AnnoTainted: Automating Physical Activity Ground Truth Collection Using Smartphones

Abstract

In this work, we provide motivation for a zero-effort crowdsensing task: auto-annotated ground truth collection for physical activity recognition. Data obtained through Smartphones for classification of human activities is prone to discrepancies, which reiterates the need for better and larger activity datasets. Artificial data generation algorithms fail to efficiently generate quality instances for minority data. In the proposed model, crowd-sourced sensor data is classified by a robust classifier built by researchers ground up. We nominate a Generic Classifier with ≥ 95% accuracy for this purpose. Data collection and distribution models which ensure that the crowd client receives non-skewed, quality data from locations with higher degree of activity occurrence are elucidated upon. Also integrated within our proposed model are Location-Specific Classifiers, which can be utilized by developers to optimize on location-specific tasks. Effective validation of classified activities using diverse sensor data streams improves the proposed classifier systems and boosts ground-truth accuracy.