Individual Convolution of Ankle, Hip, and Wrist Data for Activities-of-Daily-Living Classification

Abstract

The Activities of Daily Living (ADL) include activities such as brushing teeth, sweeping, and walking that are critical to on-going health, especially in older adults. Activities may be determined using recorded video and 2D-CNNs, however video recordings present privacy and coverage challenges in personal spaces. Smartphones and newer wristworn devices that record motion data can also be used for activity recognition tasks. Ankle or shoe-based devices such as the retired Nike+ sensor are less common, however ear-based devices which may record head movement are gaining popularity. In this work we use accelerometer data from a recently released dataset using devices placed on the ankle, hip, and wrist. First, we evaluate a simple 1D-CNNs ability to classify the 17 included activities in subject-dependent and subject-independent analysis. Then we process the accelerometer data from the three sensors individually to evaluate each location’s ability to predict activities. Finally, we develop a functional model which independently executes a 1D-CNN for each sensor’s data and combines the results using Global Average Pooling. The functional model achieves a subject-independent accuracy of 70.7%.