检索结果-内蒙古大学图书馆

International Conference on intelligent Informatics and Biomedical Sciences (ICIIBMS)

作者： Nian Liu Xinyu Liu Zhihao Zhang Xueming Xu Tong Chen chool of Electronic and Information Engineering Southwest University Chongqing Key Laboratory of Non-linear Circuit and Intelligent Information Processing Chongqing China

ISBN: (数字)9781728180229

ISBN: (纸本)9781728180236

Micro-expression is a spontaneous facial expression, which may reveal people's real emotions. The micro-expression recognition has recently attracted much attention in psychology and computer vision community. In this paper, we designed a multi-stream Convolutional Neural Network (CNN) combined with the Capsule Network(CapsNet) *** CNNCapsNet, to improve the performance of micro-expression recognition. Firstly, both vertical and horizontal optical flow are computed from the onset to the apex, and from the apex to the offset frame respectively, which is the first time that the offset frame information has been taken into account in the field of micro-expression recognition. Secondly, these four optical flow images and the grayscale image of apex frame are input into the five-stream CNN model to extract features. Finally, CapsNet completes micro-expression recognition by learning the features extracted by CNN. The method proposed in this paper are evaluated using the Leave-One-Subject-Out (LOSO) cross-validation protocol on CASME II. The results show that the offset information, which is often neglected, is more important than onset information for the recognition task. Our CNNCapsNet framework can achieve the accuracy of 64.63% for the five-class micro-expression classification.

关键词： Computer vision Protocols Psychology Feature extraction Convolutional neural networks Task analysis Optical flow

来源：评论

学校读者我要写书评

暂无评论

Effects of Acute Moderate Intensity Exercise on Emotion Based on beta Power in EEG 2019

Effects of Acute Moderate Intensity Exercise on Emotion Base...

引用

Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence

作者： Pengfei Gao Zhengji Long Zhangyan Xiao Fu Yang Jihai Zhang Guangyuan Liu School of Electronic and Information Engineering Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Processing Chongqing China

ISBN: (纸本)9781450376273

According to previous studies, high anxiety leads to an increase in beta power, while pleasure and relaxation of emotion reduces beta power. In this experiment, the International Standard Picture Stimulation Library(IAPS) was used to induce positive and negative emotions of subjects, and EEG signals were collected when subjects were looking at pictures. Comparing the beta power of positive and negative EEG induced by before and after exercise, we found that the power of beta stimulated by positive and negative pictures before exercise is generally greater than that after exercise. It indicates that subjects were happier when facing positive stimuli than before exercise, and less negative emotions were produced when facing negative stimuli than before exercise. In short, acute moderate intensity exercise can improve people's negative emotion in the face of negative stimuli. The purpose of this study is to explore the mechanism of the effect of acute moderate intensity exercise on emotion by analyzing beta power in late positive potential (LPP).

关键词： moderate emotion exercise beta power

来源：评论

学校读者我要写书评

暂无评论

Effects of acute moderate intensity exercise on emotion based on beta power in EEG 3

Effects of acute moderate intensity exercise on emotion base...

引用

3rd International Conference on Computer Science and Artificial Intelligence, CSAI 2019 and its Workshop - The 11th International Conference on information and Multimedia Technology, ICIMT 2019

作者： Gao, Pengfei Long, Zhengji Xiao, Zhangyan Yang, Fu Zhang, Jihai Liu, Guangyuan School of Electronic and Information Engineering Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Processing Chongqing China

ISBN: (纸本)9781450376273

关键词： Facings

来源：评论

学校读者我要写书评

暂无评论

Accelerated Row-stochastic Optimization over Directed Graphs with Uncoordinated Step Sizes

Accelerated Row-stochastic Optimization over Directed Graphs...

