期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到995篇文章
< 1 2 … 50 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
A high-performance parallel algorithm based on problem independent machine learning(PIML)for large-scale topology optimization 认领 引用
1
作者 Xinyu Ma Mengcheng Huang +4 位作者 Zongliang Du Yilin Guo Chang Liu Yue Mei Xu Guo 《Acta Mechanica Sinica》 SCIE EI CAS CSCD 2026年第3期197-213,共17页
Although supplying extensive design space,the curse of dimensionality restricts the widespread application of largescale topology optimization in practical engineering.Various acceleration techniques have been integra... Although supplying extensive design space,the curse of dimensionality restricts the widespread application of largescale topology optimization in practical engineering.Various acceleration techniques have been integrated with topology optimization,achieving significant attention and progress in large-scale problems.This work aims to investigate how much benefit can be obtained by combining parallel computing and machine learning techniques to enhance the efficiency of large-scale topology optimization algorithms.Accordingly,a parallel problem independent machine learning(PIML)-enhanced topology optimization method is proposed.The PIML model substantially reduces the dimension of the condensed stiffness matrix and its computational cost,and parallel computing reduces the workload per process and enables the application of a parallel multigrid solver.Besides,several techniques,such as matrix-free implementation,direct condensation of uniform coarse elements,and adjusting computational resource limits,have been developed to enhance computational efficiency.The weak scaling efficiency,strong scaling speedup,and maximum achievable efficiency of the proposed method are validated across multiple numerical examples,showing significant improvement in the tractable problem size and solution efficiency compared to traditional topology optimization algorithms. 展开更多
关键词 Topology optimization Large-scale Problem independent machine learning(PIML) Parallel computing
暂未订购 下载PDF
A Deep Reinforcement Learning-Based Partitioning Method for Power System Parallel Restoration 认领 引用
2
作者 Changcheng Li Weimeng Chang +1 位作者 Dahai Zhang Jinghan He 《Energy Engineering》 EI 2026年第1期243-264,共22页
Effective partitioning is crucial for enabling parallel restoration of power systems after blackouts.This paper proposes a novel partitioning method based on deep reinforcement learning.First,the partitioning decision... Effective partitioning is crucial for enabling parallel restoration of power systems after blackouts.This paper proposes a novel partitioning method based on deep reinforcement learning.First,the partitioning decision process is formulated as a Markov decision process(MDP)model to maximize the modularity.Corresponding key partitioning constraints on parallel restoration are considered.Second,based on the partitioning objective and constraints,the reward function of the partitioning MDP model is set by adopting a relative deviation normalization scheme to reduce mutual interference between the reward and penalty in the reward function.The soft bonus scaling mechanism is introduced to mitigate overestimation caused by abrupt jumps in the reward.Then,the deep Q network method is applied to solve the partitioning MDP model and generate partitioning schemes.Two experience replay buffers are employed to speed up the training process of the method.Finally,case studies on the IEEE 39-bus test system demonstrate that the proposed method can generate a high-modularity partitioning result that meets all key partitioning constraints,thereby improving the parallelism and reliability of the restoration process.Moreover,simulation results demonstrate that an appropriate discount factor is crucial for ensuring both the convergence speed and the stability of the partitioning training. 展开更多
关键词 Partitioning method parallel restoration deep reinforcement learning experience replay buffer partitioning modularity
暂未订购 下载PDF
VulSCP: Automated Code Vulnerability Detection via Sequential Convolution and Parallel Attention Mechanism 认领 引用
3
作者 Zhe Wang Yu Yan +3 位作者 Junqi Tong Yijun Lin Dechun Yin Xiaoliang Zhao 《Computers, Materials & Continua》 SCIE EI 2026年第8期1057-1081,共25页
