interesting directions are also illustrated as future work.

关键词： Accelerator Binarization Field-programmable gate array(FPGA) Neural networks Quantification

来源：评论

学校读者我要写书评

暂无评论

A Line Complex-Based Evolutionary Algorithm for Many-Objective Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1150-1167页

作者： Liang Zhang Qi Kang Qi Deng Luyuan Xu Qidi Wu the Department of Control Science and Engineering Tongji UniversityShanghai 201804 the Jiangsu Province Support Software Engineering R&D Center for Modern Information Technology Application in Enterprise Suzhou 215104China the Shanghai Institute of Intelligent Science and Technology Tongji UniversityShanghai 200092China

In solving many-objective optimization problems(MaO Ps),existing nondominated sorting-based multi-objective evolutionary algorithms suffer from the fast loss of selection *** candidate solutions become nondominated during the evolutionary process,thus leading to the failure of producing offspring toward Pareto-optimal front with *** we find a more effective way to select nondominated solutions and resolve this issue?To answer this critical question,this work proposes to evolve solutions through line complex rather than solution points in Euclidean ***,Plücker coordinates are used to project solution points to line complex composed of position vectors and momentum *** position vectors of the solution points,momentum vectors are used to extend the comparability of nondominated solutions and enhance selection ***,a new distance function designed for high-dimensional space is proposed to replace Euclidean distance as a more effective distancebased *** on them,a novel many-objective evolutionary algorithm(MaOEA)is proposed by integrating a line complex-based environmental selection strategy into the NSGAⅢ*** proposed algorithm is compared with the state of the art on widely used benchmark problems with up to 15 *** results demonstrate its superior competitiveness in solving MaOPs.

关键词： Environmental selection line complex many-objective optimization problems(MaOPs) Plücker coordinate

来源：评论

学校读者我要写书评

暂无评论

An Uncertainty Quantization-Based Method for Anti-UAV Detection in Infrared Images

引用

Computers, Materials & Continua 2025年第4期83卷 1439-1458页

作者： Can Wu Wenyi Tang Yunbo Rao Yinjie Chen Hui Ding Shuzhen Zhu Yuanyuan Wang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China State Key Laboratory of Air Traffic Management System Nanjing210000China National Airspace Management Center Beijing100094China

Infrared unmanned aerial vehicle(UAV)target detection presents significant challenges due to the inter-play between small targets and complex *** methods,while effective in controlled environments,often fail in scenarios involving long-range targets,high noise levels,or intricate backgrounds,highlighting the need for more robust *** address these challenges,we propose a novel three-stage UAV segmentation framework that leverages uncertainty quantification to enhance target *** framework incorporates a Bayesian convolutional neural network capable of generating both segmentation maps and probabilistic uncertainty *** utilizing uncer-tainty predictions,our method refines segmentation outcomes,achieving superior detection ***,this marks the first application of uncertainty modeling within the context of infrared UAV target *** evaluations on three publicly available infrared UAV datasets demonstrate the effectiveness of the proposed *** results reveal significant improvements in both detection precision and robustness when compared to state-of-the-art deep learning *** approach also extends the capabilities of encoder-decoder convolutional neural networks by introducing uncertainty modeling,enabling the network to better handle the challenges posed by small targets and complex environmental *** bridging the gap between theoretical uncertainty modeling and practical detection tasks,our work offers a new perspective on enhancing model interpretability and *** codes of this work are available openly at https://***/general-learner/UQ_Anti_UAV(acceessed on 11 November 2024).

关键词： Object segmentation uncertainty quantification bayesian convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Multi-layer composite autoencoders for semi-supervised change detection in heterogeneous remote sensing images

引用

Science China(information Sciences) 2023年第4期66卷 124-125页

作者： Jiao SHI Tiancheng WU Hanwen YU A.K.QIN Gwanggil JEON Yu LEI School of Electronics and Information Northwestern Polytechnical University School of Resources and Environment University of Electronic Science and Technology of China Department of Computer Science and Software Engineering Swinburne University of Technology Department of Embedded Systems Engineering Incheon National University

With the increasing complexity of application scenarios, the fusion of different remote sensing data types has gradually become a trend, which can greatly improve the utilization of massive remote sensing *** the problem of change detection for heterogeneous remote images can be much more complicated than the traditional change detection for homologous remote sensing images,

关键词：

来源：评论

学校读者我要写书评

暂无评论

IEARACDA: Predicting circRNA-disease associations based on information enhancement and arctangent rank approximation

