检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Zhang, Guohao Wen, Shuhuan Li, Jiaqi Che, Haijun Department of Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066004 China

Research on human action recognition based on skeleton has received a lot of attention. But most of the research focuses on improving the generalization ability of the model, while ignoring significant efficiency issues. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this paper, we investigate the under-studied but practically critical recognition model efficiency problem. To this end, we present a new Fast Recognition Distillation (FRD) model learning strategy. Specifically, FRD trains a lightweight recognition neural network structure that can be quickly executed at low computational cost. It can be achieved by effectively disseminating the identification probability information of the teacher network to the lightweight network. We call the probability information of the teacher network as soft-target, and FRD can learn more potential information from soft-target. In addition, we also used a special loss function for soft-target. Through the FRD network, while basically maintaining the recognition accuracy, we minimized the network structure. Extensive experiments on the two large-scale datasets, NTU-RGBD and Kinetics-Skeleton, demonstrate that our model (FRD) is more lightweight and refined than other models. Therefore, our model FRD is very practical. © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Decision Variable Classification-Based Evolutionary Algorithm for Dynamic Multi-Objective Optimization

SSRN

引用

SSRN 2023年

作者： Wei, Lixin Yang, Qingshuai Guo, Zeyin Institute of Electrical Engineering Yanshan University Hebei Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Hebei Province Qinhuangdao066004 China

There are many dynamic multi-objective optimization problems (DMOPs) in real life, and such problems require the algorithms to converge quickly to a new Pareto Front and maintain the diversity of solution sets after the environment changes. To achieve these objectives, a dynamic multi-objective evolutionary algorithm (DEA) based on decision variable classification is proposed in this paper. First, the decision variables are classified into two categories using the decision variable clustering method: convergence-related variables and diversity-related variables. Then, the convergence optimization strategy and the diversity optimization strategy are used to optimize these two categories of decision variables, so that the algorithm can obtain excellent convergence and good diversity while fast tracking the Pareto front. In addition, a method for calculating the degree of environmental change, which uses the information after environmental change, is proposed to improve the algorithm’s ability to respond to environmental change. The proposed algorithm is compared with three state-of-the-art dynamic multi-objective optimization evolutionary algorithms on 16 benchmark problems. The experimental results show that the algorithm can effectively solve dynamic multi-objective optimization problems. © 2023, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

A Heterogeneous Reinforcement Learning Approach for Joint Relay Selection and Power Allocation in Time-Varying Uasns with Energy Harvesting

SSRN

引用

SSRN 2024年

作者： Han, Song Wang, Ziyuan Li, Aijia Li, Xinbin Liu, Zhixin Yan, Lei Zhang, Tong Wei Key Lab of Industrial Computer Control Engineering of Hebei Province Institute of Electrical Engineering Yanshan University Hebei Province Qinhuangdao066004 China School of Computer and Communication Engineering Northeastern University Hebei Province Qinhuangdao066004 China Department of Technology Northeastern University Shandong Province Qingdao266237 China

In this study, we investigate the joint relay selection and power allocation problem for underwater acoustic communication networks with energy harvesting to maximize the cumulative capacity. We specially formulate a heterogeneous reinforcement learning-based framework. In the different decision layers, the Upper Confidence Bound 1 and enhanced Deep Deterministic Policy Gradient algorithms are employed to efficiently explore the discrete and continuous action spaces, respectively. Therefore, the solving difficulty of the complex hybrid discrete-continuous optimization problem can be significantly mitigated. Furthermore, a circular interaction structure is constructed to facilitate the exchange of decision-making information between the two decision layers. The strongly interdependent relationship of the different substrategies can be comprehensively considered, thereby improving the entire performance of thejoint strategy. Moreover, we propose an adaptive reward function, which can guide the user to balance the instantaneous capacity and interruptions, thereby effectively utilizing the green energy harvesting technology and enhancing long-term cumulative performance. Simulation results verify the effectiveness of our proposed algorithm. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SwinTaste: Bimodal Biosignals Taste Sensation Recognition via Swin Transformer

SwinTaste: Bimodal Biosignals Taste Sensation Recognition vi...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Han Gao Shuo Zhao You Wang Jin Zhang Wei Yao Zhiyuan Luo Guang Li State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China Department of Computer Science Royal Holloway University of London Egham U.K.

