检索结果-内蒙古大学图书馆

A distributed stochastic optimization algorithm with gradient-tracking and distributed heavy-ball acceleration

Frontiers of information Technology & Electronic Engineering 2021年第11期22卷 1463-1476页

作者： Bihao SUN Jinhui HU Dawen XIA Huaqing LI Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information EngineeringSouthwest UniversityChongqing400715China College of Data Science and Information Engineering Guizhou Minzu UniversityGuiyang550025China

Distributed optimization has been well developed in recent years due to its wide applications in machine learning and signal *** this paper,we focus on investigating distributed optimization to minimize a global *** objective is a sum of smooth and strongly convex local cost functions which are distributed over an undirected network of n *** contrast to existing works,we apply a distributed heavy-ball term to improve the convergence performance of the proposed *** accelerate the convergence of existing distributed stochastic first-order gradient methods,a momentum term is combined with a gradient-tracking *** is shown that the proposed algorithm has better acceleration ability than GT-SAGA without increasing the *** experiments on real-world datasets verify the effectiveness and correctness of the proposed algorithm.

关键词： Distributed optimization High-performance algorithm Multi-agent system Machine-learning problem Stochastic gradient

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

Movie preference prediction based on EEG signal under high brain correlation 4

Movie preference prediction based on EEG signal under high b...

引用

4th International Conference on Signal processing and Computer Science, SPCS 2023

作者： Yue, Yuanhao Zhao, Xingcong Zhou, Wei Liu, Guangyuan School of Electronic and Information Engineering Southwest University Tiansheng Road Beibei Chongqing400715 China Institute of Affective Computing and Information Processing Southwest University Tiansheng Road Beibei Chongqing400715 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Southwest University Tiansheng Road Beibei Chongqing400715 China

ISBN: (纸本)9781510672505

In this study, we recorded the electroencephalography (EEG) of human subjects when they watched a movie trailer. Based on the willingness preference from the subjects after finished the movie trailer watching, the EEG signals were analyzed to build regression models to predict the subjects' movie preferences. We proposed a new approach to rise the prediction accuracy. Specifically, the correlated component analysis (CCA) algorithm was used to calculate the inter-subject correlation (ISC) of each time segment in the movie trailer and the ISC of each channel in the EEG. These two states were selected to locate the moment when a specific area of the brain responds most strongly to the video stimulation, as an effective indicator for predicting individual movie preferences. The experimental results show that the method of selecting effective EEG signals at the level of ISC has achieved a better prediction effect on the GBDT regression model (R2 = 0.733, RMSE = 0.681). We also found that low-frequency EEG signals in the θ and δ bands of the parietal and occipital sites are more effective in predicting movie preferences than high-frequency EEG signals. © 2023 SPIE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

TS-CAN+: A Improved TS-CAN Architecture for Non-Contact Heart Rate Measurement

引用

IEEE Transactions on Consumer Electronics 2024年 1-1页

作者： Li, Yihang Huang, Junjian Zhao, Jichao Wu, Dayu Zheng, Mao Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing China University of Auckland Auckland New Zealand

Heart rate is one of the most crucial physiological indicators of the human body, which can reflect the health status of the cardiovascular and cerebrovascular. Therefore, heart rate monitoring in real-time is essential for the prevention and treatment of cardiovascular and cerebrovascular diseases. Remote Photoplethysmography (rPPG) is a non-contact heart rate measurement method, which addresses the limitation of traditional heart rate measurement methods that need to contact with the subjects, and has a broad application prospect in ward vital signs monitoring and remote physiological health monitoring. How to use the rPPG method to measure heart rate more accurately is still a challenging problem. In this paper, we propose the TS-CAN+ method, which is based on TS-CAN and further incorporates convolutional block attention modules and replaces the ordinary convolution of the appearance branch with the depthwise separable convolution to improve the network accuracy. To validate the performance of our model, we conduct extensive experiments on the public PURE, UBFC-rPPG, and MMPD datasets. The experimental results indicate that compared with TS-CAN, the mean absolute error of TS-CAN+ is reduced by 37.21% in the cross-dataset test on UBFC-rPPG dataset and reduced by 12.18% on MMPD dataset. IEEE

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A decentralized Nesterov gradient method for stochastic optimization over unbalanced directed networks

A decentralized Nesterov gradient method for stochastic opti...

