A Context Model for Personal Data Streams

TL;DR

This paper introduces a context model for personal sensor data streams that helps organize and reason about large-scale data from mobile devices, validated on extensive real-world datasets.

Contribution

It presents a novel model of situational context for personal data streams, enabling better organization and reasoning over massive sensor data collected from mobile devices.

Findings

Model effectively organizes large sensor data streams.

Validated on data from 158 individuals over four weeks.

Demonstrates potential for improved personal data analysis.

Abstract

We propose a model of the situational context of a person and show how it can be used to organize and, consequently, reason about massive streams of sensor data and annotations, as they can be collected from mobile devices, e.g. smartphones, smartwatches or fitness trackers. The proposed model is validated on a very large dataset about the everyday life of one hundred and fifty-eight people over four weeks, twenty-four hours a day.