As software applications grow increasingly large and complex,traditional code vulnerability detection methods struggle with performance and efficiency.Although code visualization-based algorithms have demonstrated eff... As software applications grow increasingly large and complex,traditional code vulnerability detection methods struggle with performance and efficiency.Although code visualization-based algorithms have demonstrated effectiveness in capturing sparse features and complex workflows in large-scale source code,their capacity to extract global semantic information and intricate long-range dependencies remains limited.Recent large language model(LLM)-based approaches have shown promising accuracy by leveraging rich contextual information,but their high computational cost often limits practical efficiency.To address these challenges,we propose VulSCP,a new framework that integrates sequential convolution with a parallel attention mechanism.Specifically,VulSCP first constructs a semantically weighted graph from the source code,then employs sequential convolution to extract local vulnerability-related features,and finally enhances the global feature representation through parallel attention.Experimental results on large-scale C/C++function-level datasets show that VulSCP achieves an accuracy of 85.14%and a false positive rate of 17.25%,outperforming the best baseline in accuracy by 1.73 percentage points and reducing the false positive rate by 3.38 percentage points.Moreover,while maintaining high detection accuracy,VulSCP achieves a low average inference time of 1.89 s per sample,showing favorable efficiency compared with the evaluated LLM-based methods.These results suggest that VulSCP is a promising approach for vulnerability detection in large and complex software systems,offering a favorable balance between accuracy and efficiency.The source code of VulSCP is publicly available at http://gffzz188fe103f8f1460as5ofobvx9p6wu66v9.ffgz.tsg.suse.edu.cn/Hwzx-ZeL/VulSCP. 展开更多
关键词 Code vulnerability detection sequential convolution parallel attention program dependency graph semantic graph representation
暂未订购 下载PDF
Multi-Objective Parallel Human-machine Steering Coordination Control Strategy of Intelligent Vehicles Path Tracking Based on Deep Reinforcement Learning 认领 引用 被引量：1
4
作者 Hongbo Wang Lizhao Feng +2 位作者 Shaohua Li Wuwei Chen Juntao Zhou 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2025年第3期393-411,共19页
In the parallel steering coordination control strategy for path tracking,it is difficult to match the current driver steering model using the fixed parameters with the actual driver,and the designed steering coordinat... In the parallel steering coordination control strategy for path tracking,it is difficult to match the current driver steering model using the fixed parameters with the actual driver,and the designed steering coordination control strategy under a single objective and simple conditions is difficult to adapt to the multi-dimensional state variables’input.In this paper,we propose a deep reinforcement learning algorithm-based multi-objective parallel human-machine steering coordination strategy for path tracking considering driver misoperation and external disturbance.Firstly,the driver steering mathematical model is constructed based on the driver preview characteristics and steering delay response,and the driver characteristic parameters are fitted after collecting the actual driver driving data.Secondly,considering that the vehicle is susceptible to the influence of external disturbances during the driving process,the Tube MPC(Tube Model Predictive Control)based path tracking steering controller is designed based on the vehicle system dynamics error model.After verifying that the driver steering model meets the driver steering operation characteristics,DQN(Deep Q-network),DDPG(Deep Deterministic Policy Gradient)and TD3(Twin Delayed Deep Deterministic Policy Gradient)deep reinforcement learning algorithms are utilized to design a multi-objective parallel steering coordination strategy which satisfies the multi-dimensional state variables’input of the vehicle.Finally,the tracking accuracy,lateral safety,human-machine conflict and driver steering load evaluation index are designed in different driver operation states and different road environments,and the performance of the parallel steering coordination control strategies with different deep reinforcement learning algorithms and fuzzy algorithms are compared by simulations and hardware in the loop experiments.The results show that the parallel steering collaborative strategy based on a deep reinforcement learning algorithm can more effectively assist the driver in tracking the target path under lateral wind interference and driver misoperation,and the TD3-based coordination control strategy has better overall performance. 展开更多
关键词 Path tracking Human-machine co-driving Parallel steering coordination Deep reinforcement learning
暂未订购 下载PDF