引用

作者： Hu, Jinhui Xia, Dawen Cheng, Huqiang Feng, Liping Ji, Lianghao Guo, Jing Li, Huaqing Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing China College of Data Science and Information Engineering Guizhou Minzu University Guiyang China Department of Computer Science Xinzhou Teachers University Shanxi China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing China

Decentralized stochastic gradient methods play significant roles in large-scale optimization that finds many practical applications in machine learning and coordinated control. This paper studies optimization problems over unbalanced directed networks, where the mutual goal of agents in the network is to optimize a global objective function expressed as a sum of local objective functions. Each agent using only local computation and communication in the networks is assumed to get access to a stochastic first-order oracle. In order to devise a noise-tolerant decentralized algorithm with accelerated linear convergence, a decentralized Nesterov gradient algorithm with the constant step-size and parameter using stochastic gradients is proposed in this paper. The proposed algorithm employing a gradient-tracking technique is proved to converge linearly to an error ball around the optimal solution via the analysis on a linear system when the positive constant step-size and parameter are sufficiently small. We further recover the exact linear convergence for the proposed algorithm with exact gradients under the same selection conditions of the constant step-size and parameter. Some real-world data sets are used in simulations to validate the correctness of the theoretical findings and practicability of the proposed algorithm. © 2020 Chinese Automatic Control Society and John Wiley & Sons Australia, Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Exploring Regulation Effect of Jogging on Human Emotion Based on Pulse Signal

Exploring Regulation Effect of Jogging on Human Emotion Base...

引用

International Symposium on Computational Intelligence and Design, ISCID

作者： Jianguang Yuan Guangyuan Liu Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Southwest University Chongqing China

ISBN: (纸本)9781509035595

Until recently, claims for the psychological benefits of physical exercise have tended to precede supportive evidence. Actually, emotional effects of exercise remain confusing, both positive and negative effects being reported. Meanwhile, several studies have shown that the aerobic exercise has impact on human's mood through making subjective evaluation of the Profile of Mood States (POMS) before and after exercise. However, the conclusion via comparing with the Profile of Mood States (POMS) scores was lack of the objective basis. In order to explain the result that exercise has effects of adjustment to fear emotion from the objective point of view, therefore, this study researched exercise which can improve mood based on the subjects' physiological signal, and analyzed data using the affective computing. Issues involved in this study are discussed.

关键词： Mood Physiology Time series analysis Affective computing Fatigue Computational intelligence nonlinear circuits

来源：评论

学校读者我要写书评

暂无评论

Stability analysis of hybrid neural networks with impulsive time window

引用

International Journal of Biomathematics 2017年第1期10卷 195-208页

作者： Xin Wang Hui Wang Chuandong Li Tingwen Huang Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronics and Information EngineeringSouthwest University Chongqing 400715 P. R. China Key Laboratory of Machine Perception and Children's Intelligence DevelopmentChongqing University of Education P. R. China College of Mathematics Science Chongqing Normal University Chongqing 401331 P. R. China Texas A&M University at QatarDoha P. O. Box 23874 Qatar

The urgent problem with impulsive moments cannot be determined in advance brings new challenges beyond the conventional impulsive systems theory. In order to solve this problem, in this paper, a novel class of system with impulsive time window is proposed. Different from the conventional impulsive control strategies, the main characteristic of the impulsive time window is that impulse occurs in a random manner. Moreover, for the importance of the hybrid neural networks, using switching Lyapunov functions and a generalized Hanlanay inequality, some general criteria for asymptotic and exponential stability of the hybrid neural networks with impulsive time window are established. Finally, some simulations are provided to further illustrate the effectiveness of the results.

