Analysis of motorcycle accidents using association rule mining-based framework with parameter optimization and GIS technology
•An ARM-based framework is proposed to analyze motorcycle accidents.•Parameter optimization and rule analysis in ARM are addressed for better analysis.•Five individual key factors and four boosting factors are related to fatal injury.•Hot spots of motorcycle accidents related to fatal factors are pr...
Gespeichert in:
| Veröffentlicht in: | Journal of safety research 2020-12, Vol.75, p.292-309 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 309 |
|---|---|
| container_issue | |
| container_start_page | 292 |
| container_title | Journal of safety research |
| container_volume | 75 |
| creator | Jiang, Feifeng Yuen, Kwok Kit Richard Lee, Eric Wai Ming |
| description | •An ARM-based framework is proposed to analyze motorcycle accidents.•Parameter optimization and rule analysis in ARM are addressed for better analysis.•Five individual key factors and four boosting factors are related to fatal injury.•Hot spots of motorcycle accidents related to fatal factors are presented in GIS maps.•The framework has been validated to have better performance on severity analysis.
Analyzing key factors of motorcycle accidents is an effective method to reduce fatalities and improve road safety. Association Rule Mining (ARM) is an efficient data mining method to identify critical factors associated with injury severity. However, the existing studies have some limitations in applying ARM: (a) Most studies determined parameter thresholds of ARM subjectively, which lacks objectiveness and efficiency; (b) Most studies only listed rules with high parameter thresholds, while lacking in-depth analysis of multiple-item rules. Besides, the existing studies seldom conducted a spatial analysis of motorcycle accidents, which can provide intuitive suggestions for policymakers. Method: To address these limitations, this study proposes an ARM-based framework to identify critical factors related to motorcycle injury severity. A method for parameter optimization is proposed to objectively determine parameter thresholds in ARM. A method of factor extraction is proposed to identify individual key factors from 2-item rules and boosting factors from multiple-item rules. Geographic information system (GIS) is adopted to explore the spatial relationship between key factors and motorcycle injury severity. Results and conclusions: The framework is applied to a case study of motorcycle accidents in Victoria, Australia. Fifteen attributes are selected after data preprocessing. 0.03 and 0.7 are determined as the best thresholds of support and confidence in ARM. Five individual key factors and four boosting factors are identified to be related to fatal injury. Spatial analysis is conducted by GIS to present hot spots of motorcycle accidents. The proposed framework has been validated to have better performance on parameter optimization and rule analysis in ARM. Practical applications: The hot spots of motorcycle accidents related to fatal factors are presented in GIS maps. Policymakers can refer to those maps straightforwardly when decision making. This framework can be applied to various kinds of traffic accidents to improve the performance of severity analysis. |
| doi_str_mv | 10.1016/j.jsr.2020.09.004 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2471459186</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0022437520301109</els_id><sourcerecordid>2471459186</sourcerecordid><originalsourceid>FETCH-LOGICAL-c409t-3dfaaad3794d0eba84a7bf37437fcea74c2dbf83aa2c3216eaa4a2b10b6559d03</originalsourceid><addsrcrecordid>eNp9kU9v1DAQxS0EokvhA3BBlrhwSRgnzj9xqioolSpxAM7WxJ60Dom92A7VIvHd8WoLBw7MxRrr95407zH2UkApQLRv53KOoaygghKGEkA-YjvRd0MhKtk9ZjuAqipk3TVn7FmMMwC0jRBP2VmdR8q-37FfFw6XQ7SR-4mvPvmgD3ohjlpbQy5FvkXrbjnG6LXFZL3jYcvAal3-L0aMZPgUcKV7H77xe5vu-B6Pe6LA_T7Z1f486dAZfnX9mSfSd84v_vbwnD2ZcIn04uE9Z18_vP9y-bG4-XR1fXlxU2gJQypqMyGiqbtBGqARe4ndONVdPm3ShJ3UlRmnvkasdF2JlhAlVqOAsW2awUB9zt6cfPfBf98oJrXaqGlZ0JHfospxCdkMom8z-vofdPZbyCEdqT77CeiaTIkTpYOPMdCk9sGuGA5KgDp2o2aVu1HHbhQMKneTNa8enLdxJfNX8aeMDLw7AZSj-GEpqKgtOU3GBtJJGW__Y_8bStCiXg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2486551075</pqid></control><display><type>article</type><title>Analysis of motorcycle accidents using association rule mining-based framework with parameter optimization and GIS technology</title><source>MEDLINE</source><source>Access via ScienceDirect (Elsevier)</source><creator>Jiang, Feifeng ; Yuen, Kwok Kit Richard ; Lee, Eric Wai Ming</creator><creatorcontrib>Jiang, Feifeng ; Yuen, Kwok Kit Richard ; Lee, Eric Wai Ming</creatorcontrib><description>•An ARM-based framework is proposed to analyze motorcycle accidents.•Parameter optimization and rule analysis in ARM are addressed for better analysis.•Five individual key factors and four boosting factors are related to fatal injury.•Hot spots of motorcycle accidents related to fatal factors are presented in GIS maps.•The framework has been validated to have better performance on severity analysis.