Fast Parallel Magnetic Resonance Imaging Reconstruction Based on Sparsifying Transform Learning and Structured Low-Rank Model 认领 引用
5
作者 DUAN Jizhong XU Yuhan HUANG Huan 《Journal of Shanghai Jiaotong university(Science)》 EI 2025年第3期499-509,共11页
The structured low-rank model for parallel magnetic resonance(MR)imaging can efficiently reconstruct MR images with limited auto-calibration signals.To improve the reconstruction quality of MR images,we integrate the ... The structured low-rank model for parallel magnetic resonance(MR)imaging can efficiently reconstruct MR images with limited auto-calibration signals.To improve the reconstruction quality of MR images,we integrate the joint sparsity and sparsifying transform learning(JTL)into the simultaneous auto-calibrating and k-space estimation(SAKE)structured low-rank model,named JTLSAKE.The alternate direction method of multipliers is exploited to solve the resulting optimization problem,and the optimized gradient method is used to improve the convergence speed.In addition,a graphics processing unit is used to accelerate the proposed algorithm.The experimental results on four in vivo human datasets demonstrate that the reconstruction quality of the proposed algorithm is comparable to that of JTL-based low-rank modeling of local k-space neighborhoods with parallel imaging(JTL-PLORAKS),and the proposed algorithm is 46 times faster than the JTL-PLORAKS,requiring only 4 s to reconstruct a 200×200 pixels MR image with 8 channels. 展开更多
关键词 structured low-rank parallel magnetic resonance imaging sparsifying transform learning alternating direction method of multipliers optimized gradient method
暂未订购 下载PDF
Improved Sensitivity Encoding Parallel Magnetic Resonance Imaging Reconstruction Algorithm Based on Efficient Sum of Outer Products Dictionary Learning 认领 引用
6
作者 DUAN Jizhong SU Yan 《Journal of Shanghai Jiaotong university(Science)》 EI 2025年第3期561-571,共11页
Sensitivity encoding(SENSE)is a parallel magnetic resonance imaging(MRI)reconstruction model by utilizing the sensitivity information of receiver coils to achieve image reconstruction.The existing SENSE-based reconstr... Sensitivity encoding(SENSE)is a parallel magnetic resonance imaging(MRI)reconstruction model by utilizing the sensitivity information of receiver coils to achieve image reconstruction.The existing SENSE-based reconstruction algorithms usually used nonadaptive sparsifying transforms,resulting in a limited reconstruction accuracy.Therefore,we proposed a new model for accurate parallel MRI reconstruction by combining the L0 norm regularization term based on the efficient sum of outer products dictionary learning(SOUPDIL)with the SENSE model,called SOUPDIL-SENSE.The SOUPDIL-SENSE model is mainly solved by utilizing the variable splitting and alternating direction method of multipliers techniques.The experimental results on four human datasets show that the proposed algorithm effectively promotes the image sparsity,eliminates the noise and artifacts of the reconstructed images,and improves the reconstruction accuracy. 展开更多
关键词 parallel magnetic resonance imaging(MRI) sensitivity encoding(SENSE) efficient sum of outer products dictionary learning(SOUPDIL) alternating direction method of multipliers
暂未订购 下载PDF
Advancements and theoretical foundations of cable-driven parallel robots:A comprehensive overview 认领 引用
7
作者 Kamran Joyo Han Yuan +2 位作者 Jun Wu Wenfu Xu Honghao Yue 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2026年第3期280-305,共26页
Parallel robotic mechanisms using cables instead of rigid limbs are termed cable-driven parallel robots(CDPRs).Electric motors and pulley mechanisms actuate cables to provide motion for an end-effector in a cable robo... Parallel robotic mechanisms using cables instead of rigid limbs are termed cable-driven parallel robots(CDPRs).Electric motors and pulley mechanisms actuate cables to provide motion for an end-effector in a cable robot.Consequently,CDPRs have emerged as indispensable tools across a spectrum of industrial and technological domains,including astronomy,aerospace,logistics,simulators,and rehabilitation.Their inherent compatibility with the evolving concept of rigid-flexible fusion places CDPRs at the forefront of cutting-edge robotics research.This comprehensive paper aims to consolidate the core theories and advancements underpinning CDPRs,en-compassing key aspects such as configuration design,cable-force distribution,workspace and stiffness analysis,performance evaluation,optimisation techniques,and motion control.We provide in-depth insights into kine-matic modelling,workspace exploration,and cable-force solutions.Furthermore,the paper delves into the in-tricacies of stiffness and dynamic modelling,presenting a range of analytical methods to elucidate their effects on CDPR performance.Addressing reliability concerns and developing a unified control framework are identified as essential in ensuring the practical deployment of CDPRs in real-world scenarios.This research paper offers a comprehensive overview of the theories and advancements in CDPRs,identifying critical areas for further re-search and development to unlock the full potential of these versatile and high-performance robotic systems. 展开更多
关键词 Cable-driven parallel robots Optimisation Path generation Statics Machine learning
暂未订购 下载PDF
Multi-Head Attention Enhanced Parallel Dilated Convolution and Residual Learning for Network Traffic Anomaly Detection 认领 引用 被引量：2
8
作者 Guorong Qi Jian Mao +2 位作者 Kai Huang Zhengxian You Jinliang Lin 《Computers, Materials & Continua》 SCIE EI 2025年第2期2159-2176,共18页
Abnormal network traffic, as a frequent security risk, requires a series of techniques to categorize and detect it. Existing network traffic anomaly detection still faces challenges: the inability to fully extract loc... Abnormal network traffic, as a frequent security risk, requires a series of techniques to categorize and detect it. Existing network traffic anomaly detection still faces challenges: the inability to fully extract local and global features, as well as the lack of effective mechanisms to capture complex interactions between features;Additionally, when increasing the receptive field to obtain deeper feature representations, the reliance on increasing network depth leads to a significant increase in computational resource consumption, affecting the efficiency and performance of detection. Based on these issues, firstly, this paper proposes a network traffic anomaly detection model based on parallel dilated convolution and residual learning (Res-PDC). To better explore the interactive relationships between features, the traffic samples are converted into two-dimensional matrix. A module combining parallel dilated convolutions and residual learning (res-pdc) was designed to extract local and global features of traffic at different scales. By utilizing res-pdc modules with different dilation rates, we can effectively capture spatial features at different scales and explore feature dependencies spanning wider regions without increasing computational resources. Secondly, to focus and integrate the information in different feature subspaces, further enhance and extract the interactions among the features, multi-head attention is added to Res-PDC, resulting in the final model: multi-head attention enhanced parallel dilated convolution and residual learning (MHA-Res-PDC) for network traffic anomaly detection. Finally, comparisons with other machine learning and deep learning algorithms are conducted on the NSL-KDD and CIC-IDS-2018 datasets. The experimental results demonstrate that the proposed method in this paper can effectively improve the detection performance. 展开更多
关键词 Network traffic anomaly detection multi-head attention parallel dilated convolution residual learning
暂未订购 下载PDF
Terminal Multitask Parallel Offloading Algorithm Based on Deep Reinforcement Learning 认领 引用
9
作者 Zhang Lincong Li Yang +2 位作者 Zhao Weinan Liu Xiangyu Guo Lei 《China Communications》 SCIE EI CSCD 2025年第7期30-43,共14页
The advent of the internet-of-everything era has led to the increased use of mobile edge computing.The rise of artificial intelligence has provided many possibilities for the low-latency task-offloading demands of use... The advent of the internet-of-everything era has led to the increased use of mobile edge computing.The rise of artificial intelligence has provided many possibilities for the low-latency task-offloading demands of users,but existing technologies rigidly assume that there is only one task to be offloaded in each time slot at the terminal.In practical scenarios,there are often numerous computing tasks to be executed at the terminal,leading to a cumulative delay for subsequent task offloading.Therefore,the efficient processing of multiple computing tasks on the terminal has become highly challenging.To address the lowlatency offloading requirements for multiple computational tasks on terminal devices,we propose a terminal multitask parallel offloading algorithm based on deep reinforcement learning.Specifically,we first establish a mobile edge computing system model consisting of a single edge server and multiple terminal users.We then model the task offloading decision problem as a Markov decision process,and solve this problem using the Dueling Deep-Q Network algorithm to obtain the optimal offloading strategy.Experimental results demonstrate that,under the same constraints,our proposed algorithm reduces the average system latency. 展开更多
