Diary-Like Long-Term Activity Recognition: Touch or Voice Interaction?

The experience sampling methodology is a well known tool in psychology to asses a subject's condition. Regularly or whenever an important event happens the subject stops whatever he is currently involved in and jots down his current perceptions, experience, and activities, which in turn form the basis of these diary studies. Such methods are also widely in use for gathering labelled data for wearable long-term activity recognition, where subjects are asked to note conducted activities. We present the design of a personal electronic diary for daily activities, including user interfaces on a PC, Smartphone, and Google Glass. A 23-participant structured in-field study covering seven different activities highlights the difference of mobile touch interaction and ubiquitous voice recognition for tracking activities.

I. Introduction

Ecological Momentary Assessment (EMA) [1] is a type of psychological study design concerned with the sampling of experiences throughout the course of a day. In contrast to study designs like End-of-Day diaries, EMA designs are less prone recall, recency, peak and summary bias [2]. Mainly because the sampling happens on a regular basis by the use of electronic diaries. These can be either watches, palm computers, Smartphones or any other mobile computing device, which remind the participant that an input is necessary. This “manual” sampling of experiences / activities is dual to gathering self-reported ground truth for wearable activity recognition systems.