引用

International Conference on Control and Automation (ICCA)

作者： Kang Zhou Zhenyuan Du Huaqing Li Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing PR China

ISBN: (数字)9781728190938

ISBN: (纸本)9781728190945

This paper investigates a distributed optimization problem over a multiagent network, in which the target of agents is to collaboratively optimize the sum of all local objective functions. The case discusses that the network topology among agents is described by a strongly connected directed graph. The proposed algorithm utilizes row-stochastic weight matrices and uncoordinated step sizes. Under conditions that the objective functions are strong convex, and have Lipschitz continuous gradients, we manifest that proposed algorithm faster linearly converges to the global optimization solution than other algorithms as long as the chosen step sizes do not exceed an exact characterized upper bound. Numerical experiments are also provided to testify the theoretical analysis.

关键词： Optimization Convergence Acceleration Directed graphs Convex functions Communication networks Upper bound

来源：评论

学校读者我要写书评

暂无评论

Kernel Least Mean Square Based on the Sparse Nyström Method

Kernel Least Mean Square Based on the Sparse Nyström Method

引用

IEEE International Symposium on circuits and Systems (ISCAS)

作者： Haonan Zhang Han Jiang Shiyuan Wang Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing 400715 China

ISBN: (数字)9781728133201

ISBN: (纸本)9781728133218

Kernel least mean square based on the Nyström method (NysKLMS) has been proposed to fix the network structure of kernel least mean square (KLMS) by approximating a large Gram matrix with a low-rank matrix generated by sampling from input vectors. However, the computational burden of NysKLMS increases with the growth of the input dimension. To alleviate this computational burden, a novel KLMS based on a sparse Nyström method (SNKLMS) algorithm is proposed in this paper. Unlike NysKLMS using the k-means sampling to obtain k centroids from input data, the proposed SNKLMS algorithm first divides input data into several clusters, and then selects k centroids from the obtained clusters equally. According to the relation between the Gaussian kernel and the distance of different clusters, partial submatrices in the low-rank matrix of SNKLMS can be omitted to further reduce the operations of multiplication and addition, and thus a sparse low-rank matrix is obtained. Simulations on the channel equalization and chaotic time-series prediction validate the superiorities of SNKLMS.

关键词： Kernel Sparse matrices Signal processing algorithms Approximation algorithms Clustering algorithms Matrix decomposition Training data

来源：评论

学校读者我要写书评

暂无评论

The Kernel Recursive Generalized Cauchy Kernel Loss Algorithm 6

The Kernel Recursive Generalized Cauchy Kernel Loss Algorith...

引用

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

作者： Shi, Wei Xiong, Kui Wang, Shiyuan College of Electronic and Information Engineering Southwest University Chongqing Key Laboratory of Nonlinear Circuits Intelligent Information Processing Chongqing400715 China

ISBN: (纸本)9781728158570

As a nonlinear measure similarity developed in a kernel space, the generalized correntropic loss (GC-Loss) has been successfully used for signal processing and machine learning in non-Gaussian situations thanks to its ability of extracting high-order statistical properties of data. However, a highly non-convex performance surface in GC-Loss leads to poor optimization performance. To address this issue, we propose a new similarity measure developed in the kernel space by combining a generalized Gaussian distributed kernel function into the Cauchy loss. By minimizing the proposed loss function and using the kernel method, a novel kernel recursive generalized Cauchy kernel loss (KRGCKL) algorithm in the reproducing kernel Hilbert space (RKHS) is proposed. Simulations on different examples under non-Gaussian noises show the superiorities of KRGCKL over other representative algorithms in terms of filtering accuracy and robustness to large outliers. © 2019 IEEE.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Association Rules Hiding via Multi-Objective Differential Evolution Algorithm 6

Association Rules Hiding via Multi-Objective Differential Ev...

引用

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

作者： Mu, Nankun Yang, Fan Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

ISBN: (纸本)9781728158570

Association rules (ARs) mining has been widely used in discovering interesting patterns from massive data as a key data mining technique. However, this mining technique may lead to the disclosure of sensitive ARs, and thus, the ARs hiding strategy is very important and necessary. In this paper, a novel ARs hiding method (DEvoArH) is proposed for hiding the ARs. Noting that there are three side-effects in ARs hiding (ARH), i.e., the hiding failure rate, the lost rules rate, and the ghost rules rate, a multi-objective differential evolution algorithm is carefully designed. Specifically, the Pareto-optimal solutions are defined as the elite set, and then each solution is capable of learning from the elite set with a certain probability. Considering the convergence speed and search ability, a directional mutation and random mutate round is introduced into the mutation operator. Besides, to further decrease the data change rate, a database pre-processing mechanism is proposed to filter the unrelated data before the hiding process. Finally, the results of the comparison experiments also demonstrate the superiority of the proposed ARH method in terms of the three side-effects and efficiency. © 2019 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