关键词 deep reinforcement learning mobile edge computing multitask parallel offloading task offloading
暂未订购 下载PDF
Structural damage detection of shear frame model using parallel physics-informed neural network 认领 引用
10
作者 Surendra BANIYA Damodar MAITY 《ENGINEERING Structure and Civil Engineering》 SCIE EI CAS CSCD 2026年第1期15-35,共21页
Conventional numerical and data-driven methods for structural damage identification often struggle with problems such as poor generalization,sensitivity to noise,and limited accuracy in quantifying and localizing dama... Conventional numerical and data-driven methods for structural damage identification often struggle with problems such as poor generalization,sensitivity to noise,and limited accuracy in quantifying and localizing damage,especially under real-world uncertainties.This study introduces a novel parallel physics-informed neural network framework that addresses these limitations by integrating physical constraints directly into the learning process and employing a nondimensionalized formulation of the governing equations to improve training stability and convergence.The method is applied to simultaneously identify the location and severity of damage in numerical and experimental shear frame model using measured acceleration responses from the structure.In the numerical case,different damage scenarios are analyzed under white Gaussian noise and real earthquake excitations,across various noise levels.The model demonstrates high accuracy in identifying damaged locations even under high noise conditions,and outperforms traditional response surface methods by reducing false positive cases.Experimental validation using open-source shear frame data further confirms the model’s effectiveness.Despite the presence of modeling uncertainty and measurement,the model accurately identifies damage locations and estimates their severity in agreement with experimental observations.Overall,the model proves its efficacy in predicting damage locations and assessing the severity levels even under uncertainty and noise levels. 展开更多
关键词 structural health monitoring damage detection parallel physics-informed neural network deep learning
暂未订购 下载PDF
Online Sequential Double Parallel Extreme Learning Machine for Classifications 认领 引用
11
作者 Mingchen YAO Chao ZHANG Wei WU 《Journal of Mathematical Research with Applications》 CSCD 2016年第5期621-630,共10页
Double parallel forward neural network （DPFNN） model is a mixture structure of single-layer perception and single-hidden-layer forward neural network （SLFN）. In this paper, by making use of the idea of online sequ... Double parallel forward neural network （DPFNN） model is a mixture structure of single-layer perception and single-hidden-layer forward neural network （SLFN）. In this paper, by making use of the idea of online sequential extreme learning machine （OS-ELM） on DPFNN, we derive the online sequential double parallel extreme learning machine algorithm （OS-DPELM）. Compared to other similar algorithms, our algorithms can achieve approximate learning performance with fewer numbers of hidden units, as well as the parameters to be determined. The experimental results show that the proposed algorithm has good generalization performance for real world classification problems, and thus can be a necessary and beneficial complement to OS-ELM. 展开更多
关键词 double parallel forward neural network perception extreme learning machine classification problems
暂未订购 下载PDF
Parallel Reinforcement Learning:A Framework and Case Study 认领 引用 被引量：12
12
作者 Teng Liu Bin Tian +3 位作者 Yunfeng Ai Li Li Dongpu Cao Fei-Yue Wang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2018年第4期827-835,共9页
In this paper, a new machine learning framework is developed for complex system control, called parallel reinforcement learning. To overcome data deficiency of current data-driven algorithms, a parallel system is buil... In this paper, a new machine learning framework is developed for complex system control, called parallel reinforcement learning. To overcome data deficiency of current data-driven algorithms, a parallel system is built to improve complex learning system by self-guidance. Based on the Markov chain(MC) theory, we combine the transfer learning, predictive learning, deep learning and reinforcement learning to tackle the data and action processes and to express the knowledge. Parallel reinforcement learning framework is formulated and several case studies for real-world problems are finally introduced. 展开更多
