Abstract
We propose and compare combinations of several methods for classifying transportation activity data from smartphone GPS and accelerometer sensors. We have two main objectives. First, we aim to classify our data as accurately as possible. Second, we aim to reduce the dimensionality of the data as much as possible in order to reduce the computational burden of the classification. We combine dimension reduction and classification algorithms and compare them with a metric that balances accuracy and dimensionality. In doing so, we develop a classification algorithm that accurately classifies five different modes of transportation (i.e., walking, biking, car, bus and rail) while being computationally simple enough to run on a typical smartphone. Further, we use data that required no behavioral changes from the smartphone users to collect. Our best classification model uses the random forest algorithm to achieve 96.8% accuracy.
Highlights
Smartphones have become ubiquitous in the lives of billions
We evaluated the performance of four techniques defined by combining two dimension reduction techniques, principal component analysis (PCA) and recursive feature elimination (RFE), and two popular machine learning techniques, k-nearest neighbors and random forests (RF)
We considered two popular machine learning techniques for classification that could be trained offline and yield relatively simple prediction rules that are implemented on a smartphone: k-nearest neighbors and random forests (RF)
Summary
Smartphones have become ubiquitous in the lives of billions. The development of smartphone technology has led to the incorporation of increasingly advanced sensors, opening up a number of opportunities for data mining applications. Smartphones generate a constant stream of data describing the phone’s acceleration (via an onboard accelerometer) and location (via the Global Positioning System (GPS)). These data streams can be used to predict a user’s mode of transportation (i.e., whether an individual is traveling by car, bus, bike, rail or on foot) in near real time. Learning about a smartphone user’s mode of transportation has many useful applications. Government agencies currently collect transportation information using surveys. This requires time-consuming manual data collection, nearly one hour on average for a one-day survey for a single household [1], and is prone to response bias and inaccuracy [2]. GPS data are more representative of actual societal transportation patterns [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
