Recognition of Bike-Riding States with HMM Analysis
Abstract
In this paper, we design and implement an sBike (Sensorized Bike) prototype to support cyclists by recognizing various riding states including going straight, turning right or left, meandering, and stopping. An Android phone, which is equipped with a gyro sensor, an accelerometer, and a GPS receiver, is mounted on the handle of bicycle to collect necessary data for analysis. Hidden Markov model (HMM) is adopted to recognize the riding states from raw sensor data. The experimental results show that the accuracy of recognition is as high as 98%. By knowing the riding states of cyclists, road conditions can be inferred and shared amongst users.
- Publication:
-
2011 International Symposium on Computational Models for Life Sciences (CMLS-11)
- Pub Date:
- June 2011
- DOI:
- 10.1063/1.3596658
- Bibcode:
- 2011AIPC.1371..339T
- Keywords:
-
- sensors;
- Markov processes;
- data acquisition;
- biomechanics;
- 42.81.Pa;
- 02.50.Ga;
- 07.05.Hd;
- 87.85.G-;
- Sensors gyros;
- Markov processes;
- Data acquisition: hardware and software;
- Biomechanics