检索结果-内蒙古大学图书馆

Computer Engineering and intelligent Communications (ISCEIC), International Symposium on

作者： Liupeng Guo Yannan Xiao Yayuan Wen Peizhi Wen School of Computer and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China School of Computer and Information Security Guilin University of Electronic Technology Guilin China School of Electronic and Information Engineering/School of Integrated Circuits GUANGXI Normal University Guilin China

Generative summarization based on the seq2seq model has gained widespread adoption due to the advancements and efficacy of the sequence-to-sequence framework. However, these models encounter challenges in handling out-of-vocabulary words and may produce summaries with factual inaccuracies. This paper addresses these issues by proposing a summarization generation model, MBC, which is built upon the Transformer as the baseline model. Additionally, it incorporates the BERT pre-trained model, pointer generation network, contrastive attention mechanism, and coverage loss. The model employs a pointer generation network to augment its vocabulary coverage capabilities by generating new terms. To enhance the representation of key information from the source text, a contrastive attention mechanism is employed during summary generation. In addition, by introducing coverage loss, the model can reduce repetitive content in the summary. To assess the model’s performance, this paper employs ROUGE values as evaluation metrics and conducts comparative experiments with other models using the LCSTS dataset. The experimental results demonstrate that, in comparison with other models, this model is more adept at attending to salient information within the source text and generating summaries of greater accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Loading Effects of the Human Body on An Ultrawideband Wearable Textile Antenna

Loading Effects of the Human Body on An Ultrawideband Wearab...

引用

IEEE Asia-Pacific Conference on Antennas and Propagation (APCAP)

作者： Ziang Xu Xiang Gao Zhuzhang Mao Wenfei Tang Kun Guo School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China School of Integrated Circuits and Electronics Beijing Institute of Technology Beijing China School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (数字)9798350351019

ISBN: (纸本)9798350351026

This paper presents an ultrawideband wearable textile antenna for emergency communication applications, and investigates the loading effects of the human body on radiation performance of the antenna. The proposed antenna has a measured operating bandwidth from 0.31 to 1.2 GHz and an average realized gain of 3.32 dBi in free space. Furthermore, the results show that the antenna gain can effectively be improved by properly adjusting the distance between the human body and the antenna.

关键词： Antenna measurements Loading Bandwidth Gain measurement Extraterrestrial measurements Ultra wideband antennas Reflection Wearable antennas Textile antennas Loaded antennas

来源：评论

学校读者我要写书评

暂无评论

EEG-based Emotion Recognition on Unstable Patterns over Time

EEG-based Emotion Recognition on Unstable Patterns over Time

引用

International Conference on Digital Home (ICDH)

作者： Guopei Wu Sheng Qin Yuling Luo Qiang Fu Jin Zeng Su Yang Junxiu Liu Guangxi Key Lab of Brain-inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin China Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Nonlinear Circuits and Optical Communications (Guangxi Normal University) Guilin China Department of Computer Science Swansea University UK

ISBN: (数字)9798331509873

ISBN: (纸本)9798331509880

In brain-computer interface (BCI) systems, users' emotion can be recognized by using electroencephalography (EEG) data. Recent researches proposed different methods for feature extraction and EEG-based emotion classification. However, EEG data collected over time is not always stable and accuracies of emotion recognition are found not robust. In this paper, a novel EEG emotion recognition system is proposed by combining ReliefF for extracting features, and Long Short-Term Memory Network coupled with Support Vector Machine for classification. A public EEG emotion dataset of SEED which contains three different recordings of EEG data is used in the experiments. It is shown that the proposed network is effective for mitigating the phenomenon of unstable accuracies, and achieves higher emotion classification accuracies compared to other approaches using the same dataset.

关键词： Support vector machines Emotion recognition Accuracy Feature extraction Electroencephalography Brain-computer interfaces Recording Classification algorithms Long short term memory Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Effects of Negative Stimulation After Exercise on Frontal Asymmetry in Unregular Exercisers

引用

IOP Conference Series: Materials Science and Engineering 2019年第5期612卷

作者： Tengfei Wang Guangyuan Liu School of Electronic and Information Engineering Southwest University Chongqing 400700 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing 400700 China

As a signal to recognize emotion, the electroencephalogram (EEG) is used widely. Frontal asymmetry is not only related to emotion, but also affected by exercise. The purpose of our research is to explore the effects of exercise for negative emotion, and how the activity of the frontal of the college students who did not exercise regularly is. We used the frontal asymmetry between F3 and F4 channels of the alpha band. The result showed that the power of frontal asymmetry increased after exercise compared to that before exercise within 3 seconds after stimulation, and the change of the power during the 2nd second was more obvious. The activity of the frontal of the students without exercise habits can be altered by exercise. The frontal asymmetry is related to emotion, which confirms that exercise has an effect on the students without exercise habits after negative stimulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

