影片片段诱发情绪的生理活动研究

目的探讨和研究影片诱发基本情绪的脑电和自主神经反应模式。方法20名在校研究生作为被试,用影片片段来诱发快乐和悲伤两种基本情绪和一种中性状态,用多导生理仪记录被试在观看影片片段时的各项生理指标,研究了基本情绪的脑电和自主神经反应模式。结果呼吸频率和皮肤电受情绪影响显著,呼吸深度和血氧饱和度存在性别主效应。结论悲伤影片较多地激活了额区的α波,愉快影片较多地激活了枕区的α波,另外β和θ波的最大能量,在不同脑区都受到情绪的显著影响。     

基于深浅特征融合的深度卷积残差网络的脑电情绪识别模型

基于脑电信号的智能情绪识别系统具有便携性、高时间分辨率、实时性等特点,能够在健康、娱乐、教育等多个领域实现情绪监控与调节的应用.但由于脑电信号的非平稳性和个体差异性,传统分类器难以深入提取脑电信号中潜在的与情绪语义相关的特征.为了有效地提取脑电特征,提高脑电-情绪识别的准确性,提出一种新型的基于深浅特征融合的深度卷积残...     

基于生理信号的情绪识别研究进展

情绪识别在文教医疗、人机交互等领域均有广阔应用前景。情绪可通过语音、面部表情、姿态等行为信号或脑电、心电等生理信号进行识别。相对而言,基于生理信号的情绪识别方法不易伪装,可获得更加客观、有效的结果。本文从情绪分类模型、诱发与识别流程等方面介绍了近年来基于生理信号的主要情绪识别方法和研究进展,归纳总结了其中的难点和未来的发展趋势。     

一种改进脑电特征提取算法及其在情感识别中的应用

音乐诱发下的情感状态评估结果可为辅助音乐治疗提供理论支持与帮助。情感状态评估的关键是情感脑电的特征提取,故本文针对情感脑电特征提取算法的性能优化问题开展研究。采用Koelstra等提出的分析人类情绪状态的多模态标准数据库DEAP,提取8种正负情绪代表各个脑区的14个通道脑电数据,基于小波分解重构δ、θ、α、β四种节律波;在分析比较小波特征(小波系数能量和小波熵)、近似熵和Hurst指数三种脑电特征情感识别效果的基础上,提出一种基于主成分分析(PCA)融合小波特征、近似熵和Hurst指数的脑电特征提取算法。本算法保留累积贡献率大于85%的主成分,并选择特征根差异较大的特征参数,基于支持向量机实现情感状态评估。结果表明,使用单一小波特征(小波系数能量和小波熵)、近似熵和Hurst指数特征量,情感识别的正确率均值分别是73.15%、50.00%和45.54%,而改进算法识别准确率均值在85%左右。基于改进算法情感识别的分类准确率比传统方法至少能提升12%,可为情感脑电特征提取以及辅助音乐治疗提供帮助。     

情绪与电生理研究进展

系统介绍了利用电生理方法一脑电图进行情绪研究的现状，着重从脑电（EEG）的频谱分析、诱发电位（EP）和事件相关电位（ERP）及非线性动力学等方面，阐述了如何利用电生理方法进行情绪研究及其取得的最新进展，并探讨了情绪对其它脑功能如记忆的影响，展望了情绪研究的发展方向，为我国进行情绪研究提供借鉴。     

脑电信号驱动的个性化情绪音乐播放系统算法研究及初步实现

为了能实时监测听众的情绪状态变化并据此调整音乐播放列表,本文中,我们基于便携式干电极脑电数据提出了一种脑电驱动的个性化情绪音乐推荐系统的算法框架,并在Android平台上进行了初步开发实现。我们以效价和唤醒度二维情绪模型为基准,将脑电和相应种子歌曲映射到各个情绪坐标象限内,从而建立映射关系。然后应用美尔频率倒谱系数分析音乐库中各歌曲与种子歌曲之间的相似度并进行排序。最后,在播放歌曲阶段,我们通过脑电来识别听众的情绪状态,根据事先获得的情绪状态匹配关系播放并实时调整相应的歌曲曲目列表。     

基于脑电的脑网络稳定模式情绪识别研究

利用锁相值构建不同时间段的情绪脑网络，探讨不同时间情绪相关脑网络模式的稳定性，提出基于脑网络二阶特征的情绪识别框架。结果表明，在跨被试研究和单被试研究中最高准确率分别为79.17%和82.92%,ANOVA分析3个时间段的识别结果无显著性差异，证明本研究提出的情绪识别框架是稳定的。在不同时间段，同类别的情绪均具有相同的脑网络连接模式和最小生成树的结构，说明相同情绪在不同时间存在稳定的脑网络模式。使用脑网络特征进行情绪识别是稳定且可靠的，这为人机交互中情绪识别提供一种新途径。     

