Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery
This work addresses adaptability and performance issues in mobile activity recognition for wearable computing users, though it appears incremental as it builds on existing deep learning and uncertainty quantification methods.
The paper tackled the challenges of context-dependent activity characteristics and unknown contexts in wearable activity recognition by developing a context-aware mixture of deep models with uncertainty quantification, improving accuracy and F score by 10% through data-driven context identification and unknown context discovery.
Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur from time to time, requiring flexibility and adaptability of the algorithm. We develop a context-aware mixture of deep models termed the α-\b{eta} network coupled with uncertainty quantification (UQ) based upon maximum entropy to enhance human activity recognition performance. We improve accuracy and F score by 10% by identifying high-level contexts in a data-driven way to guide model development. In order to ensure training stability, we have used a clustering-based pre-training in both public and in-house datasets, demonstrating improved accuracy through unknown context discovery.