关键词 Deep learning machine learning parallel reinforcement learning parallel system predictive learning transfer learning
暂未订购 下载PDF
Parallel Learning:a Perspective and a Framework 认领 引用 被引量：60
13
作者 Li Li Yilun Lin +1 位作者 Nanning Zheng Fei-Yue Wang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2017年第3期389-395,共7页
The development of machine learning in complex system is hindered by two problems nowadays.The first problem is the inefficiency of exploration in state and action space,which leads to the data-hungry of some state-of... The development of machine learning in complex system is hindered by two problems nowadays.The first problem is the inefficiency of exploration in state and action space,which leads to the data-hungry of some state-of-art data-driven algorithm.The second problem is the lack of a general theory which can be used to analyze and implement a complex learning system.In this paper,we proposed a general methods that can address both two issues.We combine the concepts of descriptive learning,predictive learning,and prescriptive learning into a uniform framework,so as to build a parallel system allowing learning system improved by self-boosting.Formulating a new perspective of data,knowledge and action,we provide a new methodology called parallel learning to design machine learning system for real-world problems. 展开更多
关键词 Descriptive learning machine learning parallel learning parallel systems predictive learning prescriptive learning
暂未订购 下载PDF
Parallel Learning:Overview and Perspective for Computational Learning Across Syn2Real and Sim2Real 认领 引用 被引量：29
14
作者 Qinghai Miao Yisheng Lv +2 位作者 Min Huang Xiao Wang Fei-Yue Wang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2023年第3期603-631,共29页
The virtual-to-real paradigm,i.e.,training models on virtual data and then applying them to solve real-world problems,has attracted more and more attention from various domains by successfully alleviating the data sho... The virtual-to-real paradigm,i.e.,training models on virtual data and then applying them to solve real-world problems,has attracted more and more attention from various domains by successfully alleviating the data shortage problem in machine learning.To summarize the advances in recent years,this survey comprehensively reviews the literature,from the viewport of parallel intelligence.First,an extended parallel learning framework is proposed to cover main domains including computer vision,natural language processing,robotics,and autonomous driving.Second,a multi-dimensional taxonomy is designed to organize the literature in a hierarchical structure.Third,the related virtual-toreal works are analyzed and compared according to the three principles of parallel learning known as description,prediction,and prescription,which cover the methods for constructing virtual worlds,generating labeled data,domain transferring,model training and testing,as well as optimizing the strategies to guide the task-oriented data generator for better learning performance.Key issues remained in virtual-to-real are discussed.Furthermore,the future research directions from the viewpoint of parallel learning are suggested. 展开更多
关键词 Machine learning parallel learning parallel systems sim-to-real syn-to-real virtual-to-real
暂未订购 下载PDF
Parallel Reinforcement Learning-Based Energy Efficiency Improvement for a Cyber-Physical System 认领 引用 被引量：18
15
作者 Teng Liu Bin Tian +1 位作者 Yunfeng Ai Fei-Yue Wang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2020年第2期617-626,共10页
As a complex and critical cyber-physical system(CPS),the hybrid electric powertrain is significant to mitigate air pollution and improve fuel economy.Energy management strategy(EMS)is playing a key role to improve the... As a complex and critical cyber-physical system(CPS),the hybrid electric powertrain is significant to mitigate air pollution and improve fuel economy.Energy management strategy(EMS)is playing a key role to improve the energy efficiency of this CPS.This paper presents a novel bidirectional long shortterm memory(LSTM)network based parallel reinforcement learning(PRL)approach to construct EMS for a hybrid tracked vehicle(HTV).This method contains two levels.The high-level establishes a parallel system first,which includes a real powertrain system and an artificial system.Then,the synthesized data from this parallel system is trained by a bidirectional LSTM network.The lower-level determines the optimal EMS using the trained action state function in the model-free reinforcement learning(RL)framework.PRL is a fully data-driven and learning-enabled approach that does not depend on any prediction and predefined rules.Finally,real vehicle testing is implemented and relevant experiment data is collected and calibrated.Experimental results validate that the proposed EMS can achieve considerable energy efficiency improvement by comparing with the conventional RL approach and deep RL. 展开更多
