Health Assistant Wearable-Based Data Science System Model: A Pilot Study
Authors:
- 1 September 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 438-442
Abstract
The rapid development of Information and Communication Technology (ICT) has an impact on the innovation of new technology that gives benefits for health. One of its latest development is wearable device technology. Nowadays, the growth of this technology market is very positive. But unfortunately the growth of this technology is not followed by the availability of supporting applications that provide maximum benefits for users by utilizing personal health and activity data. This paper is intended to provide a report of our initial research in developing a health assistant solution that utilizes wearable device generated data. The whole research process is executed using Design Thinking approach that put the users as the main consideration. This initial research is started by designing a field research that can potentially gathered users' data generated from wearable device. A series of statistical and machine learning techniques are presented to analyze time series data to create a model. Finally, to implement the model, a mobile application prototype is also proposed. The outcomes from this initial research will be used to develop a fully working solution.Keywords
This publication has 12 references indexed in Scilit:
- Computer vision-based visitor study as a decision support system for museum2017
- Video processing using GPU-accelerator under desktop virtualization environment2016
- Sustainable Wearables: Wearable Technology for Enhancing the Quality of Human LifeSustainability, 2016
- The Rise of Consumer Health Wearables: Promises and BarriersPLOS Medicine, 2016
- Deep learningNature, 2015
- Analysis of Ordinal Categorical Data2010
- Sitting Time and Mortality from All Causes, Cardiovascular Disease, and CancerMedicine & Science in Sports & Exercise, 2009
- TV Viewing and Physical Activity Are Independently Associated with Metabolic Risk in Children: The European Youth Heart StudyPLOS Medicine, 2006
- Recurrent neural networks for time series classificationNeurocomputing, 2003
- A training algorithm for optimal margin classifiers1992