Left-Right Swapping and Upper-Lower Limb Pairing for Robust Multi-Wearable Workout Activity Detection
This work addresses robust activity detection for fitness tracking using wearables, but it is incremental as it builds on existing methods with specific data augmentations.
The paper tackled inconsistencies in wearable orientation for workout activity detection by exploring multi-wearable data augmentation techniques, resulting in macro F1-score improvements from 90.01% to up to 91.87%.
This work presents the solution of the Signal Sleuths team for the 2024 HASCA WEAR challenge. The challenge focuses on detecting 18 workout activities (and the null class) using accelerometer data from 4 wearables - one worn on each limb. Data analysis revealed inconsistencies in wearable orientation within and across participants, leading to exploring novel multi-wearable data augmentation techniques. We investigate three models using a fixed feature set: (i) "raw": using all data as is, (ii) "left-right swapping": augmenting data by swapping left and right limb pairs, and (iii) "upper-lower limb paring": stacking data by using upper-lower limb pair combinations (2 wearables). Our experiments utilize traditional machine learning with multi-window feature extraction and temporal smoothing. Using 3-fold cross-validation, the raw model achieves a macro F1-score of 90.01%, whereas left-right swapping and upper-lower limb paring improve the scores to 91.30% and 91.87% respectively.