关键词： Hybrid neural networks impulsive time window stability.

来源：评论

学校读者我要写书评

暂无评论

Kernel least mean square algorithm with mixed kernel

Kernel least mean square algorithm with mixed kernel

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Qitang Sun Lujuan Dang Wanli Wang Shiyuan Wang College of Electronic and Information Engineering Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing China

This paper presents a novel kernel least square algorithm with mixed kernel (KLMS-MK) to improve the filtering performance of kernel least mean square (KLMS). By applying the convex combination method to the kernel function in KLMS, KLMS-MK bears the advantages of both the Gaussian kernel and the Laplace kernel. In KLMS-MK, the mixed parameter for the convex combination is updated with the stochastic gradient descent. Therefore, the steady-state mean square error (MSE) and the convergence rate are improved by KLMS-MK, simultaneously. Simulation results on chaotic time series prediction and nonlinear regression validate the excellent performance of KLMS-MK from the aspects of the convergence rate and estimation accuracy.

关键词： Kernel Testing Signal processing algorithms Gaussian noise Convergence Approximation algorithms Time series analysis

来源：评论

学校读者我要写书评

暂无评论

An Image Denoising Method Based on Deep Residual GAN 4

An Image Denoising Method Based on Deep Residual GAN

引用

2020 4th International Workshop on Advanced Algorithms and Control Engineering, IWAACE 2020

作者： Wang, Ziyuan Wang, Lidan Duan, Shukai Li, Yunfei Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing400715 China Schoolof Electronic and Information Engineering Southwest University Chongqing400715 China College of Artificiall Intelligence Southwest University Chongqing400715 China Braininspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing400715 China

As people come into contact with image data more often, high quality and clear images attract more attention. Many methods have been proposed to deal with image noise problem including deep learning (DL). However most of them is lack of capability when customers want more perceptual details of the image without information loss. In this paper, a deep residual network based on generative adversarial (GAN) network was proposed to complete the image denoising mission. Firstly, a generative-adversarial network structure based on residual blocks was designed. Secondly, a refined loss function was given to train the GAN network. The well designed loss function can help the generated image to be very close to the clear counterpart (ground truth) while enhancing more details in colours and brightness. Finally, extensive experiments show that our network is not only convincing for images denoising, but also effective for other image process tasks, such as image defogging, medical CT denoising etc., presenting impressive and competitive effects. © Published under licence by IOP Publishing Ltd.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Technique with VGG-16 for Near-Infrared Facial Expression Recognition 2

Transfer Learning Technique with VGG-16 for Near-Infrared Fa...

引用

2021 2nd International Workshop on Electronic communication and Artificial Intelligence, IWECAI 2021

作者： Atabansi, Chukwuemeka C. Chen, Tong Cao, Ranlei Xu, Xueming School of Electronic and Information Engineering Southwest University Beibei District Chongqing400715 China Chongqing Key Laboratory of Nonlinear Circuit and Intelligent Information Processing Southwest University Beibei District Chongqing400715 China

In this paper, we investigate a deep learning vgg-16 network architecture for facial expression recognition under active near-infrared illumination condition and background. In particular, we consider the concept of transfer learning whereby features learned from high resolution images of huge datasets can be used to train a model of relatively small dataset without loosing the generalization ability. The pre-trained vgg-16 network architecture with transfer learning technique has been trained and validated on the Oulu-CASIA NIR dataset comprising of six (6) distinct facial expressions, and average test accuracy of 98.11% was achieved. The validation on our test data using the confusion, the precision, and the recall matrix reveals that our method achieves better results in comparison with the other methods in the literature. © Published under licence by IOP Publishing Ltd.

关键词： Network architecture

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：