{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T23:52:15Z","timestamp":1790034735262,"version":"4.0.1"},"reference-count":32,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2015,4,28]],"date-time":"2015-04-28T00:00:00Z","timestamp":1430179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["INOSENSE Project"],"award-info":[{"award-number":["INOSENSE Project"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper presents the results of research on the use of smartphone sensors (namely, GPS and accelerometers), geospatial information (points of interest, such as bus stops and train stations) and machine learning (ML) to sense mobility contexts. Our goal is to develop techniques to continuously and automatically detect a smartphone user\u2019s mobility activities, including walking, running, driving and using a bus or train, in real-time or near-real-time (&lt;5 s). We investigated a wide range of supervised learning techniques for classification, including decision trees (DT), support vector machines (SVM), naive Bayes classifiers (NB), Bayesian networks (BN), logistic regression (LR), artificial neural networks (ANN) and several instance-based classifiers (KStar, LWLand IBk). Applying ten-fold cross-validation, the best performers in terms of correct classification rate (i.e., recall) were DT (96.5%), BN (90.9%), LWL (95.5%) and KStar (95.6%). In particular, the DT-algorithm RandomForest exhibited the best overall performance. After a feature selection process for a subset of algorithms, the performance was improved slightly. Furthermore, after tuning the parameters of RandomForest, performance improved to above 97.5%. Lastly, we measured the computational complexity of the classifiers, in terms of central processing unit (CPU) time needed for classification, to provide a rough comparison between the algorithms in terms of battery usage requirements. As a result, the classifiers can be ranked from lowest to highest complexity (i.e., computational cost) as follows: SVM, ANN, LR, BN, DT, NB, IBk, LWL and KStar. The instance-based classifiers take considerably more computational time than the non-instance-based classifiers, whereas the slowest non-instance-based classifier (NB) required about five-times the amount of CPU time as the fastest classifier (SVM). The above results suggest that DT algorithms are excellent candidates for detecting mobility contexts in smartphones, both in terms of performance and computational complexity.<\/jats:p>","DOI":"10.3390\/s150509962","type":"journal-article","created":{"date-parts":[[2015,4,29]],"date-time":"2015-04-29T04:42:57Z","timestamp":1430282577000},"page":"9962-9985","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Beyond Where to How: A Machine Learning Approach for Sensing Mobility Contexts Using Smartphone Sensors"],"prefix":"10.3390","volume":"15","author":[{"given":"Robert","family":"Guinness","sequence":"first","affiliation":[{"name":"Finnish Geospatial Research Institute, Geodeetinrinne 2, FI-02430 Masala, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2015,4,28]]},"reference":[{"key":"ref_1","unstructured":"Dey, A. (2010). Ubiquitous Computing Fundamentals, Chapman and Hall\/CRC."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/MPRV.2012.41","article-title":"From Smart to Cognitive Phones","volume":"11","author":"Campbell","year":"2012","journal-title":"IEEE Pervasive Comput."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"13:1","DOI":"10.1145\/1689239.1689243","article-title":"Using mobile phones to determine transportation modes","volume":"6","author":"Reddy","year":"2010","journal-title":"ACM Trans. Sens. Netw."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bancroft, J.B., Garrett, D., and Lachapelle, G. (2012, January 13\u201315). Activity and environment classification using foot mounted navigation sensors. Sydney, NSW, Australia.","DOI":"10.1109\/IPIN.2012.6418902"},{"key":"ref_5","unstructured":"Mawston, N. Worldwide Smartphone Population Tops 1 Billion in Q3 2012. Available online: http:\/\/blogs.strategyanalytics.com\/WDS\/post\/2012\/10\/17\/Worldwide-Smartphone-Population-Tops-1-Billion-in-Q3-2012.aspx."},{"key":"ref_6","unstructured":"Guinness, R.E. (2013, January 16\u201320). Beyond Where to How: A Machine Learning Approach for Sensing Mobility Contexts Using Smartphone Sensors. Nashville, TN, USA."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1016\/j.jsams.2008.10.010","article-title":"Applying GPS to enhance understanding of transport-related physical activity","volume":"12","author":"Duncan","year":"2009","journal-title":"J. Sci. Med. Sport"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1123\/jpah.7.1.102","article-title":"Combining GPS, GIS, and accelerometry: Methodological issues in the assessment of location and intensity of travel behaviors","volume":"7","author":"Oliver","year":"2010","journal-title":"J. Phys. Act. Health"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Elhoushi, M., Georgy, J., Korenberg, M., and Noureldin, A. (2014, January 5\u20138). Robust Motion Mode Recognition for Portable Navigation Independent on Device Usage. Monterey, CA, USA.","DOI":"10.1109\/PLANS.2014.6851370"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.ypmed.2010.02.002","article-title":"Using accelerometers and GPS units to identify the proportion of daily physical activity located in parks with playgrounds in New Zealand children","volume":"50","author":"Quigg","year":"2010","journal-title":"Prev. