MPED: A Multi-Modal Physiological Emotion Database for Discrete Emotion Recognition

• Published in: IEEE access Vol. 7; pp. 12177 - 12191
• Main Authors: Song, Tengfei, Zheng, Wenming, Lu, Cheng, Zong, Yuan, Zhang, Xilei, Cui, Zhen
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: affective computing; Brain modeling; Clips; Discrete emotion recognition; EEG; Electrocardiography; Electroencephalography; Emotion recognition; Emotions; Feature extraction; Galvanic skin response; LSTM; machine learning; Physiological responses; physiological signals; Physiology; Support vector machines; video-induced emotion
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2891579

To explore human emotions, in this paper, we design and build a multi-modal physiological emotion database, which collects four modal physiological signals, i.e., electroencephalogram (EEG), galvanic skin response, respiration, and electrocardiogram (ECG). To alleviate the influence of culture dependent elicitation materials and evoke desired human emotions, we specifically collect an emotion elicitation material database selected from more than 1500 video clips. By the considerable amount of strict man-made labeling, we elaborately choose 28 videos as standardized elicitation samples, which are assessed by psychological methods. The physiological signals of participants were synchronously recorded when they watched these standardized video clips that described six discrete emotions and neutral emotion. With three types of classification protocols, different feature extraction methods and classifiers (support vector machine and k-NearestNeighbor) were used to recognize the physiological responses of different emotions, which presented the baseline results. Simultaneously, we present a novel attention-long short-term memory (A-LSTM), which strengthens the effectiveness of useful sequences to extract more discriminative features. In addition, correlations between the EEG signals and the participants' ratings are investigated. The database has been made publicly available to encourage other researchers to use it to evaluate their own emotion estimation methods.