Loading…
Beyond where to how: a machine learning approach for sensing mobility contexts using smartphone sensors
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...
Saved in:
| Published in: | Sensors (Basel, Switzerland) Switzerland), 2015-04, Vol.15 (5), p.9962-9985 |
|---|---|
| Main Author: | |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c505t-69bdb1afc6098d54114307d50dfe45750cbe613867177e53a238a3b5cbc805403 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c505t-69bdb1afc6098d54114307d50dfe45750cbe613867177e53a238a3b5cbc805403 |
| container_end_page | 9985 |
| container_issue | 5 |
| container_start_page | 9962 |
| container_title | Sensors (Basel, Switzerland) |
| container_volume | 15 |
| creator | Guinness, Robert E |
| description | 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's mobility activities, including walking, running, driving and using a bus or train, in real-time or near-real-time ( |
| doi_str_mv | 10.3390/s150509962 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_a165a4782bef4f6b81c965aa5667665f</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_a165a4782bef4f6b81c965aa5667665f</doaj_id><sourcerecordid>1718935662</sourcerecordid><originalsourceid>FETCH-LOGICAL-c505t-69bdb1afc6098d54114307d50dfe45750cbe613867177e53a238a3b5cbc805403</originalsourceid><addsrcrecordid>eNqFkktv1TAQRiMEoqWw4QcgS2wQ0gW_Hywq0YpHpUpsYG05zuQmV4kd7IRy_32d3lJaNqxsfT46M2NNVb0k-B1jBr_PRGCBjZH0UXVMOOUbTSl-fO9-VD3LeYcxZYzpp9URFYZqLPFxtT2DfQwNuuogAZoj6uLVB-TQ6HzXB0ADuBT6sEVumlIsIWpjQhlCXsMx1v3Qz3vkY5jh95zRcpPn0aV56mIRrGhM-Xn1pHVDhhe350n14_On7-dfN5ffvlycf7zc-DLDvJGmbmriWi-x0Y3ghHCGVSNw0wIXSmBfgyRMS0WUAsEcZdqxWvjaayw4ZifVxcHbRLezU-pLJ3sbXW9vgpi2trTW-wGsI1I4rjStoeWtrDXxpiROSKmkFG1xnR5c01KP0HgIc3LDA-nDl9B3dht_Wc41McYUwZtbQYo_F8izHfvsYRhcgLhkSxTRhpV69P-oVFpxI_A64ut_0F1cUii_WigjGMVCrrXfHiifYs4J2ru-Cbbr2ti_a1PgV_cnvUP_7Am7Bm8yvPI</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1695320569</pqid></control><display><type>article</type><title>Beyond where to how: a machine learning approach for sensing mobility contexts using smartphone sensors</title><source>Publicly Available Content Database</source><source>PubMed Central</source><creator>Guinness, Robert E</creator><creatorcontrib>Guinness, Robert E</creatorcontrib><description>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's mobility activities, including walking, running, driving and using a bus or train, in real-time or near-real-time (<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.</description><identifier>ISSN: 1424-8220</identifier><identifier>EISSN: 1424-8220</identifier><identifier>DOI: 10.3390/s150509962</identifier><identifier>PMID: 25928060</identifier><language>eng</language><publisher>Switzerland: MDPI AG</publisher><subject>Accelerometers ; Algorithms ; Bayesian analysis ; Cellular telephones ; Classification ; Classifiers ; context awareness ; Learning theory ; Machine learning ; mobility context ; Neural networks ; Sensors ; smartphone sensors ; Smartphones ; supervised learning ; Support vector machines</subject><ispartof>Sensors (Basel, Switzerland), 2015-04, Vol.15 (5), p.9962-9985</ispartof><rights>Copyright MDPI AG 2015</rights><rights>2015 by the authors; licensee MDPI, Basel, Switzerland. 2015</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c505t-69bdb1afc6098d54114307d50dfe45750cbe613867177e53a238a3b5cbc805403</citedby><cites>FETCH-LOGICAL-c505t-69bdb1afc6098d54114307d50dfe45750cbe613867177e53a238a3b5cbc805403</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/1695320569/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/1695320569?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,881,25731,27901,27902,36989,36990,44566,53766,53768,74869</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/25928060$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Guinness, Robert E</creatorcontrib><title>Beyond where to how: a machine learning approach for sensing mobility contexts using smartphone sensors</title><title>Sensors (Basel, Switzerland)</title><addtitle>Sensors (Basel)</addtitle><description>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's mobility activities, including walking, running, driving and using a bus or train, in real-time or near-real-time (<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.