We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Real-Time Sensor-Based Human Activity Recognition for eFitness and eHealth Platforms.
- Authors
Czekaj, Łukasz; Kowalewski, Mateusz; Domaszewicz, Jakub; Kitłowski, Robert; Szwoch, Mariusz; Duch, Włodzisław
- Abstract
Human Activity Recognition (HAR) plays an important role in the automation of various tasks related to activity tracking in such areas as healthcare and eldercare (telerehabilitation, telemonitoring), security, ergonomics, entertainment (fitness, sports promotion, human–computer interaction, video games), and intelligent environments. This paper tackles the problem of real-time recognition and repetition counting of 12 types of exercises performed during athletic workouts. Our approach is based on the deep neural network model fed by the signal from a 9-axis motion sensor (IMU) placed on the chest. The model can be run on mobile platforms (iOS, Android). We discuss design requirements for the system and their impact on data collection protocols. We present architecture based on an encoder pretrained with contrastive learning. Compared to end-to-end training, the presented approach significantly improves the developed model's quality in terms of accuracy (F1 score, MAPE) and robustness (false-positive rate) during background activity. We make the AIDLAB-HAR dataset publicly available to encourage further research.
- Subjects
HUMAN activity recognition; ARTIFICIAL neural networks; HUMAN-computer interaction; MOTION detectors; END-to-end delay; MOBILE operating systems
- Publication
Sensors (14248220), 2024, Vol 24, Issue 12, p3891
- ISSN
1424-8220
- Publication type
Article
- DOI
10.3390/s24123891