检索结果-内蒙古大学图书馆

11th International Conference on intelligent Human-Machine Systems and Cybernetics, IHMSC 2019

作者： Jiang, Wenge Liu, Guangyuan Zhao, Xingcong Yang, Fu School of Electronic and Information Engineering Southwest University China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Southwest University Chongqing China

ISBN: (纸本)9781728118598

Many of the current emotion recognitions are intra-subject, the reason is that recognize cross-subject emotions have always been difficult. In this paper, we proposed a decision tree classifier based on sequential backward selection (DT-SBS), and 'leave-one-subject-out' verification strategy was used for evaluating performance of cross-subject emotion recognition. Power spectral density (PSD) was extracted from EEG signals as feature set. The emotion recognition performance of the method we proposed was examined on EEG data of a group of subjects. The pictures were utilized to stimulate the emotion of 12 subjects and we collected their EEG signals (PEEG), the mean recognition accuracy of 65.8%. The dataset for emotion analysis using physiological signals (DEAP) was utilized to verify the method we proposed in this paper and the mean recognition accuracy of 65.2%. Compared with the performance reported in the existing literature, the method we proposed in this paper was effective in cross-subject emotion recognition. In addition, the emotion recognition performance of different rhythms were explored, we found that the mean recognition accuracy of PSD in the gamma rhythm achieved the best mean recognition accuracy compared with the other rhythms;the high frequency bands contained higher emotional information than the low frequency bands. © 2019 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Tracking control with event-triggered strategy for multi-agent systems with noises

Tracking control with event-triggered strategy for multi-age...

引用

作者： Tang, Zhaojun Li, Chuandong Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Department of Electronics and Information Engineering Southwest University Chongqing400715 China School of Science Chongqing University of Technology Chongqing400054 China

This paper is concerned with a tracking control problem of multi-agent systems with noises. It is assumed that each agent in the network updates its state only at some discrete time instants, which determined by the event-triggered condition, and the agents are affected by noises. In order to attenuate the effect of noises, consensus-gain function is introduced in the control protocol. Centralized and decentralized event-triggered protocols are proposed to ensure that the followers track the considered leader. With the help of matrix theory and Lyapunov method, sufficient conditions are derived to solve the mean square tracking control. Simulation results are provided to illustrate the theoretical results. © 2018 John Wiley & Sons, Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

The Effect of Long-Term Apnea on the Autonomic Nervous System

The Effect of Long-Term Apnea on the Autonomic Nervous Syste...

引用

International Conference on intelligent Human-Machine Systems and Cybernetics, IHMSC

作者： Fanmeng Kong Wanhui Wen Guangyuan Liu Xuehong Yang Ronglong Xiong School of Electronic and Information Engineering Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Processing acceptable Chongqing China

The complexity of physiological system can be well represented by the complexity of time series. In this paper, complexity analysis was performed on the inter-beat-interval(IBI) of apnea syndrome and normal sleep population. Hurst exponent, sample entropy and fractal dimension were used as three indicators of complexity measurement. The results show that optimal combination of statistical and nonlinear features with the Support Vector Machine (SVM) can achieve the apnea recognition accuracy of up to 75.51%. In the complexity measurement, t-test shows that the average of Hurst exponent, sample entropy or fractal dimension of the normal sleep group was significantly larger than that of the apnea group. The results show that long-term apnea syndrome will cause certain damage to the autonomic nerve system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A recurrent neural network for optimal energy management considering the battery cycle-life in smart grid 6

A recurrent neural network for optimal energy management con...

