Methods for Real-Time Prediction of the Mode of Travel Using Smartphone-Based GPS and Accelerometer Data
| Autor: | Vittorio Addona, Yingling Fan, Julian Wolfson, Gediminas Adomavicius, Bryan D Martin |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Engineering
dimension reduction Transportation 02 engineering and technology Walking Real time prediction lcsh:Chemical technology Accelerometer computer.software_genre Biochemistry Article Analytical Chemistry movelets 11. Sustainability 0502 economics and business Accelerometry 0202 electrical engineering electronic engineering information engineering lcsh:TP1-1185 mode prediction Electrical and Electronic Engineering classification Instrumentation 050210 logistics & transportation business.industry Dimensionality reduction 05 social sciences Reproducibility of Results 020206 networking & telecommunications Atomic and Molecular Physics and Optics Random forest Statistical classification Population Surveillance Metric (mathematics) Global Positioning System Geographic Information Systems Data mining Smartphone business computer Algorithms Curse of dimensionality |
| Zdroj: | Sensors; Volume 17; Issue 9; Pages: 2058 Sensors (Basel, Switzerland) Sensors, Vol 17, Iss 9, p 2058 (2017) |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s17092058 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|