Loading…
A Machine Learning Approach to Road Surface Anomaly Assessment Using Smartphone Sensors
Road surface quality is essential for improving driving experience and reducing traffic accidents. Traditional road condition monitoring systems are limited in their temporal (speed) and spatial (coverage) responses needed for maintaining overall road quality. Several alternative systems have been p...
Saved in:
| Published in: | IEEE sensors journal 2020-03, Vol.20 (5), p.2635-2647 |
|---|---|
| Main Authors: | , , , |
| 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-c336t-2e773d5283a6487926fd9923e365cb26a93113f645a3cf1241d7d4c96303e9503 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c336t-2e773d5283a6487926fd9923e365cb26a93113f645a3cf1241d7d4c96303e9503 |
| container_end_page | 2647 |
| container_issue | 5 |
| container_start_page | 2635 |
| container_title | IEEE sensors journal |
| container_volume | 20 |
| creator | Basavaraju, Akanksh Du, Jing Zhou, Fujie Ji, Jim |
| description | Road surface quality is essential for improving driving experience and reducing traffic accidents. Traditional road condition monitoring systems are limited in their temporal (speed) and spatial (coverage) responses needed for maintaining overall road quality. Several alternative systems have been proposed that utilize sensors mounted on vehicles. In particular, with the ubiquitous use of smartphones for navigation, smartphone-based road condition assessment has emerged as a promising new approach. In this paper, we propose to analyze different multiclass supervised machine learning techniques to effectively classify road surface conditions using accelerometer, gyroscope and GPS data collected from smartphones. Our work focuses on classification of three main class labels- smooth road, potholes, and deep transverse cracks. We hypothesize that using features from all three axes of the sensors provides more accurate results as compared to using features from only one axis. We also investigate the performance of deep neural networks to classify road conditions with and without explicit manual feature extraction. Our results indicate that models trained with features from all axes of the smartphone sensors outperform models that use only one axis. We also observe that the use of neural networks provides a significantly improved data classification. The machine learning approach discussed here can be implemented on a larger scale to monitor roads for defects that present a safety risk to commuters as well as to provide maintenance information to relevant authorities. |
| doi_str_mv | 10.1109/JSEN.2019.2952857 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_2352193946</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8896015</ieee_id><sourcerecordid>2352193946</sourcerecordid><originalsourceid>FETCH-LOGICAL-c336t-2e773d5283a6487926fd9923e365cb26a93113f645a3cf1241d7d4c96303e9503</originalsourceid><addsrcrecordid>eNo9kF9LwzAUxYMoOKcfQHwJ-Nya5DZJ81jG_MdUsA59C7FNXcfW1KR72Lc3ZcOne7mcc-7hh9A1JSmlRN09l_PXlBGqUqY4y7k8QRPKeZ5QmeWn4w4kyUB-naOLENYkKiWXE_RZ4BdTrdrO4oU1vmu7H1z0vXfxiAeH352pcbnzjaksLjq3NZs9LkKwIWxtN-BlGB3l1vihX7mYUtouOB8u0VljNsFeHecULe_nH7PHZPH28DQrFkkFIIaEWSmhjoXBiCyXiommVoqBBcGrbyaMAkqhERk3UDWUZbSWdVYpAQSs4gSm6PaQGyv_7mwY9NrtfBdfagacUQUqE1FFD6rKuxC8bXTv29h5rynRIz898tMjP33kFz03B09rrf3X57kSJML8A36NapM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2352193946</pqid></control><display><type>article</type><title>A Machine Learning Approach to Road Surface Anomaly Assessment Using Smartphone Sensors</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Basavaraju, Akanksh ; Du, Jing ; Zhou, Fujie ; Ji, Jim</creator><creatorcontrib>Basavaraju, Akanksh ; Du, Jing ; Zhou, Fujie ; Ji, Jim</creatorcontrib><description>Road surface quality is essential for improving driving experience and reducing traffic accidents. Traditional road condition monitoring systems are limited in their temporal (speed) and spatial (coverage) responses needed for maintaining overall road quality. Several alternative systems have been proposed that utilize sensors mounted on vehicles. In particular, with the ubiquitous use of smartphones for navigation, smartphone-based road condition assessment has emerged as a promising new approach. In this paper, we propose to analyze different multiclass supervised machine learning techniques to effectively classify road surface conditions using accelerometer, gyroscope and GPS data collected from smartphones. Our work focuses on classification of three main class labels- smooth road, potholes, and deep transverse cracks. We hypothesize that using features from all three axes of the sensors provides more accurate results as compared to using features from only one axis. We also investigate the performance of deep neural networks to classify road conditions with and without explicit manual feature extraction. Our results indicate that models trained with features from all axes of the smartphone sensors outperform models that use only one axis. We also observe that the use of neural networks provides a significantly improved data classification. The machine learning approach discussed here can be implemented on a larger scale to monitor roads for defects that present a safety risk to commuters as well as to provide maintenance information to relevant authorities.