Prism: Mining Task-aware Domains in Non-i.i.d. IMU Data for Flexible User Perception

TL;DR

Prism is a novel approach that identifies task-aware domains within non-i.i.d. IMU data to enable accurate and flexible user perception on mobile devices, overcoming limitations of traditional methods.

Contribution

The paper introduces Prism, a method that discovers latent domains in IMU data and trains domain-aware models, improving online prediction accuracy in uncontrolled settings.

Findings

Achieves high FUP accuracy on mobile devices.

Outperforms existing methods with low latency.

Validated through extensive experiments.

Abstract

A wide range of user perception applications leverage inertial measurement unit (IMU) data for online prediction. However, restricted by the non-i.i.d. nature of IMU data collected from mobile devices, most systems work well only in a controlled setting (e.g., for a specific user in particular postures), limiting application scenarios. To achieve uncontrolled online prediction on mobile devices, referred to as the flexible user perception (FUP) problem, is attractive but hard. In this paper, we propose a novel scheme, called Prism, which can obtain high FUP accuracy on mobile devices. The core of Prism is to discover task-aware domains embedded in IMU dataset, and to train a domain-aware model on each identified domain. To this end, we design an expectation-maximization (EM) algorithm to estimate latent domains with respect to the specific downstream perception task. Finally, the best-fit model can be automatically selected for use by comparing the test sample and all identified domains in the feature space. We implement Prism on various mobile devices and conduct extensive experiments. Results demonstrate that Prism can achieve the best FUP performance with a low latency.