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Objective assessment of taste sensation is essential for medical diagnosis, food development, and multisensory interaction. Human taste sensation can be characterized through biosignals such as electroencephalography (EEG) and electromyography (EMG). However, taste sensation recognition on multiple-subject datasets remains challenging due to the low signal-to-noise ratio and substantial individual variability of biosignals. To address these problems, we propose SwinTaste for accurate and generalized taste sensation recognition from bimodal biosignals. The Transformer is introduced to extract hierarchical features. A two-stage patch partition module is optimized for the characteristics of biosignals. Moreover, a multi-task learning strategy is adopted to improve the generalization and subject adaptation abilities. The SwinTaste is evaluated on a multiple-subject taste sensation dataset. Comparison experiments and ablation studies demonstrate the superior performance of SwinTaste, indicating the potential for generalized application in biosignal recognition.

关键词： Accuracy Sensitivity Biological system modeling Brain modeling Transformers Multitasking Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DEEPCON: Improving Distributed Deep Learning Model Consistency in Edge-Cloud Environments via Distillation

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Qian, Bin Qian, Jiaxu Wen, Zhenyu Wu, Di He, Shibo Chen, Jiming Ranjan, Rajiv Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou China Zhejiang University of Technology Institute of Cyberspace Security College of Information Engineering Hangzhou China University of St Andrews School of Computer Science United Kingdom Newcastle University United Kingdom

In a typical distributed Deep Learning (DL) based application, models are configured differently to meet the requirements of resource constraints. For instance, a large ResNet56 model is deployed on the cloud server while a small lightweight MobileNet model is more suitable for the end-user device with fewer computation resources. However, the heterogeneity of the model architectures and configurations may bring a systemic problem -models may produce different outputs when given the same input. This inconsistency problem may cause severe system failure of prediction agreement inside the application. Current research has not studied the systemic design for efficiently detecting and reducing the inconsistency among models in distributed DL applications. With the increasing scale of distributed DL applications, the challenges of inconsistency mitigation should consider both algorithm and system design. To this end, we design and implement DEEPCON, an adaptive deployment system across the edge-cloud layer with over-the-air model updates. We implement ASRS sampling for efficiently sampling data to reveal the real data distribution as well as model prediction inconsistency. Then, we implement DMML-Par, an asynchronous parallel training algorithm for quickly updating the models and reducing inconsistency. implements over-the-air updates with a set of APIS to enable seamless inconsistency detection and reduction in such deep learning applications. Our experiment results on both vision and language tasks demonstrate that DMML could improve the model consistency up to 4%, 7%, and 13% at CIFAR10/100 and IMDB datasets without sacrificing the accuracy of individual models. We also show that the ASRS sampling can save 90% network bandwidth of data transmission and that DMML-Par is up to 60% faster compared to simple synchronous parallel training. 2015 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

A Recurrent Neural Network Based Bicriteria Repetitive Motion Collision Avoidance Scheme for Motion Planning of Dual Redundant Manipulators 13

A Recurrent Neural Network Based Bicriteria Repetitive Motio...

引用

13th International Conference on Intelligent control and Information Processing, ICICIP 2025

作者： Chen, Shirui Gao, Huanli Hu, Shaolin Zhang, Zhijun The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China The School of Automation Guangdong University of Petrochemical Technology Maoming Guangzhou525000 China The Guangzhou Key Laboratory of Brain-Computer Interaction and Applications Guangzhou China The Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China Guangzhou510555 China The Jiangxi Thousand Talents Plan Nanchang University Nanchang330031 China The College of Computer Science and Engineering Jishou University Jishou416000 China Guangzhou510335 China The Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Shaanxi University of Technology Hanzhong723001 China The School of Information Science and Engineering Changsha Normal University Changsha410100 China The School of Automation Science and Engineering Maoming525000 China The Institute of Artificial Intelligence and Automation Guangdong University of Petrochemical Technology Maoming525000 China

