COMPASS: Unsupervised and Online Clustering of Complex Human Activities from Smartphone Sensors

TL;DR

COMPASS is an unsupervised, online clustering algorithm that dynamically identifies user contexts from high-dimensional smartphone sensor data without predefined categories, outperforming existing methods in accuracy and efficiency.

Contribution

This paper introduces COMPASS, a novel unsupervised and online clustering method capable of discovering arbitrary user contexts from sensor streams without prior knowledge.

Findings

Successfully identifies user contexts in real-time from sensor data

Outperforms state-of-the-art solutions in cluster quality and purity

Processes 1000 samples in less than 20 seconds

Abstract

Modern mobile devices are able to provide context-aware and personalized services to the users, by leveraging on their sensing capabilities to infer the activity and situation in which a person is currently involved. Current solutions for context-recognition rely on annotated data and experts’ knowledge to predict the user context. In addition, their prediction ability is strongly limited to the set of situations considered during the model training or definition. However, in a mobile environment, the user context continuously evolves, and it cannot be merely restricted to a set of predefined classes. To overcome these limitations, we propose COMPASS, a novel unsupervised and online clustering algorithm aimed at identifying the user context in mobile environments based on the stream of high-dimensional data generated by smartphone sensors. COMPASScan distinguish an arbitrary number of user’s contexts from the sensors’ data, without defining a priori the collection of expected situations. This key feature makes it a general-purpose solution to provide context-aware features to mobile devices, supporting a broad set of applications. Experimental results on 18 synthetic and 2 real-world datasets show that COMPASS correctly identifies the user context from the sensors’ data stream, and outperforms the state-of-the-art solutions in terms of both clusters configuration and purity. Eventually, we evaluate its performances in terms of execution time and the results show that COMPASS can process 1000 high-dimensional samples in less than 20 seconds, while the reference solutions require about 60 minutes to evaluate the entire dataset. Keywords: Context-awareness, Unsupervised Machine Learning, Online Clustering, Mobile Computing