IEARACDA: Predicting circRNA-disease associations based on i...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Pang, Shanchen Song, Zheqi Liu, Tiyao Wu, Wenhao Zhang, Yuanyuan Wang, Shudong College of Computer Science and Technology Qingdao Institute of Software Qingdao China Qingdao University of Technology School of Information and Control Engineering Qingdao China

ISBN: (纸本)9798350386226

Circular RNAs (circRNAs) are non-coding RNA molecules that play a significant role in cell regulation and disease occurrence. In recent years, the use of computational methods to predict circRNAs associated with diseases has become a research focus. However, these methods are often constrained by the noise interference and an insufficient exploration of the underlying information in known associations. Therefore, this paper proposes an information enhancement and arctangent rank approximation based method to predict potential circRNA-disease associations (IEARACDA). Firstly, information enhancement methods are used to make circRNA and disease similarity information more complete and to reduce the sparsity of known association. Subsequently, the arctangent rank approximation method is employed to mitigate the potential bias issues that may arise from the nuclear norm, and optimization is carried out using the inexact augmented Lagrange multiplier (IALM) method. Finally, potential associations are predicted through heterogeneous graph inference method. The experimental results demonstrate that IEARACDA exhibits superior performance compared to existing methods. Furthermore, case studies for hepatocellular carcinoma and lung cancer provide additional confirmation of the accuracy and practical significance of the model predictions. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

An Improved SlowFast Model for Violence Detection 4

An Improved SlowFast Model for Violence Detection

引用

4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024

作者： Huang, Qinxue Zhang, Chaolong Xu, Yuanping Wang, Weiye Xu, Zhijie Guo, Benjun Jin, Jin Kong, Chao School of Software Engineering Chengdu University of Information Technology Chengdu China School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou China

ISBN: (纸本)9798331541729

As social safety concerns become increasingly prominent, the importance of violence detection has become increasingly significant. Accurately identifying violent behavior helps facilitate timely interventions, reducing harm and losses, thereby enhancing public safety. To minimize the interference from irrelevant actions (e.g., those from spectators and uninvolved individuals) during violence detection, this study proposes an improved SlowFast method that enhances the robustness of the model by modifying the network structure of the Slow Pathway and lateral connections. In the Slow Pathway, the original residual block is replaced with an SE-Res residual block, which strengthens the weighting of channel importance, making the model more stable in complex scenarios. The lateral connections are improved by integrating a 3D-Convolutional Block Attention Module(3DCBAM), enhancing feature fusion and increasing the model's sensitivity to key features across different temporal scales. Furthermore, to address the class imbalance issue within the dataset, the Focal Loss function has been modified, effectively improving the performance of each class. The improved model demonstrates excellent performance in violence detection tasks, achieving an accuracy of 96.67%, which is a 1.12% improvement over the classical model. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Convolutional Dual-Channel Transformer Framework for Efficient Part Segmentation of Point Cloud Data 4

A Lightweight Convolutional Dual-Channel Transformer Framewo...

引用

4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024

作者： Li, Jianhua Xu, Yuanping Zhang, Chaolong Kong, Chao Jin, Jin Wang, Weiye Xu, Zhijie Guo, Benjun Tang, Dan School of Software Engineering Chengdu University of Information Technology Chengdu China School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou China

ISBN: (纸本)9798331541729

In recent years, transformer-based models have made significant breakthroughs in natural language processing and computer vision. However, these models have encountered challenges when dealing with point cloud data because the irregular and disordered structure of point cloud data leads to a huge computational and memory burden. To address this problem, this paper proposes a Multidimensional Convolution-Dual Channel Transformer Network for efficient processing of point cloud data. The MCDTN framework consists of two branches: the main channel enhances the modeling of cross-channel features through dynamic attention to optimize feature representation;the auxiliary channel further improves fine-grained segmentation capabilities through encoders, multi-scale information interaction, and spatial attention. Experimental results show that MCDTN performs excellently in shape classification and part segmentation tasks, effectively reducing computational costs. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Energy Oriented Three-Tier Computation Offloading Scheme in Maritime Edge Computing Network

