Improving the Recognition of Eating Gestures Using Intergesture Sequential Dependencies
| Autor: | Eric R. Muth, Raul I. Ramos-Garcia, John N. Gowdy, Adam Hoover |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
InformationSystems_INFORMATIONINTERFACESANDPRESENTATION(e.g.
HCI) Computer science Movement Speech recognition Context (language use) Motion (physics) Pattern Recognition Automated Activity recognition Eating Health Information Management Activities of Daily Living Neighbor classifier Humans Electrical and Electronic Engineering Hidden Markov model Gestures Contextual image classification business.industry Signal Processing Computer-Assisted Pattern recognition Wrist Markov Chains Telemedicine Computer Science Applications ComputingMethodologies_PATTERNRECOGNITION Gesture recognition Artificial intelligence business Algorithms Biotechnology Gesture |
| Zdroj: | IEEE Journal of Biomedical and Health Informatics. 19:825-831 |
| ISSN: | 2168-2208 2168-2194 |
| DOI: | 10.1109/jbhi.2014.2329137 |
| Popis: | This paper considers the problem of recognizing eating gestures by tracking wrist motion. Eating gestures are activities commonly undertaken during the consumption of a meal, such as sipping a drink of liquid or using utensils to cut food. Each of these gestures causes a pattern of wrist motion that can be tracked to automatically identify the activity. Previous works have studied this problem at the level of a single gesture. In this paper, we demonstrate that individual gestures have sequential dependence. To study this, three types of classifiers were built: 1) a K-nearest neighbor classifier which uses no sequential context, 2) a hidden Markov model (HMM) which captures the sequential context of subgesture motions, and 3) HMMs that model intergesture sequential dependencies. We built first-order to sixth-order HMMs to evaluate the usefulness of increasing amounts of sequential dependence to aid recognition. On a dataset of 25 meals, we found that the baseline accuracies for the KNN and the subgesture HMM classifiers were 75.8% and 84.3%, respectively. Using HMMs that model intergesture sequential dependencies, we were able to increase accuracy to up to 96.5%. These results demonstrate that sequential dependencies exist between eating gestures and that they can be exploited to improve recognition accuracy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|