Abstract
Recently, a considerable amount of research has focused on understanding transportation mobility patterns from crowdsourced smartphone data. To this end, transportation mode detection is an indispensable, yet challenging task towards deriving meaningful information from large datasets collected using smartphones. Most studies to date use Global Navigation Satellite Systems (GNSS) derived data such as speed to detect transportation mode. Limited research relies on sensors that do not depend on external sources, such as accelerometer and gyroscope. The present work proposes a methodological framework based on machine learning for identifying the transportation mode using accelerometer, gyroscope and orientation data in the absence of battery consuming sensors, such as GNSS. Different models are developed and compared based on random forest and gradient boosting machine algorithms. A comparative study between GNSS free and GNSS based algorithms is also established. Results are further discussed and possible research directions are provided.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aloul F, Zualkernan I, Abu-Salma R, Al-Ali H, Al-Merri M (2015) IBump: Smartphone application to detect car accidents. Comput Electr Eng 23:66–75. https://doi.org/10.1016/j.compeleceng.2015.03.003
Ansari Lari Z, Golroo A (2015) Automated transportation mode detection using smart phone applications via machine learning: case study mega city of Tehran. In: Transp. Res. Board 94th Annu. Meet
Berger M, Platzer M (2015) Field evaluation of the smartphone-based travel behaviour data collection app “smartMo,”. In: Transportation research procedia, pp 263–279. https://doi.org/10.1016/j.trpro.2015.12.023
Breiman L (2001) Random forests. Mach Learn 45:5–32
Chen J, Bierlaire M (2015) Probabilistic multimodal map matching with rich smartphone data. J Intell Transp Syst 19:134–148. https://doi.org/10.1080/15472450.2013.764796
Click C, Malohlava M, Parmar V, Roark H, Candel A (2018) Gradient boosting machine with H2O. In A. Bartz (ed) Mountain View, H2O.ai, Inc., CA. http://h2o.ai/resources/
Eftekhari HR, Ghatee M (2016) An inference engine for smartphones to preprocess data and detect stationary and transportation modes. Transp Res Part C Emerg Technol 69:313–327. https://doi.org/10.1016/j.trc.2016.06.005
Feng T, Timmermans HJP (2013) Transportation mode recognition using GPS and accelerometer data. Transp Res Part C Emerg Technol 37:118–130. https://doi.org/10.1016/j.trc.2013.09.014
Ferrer S, Ruiz T (2014) Travel behavior characterization using raw accelerometer data collected from smartphones. Proc Soc Behav Sci 160:140–149. https://doi.org/10.1016/j.sbspro.2014.12.125
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232. https://doi.org/10.1214/aos/1013203451
Geurs KT, Thomas T, Bijlsma M, Douhou S (2015) Automatic trip and mode detection with move smarter: first results from the Dutch mobile mobility panel. In: Transportation research procedia, pp 247–262. https://doi.org/10.1016/j.trpro.2015.12.022
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning. Elements 1:337–387. https://doi.org/10.1007/b94608
Hemminki S, Nurmi P, Tarkoma S (2013) Accelerometer-based transportation mode detection on smartphones. In: Proceedings of the 11th ACM conference on embedded networked sensor systems—SenSys’13, pp 1–14. https://doi.org/10.1145/2517351.2517367
Ho TK (1995) Random decision forests. In: Proceedings of the third international conference on document analysis and recognition, 1995. IEEE, pp 278–282
Jahangiri A, Rakha HA (2015) Applying machine learning techniques to transportation mode recognition using mobile phone sensor data. IEEE Trans Intell Transp Syst 16:2406–2417. https://doi.org/10.1109/TITS.2015.2405759
Montini L, Prost S, Schrammel J, Rieser-Schüssler N, Axhausen KW (2015) Comparison of travel diaries generated from smartphone data and dedicated GPS devices. Transp Res Proc 11:227–241. https://doi.org/10.1016/j.trpro.2015.12.020
Nikolic M, Bierlaire M (2017) Review of transportation mode detection approaches based on smartphone data. In: 17th Swiss Transp. Res. Conf
Oliver M, Badland H, Mavoa S, Duncan MJ, Duncan S (2010) Combining GPS, GIS, and accelerometry: methodological issues in the assessment of location and intensity of travel behaviors. J Phys Act Health 7:102–108. https://doi.org/10.1123/jpah.7.1.102