𝒮-asymptotically 𝓌-periodic mild solutions for noninstantaneous impulsive integro-differential equations with state-dependent delay

引用

Mathematical Methods in the Applied Sciences 2023年第9期46卷

作者： Yinuo Wang Chuandong Li Hao Deng Hongjuan Wu Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing 400715 China Communicated by: J. Banasiak

A kind of nonlinear noninstantaneous impulsive equation with state-dependent delay is studied here. By utilizing suitable fixed point theorem and the theory of semigroup in Banach space, the uniqueness and existence results of S $$ \mathcal{S} $$ -asymptotically w $$ w $$ -periodic mild solutions are obtained, respectively. In the end, two examples are presented to demonstrate the validity of the obtained results.

关键词： fixed point theorem integro-differential equations noninstantaneous impulse S$$ \mathcal{S} $$-asymptotically w$$ w $$-periodic mild solution state-dependent delay

来源：评论

学校读者我要写书评

暂无评论

Octopus-Inspired Multichannel Tactile Sensor for Enhanced Underwater Material Identification

SSRN

引用

SSRN 2024年

作者： Hao, Yutao Sun, Yanshuo Wen, Jing Gao, Xiaobo Wang, Yutong Zhu, Zhiyuan Wang, Zhong Lin Chen, Baodong Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China Beijing Institute of Nanoenergy and Nanosystems Chinese Academy of Sciences Beijing101400 China School of Nanoscience and Engineering University of Chinese Academy of Sciences Beijing100049 China Research Institute of Technology of Shougang Group Beijing100043 China The Key Laboratory of High Temperature Electromagnetic Materials and Structure of MOE Wuhan University of Science and Technology Wuhan430081 China Georgia Institute of Technology AtlantaGA30332-0245 United States

The sustainable development of the ocean requires sensors capable of detecting objects in underwater or high humidity conditions. However, traditional sensors struggle in complex underwater environments due to signal attenuation, biofouling, and flow interference, which seriously affect the performance and reliability. Inspired by the tactile system of octopus suckers, we developed a tactile sensor that mimics the structure of octopus tentacle suckers, ingeniously harnessing triboelectric tactile receptors (TTRs) to emulate the mechanism of cephalopod-specific chemoreceptors (CRs), aiming to address the challenging problem of underwater object recognition. Additionally, the superhydrophobic treatment increases the microstructure of the sensor surface, effectively mitigating environmental interference and improved underwater performance, resulting in a 67% increase in voltage output, a sensitivity of 0.195 V kPa-1, and a remarkable response time of only 85 ms. Most importantly, we have constructed an underwater material identification system (UMIS) to achieve 98% accuracy by integrating machine learning, which enables precise identification and quantitative sensing of underwater objects, offering novel insights and directions for the intelligence and autonomy of underwater robots. © 2024, The Authors. All rights reserved.

关键词： Shellfish

来源：评论

学校读者我要写书评

暂无评论

An extragradient algorithm for fixed point problems and pseudomonotone equilibrium problems

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2020年第4期82卷 89-96页

作者： Yao, Zhangsong Liou, Yeong-Cheng Zhu, Li-Jun School of Information Engineering Nanjing Xiaozhuang University Nanjing211171 China Department of Healthcare Administration and Medical Informatics Research Center of Nonlinear Analysis and Optimization Kaohsiung Medical University Department of Medical Research Kaohsiung Medical University Hospital Kaohsiung807 Taiwan The Key Laboratory of Intelligent Information and Big Data Processing of NingXia Province and Health Big Data Research Institute Advanced Intelligent Perception and Control Technology Innovative Team of NingXia North Minzu University Yinchuan750021 China

Iterative methods for solving fixed point problems and pseudomonotone equilibrium problems have been considered. An extragradient algorithm has been presnted for finding a common element of the fixed points of pseudocontractive operators and the solutions of pseudomonotone equilibrium problems in Hilbert spaces. Weak convergence result of the suggested algorithm is proved. © 2020, Politechnica University of Bucharest. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Effects of Acute Moderate Intensity Exercise on the EEGFrontal Alpha Asymmetry

引用

Journal of Physics: Conference Series 2020年第7期1486卷

作者： Zhangyan Xiao Zhengji Long Pengfei Gao Chaoling Qin Guangyuan Liu College of Electronic Information and Engineering Southwest University Chongqing China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing China College of Physical Education Southwest University Chongqing China

