Classifying Daily and Sports Activities Invariantly to the Positioning of Wearable Motion Sensor Units
| Autor: | Aras Yurtman, Billur Barshan |
|---|---|
| Přispěvatelé: | Barshan, Billur, Yurtman, Aras |
| Rok vydání: | 2020 |
| Předmět: |
Computer Networks and Communications
Computer science Feature extraction Wearable computer Inertial sensors 02 engineering and technology Activity recognition Activity recognition and monitoring Position (vector) 0202 electrical engineering electronic engineering information engineering Computer vision Flexibility (engineering) Wearable motion sensors Orientation (computer vision) business.industry 020206 networking & telecommunications Motion detection Gyroscope Rigid body Magnetometer Wearable sensing Internet of Things (IoT) Machine learning classifiers Computer Science Applications Accelerometer Hardware and Architecture Signal Processing Position-invariant sensing 020201 artificial intelligence & image processing Artificial intelligence business Information Systems |
| Zdroj: | IEEE Internet of Things Journal |
| ISSN: | 2372-2541 |
| DOI: | 10.1109/jiot.2020.2969840 |
| Popis: | We propose techniques that achieve invariance to the positioning of wearable motion sensor units on the body for the recognition of daily and sports activities. Using two sequence sets based on the sensory data allows each unit to be placed at any position on a given rigid body part. As the unit is shifted from its ideal position with larger displacements, the activity recognition accuracy of the system that uses these sequence sets degrades slowly, whereas that of the reference system (which is not designed to achieve position invariance) drops very fast. Thus, we observe a tradeoff between the flexibility in sensor unit positioning and the classification accuracy. The reduction in the accuracy is at acceptable levels, considering the convenience and flexibility provided to the user in the placement of the units. We compare the proposed approach with an existing technique to achieve position invariance and combine the former with our earlier methodology to achieve orientation invariance. We evaluate our proposed methodology on a publicly available data set of daily and sports activities acquired by wearable motion sensor units. The proposed representations can be integrated into the preprocessing stage of existing wearable systems without significant effort. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|