HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound
Researchers have introduced HARMES, a new multi-modal dataset for wearable human activity recognition. The dataset combines motion sensing, environmental data, and audio from wrist-worn devices, totaling over 80 hours of data from 20 participants performing household activities. HARMES is designed to improve the recognition of daily living activities, which can be ambiguous with single modalities, and is significantly larger than previous datasets of its kind. AI
IMPACT Provides a large, multi-modal dataset to advance research in wearable human activity recognition.