The Robust Kernel Conjugate Gradient Least Mean p-Power Algorithm∗ 2

The Robust Kernel Conjugate Gradient Least Mean p-Power Algo...

引用

2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019

作者： Huang, Xuewei Xiong, Kui Wang, Lin Wang, Shiyuan College of Electronic and Information Engineering Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing400715 China

ISBN: (纸本)9781728140919

The traditional kernel adaptive filter (KAF) based on the minimum mean square error (MMSE) criterion suffers from poor filtering accuracy and slow convergence rate in Gaussian noises. To this end, the recursive KAF based on the least squares (LS) criterion can improve filtering accuracy and convergence rate in Gaussian noises with the increase of computational and storage burdens. However, both quadratic similarity measures based filters may suffer instability in non-Gaussian noises. To address these issues, a robust kernel conjugate gradient least mean p-power (KCGLMP) algorithm based on the mean p- power error (MPE) criterion is therefore proposed by combining the conjugate gradient optimization method with kernel trick. The proposed KCGLMP algorithm improves filtering accuracy and computational efficiency, simultaneously. Simulation results confirm the superiorities of the proposed KCGLMP algorithm over other conventional KAFs in non-Gaussian noises. © 2019 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

A brief survey on dynamical systems with saturated impulses

引用

Journal of the Franklin Institute 2025年第10期362卷

作者： Hongjuan Wu Chuandong Li Zhilong He School of Computer Science and Engineering Chongqing Three Gorges University Chongqing 404120 PR China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing 400715 PR China College of Mathematics and System Science Xinjiang University Urumqi 830017 PR China

In this paper, the research results on dynamical systems with saturated impulses (DSSI) are reviewed. We emphasize on the fundamental results, and the recent progress of the saturated impulse theories and the typical applications. Four aspects of saturated impulse are surveyed. That is, the common DSSI models with the important definitions and lemmas, the basic ideas for dealing with the saturated impulses, the estimation of the domain of attraction (DOA) for DSSI, and the typical applications of DSSI. The typical applications contain the design of hybrid controller for dynamical systems, the consensus of multi-agent systems (MASs), and the stability analysis of neural networks (NNs) and other networked systems. Finally, the conclusions and some future research directions are given.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The predominant functional connections of recognizing fear and surprise expression: a MEG study

The predominant functional connections of recognizing fear a...

引用

International Conference on intelligent Informatics and Biomedical Sciences (ICIIBMS)

作者： Yang Tan Ke Zhao Tong Chen Chongqing Key Laboratory of Nonlinear Circuit and Intelligent Information Processing Southwest University Chongqing China School of Electronic and Information Engineering Southwest University Chongqing China Institute of Psychology China Academy of Sciences Beijing China

ISBN: (数字)9781728180229

ISBN: (纸本)9781728180236

Facial expression, powerful non-verbal signals, contains abundant personal information and social communication information. Accurately identifying these signals is critical to the success of interpersonal communication. Studies have shown that both children and adults tend to confuse surprise with fear rather than sadness, anger, or disgust. However, the studies of fear and surprise expression recognition using network pattern based on MEG is only a few. In this study, we monitored the brain activity of 6 subjects as they perform a recognition task of fear and surprise, and subsequently constructed a network of brain functional connections. By using rank sum test and random forest, the most discriminative and representative 6 FCs from 2278 FCs were selected. The group of these 6 FCs can give a best prediction performance of 78.56%. Additionally, we also found that people tend to refer to surprise as fear when distinguishing between fear and surprise.

关键词： Face recognition Task analysis Occipital Lobe Informatics Biomedical monitoring Random forests Monitoring

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：