引用

IEEE Transactions on Vehicular technology 2025年第5期74卷 8126-8140页

作者： Zhang, Hongxia Xi, Shiyu Shang, Bodong Zhang, Peiying Wu, Sheng Jiang, Chunxiao Qingdao Institute of Software College of Computer Science and Technology Qingdao266580 China Eastern Institute of Technology Eastern Institute for Advanced Study Ningbo315200 China Beijing University of Posts and Telecommunications School of Information and Communication Engineering Beijing100876 China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100084 China

With the development of maritime continuing to grow, large-scale maritime wireless devices (MWDs) are being deployed for various maritime applications. The rapid development of maritime Internet of Things (IoT) and growing demand for these applications have led to an increasing number of computation-intensive and resource-sensitive tasks. Considering the limited computing capacity and energy of MWDs, it is challenging to transmit and process massive maritime computing tasks in an energy efficient manner. In this paper, we propose a three-tier maritime edge computing system in which low earth orbit (LEO) satellite and offshore base station (OBS) support to provide communication and computing services for MWDs. The system optimizes association variable, task partitioning, transmission power, and computing resource allocation to reduce system energy consumption under latency constraints. The optimization problem is formulated as a mixed integer non-linear programming (MINLP) optimization problem. We decompose the original problem into four subproblems and design algorithms to solve them. Firstly, the association variable optimization subproblem is solved by slack variable method. Then, we adopt quadratic transformation and design a difference of convex algorithm to solve transmission power optimization subproblem. Further, task partitioning subproblem is solved by obtaining upper and lower bounds of offloading task size by strict deduction, and then solved by the standard convex method. Finally, Lagrangian dual method is utilized to deal with joint computing resource optimization subproblem of LEO satellite and OBS. In simulation results, the proposed algorithm saves 39.3% of system energy consumption compared to benchmark schemes. © 1967-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Enhancing Classification Algorithm Recommendation in Automated Machine Learning: A Meta-Learning Approach Using Multivariate Sparse Group Lasso

引用

Computer Modeling in engineering & Sciences 2025年第2期142卷 1611-1636页

作者： Irfan Khan Xianchao Zhang Ramesh Kumar Ayyasamy Saadat M.Alhashmi Azizur Rahim School of Software Dalian University of TechnologyDalian116620China Faculty of Information and Communication Technology Universiti Tunku Abdul RahmanKampar31900Malaysia College of Computing and Informatics University of SharjahSharjah27272United Arab Emirates Department of Computer Systems Engineering University of Engineering and Applied SciencesSwat19200Pakistan

The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource *** Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification *** paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these *** method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature *** Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization *** validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.

关键词： Meta-learning machine learning automated machine learning classification meta-features

来源：评论

学校读者我要写书评

暂无评论

An Improved PointNet++ Based Method for 3D Point Cloud Geometric Features Segmentation in Mechanical Parts 18

An Improved PointNet++ Based Method for 3D Point Cloud Geome...

引用

18th CIRP Conference on Computer Aided Tolerancing, CAT 2024

作者： Zhang, Peng Kong, Chao Xu, Yuanping Zhang, Chaolong Jin, Jin Li, Tukun Jiang, Xiangqian Tang, Dan School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing and Engineering University of Huddersfield Queensgate Huddersfield United Kingdom

The extraction of geometric features such as holes, arcs, and surfaces of mechanical parts is crucial for quality control. The existing methods for geometrical feature segmentations on 3D point clouds still have limitations, especially for simultaneously extracting multiple types of geometric features from comprehensive workpieces. To this end, this study investigates segmentation methods that take 3D point cloud datasets of mechanical parts as inputs, and employs an improved PointNet++ deep learning model to solve this extraction difficulty. Firstly, the Set Abstraction module in PointNet++ was modified by incorporating Self-Attention mechanisms to increase interactivity and global correlation among data points. Then, the local feature extraction Multilayer Perceptron (MLP) from PointNet-Transformer was integrated to enhance the feature extraction accuracy. Due to the inherent class imbalance issue, the Focal Tversky Loss is employed as the loss function to ensure that geometric features with relatively lower proportions can be fully trained. Finally, the Statistical filtering algorithm is utilized to mitigate noise and attenuate subtle irregularities, such that the smoothness of geometric features can be substantially enhanced. The experimental results demonstrate that the proposed model achieves an accuracy of 86.6% on geometric feature segmentations and a mean Intersection over Union (mIoU) of 0.84. The comparison with the original PointNet++ proves that the proposed method can improve accuracy and mIoU by 3.7% and 0.03 respectively. © 2024 The Authors. Published by Elsevier B.V.

关键词： Geometry

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：