脑电时间效应对情绪识别模型的影响及解决措施研究

近年来,越来越多的研究者投入到基于脑电的情绪识别研究中。然而在实际应用中,建立高精确度的情绪识别模型仍面临巨大的挑战,其中一个难点就是如何剔除或降低脑电信号的时间效应,进而提高情绪识别模型的时间鲁棒性。拟通过增加情绪模型中训练样本的天数,降低时间效应对识别模型的影响。利用视频诱发被试的正性、中性、负性3种情绪状态,共9名被试参与实验,每名被试需在1个月内进行5次数据采集,每次采集的时间间隔分别是1天、3天、1周和2周。采集被试60导联的脑电信号,并提取6个频段的功率谱特征。在模式识别阶段,分类器的训练样本分别来自N天的样本(N=1,2,3,4),剩余(5-N)天的数据则作为测试样本,得到不同训练天数下的分类正确率。结果表明:脑电时间效应的确会影响情绪识别的正确率,当训练集与测试集中的样本来源于不同的两天时,识别率显著下降(P<0.01);随着训练集样本天数的增加,正确率提高,正确率与训练样本的天数呈正相关;当训练集中样本来源于2~4天时,相比于1天的情况,平均正确率的提高率分别为6.45%(P=0.006)、10.48%(P=0.000)、14.40%(P=0.000),即增加训练集中样本的来源天数,能显著降低时间效应对分类效果的影响。结果证实,脑电时间效应能显著降低情绪识别模型的识别正确率,增加训练样本的天数可降低时间效应对识别模型的影响,并提高情绪识别模型的时间鲁棒性,从而为情绪模型从理论研究走向应用提供技术支持与研究思路。     

基于脑电信号的情感识别方法综述

情感识别是让计算机感知人类情感状态从而进行人机情感交互的关键技术,已经成为人工智能领域的研究热点。计算机对人类情感的感知可分为"感"和"知"两部分:"感"是指计算机对人类面部表情和语音等非生理信号以及外围神经和脑部电信号等生理信号的获取;"知"是指计算机对获取信号的识别和推断。基于脑电信号的感知方法因其具有较高的识别率而成为情感识别最主要的手段之一,其主要步骤为脑电信号获取、预处理、特征提取以及分类识别。本文对脑电情感识别方法中各步骤所涉及的研究方法进行了归纳和总结,介绍了脑电信号的采集和常用数据库以及去除伪迹信号的预处理方法,从时域、频域、时频域和非线性动力学角度归纳了脑电信号的特征提取方法,总结了常用的机器识别分类的无监督学习和有监督学习方法,最后探讨了脑电信号情感识别研究中存在的问题并展望了未来发展方向,以期为相关研究带来一定的借鉴。     

基于ZigBee技术的儿童生理参数采集与情绪检测系统

为了实现儿童情绪检测与识别的功能,我们提出了穿戴式生理参数检测系统的概念,并设计了以CC2530芯片为核心,以Zig Bee为传输技术的穿戴式儿童情绪生理参数检测系统。系统采集处理的生理指标主要有心电信号、体温和皮肤电反应。传感器获取的模拟信号经过前置滤波放大后,通过A/D转换器转换成数字量,然后经由Zig Bee无线网络节点上传至上位机,由系统实时地处理数据。经仿真试验,系统具有较高的识别准确率。     

基于变尺度符号化补偿传递熵的EEG压力情感分析

基于脑电信号的情感识别,对于相关情感疾病的诊断与治疗有着重要的临床和科研意义.如何有效地提取特征,提高识别率,减少计算时间是研究的重点.从研究脑通道间定向信息交互的角度出发,结合对瞬时因果效应的补偿算法,提出以变尺度符号化补偿传递熵(VSSCTE)为特征的情感分析方法,并以此构建情感因效性脑网络,使用网络测度与Reli...     

Emotion recognition from physiological signals

Emotion recognition is one of the great challenges in human–human and human–computer interaction. Accurate emotion recognition would allow computers to recognize human emotions and therefore react accordingly. In this paper, an approach for emotion recognition based on physiological signals is proposed. Six basic emotions: joy, sadness, fear, disgust, neutrality and amusement are analysed using physiological signals. These emotions are induced through the presentation of International Affecting Picture System (IAPS) pictures to the subjects. The physiological signals of interest in this analysis are: electromyogram signal (EMG), respiratory volume (RV), skin temperature (SKT), skin conductance (SKC), blood volume pulse (BVP) and heart rate (HR). These are selected to extract characteristic parameters, which will be used for classifying the emotions. The SVM (support vector machine) technique is used for classifying these parameters. The experimental results show that the proposed methodology provides in general a recognition rate of 85% for different emotional states.     