关键词 Bidirectional long short-term memory(LSTM)network cyber-physical system(CPS) energy management parallel system reinforcement learning(RL)
暂未订购 下载PDF
Autonomous air combat decision-making of UAV based on parallel self-play reinforcement learning 认领 引用 被引量：17
16
作者 Bo Li Jingyi Huang +4 位作者 Shuangxia Bai Zhigang Gan Shiyang Liang Neretin Evgeny Shouwen Yao 《CAAI Transactions on Intelligence Technology》 SCIE EI 2023年第1期64-81,共18页
Aiming at addressing the problem of manoeuvring decision-making in UAV air combat,this study establishes a one-to-one air combat model,defines missile attack areas,and uses the non-deterministic policy Soft-Actor-Crit... Aiming at addressing the problem of manoeuvring decision-making in UAV air combat,this study establishes a one-to-one air combat model,defines missile attack areas,and uses the non-deterministic policy Soft-Actor-Critic(SAC)algorithm in deep reinforcement learning to construct a decision model to realize the manoeuvring process.At the same time,the complexity of the proposed algorithm is calculated,and the stability of the closed-loop system of air combat decision-making controlled by neural network is analysed by the Lyapunov function.This study defines the UAV air combat process as a gaming process and proposes a Parallel Self-Play training SAC algorithm(PSP-SAC)to improve the generalisation performance of UAV control decisions.Simulation results have shown that the proposed algorithm can realize sample sharing and policy sharing in multiple combat environments and can significantly improve the generalisation ability of the model compared to independent training. 展开更多
关键词 air combat decision deep reinforcement learning parallel self-play SAC algorithm UAV
暂未订购 下载PDF
Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis 认领 引用 被引量：6
17
作者 Yesheng Xu Ming Kong +7 位作者 Wenjia Xie Runping Duan Zhengqing Fang Yuxiao Lin Qiang Zhu Siliang Tang Fei Wu Yu-Feng Yao 《Engineering》 SCIE EI CAS CSCD 2021年第7期1002-1010,共9页
Infectious keratitis is the most common condition of corneal diseases in which a pathogen grows in the cornea leading to inflammation and destruction of the corneal tissues.Infectious keratitis is a medical emergency ... Infectious keratitis is the most common condition of corneal diseases in which a pathogen grows in the cornea leading to inflammation and destruction of the corneal tissues.Infectious keratitis is a medical emergency for which a rapid and accurate diagnosis is needed to ensure prompt and precise treatment to halt the disease progression and to limit the extent of corneal damage;otherwise,it may develop a sight-threatening and even eye-globe-threatening condition.In this paper,we propose a sequentiallevel deep model to effectively discriminate infectious corneal disease via the classification of clinical images.In this approach,we devise an appropriate mechanism to preserve the spatial structures of clinical images and disentangle the informative features for clinical image classification of infectious keratitis.In a comparison,the performance of the proposed sequential-level deep model achieved 80%diagnostic accuracy,far better than the 49.27%±11.5%diagnostic accuracy achieved by 421 ophthalmologists over 120 test images. 展开更多
关键词 Deep learning Corneal disease Sequential features Machine learning Long short-term memory
暂未订购 下载PDF
A deep learning-based method for segmentation and quantitative characterization of microstructures in weathering steel from sequential scanning electron microscope images 认领 引用 被引量：3
18
作者 Bing Han Wei-hao Wan +3 位作者 Dan-dan Sun Cai-chang Dong Lei Zhao Hai-zhou Wang 《Journal of Iron and Steel Research International》 SCIE EI CAS CSCD 2022年第5期836-845,共10页
Microstructural classification is typically done manually by human experts,which gives rise to uncertainties due to subjectivity and reduces the overall efficiency.A high-throughput characterization is proposed based ... Microstructural classification is typically done manually by human experts,which gives rise to uncertainties due to subjectivity and reduces the overall efficiency.A high-throughput characterization is proposed based on deep learning,rapid acquisition technology,and mathematical statistics for the recognition,segmentation,and quantification of microstructure in weathering steel.The segmentation results showed that this method was accurate and efficient,and the segmentation of inclusions and pearlite phase achieved accuracy of 89.95%and 90.86%,respectively.The