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/s10916-007-9111-y","article-title":"Context awareness of human motion states using accelerometer","volume":"32","author":"Jin","year":"2008","journal-title":"J. Med. Syst."},{"key":"ref_12","unstructured":"Ravi, N., Dandekar, N., Mysore, P., and Littman, M.L. (2005, January 11\u201313). Activity recognition from accelerometer data. Pittsburgh, PA, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Frank, K., Nadales, M., Robertson, P., and Angermann, M. (2010, January 21\u201324). Reliable Real-Time Recognition of Motion Related Human Activities Using MEMS Inertial Sensors. Portland, OR, USA.","DOI":"10.1145\/1864431.1864480"},{"key":"ref_14","unstructured":"Pei, L., Chen, R., Liu, J., Chen, W., Kuusniemi, H., Tenhunen, T., Kr\u00f6ger, T., Chen, Y., Lepp\u00e4koski, H., and Takala, J. (2010, January 21\u201324). Motion recognition assisted indoor wireless navigation on a mobile phone. Portland, OR, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1402","DOI":"10.3390\/s130201402","article-title":"Human Behavior Cognition Using Smartphone Sensors","volume":"13","author":"Pei","year":"2013","journal-title":"Sensors"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.3390\/s130201539","article-title":"Motion Mode Recognition and Step Detection Algorithms for Mobile Phone Users","volume":"13","author":"Susi","year":"2013","journal-title":"Sensors"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Stenneth, L., Wolfson, O., Yu, P.S., and Xu, B. (2011, January 1\u20134). Transportation mode detection using mobile phones and GIS information. Chicago, IL, USA.","DOI":"10.1145\/2093973.2093982"},{"key":"ref_18","unstructured":"Stenneth, L. (2013). Human Activity Detection Using Smartphones and Maps. [Ph.D. Thesis, University of Illinois at Chicago]."},{"key":"ref_19","unstructured":"El-Shiemy, N. The Promise of MEMS to LBS and Navigation Applications. Available online: http:\/\/www.cwins.wpi.edu\/workshop12\/presentation\/Application_panel\/ElSheimy.pdf."},{"key":"ref_20","unstructured":"Google Places API Developer's Guide. Available online: http:\/\/bit.ly\/1vBPd20."},{"key":"ref_21","unstructured":"Reittiopas API Developer's Guide. Available online: https:\/\/www.hsl.fi\/en\/helsinki-regional-transport-authority."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"6155","DOI":"10.3390\/s120506155","article-title":"Using LS-SVM Based Motion Recognition for Smartphone Indoor Wireless Positioning","volume":"12","author":"Pei","year":"2012","journal-title":"Sensors"},{"key":"ref_23","unstructured":"Weka Documentation. Available online: http:\/\/bit.ly\/1AaQEQf."},{"key":"ref_24","unstructured":"Guinness, R. Mobility Context data for 2013 ION Paper. Available online: http:\/\/bit.ly\/MLdata2013."},{"key":"ref_25","unstructured":"Quinlan, J.R. (1993). C4.5: Programs for Machine Learning, Morgan Kaufmann."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","article-title":"The WEKA data mining software: An update","volume":"11","author":"Hall","year":"2009","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Murmuria, R., Medsger, J., Stavrou, A., and Voas, J.M. (2012, January 20\u201322). Mobile Application and Device Power Usage Measurements. Gaithersburg, MD, USA.","DOI":"10.1109\/SERE.2012.19"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"367","DOI":"10.15623\/ijret.2014.0310059","article-title":"Parallel kNN on GPU architecture using OpenCL","volume":"3","author":"Nikam","year":"2014","journal-title":"Int. J. Res. Eng. Technol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1613\/jair.816","article-title":"An analysis of reduced error pruning","volume":"15","author":"Elomaa","year":"2001","journal-title":"J. Artif. Intell. Res."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Dietterich, T.G. (2002, January 6\u20139). Machine learning for sequential data: A review. Windsor, ON, Canada.","DOI":"10.1007\/3-540-70659-3_2"},{"key":"ref_32","unstructured":"OpenStreetMap API Documentation. Available online: http:\/\/bit.ly\/181w1zw."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/15\/5\/9962\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T20:45:28Z","timestamp":1760215528000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/15\/5\/9962"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4,28]]},"references-count":32,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2015,5]]}},"alternative-id":["s150509962"],"URL":"https:\/\/doi.org\/10.3390\/s150509962","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,4,28]]}}}