ISBN: (纸本)9798331516147

To achieve low joint-angle drift and avoid mutual collision between dual redundant manipulators (DRMs) when they are doing collaboration works, a recurrent neural network based bicriteria repetitive motion collision avoidance (BRMCA) scheme is proposed for motion planning of DRMs. By designing a combined optimization objective encompassing both repetitive motion criterion and collision avoidance criterion, the BRMCA scheme has larger feasible region and less constraint contradiction issues compared with traditional inequality constraints based method. Furthermore, by incorporating velocity-level kinematic model and physical limits of DRMs into the scheme, a time varying quadratic programming (TVQP) problem is formulated. The linear variational inequality-based primal–dual neural network (LVI-PDNN) is used to solve the proposed scheme due to the high accuracy and low computation complexity. Finally, through comparison simulations of tracking Circle-shape and C-shape trajectories between BRMCA scheme and minimum velocity norm (MVN) scheme, it exhibits that the proposed BRMCA scheme can achieve low joint-angle drift, collision avoidance and high tracking accuracy when DRMs are doing cooperative tasks. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimal Time and Power Allocation in Full-Duplex Wireless-Powered Cognitive Radio Networks

Optimal Time and Power Allocation in Full-Duplex Wireless-Po...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent Systems

作者： Zhenyu Feng Ming Su Meihua Zhou Zhixin Liu School of Electrical Engineering Yanshan University Qinhuangdao China Training Center of Liren College Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao Hebei Province China

In this paper, we integrate wireless powered communication networks (WPCNs) with cognitive radio networks (CRNs) in order to develop wireless powered CRNs (WP-CRNs). The hybrid access point (HAP) is used to broadcast radio-frequency signals to the devices at the downlink stage, and to receive information from these devices. The HAP has two antennas to achieve full-duplex: one is for downlink wireless power transfer and the other is for receiving uplink information transmission from the users simultaneously in the uplink. In the underlay paradigms. The SUs can harvest energy to transmit data when the interference to primary users (PUs) does not exceed a tolerable threshold. To tackle the above network issues, an optimal resource allocation method is proposed to maximize the secondary system uplink throughput. The optimization problem with respect to time and power allocation is formulated including the constraint of energy causality and interference level. The non-convex problem is transformed into an equivalent convex optimization problem, then the joint optimal power and time allocation (JOPTA) algorithm is presented to determine the optimal solutions. The effectiveness of the proposed algorithm is verified in the simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Water quality prediction of copper-molybdenum miningbeneficiation wastewater based on the PSO-SVR model

引用

Frontiers of Environmental Science & engineering 2023年第8期17卷 81-94页

作者： Xiaohua Fu Qingxing Zheng Guomin Jiang Kallol Roy Lei Huang Chang Liu Kun Li Honglei Chen Xinyu Song Jianyu Chen Zhenxing Wang Ecological Environment Management and Assessment Center Central South University of Forestry and TechnologyChangsha 410004China State Environmental Protection Key Laboratory of Water Environmental Simulation and Pollution Control South China Institute of Environmental SciencesMinistry of Ecology and EnvironmentGuangzhou 510655China Chinese Non-Ferrous Industrial Engineering Center of Pollution Control Technology&Equipment Science Environment Protection Co.Ltd.Changsha 410036China Institute of Computer Science University of TartuTartu 51009Estonia School of Environmental Science and Engineering Guangzhou UniversityGuangzhou 510006China A.B Freeman School of Business Tulane UniversityNew OrleansLA 70118USA Guangzhou Huacai Environmental Protection Technology Co. Ltd.Guangzhou 511480China