Analyzing key factors of motorcycle accidents is an effective method to reduce fatalities and improve road safety. Association Rule Mining (ARM) is an efficient data mining method to identify critical factors associated with injury severity. However, the existing studies have some limitations in applying ARM: (a) Most studies determined parameter thresholds of ARM subjectively, which lacks objectiveness and efficiency; (b) Most studies only listed rules with high parameter thresholds, while lacking in-depth analysis of multiple-item rules. Besides, the existing studies seldom conducted a spatial analysis of motorcycle accidents, which can provide intuitive suggestions for policymakers. Method: To address these limitations, this study proposes an ARM-based framework to identify critical factors related to motorcycle injury severity. A method for parameter optimization is proposed to objectively determine parameter thresholds in ARM. A method of factor extraction is proposed to identify individual key factors from 2-item rules and boosting factors from multiple-item rules. Geographic information system (GIS) is adopted to explore the spatial relationship between key factors and motorcycle injury severity. Results and conclusions: The framework is applied to a case study of motorcycle accidents in Victoria, Australia. Fifteen attributes are selected after data preprocessing. 0.03 and 0.7 are determined as the best thresholds of support and confidence in ARM. Five individual key factors and four boosting factors are identified to be related to fatal injury. Spatial analysis is conducted by GIS to present hot spots of motorcycle accidents. The proposed framework has been validated to have better performance on parameter optimization and rule analysis in ARM. Practical applications: The hot spots of motorcycle accidents related to fatal factors are presented in GIS maps. Policymakers can refer to those maps straightforwardly when decision making. This framework can be applied to various kinds of traffic accidents to improve the performance of severity analysis.</description><identifier>ISSN: 0022-4375</identifier><identifier>EISSN: 1879-1247</identifier><identifier>DOI: 10.1016/j.jsr.2020.09.004</identifier><identifier>PMID: 33334488</identifier><language>eng</language><publisher>United States: Elsevier Ltd</publisher><subject>Accidents ; Accidents, Traffic - statistics & numerical data ; Accurate and Efficient Classification Based on Multiple Class-Association Rules (CMAR) ; Adult ; Aged ; Aged, 80 and over ; Association Rule Mining (ARM) ; Data mining ; Data Mining - standards ; Data processing ; Decision making ; Female ; Geographic Information System (GIS) ; Geographic information systems ; Geographic Information Systems - statistics & numerical data ; Humans ; Identification methods ; Injury analysis ; Injury prevention ; Key Factors ; Male ; Middle Aged ; Mining accidents & safety ; Motorcycle Accidents ; Motorcycles ; Optimization ; Parameters ; Performance enhancement ; Remote sensing ; Spatial analysis ; Technology assessment ; threshold determination ; Thresholds ; Traffic accidents ; Traffic accidents & safety ; Traffic safety ; Victoria ; Young Adult</subject><ispartof>Journal of safety research, 2020-12, Vol.75, p.292-309</ispartof><rights>2020</rights><rights>Copyright © 2020. Published by Elsevier Ltd.</rights><rights>Copyright Pergamon Press Inc. Dec 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c409t-3dfaaad3794d0eba84a7bf37437fcea74c2dbf83aa2c3216eaa4a2b10b6559d03</citedby><cites>FETCH-LOGICAL-c409t-3dfaaad3794d0eba84a7bf37437fcea74c2dbf83aa2c3216eaa4a2b10b6559d03</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.jsr.2020.09.004$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33334488$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Jiang, Feifeng</creatorcontrib><creatorcontrib>Yuen, Kwok Kit Richard</creatorcontrib><creatorcontrib>Lee, Eric Wai Ming</creatorcontrib><title>Analysis of motorcycle accidents using association rule mining-based framework with parameter optimization and GIS technology</title><title>Journal of safety research</title><addtitle>J Safety Res</addtitle><description>•An ARM-based framework is proposed to analyze motorcycle accidents.•Parameter optimization and rule analysis in ARM are addressed for better analysis.•Five individual key factors and four boosting factors are related to fatal injury.•Hot spots of motorcycle accidents related to fatal factors are presented in GIS maps.•The framework has been validated to have better performance on severity analysis.