Exercise can improve physical and psychological states efficiently. Previous studies have shown that the frontal alpha asymmetry can be used to express emotional states, while relative activity in the larger left frontal can predict positive effects. In this study, our purpose is to observe the effects of pedalling exercise (PE) on the frontal alpha asymmetry during negative stimulation. The electroence phalograph (EEG)signals obtained are processed by matlab to obtain the frontal asymmetry value. By observing and comparing the frontal alpha asymmetry between two groups, we can find that the frontal alpha asymmetry of the sports group increased significantly, while the control group have no significantly change. The study shows that the acute moderate intensity PE can improve the resistance to negative stimuli and increase positive emotions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decentralized Nonconvex Robust Optimization over Unsafe Multiagent Systems: System Modeling, Utility, Resilience, and Privacy Analysis

arXiv

引用

arXiv 2024年

作者： Hu, Jinhui Chen, Guo Li, Huaqing Cheng, Huqiang Guo, Xiaoyu Huang, Tingwen School of Automation Central South University Changsha410083 China Department of Biomedical Engineering City University of Hong Kong Kowloon Hong Kong School of Electrical Engineering and Telecommunications University of New South Wales SydneyNSW2052 Australia Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China Key Laboratory of Dependable Services Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China

Privacy leakage and Byzantine failures are two adverse factors to the intelligent decision-making process of multiagent systems (MASs). Considering an unsafe MAS with these two issues, this paper targets the resolution of a class of nonconvex optimization problems under the Polyak-Lojasiewicz (P-L) condition. To address this problem, we first identify and construct the unsafe MAS model. Under this kind of unfavorable MASs, we mask the local gradients with Gaussian noises and adopt a resilient aggregation method self-centered clipping (SCC) to design a differentially private (DP) decentralized Byzantine-resilient algorithm, namely DP-SCC-PL, which simultaneously achieves differential privacy and Byzantine resilience. The convergence analysis of DP-SCC-PL is challenging since the convergence error can be contributed jointly by privacy-preserving and Byzantine-resilient mechanisms, as well as the nonconvex relaxation, which is addressed via seeking the contraction relationships among the disagreement measure of reliable agents before and after SCC aggregation, together with the optimal gap. Theoretical results reveal that DP-SCC-PL achieves consensus among all reliable agents and sublinear (inexact) convergence with well-designed step-sizes. It has also been proved that if there are no privacy issues and Byzantine agents, then the asymptotic exact convergence can be recovered. Numerical experiments verify the utility, resilience, and differential privacy of DP-SCC-PL by tackling a nonconvex optimization problem satisfying the P-L condition under various Byzantine attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Personality Recognition in Response to Virtual Reality and Two-Dimensional Emotional Stimulus Using ECG Signals

引用

ACM Transactions on Interactive intelligent Systems 1000年

作者： Jialan Xie Ping Lan Zhaonian Hu Guangyuan Liu College of Electronic and Information Engineering Southwest University Chongqing China Institute of Affective Computing and Information Processing Southwest University Chongqing China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Southwest University Chongqing China Key Laboratory of Cognition and Personality Ministry of Education Faculty of Psychology Southwest University Chongqing China

Personality primarily refers to the unique and stable way of a person’s thinking and behavior. A few studies have recently been conducted on personality recognition using physiological signals, most of which have used two-dimensional (2D) emotional stimulus materials. Virtual reality (VR) has been utilized in many fields, and its superiority over 2D in emotion recognition has been proven. However, relevant research on VR scenes is lacking in the field of personality recognition. In this study, based on the psychological principle that emotional arousal can expose an individual’s personality, we attempt to explore the feasibility and effect of using electrocardiogram (ECG) signals in response to VR emotional stimuli for personality identification. For this purpose, a VR-2D emotion-induction experiment was conducted in which ECG signals were collected, and physiological datasets of emotional personalities were constructed through preprocessing and feature extraction. Statistical analysis of the emotion scale scores and ECG features of the participants showed that the VR group had a higher number of significantly correlated features. Meanwhile, VR- and 2D-based personality recognition models were constructed using machine learning algorithms. The results showed that the VR-based personality recognition model achieved better results for the four personality dimensions, with a maximum accuracy of 79.76%. These findings indicate that VR not only enhances the physiological correlation between emotion and personality but also improves the classification accuracy of personality recognition.

关键词： Big Five personality Electrocardiogram Emotion Personality recognition Virtual reality

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：