OSeven T (2015) OSEVEN Home [WWW Document]. https://www.oseven.io. Accessed 26 Feb 2018
Reddy S, Burke J, Estrin D, Hansen M, Srivastava M (2008) Determining transportation mode on mobile phones. In: Proceedings—international symposium on wearable computers, ISWC, pp 25–28. https://doi.org/10.1109/ISWC.2008.4911579
Reddy S, Mun M, Burke J, Estrin D, Hansen M, Srivastava M (2010) Using mobile phones to determine transportation modes. ACM Trans Sens Netw 6:1–27. https://doi.org/10.1145/1689239.1689243
Rifkin R, Klautau A (2004) In defense of one-vs-all classification. J Mach Learn Res 5:101–141
Saiprasert C, Pattara-Atikom W (2013) Smartphone enabled dangerous driving report system. In: 2013 46th Hawaii international conference on system sciences. IEEE, pp 1231–1237. https://doi.org/10.1109/HICSS.2013.484
Shafique MA, Hato E (2016) Travel mode detection with varying smartphone data collection frequencies. Sensors (Switzerland) 16:716. https://doi.org/10.3390/s16050716
Shin D, Aliaga D, Tunçer B, Arisona SM, Kim S, Zünd D, Schmitt G (2015) Urban sensing: using smartphones for transportation mode classification. Comput Environ Urban Syst. https://doi.org/10.1016/j.compenvurbsys.2014.07.011
Sonderen T (2016) Detection of transportation mode solely using smartphones. Twente Student Conf, IT
Stenneth L, Wolfson O, Yu PS, Xu B (2011) Transportation mode detection using mobile phones and GIS information. In: Proceedings of the 19th ACM SIGSPATIAL international conference on advances in geographic information systems—GIS’11, p 54. https://doi.org/10.1145/2093973.2093982
Team THA (2017) h2o: r interface for H2O, R package version 3.10.5.3 [WWW Document]
Team RDC, R Development Core Team, R (2016) R: a language and environment for statistical computing. R Found Stat Comput. https://doi.org/10.1007/978-3-540-74686-7
Vlahogianni EI, Barmpounakis EN (2017) Driving analytics using smartphones: algorithms, comparisons and challenges. Transp Res Part C Emerg Technol 79:196–206. https://doi.org/10.1016/j.trc.2017.03.014
Wang S, Chen C, Ma J (2010) Accelerometer based transportation mode recognition on mobile phones. In: APWCS 2010–2010 Asia-Pacific conference on wearable computing systems, pp 44–46. https://doi.org/10.1109/APWCS.2010.18
Weiss G, McCarthy K, Zabar B (2007) Cost-sensitive learning vs. sampling: Which is best for handling unbalanced classes with unequal error costs? Dmin 7:1–7
Wu L, Yang B, Jing P (2016) Travel mode detection based on GPS raw data collected by smartphones: a systematic review of the existing methodologies. Information 7:67. https://doi.org/10.3390/info7040067
Yang J (2009) Toward physical activity diary: motion recognition using simple acceleration features with mobile phones. In: Proceedings of the 1st international workshop on interactive multimedia for consumer electronics. https://doi.org/10.1145/1631040.1631042
Zhao F, Ghorpade A, Pereira FC, Zegras C, Ben-Akiva M (2015) Stop detection in smartphone-based travel surveys. In: Transportation research procedia, pp 218–226. https://doi.org/10.1016/j.trpro.2015.12.019
Zheng Y, Liu L, Wang L, Xie X (2008) Learning transportation mode from raw gps data for geographic applications on the web. In: Proceeding of the 17th international conference on World Wide Web—WWW’08. p 247. https://doi.org/10.1145/1367497.1367532
Zhu L, Gonder JD (2018) A driving cycle detection approach using map service API. Transp Res Part C Emerg Technol 92:349–363. https://doi.org/10.1016/j.trc.2018.05.010
Zhu L, Gonder J, Lin L (2017) Prediction of individual social-demographic role based on travel behavior variability using long-term GPS data. J Adv Transp 2017:1–13. https://doi.org/10.1155/2017/7290248
Zong F, Bai Y, Wang X, Yuan Y, He Y (2015) Identifying travel mode with GPS data using support vector machines and genetic algorithm. Information 6:212–227. https://doi.org/10.3390/info6020212
Acknowledgements
This research has exploited data provided by OSeven Telematics, London, UK.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Efthymiou, A., Barmpounakis, E.N., Efthymiou, D. et al. Transportation Mode Detection from Low-Power Smartphone Sensors Using Tree-Based Ensembles. J. Big Data Anal. Transp. 1, 57–69 (2019). https://doi.org/10.1007/s42421-019-00004-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42421-019-00004-w