Smart environment architecture for emotion detection and regulation

This paper introduces an architecture as a proof-of-concept for emotion detection and regulation in smart health environments. The aim of the proposal is to detect the patient’s emotional state by analysing his/her physiological signals, facial expression and behaviour. Then, the system provides the best-tailored actions in the environment to regulate these emotions towards a positive mood when possible. The current state-of-the-art in emotion regulation through music and colour/light is implemented with the final goal of enhancing the quality of life and care of the subject. The paper describes the three main parts of the architecture, namely “Emotion Detection”, “Emotion Regulation” and “Emotion Feedback Control”. “Emotion Detection” works with the data captured from the patient, whereas “Emotion Regulation” offers him/her different musical pieces and colour/light settings. “Emotion Feedback Control” performs as a feedback control loop to assess the effect of emotion regulation over emotion detection. We are currently testing the overall architecture and the intervention in real environments to achieve our final goal.     

Emotion recognition from physiological signals

Emotion recognition is one of the great challenges in human-human and human-computer interaction. Accurate emotion recognition would allow computers to recognize human emotions and therefore react accordingly. In this paper, an approach for emotion recognition based on physiological signals is proposed. Six basic emotions: joy, sadness, fear, disgust, neutrality and amusement are analysed using physiological signals. These emotions are induced through the presentation of International Affecting Picture System (IAPS) pictures to the subjects. The physiological signals of interest in this analysis are: electromyogram signal (EMG), respiratory volume (RV), skin temperature (SKT), skin conductance (SKC), blood volume pulse (BVP) and heart rate (HR). These are selected to extract characteristic parameters, which will be used for classifying the emotions. The SVM (support vector machine) technique is used for classifying these parameters. The experimental results show that the proposed methodology provides in general a recognition rate of 85% for different emotional states.     

面孔表情的ERP研究进展

情绪 (emotion)是情感的外部表现 ,是人们适应性的一种表现 ,也构成了一个基本的动机系统。面孔是人类表达、认知情感的重要工具和途径 ,正确的表达和识别面部表情是人类生存的一项重要的技能。人们运用各种手段研究面孔、情绪、大脑及其与其他认知方面的关系 ,本文总结了前人利用事件相关电位 (ERP)技术研究面孔和情绪的方法、结果、影响因素并且对面孔及情绪的ERP研究提出问题并做出了展望。     

Emotion recognition system using short-term monitoring of physiological signals

A physiological signal-based emotion recognition system is reported. The system was developed to operate as a user-independent system, based on physiological signal databases obtained from multiple subjects. The input signals were electrocardiogram, skin temperature variation and electrodermal activity, all of which were acquired without much discomfort from the body surface, and can reflect the influence of emotion on the autonomic nervous system. The system consisted of preprocessing, feature extraction and pattern classification stages. Preprocessing and feature extraction methods were devised so that emotion-specific characteristics could be extracted from short-segment signals. Although the features were carefully extracted, their distribution formed a classification problem, with large overlap among clusters and large variance within clusters. A support vector machine was adopted as a pattern classifier to resolve this difficulty. Correct-classification ratios for 50 subjects were 78.4% and 61.8%, for the recognition of three and four categories, respectively.     

羞耻和一般负性情绪的认知调节策略

目的:研究个体对羞耻与一般负性情绪的认知情绪调节的差异,以及高低特质羞耻者对羞耻与一般负性情绪的认知调节特点.方法:采用方便取样,500名大学生填写羞耻体验量表(Experience of Shame Scale,ESS)和认知情绪调节问卷(Cognitive Emotion Regulation Questionnaire,CERQ).结果:个体在羞耻情绪和一般负性情绪时使用的认知调节策略有显著差异;高羞耻和低羞耻者倾向于使用不同的认知调节策略,而且这种差异大体一致地存在于调节羞耻情绪和一般负性情绪时.结论:个体对羞耻情绪的认知调节不同于对一般负性情绪的认知调节,特质羞耻者有其独特的认知情绪调节方式.     

Colour influences perception of facial emotions but this effect is impaired in healthy ageing and schizophrenia

Introduction. Social cognition is commonly assessed by identification of emotions in facial expressions. Presence of colour, a salient feature of stimuli, might influence emotional face perception.

Methods. We administered 2 tests of facial emotion recognition, the Emotion Recognition Test (ER40) using colour pictures and the Penn Emotional Acuity Test using monochromatic pictures, to 37 young healthy, 39 old healthy and 37 schizophrenic men.

Results. Among young healthy individuals recognition of emotions was more accurate and faster in colour than in monochromatic pictures. Compared to the younger group, older healthy individuals revealed impairment in identification of sad expressions in colour but not monochromatic pictures. Schizophrenia patients showed greater impairment in colour than monochromatic pictures of neutral and sad expressions and overall total score compared to both healthy groups. Patients showed significant correlations between cognitive impairment and perception of emotion in colour but not monochromatic pictures.

Conclusions. Colour enhances perception of general emotional clues and this contextual effect is impaired in healthy ageing and schizophrenia. The effects of colour need to be considered in interpreting and comparing studies of emotion perception. Coloured face stimuli may be more sensitive to emotion processing impairments but less selective for emotion-specific information than monochromatic stimuli. This may impact on their utility in early detection of impairments and investigations of underlying mechanisms.