Few-Shot Classification for Human Context Recognition Using Smartphone Data Traces

Luke Buquicchio, Walter Gerych, Abdulaziz Alajaji, Kavin Chandrasekaran, Hamid Mansoor, Elke A. Rundensteiner, Emmanuel Agu

Abstract: Human Context Recognition (HCR) is an important field at the intersection of personalized healthcare and ubiquitous computing that aims to describe the current state of a person given mobile sensor data. Previous work has demonstrated the ability to detect various ailments through context patterns and deviations from those patterns, illustrating an important application of HCR. Contexts captured by mobile sensor data are often associated with high intra-subject and inter-subject variability, which hinders the process of effectively learning representations for each class. Obtaining a sufficient quantity of labeled context data for reliable predictions becomes prohibitively expensive as the number of users and targeted contexts increases. Few-Shot Classification is a family of methods wherein models are trained with limited amounts of labeled data such that their latent representations can be used for transferring information from one context to another. In this paper, we provide the first comprehensive study of state-of-the-art Few-Shot classifiers on HCR data. We find that methods that fine-tune classifiers using a general feature extractor on limited labeled samples outperform more sophisticated Few Shot techniques in the HCR setting by up to 50%.