Learning Behavioral Representations of Routines From Large-scale Unlabeled Wearable Time-series Data Streams using Hawkes Point Process

TL;DR

This paper introduces HOT-ROD, a novel framework that uncovers human behavioral routines from unlabeled wearable sensor data using clustering and Hawkes point process modeling, without relying on activity labels or additional context.

Contribution

The work presents a new method for discovering routines directly from unlabeled wearable time-series data using covariance-based clustering and Hawkes process modeling, avoiding privacy-invasive contextual data.

Findings

Successfully extracted routines from data of over 100 individuals.

Captured daily transitions between physical activity states.

Behavioral patterns linked to personality and affect insights.

Abstract

Continuously-worn wearable sensors enable researchers to collect copious amounts of rich bio-behavioral time series recordings of real-life activities of daily living, offering unprecedented opportunities to infer novel human behavior patterns during daily routines. Existing approaches to routine discovery through bio-behavioral data rely either on pre-defined notions of activities or use additional non-behavioral measurements as contexts, such as GPS location or localization within the home, presenting risks to user privacy. In this work, we propose a novel wearable time-series mining framework, Hawkes point process On Time series clusters for ROutine Discovery (HOT-ROD), for uncovering behavioral routines from completely unlabeled wearable recordings. We utilize a covariance-based method to generate time-series clusters and discover routines via the Hawkes point process learning algorithm. We empirically validate our approach for extracting routine behaviors using a completely unlabeled time-series collected continuously from over 100 individuals both in and outside of the workplace during a period of ten weeks. Furthermore, we demonstrate this approach intuitively captures daily transitional relationships between physical activity states without using prior knowledge. We also show that the learned behavioral patterns can assist in illuminating an individual's personality and affect.