A Multi-Sensor Deep Learning Approach for Complex Daily Living Activity Recognition

With the ever increasing elderly population, human activity trackers can help monitor the daily physical activities performed by the elderly in order to contribute towards improvements in independent living and quality of life. Little activity recognition research has explored the use of multiple Inertial Measurement Units (IMU) to capture both simple and complex human activities. Therefore, existing research may not benefit the monitoring of the elderly population wherein the complexity in the details of changes are not captured. This work proposes a multi-sensor approach measuring acceleration and quaternion values to recognise both simple and complex daily living activities using a deep learning approach. We compare and evaluate the performance of using 1, 3 and 5 on-body IMU sensors to train CNN and LSTM networks with both acceleration and quaternion values. The results show that the adoption of the quaternion values from 5 on-body sensors using the LSTM model outperforms all other models (F1-score-0.9606). This high performance provides many opportunities for the accurate monitoring of complex daily living activities.

Automated summary

With the increasing elderly population, human activity trackers can monitor daily physical activities of the elderly, improving independent living and quality of life. Limited research has explored the use of multiple Inertial Measurement Units (IMU) to capture simple and complex human activities, which may not effectively monitor the complexity of changes in the elderly population. This study proposes a multi-sensor approach using acceleration and quaternion values to recognize daily living activities, achieving high performance with the LSTM model.