Generalization of Fitness Exercise Recognition from Doppler Measurements by Domain-adaption and Few-Shot Learning
This addresses the generalization issue for mobile health applications using Doppler sensing, but it is incremental as it builds on prior work with controlled data.
The paper tackled the problem of fitness exercise recognition models trained in lab environments performing poorly in realistic scenarios due to user, environment, and device variations, and improved recognition accuracy by two to six folds compared to the baseline for different users by using domain adaptation and few-shot learning.
In previous works, a mobile application was developed using an unmodified commercial off-the-shelf smartphone to recognize whole-body exercises. The working principle was based on the ultrasound Doppler sensing with the device built-in hardware. Applying such a lab-environment trained model on realistic application variations causes a significant drop in performance, and thus decimate its applicability. The reason of the reduced performance can be manifold. It could be induced by the user, environment, and device variations in realistic scenarios. Such scenarios are often more complex and diverse, which can be challenging to anticipate in the initial training data. To study and overcome this issue, this paper presents a database with controlled and uncontrolled subsets of fitness exercises. We propose two concepts to utilize small adaption data to successfully improve model generalization in an uncontrolled environment, increasing the recognition accuracy by two to six folds compared to the baseline for different users.