time required for batch processing by MIPAR software involving thresholding segmentation,morphological processing,and small area deletion was 1.05 s for a single image.By comparison,our system required only 0.102 s,which is ten times faster than the commercial software.The quantification results were extracted from large volumes of sequential image data(150 mm2,62,216 images,1024×1024 pixels),which ensure comprehensive statistics.Microstructure information,such as three-dimensional density distribution and the frequency of the minimum spatial distance of inclusions on the sample surface of 150 mm2,were quantified by extracting the coordinates and sizes of individual features.A refined characterization method for two-dimensional structures and spatial information that is unattainable when performing manually or with software is provided.That will be useful for understanding properties or behaviors of weathering steel,and reducing the resort to physical testing. 展开更多
关键词 Deep learning High-throughput Microstructure Sequential image Rapid acquisition Quantitative characterization Segmentation
暂未订购 下载PDF
Efficient and High-quality Recommendations via Momentum-incorporated Parallel Stochastic Gradient Descent-Based Learning 认领 引用 被引量：10
19
作者 Xin Luo Wen Qin +2 位作者 Ani Dong Khaled Sedraoui MengChu Zhou 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2021年第2期402-411,共10页
A recommender system(RS)relying on latent factor analysis usually adopts stochastic gradient descent(SGD)as its learning algorithm.However,owing to its serial mechanism,an SGD algorithm suffers from low efficiency and... A recommender system(RS)relying on latent factor analysis usually adopts stochastic gradient descent(SGD)as its learning algorithm.However,owing to its serial mechanism,an SGD algorithm suffers from low efficiency and scalability when handling large-scale industrial problems.Aiming at addressing this issue,this study proposes a momentum-incorporated parallel stochastic gradient descent(MPSGD)algorithm,whose main idea is two-fold:a)implementing parallelization via a novel datasplitting strategy,and b)accelerating convergence rate by integrating momentum effects into its training process.With it,an MPSGD-based latent factor(MLF)model is achieved,which is capable of performing efficient and high-quality recommendations.Experimental results on four high-dimensional and sparse matrices generated by industrial RS indicate that owing to an MPSGD algorithm,an MLF model outperforms the existing state-of-the-art ones in both computational efficiency and scalability. 展开更多
关键词 Big data industrial application industrial data latent factor analysis machine learning parallel algorithm recommender system(RS) stochastic gradient descent(SGD)
暂未订购 下载PDF
Collaborative Clustering Parallel Reinforcement Learning for Edge-Cloud Digital Twins Manufacturing System 认领 引用 被引量：4
20
作者 Fan Yang Tao Feng +2 位作者 Fangmin Xu Huiwen Jiang Chenglin Zhao 《China Communications》 SCIE CSCD 2022年第8期138-148,共11页
To realize high-accuracy physical-cyber digital twin(DT)mapping in a manufacturing system,a huge amount of data need to be collected and analyzed in real-time.Traditional DTs systems are deployed in cloud or edge serv... To realize high-accuracy physical-cyber digital twin(DT)mapping in a manufacturing system,a huge amount of data need to be collected and analyzed in real-time.Traditional DTs systems are deployed in cloud or edge servers independently,whilst it is hard to apply in real production systems due to the high interaction or execution delay.This results in a low consistency in the temporal dimension of the physical-cyber model.In this work,we propose a novel efficient edge-cloud DT manufacturing system,which is inspired by resource scheduling technology.Specifically,an edge-cloud collaborative DTs system deployment architecture is first constructed.Then,deterministic and uncertainty optimization adaptive strategies are presented to choose a more powerful server for running DT-based applications.We model the adaptive optimization problems as dynamic programming problems and propose a novel collaborative clustering parallel Q-learning(CCPQL)algorithm and prediction-based CCPQL to solve the problems.The proposed approach reduces the total delay with a higher convergence rate.Numerical simulation results are provided to validate the approach,which would have great potential in dynamic and complex industrial internet environments. 展开更多
关键词 edge-cloud collaboration digital twins job shop scheduling parallel reinforcement learning
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 50 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