引用

6th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2019

作者： Sun, Miao He, Xing School of Microelectronics Fudan University Shanghai200433 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing School of Electronics and Information Engineering Southwest University Chongqing400715 China

ISBN: (纸本)9781728158570

This paper proposes a combined battery energy management (CBEM) model against the background of smart grid, which focus on the absorptive ability of Battery Energy Storage System (BESS) distinguishing to the traditional energy management. To solve the CBEM model, an one-layer recurrent neural network (RNN) is recommended. Furthermore, by considering the peak and valley periods division prices, the generators absorption and the distribution network bought from power grid are optimized. Meanwhile, the emission cost is considered in total cost and there is a corresponding constraint to control the emission and the outputs of generators. Finally, the effectiveness of the CBEM model is verified on Matlab. With the fluctuation of electrical price, the charge model and discharge model of BESS are showed. Results indicate that this model performs well in cutting the load in peak time and storage energy in valley time. © 2019 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A simple motion deblurring method by two continuous images

A simple motion deblurring method by two continuous images

引用

International Conference on Informative and Cybernetics for Computational Social Systems (ICCSS)

作者： Jihai Zhang Jianfeng Li Guangyuan Liu Tong Chen Tengteng Zhu Bo Li The Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing China

ISBN: (数字)9781728158570

ISBN: (纸本)9781728158587

Restoring blurred images to clear images is a challenging problem. Most previous methods only analyzed the single image. However, for motion blurring, this method missed the key trajectory description process. Based on the essence of motion blur, our research combined the continuous frame image information in video to estimate the motion track, the SIFT algorithm was proposed for the first time to match the feature points of the target in the continuous frame image. The accurate motion blur angle and motion blur distance were obtained by combining the matching information to obtain an accurate PSF. Finally, the Wiener filtering algorithm combined with PSF was used for deblurring. Experiments showed that the proposed method can improve the image sharpness after restoration compared with the previous algorithms.

关键词： motion blur continuous frame image deblurring PSF SIFT motion blur deblurring Point spread function Sifting SHARPNESS OF IMAGE images Continuous structures continuous image

来源：评论

学校读者我要写书评

暂无评论

Fat-tree-based optical networks-on-chip with WDM: Crosstalk noise exploiting

Fat-tree-based optical networks-on-chip with WDM: Crosstalk ...

引用

作者： Zhang, Jingping Xie, Yiyuan Wang, Shujian Ye, Yichen Liu, Yuzhu Pan, Gaofeng Liu, Yong Zhang, Jiliang Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing National Joint Engineering Laboratory of Intelligent Transmission and Control Technology College of Electronic and Information Engineering Southwest University Chongqing400715 China School of Optoelectronic Information University of Electronic Science and Technology of Chengdu Chengdu611731 China

Wavelength division multiplexing (WDM) technology as an extension of optical networks-on-chip (ONoCs) performance, can be applied to further overcome shortages of low bandwidth and high-power consumption in multiprocessor systems-on-chip. Nevertheless, WDM-based ONoCs (ONoCs_W) can encounter performance degradation and network scalability constraints because of its power loss and intrinsic crosstalk noise, especially the non-linear four-wave mixing crosstalk noise. Here, a formal systematical exploiting for worst-case crosstalk noise and optical signal-to-noise ratio (OSNR) in arbitrary fat-tree-based ONoCs with WDM (FONoCs_W) is proposed. Meanwhile, the worst-case OSNR optical link candidates are identified. To verify the proposed analysis method, FONoCs_W employing an optical turnaround router with WDM (WOTAR) is used for case study. The study results demonstrate that crosstalk noise significantly diminishes OSNR and restricts scalability of FONoCs_W. For instance, when input optical signal power equals 0 dBm in worst case, the average OSNR is −9.47 dB, the mean power of crosstalk noise for eight wavelengths is slightly greater than that of signal when the number of processor cores is 64;when it equals to 128, the average OSNR is −34.37 dB, decreased by 24.90 dB compared with the network with 64 processor cores. © The Institution of Engineering and Technology 2018

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Correction to: A metaheuristic-based framework for index tracking with practical constraints

引用

Complex & intelligent Systems 2022年第3期9卷 3469-3469页

作者： Yuen, Man-Chung Ng, Sin-Chun Leung, Man-Fai Che, Hangjun School of Science and Technology Hong Kong Metropolitan University Kowloon China School of Computing and Information Science Anglia Ruskin University Cambridge UK Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing China

