Identifying active travel behaviors in challenging environments using GPS, accelerometers and machine learning algorithms

• Main Authors: Katherine eEllis, Suneeta eGodbole, Simon eMarshall, Gert eLanckriet, John eStaudenmayer, Jacqueline eKerr
• Format: Article
• Language: English
• Published: Frontiers Media S.A. 2014-04-01
• Series: Frontiers in Public Health
• Subjects: physical activity; GPS; accelerometer; activity recognition; random forest; active travel
• Online Access: http://journal.frontiersin.org/Journal/10.3389/fpubh.2014.00036/full

Background: Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper we present a supervised machine learning method for transportation mode prediction from GPS and accelerometer data. Methods: We collected a dataset of about 150 hours of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-minute windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. Results: The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Conclusions: Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel.