Abstract
Recently, as the number of smartphone users increases rapidly, various applications using GPS become widespread. Because GPS sensor has drawback that consumes too much energy, we have to decrease the unnecessary usage of GPS receiver at indoors to reduce the energy consumption. Most of previous works focused on how to reduce the frequency or the period to use GPS. In this paper, we propose a method to save battery using Bayesian network inference with built-in sensors in a smartphone to get location information efficiently. In order to show the usefulness of the proposed method, we have developed an application in Android platform and performed experiments to evaluate Bayesian networks. Experimental results on real datasets has shown that it is possible to predict user's location at either indoor or outdoor. On weekday, accuracy is 77% which is higher than on weekend, 68%. Analysis implies that user lifestyle and life pattern in weekday have less changes than that in weekend. In terms of battery efficiency, active person and inactive person save energy of about 5% and 3% per hour, respectively.
Original language | English |
---|---|
Pages | 204-209 |
Number of pages | 6 |
DOIs | |
Publication status | Published - 2012 |
Event | 9th IEEE International Conference on Ubiquitous Intelligence and Computing, UIC 2012 and 9th IEEE International Conference on Autonomic and Trusted Computing, ATC 2012 - Fukuoka, Japan Duration: 2012 Sep 4 → 2012 Sep 7 |
Other
Other | 9th IEEE International Conference on Ubiquitous Intelligence and Computing, UIC 2012 and 9th IEEE International Conference on Autonomic and Trusted Computing, ATC 2012 |
---|---|
Country/Territory | Japan |
City | Fukuoka |
Period | 12/9/4 → 12/9/7 |
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computer Science Applications