</description><identifier>ISSN: 1530-437X</identifier><identifier>EISSN: 1558-1748</identifier><identifier>DOI: 10.1109/JSEN.2019.2952857</identifier><identifier>CODEN: ISJEAZ</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>accelerometer ; Accelerometers ; Artificial neural networks ; Axes (reference lines) ; Classification ; Condition monitoring ; crack ; Cracks ; decision tree ; Driving ; Feature extraction ; Inspection ; Machine learning ; Manuals ; multilayer perceptron ; neural network ; Neural networks ; pavement condition ; pothole ; road condition ; Road surface ; Roads ; Roads & highways ; Sensors ; smartphone sensor ; Smartphones ; Support vector machines ; Surface properties ; Traffic accidents ; Vibrations</subject><ispartof>IEEE sensors journal, 2020-03, Vol.20 (5), p.2635-2647</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c336t-2e773d5283a6487926fd9923e365cb26a93113f645a3cf1241d7d4c96303e9503</citedby><cites>FETCH-LOGICAL-c336t-2e773d5283a6487926fd9923e365cb26a93113f645a3cf1241d7d4c96303e9503</cites><orcidid>0000-0001-7147-7920</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8896015$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>315,786,790,27957,27958,55147</link.rule.ids></links><search><creatorcontrib>Basavaraju, Akanksh</creatorcontrib><creatorcontrib>Du, Jing</creatorcontrib><creatorcontrib>Zhou, Fujie</creatorcontrib><creatorcontrib>Ji, Jim</creatorcontrib><title>A Machine Learning Approach to Road Surface Anomaly Assessment Using Smartphone Sensors</title><title>IEEE sensors journal</title><addtitle>JSEN</addtitle><description>Road surface quality is essential for improving driving experience and reducing traffic accidents. Traditional road condition monitoring systems are limited in their temporal (speed) and spatial (coverage) responses needed for maintaining overall road quality. Several alternative systems have been proposed that utilize sensors mounted on vehicles. In particular, with the ubiquitous use of smartphones for navigation, smartphone-based road condition assessment has emerged as a promising new approach. In this paper, we propose to analyze different multiclass supervised machine learning techniques to effectively classify road surface conditions using accelerometer, gyroscope and GPS data collected from smartphones. Our work focuses on classification of three main class labels- smooth road, potholes, and deep transverse cracks. We hypothesize that using features from all three axes of the sensors provides more accurate results as compared to using features from only one axis. We also investigate the performance of deep neural networks to classify road conditions with and without explicit manual feature extraction. Our results indicate that models trained with features from all axes of the smartphone sensors outperform models that use only one axis. We also observe that the use of neural networks provides a significantly improved data classification. The machine learning approach discussed here can be implemented on a larger scale to monitor roads for defects that present a safety risk to commuters as well as to provide maintenance information to relevant authorities.</description><subject>accelerometer</subject><subject>Accelerometers</subject><subject>Artificial neural networks</subject><subject>Axes (reference lines)</subject><subject>Classification</subject><subject>Condition monitoring</subject><subject>crack</subject><subject>Cracks</subject><subject>decision tree</subject><subject>Driving</subject><subject>Feature extraction</subject><subject>Inspection</subject><subject>Machine learning</subject><subject>Manuals</subject><subject>multilayer perceptron</subject><subject>neural network</subject><subject>Neural networks</subject><subject>pavement condition</subject><subject>pothole</subject><subject>road condition</subject><subject>Road surface</subject><subject>Roads</subject><subject>Roads & highways</subject><subject>Sensors</subject><subject>smartphone sensor</subject><subject>Smartphones</subject><subject>Support vector machines</subject><subject>Surface properties</subject><subject>Traffic accidents</subject><subject>Vibrations</subject><issn>1530-437X</issn><issn>1558-1748</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><recordid>eNo9kF9LwzAUxYMoOKcfQHwJ-Nya5DZJ81jG_MdUsA59C7FNXcfW1KR72Lc3ZcOne7mcc-7hh9A1JSmlRN09l_PXlBGqUqY4y7k8QRPKeZ5QmeWn4w4kyUB-naOLENYkKiWXE_RZ4BdTrdrO4oU1vmu7H1z0vXfxiAeH352pcbnzjaksLjq3NZs9LkKwIWxtN-BlGB3l1vihX7mYUtouOB8u0VljNsFeHecULe_nH7PHZPH28DQrFkkFIIaEWSmhjoXBiCyXiommVoqBBcGrbyaMAkqhERk3UDWUZbSWdVYpAQSs4gSm6PaQGyv_7mwY9NrtfBdfagacUQUqE1FFD6rKuxC8bXTv29h5rynRIz898tMjP33kFz03B09rrf3X57kSJML8A36NapM</recordid><startdate>20200301</startdate><enddate>20200301</enddate><creator>Basavaraju, Akanksh</creator><creator>Du, Jing</creator><creator>Zhou, Fujie</creator><creator>Ji, Jim</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0001-7147-7920</orcidid></search><sort><creationdate>20200301</creationdate><title>A Machine Learning Approach to Road Surface Anomaly Assessment Using Smartphone Sensors</title><author>Basavaraju, Akanksh ; Du, Jing ; Zhou, Fujie ; Ji, Jim</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c336t-2e773d5283a6487926fd9923e365cb26a93113f645a3cf1241d7d4c96303e9503</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>accelerometer</topic><topic>Accelerometers</topic><topic>Artificial neural networks</topic><topic>Axes (reference lines)</topic><topic>Classification</topic><topic>Condition monitoring</topic><topic>crack</topic><topic>Cracks</topic><topic>decision tree</topic><topic>Driving</topic><topic>Feature extraction</topic><topic>Inspection</topic><topic>Machine learning</topic><topic>Manuals</topic><topic>multilayer perceptron</topic><topic>neural network</topic><topic>Neural networks</topic><topic>pavement condition</topic><topic>pothole</topic><topic>road condition</topic><topic>Road surface</topic><topic>Roads</topic><topic>Roads & highways</topic><topic>Sensors</topic><topic>smartphone sensor</topic><topic>Smartphones</topic><topic>Support vector machines</topic><topic>Surface properties</topic><topic>Traffic accidents</topic><topic>Vibrations</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Basavaraju, Akanksh</creatorcontrib><creatorcontrib>Du, Jing</creatorcontrib><creatorcontrib>Zhou, Fujie</creatorcontrib><creatorcontrib>Ji, Jim</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998–Present</collection><collection>IEEE Xplore</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE sensors journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Basavaraju, Akanksh</au><au>Du, Jing</au><au>Zhou, Fujie</au><au>Ji, Jim</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Machine Learning Approach to Road Surface Anomaly Assessment Using Smartphone Sensors</atitle><jtitle>IEEE sensors journal</jtitle><stitle>JSEN</stitle><date>2020-03-01</date><risdate>2020</risdate><volume>20</volume><issue>5</issue><spage>2635</spage><epage>2647</epage><pages>2635-2647</pages><issn>1530-437X</issn><eissn>1558-1748</eissn><coden>ISJEAZ</coden><abstract>Road surface quality is essential for improving driving experience and reducing traffic accidents. Traditional road condition monitoring systems are limited in their temporal (speed) and spatial (coverage) responses needed for maintaining overall road quality. Several alternative systems have been proposed that utilize sensors mounted on vehicles. In particular, with the ubiquitous use of smartphones for navigation, smartphone-based road condition assessment has emerged as a promising new approach. In this paper, we propose to analyze different multiclass supervised machine learning techniques to effectively classify road surface conditions using accelerometer, gyroscope and GPS data collected from smartphones. Our work focuses on classification of three main class labels- smooth road, potholes, and deep transverse cracks. We hypothesize that using features from all three axes of the sensors provides more accurate results as compared to using features from only one axis. We also investigate the performance of deep neural networks to classify road conditions with and without explicit manual feature extraction. Our results indicate that models trained with features from all axes of the smartphone sensors outperform models that use only one axis. We also observe that the use of neural networks provides a significantly improved data classification. The machine learning approach discussed here can be implemented on a larger scale to monitor roads for defects that present a safety risk to commuters as well as to provide maintenance information to relevant authorities.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/JSEN.2019.2952857</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0001-7147-7920</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1530-437X |
| ispartof | IEEE sensors journal, 2020-03, Vol.20 (5), p.2635-2647 |
| issn | 1530-437X 1558-1748 |
| language | eng |
| recordid | cdi_proquest_journals_2352193946 |
| source | IEEE Electronic Library (IEL) Journals |
| subjects | accelerometer Accelerometers Artificial neural networks Axes (reference lines) Classification Condition monitoring crack Cracks decision tree Driving Feature extraction Inspection Machine learning Manuals multilayer perceptron neural network Neural networks pavement condition pothole road condition Road surface Roads Roads & highways Sensors smartphone sensor Smartphones Support vector machines Surface properties Traffic accidents Vibrations |
| title | A Machine Learning Approach to Road Surface Anomaly Assessment Using Smartphone Sensors |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T16%3A27%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Machine%20Learning%20Approach%20to%20Road%20Surface%20Anomaly%20Assessment%20Using%20Smartphone%20Sensors&rft.jtitle=IEEE%20sensors%20journal&rft.au=Basavaraju,%20Akanksh&rft.date=2020-03-01&rft.volume=20&rft.issue=5&rft.spage=2635&rft.epage=2647&rft.pages=2635-2647&rft.issn=1530-437X&rft.eissn=1558-1748&rft.coden=ISJEAZ&rft_id=info:doi/10.1109/JSEN.2019.2952857&rft_dat=%3Cproquest_ieee_%3E2352193946%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c336t-2e773d5283a6487926fd9923e365cb26a93113f645a3cf1241d7d4c96303e9503%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2352193946&rft_id=info:pmid/&rft_ieee_id=8896015&rfr_iscdi=true |