项目名称: 基于光学成像的情绪脑模式识别关键技术研究
项目编号: No.61273287
项目类型: 面上项目
立项/批准年度: 2013
项目学科: 自动化技术、计算机技术
项目作者: 朱朝喆
作者单位: 北京师范大学
项目金额: 83万元
中文摘要: 情绪识别是人机交互智能化中情感计算的关键环节,是情绪监控、基于脑-机接口的情绪调节能力训练等情绪识别应用领域的基础。近红外光学脑成像(fNIRS)是一种实用性很强的非侵入式神经活动观测技术。本研究拟开展基于近红外光学成像的情绪脑模式识别关键技术研究,具体包括实时可视化定位、噪声滤除、特征提取、分类器训练等核心部分。同时,本研究借助fNIRS成本低、生态效度好等优点,完成大样本量情绪识别模型验证性研究,并最终建立可靠的情绪脑模式识别模型。本研究是信息科学与认知神经科学深度交叉的创新工作。
中文关键词: 模式识别;情绪识别;近红外脑成像;重测信度;基于稳定性与可分性的特征选择
英文摘要: Emotion recognition is the key node of affective computing in intelligent human-computer interaction,and it is the fundation of both emotion monitoring and BCI-based emotion regulation training. Functional near-infrared spectroscopy (fNIRS) is a novel non-invasive brain imaging technique. In this project, we propose to use fNIRS for brain-based emotion recognition including real-time visual-localization, denoising, feature-extacting, classifier-training. Moreover, benifited from advantages of fNIRS, such as low cost and good ecological validity, we will accomplish validation of the emotion recognition model using a large sample.
英文关键词: pattern recognition;emotion recognition;fNIRS;test-retest reliability;stability and separability based feature selection