EmoWear: Wearable Physiological and Motion Dataset for Emotion Recognition and Context Awareness

The EmoWear dataset provides a bridge to explore Emotion Recognition (ER) via Seismocardiography (SCG), the measurement of small cardio-respiratory induced vibrations on the chest wall through Inertial Measurement Units (IMUs). We recorded Accelerometer (ACC), Gyroscope (GYRO), Electrocardiography (...

Full description

Saved in:
Bibliographic Details
Published in:Scientific data 2024-06, Vol.11 (1), p.648-18, Article 648
Main Authors: Rahmani, Mohammad Hasan, Symons, Michelle, Sobhani, Omid, Berkvens, Rafael, Weyn, Maarten
Format: Article
Language:English
Subjects:
631/477
639/166/985
639/705/117
706/689/112
Arousal
Correlation analysis
Data Descriptor
Datasets
EKG
Electrocardiography
Emotions
Ethics
Gait
Humanities and Social Sciences
Humans
Investigations
Motion detection
multidisciplinary
Respiration
Science
Science (multidisciplinary)
Sensors
Vibrations
Wearable Electronic Devices
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The EmoWear dataset provides a bridge to explore Emotion Recognition (ER) via Seismocardiography (SCG), the measurement of small cardio-respiratory induced vibrations on the chest wall through Inertial Measurement Units (IMUs). We recorded Accelerometer (ACC), Gyroscope (GYRO), Electrocardiography (ECG), Blood Volume Pulse (BVP), Respiration (RSP), Electrodermal Activity (EDA), and Skin Temperature (SKT) data from 49 participants who watched validated emotionally stimulating video clips. They self-assessed their emotional valence, arousal, and dominance, as well as extra questions about the video clips. Also, we asked the participants to walk, talk, and drink, so that researchers can detect gait, voice, and swallowing using the same IMU. We demonstrate the effectiveness of emotion stimulation with statistical methods and verify the quality of the collected signals through signal-to-noise ratio and correlation analysis. EmoWear can be used for ER via SCG, ER during gait, multi-modal ER, and the study of IMUs for context-awareness. Targeted contextual information include emotions, gait, voice activity, and drinking, all having the potential to be sensed via a single IMU.
ISSN:2052-4463
2052-4463
DOI:10.1038/s41597-024-03429-3