The mining-beneficiation wastewater treatment is highly complex and *** factors like influent quality,flow rate,pH and chemical dose,tend to restrict the effluent effectiveness of miningbeneficiation wastewater *** oxygen demand(COD)is a crucial indicator to measure the quality of mining-beneficiation *** COD concentration accurately of miningbeneficiation wastewater after treatment is essential for achieving stable and compliant *** reduces environmental risk and significantly improves the discharge quality of *** paper presents a novel AI algorithm PSO-SVR,to predict water *** optimization of our proposed model PSO-SVR,uses particle swarm optimization to improve support vector regression for COD *** generalization capacity tested on out-of-distribution(OOD)data for our PSOSVR model is strong,with the following performance metrics of root means square error(RMSE)is 1.51,mean absolute error(MAE)is 1.26,and the coefficient of determination(R2)is *** compare the performance of PSO-SVR model with back propagation neural network(BPNN)and radial basis function neural network(RBFNN)and shows it edges over in terms of the performance metrics of RMSE,MAE and R2,and is the best model for COD prediction of mining-beneficiation *** is because of the less overfitting tendency of PSO-SVR compared with neural network *** proposed PSO-SVR model is optimum for the prediction of COD in copper-molybdenum mining-beneficiation wastewater *** addition,PSO-SVR can be used to predict COD on a wide variety of wastewater through the process of transfer learning.

关键词： Chemical oxygen demand Mining-beneficiation wastewater treatment Particle swarm optimization Support vector regression Artificial neural network

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Active Power Dispatch for Wind Farms

Data-Driven Active Power Dispatch for Wind Farms

引用

Data Driven control and Learning Systems (DDCLS)

作者： Xuguo Jiao Daoyuan Zhang Xin Wang Zhaoxing Ma Zhenyong Zhang Wenfeng Liu School of Information and Control Engineering Qingdao University of Technology Qingdao China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Civil Engineering Qingdao University of Technology Qingdao China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

Active power dispatch of wind farms plays an important role in power grid scheduling. In this paper, a data-driven active power dispatch strategy for wind farms is proposed, which uses the key point of minimizing the standard deviation of wind turbines' output power series to reduce their fluctuations. First, to build the optimization problem, the historical active power output data of each wind turbine is collected from the Supervisory control And Data Acquisition (SCADA) system. Then, the objective function is developed based on the idea of minimizing the standard deviation of the output power time series. Meanwhile, considering the constraints of wind turbines' output power and active power balance of the grid, the feasible domain of the cost function is constructed. Further, to solve the proposed nonlinear optimization problem with equality and inequality constraints, the trust region interior point method (TRIPM) is employed to explore optimal solution within the feasible domain. Finally, actual data collected from wind farms is used to test effectiveness of the designed approach and experimental results show that our method can achieve better output power smoothing performance than conventional Proportional Dispatch (PD) method.

关键词： Fluctuations Time series analysis SCADA systems Power smoothing Wind farms Linear programming Power grids

来源：评论

学校读者我要写书评

暂无评论

Security Issues and Defensive Approaches in Deep Learning Frameworks

引用

Tsinghua Science and Technology 2021年第6期26卷 894-905页

作者： Hongsong Chen Yongpeng Zhang Yongrui Cao Jing Xie Department of Computer Science University of Science and Technology Beijing(USTB)Beijing 100083China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing 100083China Department of Computer Science and Technology University of Science and Technology Beijing(USTB)Beijing 100083China Defense Electronics Institute China Industrial Control System Cyber Emergency Response TeamBeijing 100040China

Deep learning frameworks promote the development of artificial intelligence and demonstrate considerable potential in numerous ***,the security issues of deep learning frameworks are among the main risks preventing the wide application of *** on deep learning frameworks by malicious internal or external attackers would exert substantial effects on society and *** start with a description of the framework of deep learning algorithms and a detailed analysis of attacks and vulnerabilities in *** propose a highly comprehensive classification approach for security issues and defensive approaches in deep learning frameworks and connect different attacks to corresponding defensive ***,we analyze a case of the physical-world use of deep learning security *** addition,we discuss future directions and open issues in deep learning *** hope that our research will inspire future developments and draw attention from academic and industrial domains to the security of deep learning frameworks.

关键词： adversarial examples deep learning frameworks defensive approaches security issues

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：