Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition 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 {\alpha}-\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.
Code (0)
등록된 구현이 없습니다.
Tasks
Activity RecognitionClusteringHuman Activity RecognitionUncertainty QuantificationSimilar Papers 제목 키워드 기반
Uncertainty-aware Bridge based Mobile-Former Network for Event-based Pattern Recognition
The mainstream human activity recognition (HAR) algorithms are developed based on RGB cameras, which are easily influenced by low-quality images (e.g., low illumination, motion blur). Meanwhile, the privacy protection is…
Activity RecognitionHuman Activity RecognitionSpatial Uncertainty Quantification in Wildfire Forecasting for Climate-Resilient Emergency Planning
Climate change is intensifying wildfire risks globally, making reliable forecasting critical for adaptation strategies. While machine learning shows promise for wildfire prediction from Earth observation data, current ap…
Decision MakingScenario-aware Uncertainty Quantification for Trajectory Prediction with Statistical Guarantees
Reliable uncertainty quantification in trajectory prediction is crucial for safety-critical autonomous driving systems, yet existing deep learning predictors lack uncertainty-aware frameworks adaptable to heterogeneous r…
Trajectory PredictionAutonomous DrivingSemantic Enrichment of Mobile Phone Data Records Using Background Knowledge
Every day, billions of mobile network events (i.e. CDRs) are generated by cellular phone operator companies. Latent in this data are inspiring insights about human actions and behaviors, the discovery of which is importa…
Amortized Bayesian inference for actigraph time sheet data from mobile devices
Mobile data technologies use ``actigraphs'' to furnish information on health variables as a function of a subject's movement. The advent of wearable devices and related technologies has propelled the creation of health d…
Bayesian InferenceTransfer Learning