来源：评论

学校读者我要写书评

暂无评论

Accelerated Distributed Optimization over Directed Graphs with Row and Column-Stochastic Matrices

Accelerated Distributed Optimization over Directed Graphs wi...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Jinhui Hu Yifan Zhu Huaqing Li Zheng Wang Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

In this paper, we study distributed optimization problem over multi-agent networks where the goal is to find the global optimal of a sum of convex functions over strongly connected and directed graphs. A novel distributed algorithm is proposed where both row and column-stochastic matrices are utilized to bypass the limits of the implementation of doubly-stochastic matrices or eigenvector estimation in related work. Besides, it has an evident expression and accelerated convergence by introducing the momentum term. Combining the Generalized Small Gain Theorem with Linear Time Invariant (LTI) system inequality, the algorithm is proved to be able to linearly converge to the exact optimal solution. Furthermore, the ranges of stepsize and momentum paramater are characterized, respectively. Finally, simulation results illustrate effectiveness of the method and correctness of theoretical analysis.

关键词： Radio frequency Convergence Optimization Acceleration Eigenvalues and eigenfunctions Convex functions Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Row-Stochastic Matrices Based Distributed Optimization Algorithm With Uncoordinated Step-Sizes

Row-Stochastic Matrices Based Distributed Optimization Algor...

引用

International Conference on Informative and Cybernetics for Computational Social Systems (ICCSS)

作者： Huaqing Li Jinmeng Wang Zheng Wang Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (数字)9781728158570

ISBN: (纸本)9781728158587

This paper investigates the distributed optimization problem over multi-agent networks, in which the target of agents is to collaboratively optimize the sum of all local objective functions. Each local objective function is uniquely known by a single agent. We concentrate on the scenario where communication among agents is portrayed as directed graphs. Based on the exact first order method, a fully distributed optimization algorithm is proposed to deal with the optimization problem. The proposed algorithm utilizes row-stochastic matrices and uncoordinated step-sizes, which exactly drives all agents to converge to the global optimization solution. Under the assumptions that the global objective function is strong convex and the local objective functions have Lipschitz continuous gradient, we show that the proposed algorithm linearly converges to the global optimization solution as long as the maximum step-size of agents does not exceed an explicitly characterized upper bound. Finally, numerical experiments are presented to demonstrate the correctness of theoretical analysis.

关键词： Distributed optimization directed graphs uncoordinated step-sizes row-stochastic matrices directed graphs Objective function Optimization algorithms Agents Global optimization Dyscoordination NETWORKING AGENT Distribute matrices

来源：评论

学校读者我要写书评

暂无评论

A Distributed Dynamic Resource Allocation Strategy in A Large-scale Micro-grids Group

A Distributed Dynamic Resource Allocation Strategy in A Larg...

引用

International Conference on Informative and Cybernetics for Computational Social Systems (ICCSS)

作者： Zao Fu Xing He Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (数字)9781728158570

ISBN: (纸本)9781728158587

In this paper, a dynamic economic dispatch problem (DEDP) with renewable energy generators is studied. With the purpose of minimizing the cost of DEDP and optimally allocate the load demand among the interconnected generators considering ramp-rate limits and generation limits, an effective continuous-time distributed algorithm based on interior point methods and primal-dual methods is proposed. In order to overcome the drawbacks of the renewable energy, a parallel system composed with flywheel energy storage systems and renewable energy generators is proposed to work in a constant power output mode. In addition, the using of switched systems makes the optimal solution more accurate. The excellent performance of the proposed algorithm is verified by IEEE 30-bus system with the REG based simulation.

关键词： Dynamic economic dispatch renewable energy Continuous-time distributed algorithm Renewable energy flywheel energy storage system MICRO-GRID dynamos rate limitation Switched systems DYNAMIC ECONOMIC ANALYSIS Resource utilization management of resources

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：