</description><subject>Accelerometers</subject><subject>Algorithms</subject><subject>Bayesian analysis</subject><subject>Cellular telephones</subject><subject>Classification</subject><subject>Classifiers</subject><subject>context awareness</subject><subject>Learning theory</subject><subject>Machine learning</subject><subject>mobility context</subject><subject>Neural networks</subject><subject>Sensors</subject><subject>smartphone sensors</subject><subject>Smartphones</subject><subject>supervised learning</subject><subject>Support vector machines</subject><issn>1424-8220</issn><issn>1424-8220</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNqFkktv1TAQRiMEoqWw4QcgS2wQ0gW_Hywq0YpHpUpsYG05zuQmV4kd7IRy_32d3lJaNqxsfT46M2NNVb0k-B1jBr_PRGCBjZH0UXVMOOUbTSl-fO9-VD3LeYcxZYzpp9URFYZqLPFxtT2DfQwNuuogAZoj6uLVB-TQ6HzXB0ADuBT6sEVumlIsIWpjQhlCXsMx1v3Qz3vkY5jh95zRcpPn0aV56mIRrGhM-Xn1pHVDhhe350n14_On7-dfN5ffvlycf7zc-DLDvJGmbmriWi-x0Y3ghHCGVSNw0wIXSmBfgyRMS0WUAsEcZdqxWvjaayw4ZifVxcHbRLezU-pLJ3sbXW9vgpi2trTW-wGsI1I4rjStoeWtrDXxpiROSKmkFG1xnR5c01KP0HgIc3LDA-nDl9B3dht_Wc41McYUwZtbQYo_F8izHfvsYRhcgLhkSxTRhpV69P-oVFpxI_A64ut_0F1cUii_WigjGMVCrrXfHiifYs4J2ru-Cbbr2ti_a1PgV_cnvUP_7Am7Bm8yvPI</recordid><startdate>20150428</startdate><enddate>20150428</enddate><creator>Guinness, Robert E</creator><general>MDPI AG</general><general>MDPI</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>7SP</scope><scope>7TB</scope><scope>7U5</scope><scope>8FD</scope><scope>FR3</scope><scope>L7M</scope><scope>5PM</scope><scope>DOA</scope></search><sort><creationdate>20150428</creationdate><title>Beyond where to how: a machine learning approach for sensing mobility contexts using smartphone sensors</title><author>Guinness, Robert E</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c505t-69bdb1afc6098d54114307d50dfe45750cbe613867177e53a238a3b5cbc805403</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Accelerometers</topic><topic>Algorithms</topic><topic>Bayesian analysis</topic><topic>Cellular telephones</topic><topic>Classification</topic><topic>Classifiers</topic><topic>context awareness</topic><topic>Learning theory</topic><topic>Machine learning</topic><topic>mobility context</topic><topic>Neural networks</topic><topic>Sensors</topic><topic>smartphone sensors</topic><topic>Smartphones</topic><topic>supervised learning</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Guinness, Robert E</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ: Directory of Open Access Journals</collection><jtitle>Sensors (Basel, Switzerland)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Guinness, Robert E</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Beyond where to how: a machine learning approach for sensing mobility contexts using smartphone sensors</atitle><jtitle>Sensors (Basel, Switzerland)</jtitle><addtitle>Sensors (Basel)</addtitle><date>2015-04-28</date><risdate>2015</risdate><volume>15</volume><issue>5</issue><spage>9962</spage><epage>9985</epage><pages>9962-9985</pages><issn>1424-8220</issn><eissn>1424-8220</eissn><abstract>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's mobility activities, including walking, running, driving and using a bus or train, in real-time or near-real-time (<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.</abstract><cop>Switzerland</cop><pub>MDPI AG</pub><pmid>25928060</pmid><doi>10.3390/s150509962</doi><tpages>24</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1424-8220 |
| ispartof | Sensors (Basel, Switzerland), 2015-04, Vol.15 (5), p.9962-9985 |
| issn | 1424-8220 1424-8220 |
| language | eng |
| recordid | cdi_doaj_primary_oai_doaj_org_article_a165a4782bef4f6b81c965aa5667665f |
| source | Publicly Available Content Database; PubMed Central |
| subjects | Accelerometers Algorithms Bayesian analysis Cellular telephones Classification Classifiers context awareness Learning theory Machine learning mobility context Neural networks Sensors smartphone sensors Smartphones supervised learning Support vector machines |
| title | Beyond where to how: a machine learning approach for sensing mobility contexts using smartphone sensors |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T13%3A00%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Beyond%20where%20to%20how:%20a%20machine%20learning%20approach%20for%20sensing%20mobility%20contexts%20using%20smartphone%20sensors&rft.jtitle=Sensors%20(Basel,%20Switzerland)&rft.au=Guinness,%20Robert%20E&rft.date=2015-04-28&rft.volume=15&rft.issue=5&rft.spage=9962&rft.epage=9985&rft.pages=9962-9985&rft.issn=1424-8220&rft.eissn=1424-8220&rft_id=info:doi/10.3390/s150509962&rft_dat=%3Cproquest_doaj_%3E1718935662%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c505t-69bdb1afc6098d54114307d50dfe45750cbe613867177e53a238a3b5cbc805403%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1695320569&rft_id=info:pmid/25928060&rfr_iscdi=true |