Assessing the impact of body location on the accuracy of detecting daily activities with accelerometer data

Abstract

Recent advancements in digital biomarkers have highlighted the importance of accelerometer and gyroscope data for monitoring activities, identifying motion-related diseases, and assessing disease severity. Prior studies predominantly limit sensor placement to one or two locations. Here, we conducted a trial focusing on the impact of sensor placement in predicting 21 common activities using convolutional neural networks (CNN) and long short-term memory networks (LSTM). Our research found that the optimal locations for activity detection are the right and left upper arms, right wrist, and lower back. These locations yielded an average AUC of 0.76-0.77 using both accelerometer and gyroscope data. Combining data from all locations improved AUC to 0.796 for accelerometer and 0.811 for gyroscope data. We also noted specific activity-body part sensitivity relationships. This study provides a valuable reference for selecting appropriate sensor locations in future digital biomarker studies focused on specific activities.