Analyzing key factors of motorcycle accidents is an effective method to reduce fatalities and improve road safety. Association Rule Mining (ARM) is an efficient data mining method to identify critical factors associated with injury severity. However, the existing studies have some limitations in applying ARM: (a) Most studies determined parameter thresholds of ARM subjectively, which lacks objectiveness and efficiency; (b) Most studies only listed rules with high parameter thresholds, while lacking in-depth analysis of multiple-item rules. Besides, the existing studies seldom conducted a spatial analysis of motorcycle accidents, which can provide intuitive suggestions for policymakers. Method: To address these limitations, this study proposes an ARM-based framework to identify critical factors related to motorcycle injury severity. A method for parameter optimization is proposed to objectively determine parameter thresholds in ARM. A method of factor extraction is proposed to identify individual key factors from 2-item rules and boosting factors from multiple-item rules. Geographic information system (GIS) is adopted to explore the spatial relationship between key factors and motorcycle injury severity. Results and conclusions: The framework is applied to a case study of motorcycle accidents in Victoria, Australia. Fifteen attributes are selected after data preprocessing. 0.03 and 0.7 are determined as the best thresholds of support and confidence in ARM. Five individual key factors and four boosting factors are identified to be related to fatal injury. Spatial analysis is conducted by GIS to present hot spots of motorcycle accidents. The proposed framework has been validated to have better performance on parameter optimization and rule analysis in ARM. Practical applications: The hot spots of motorcycle accidents related to fatal factors are presented in GIS maps. Policymakers can refer to those maps straightforwardly when decision making. This framework can be applied to various kinds of traffic accidents to improve the performance of severity analysis.</description><subject>Accidents</subject><subject>Accidents, Traffic - statistics & numerical data</subject><subject>Accurate and Efficient Classification Based on Multiple Class-Association Rules (CMAR)</subject><subject>Adult</subject><subject>Aged</subject><subject>Aged, 80 and over</subject><subject>Association Rule Mining (ARM)</subject><subject>Data mining</subject><subject>Data Mining - standards</subject><subject>Data processing</subject><subject>Decision making</subject><subject>Female</subject><subject>Geographic Information System (GIS)</subject><subject>Geographic information systems</subject><subject>Geographic Information Systems - statistics & numerical data</subject><subject>Humans</subject><subject>Identification methods</subject><subject>Injury analysis</subject><subject>Injury prevention</subject><subject>Key Factors</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Mining accidents & safety</subject><subject>Motorcycle Accidents</subject><subject>Motorcycles</subject><subject>Optimization</subject><subject>Parameters</subject><subject>Performance enhancement</subject><subject>Remote sensing</subject><subject>Spatial analysis</subject><subject>Technology assessment</subject><subject>threshold determination</subject><subject>Thresholds</subject><subject>Traffic accidents</subject><subject>Traffic accidents & safety</subject><subject>Traffic safety</subject><subject>Victoria</subject><subject>Young Adult</subject><issn>0022-4375</issn><issn>1879-1247</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kU9v1DAQxS0EokvhA3BBlrhwSRgnzj9xqioolSpxAM7WxJ60Dom92A7VIvHd8WoLBw7MxRrr95407zH2UkApQLRv53KOoaygghKGEkA-YjvRd0MhKtk9ZjuAqipk3TVn7FmMMwC0jRBP2VmdR8q-37FfFw6XQ7SR-4mvPvmgD3ohjlpbQy5FvkXrbjnG6LXFZL3jYcvAal3-L0aMZPgUcKV7H77xe5vu-B6Pe6LA_T7Z1f486dAZfnX9mSfSd84v_vbwnD2ZcIn04uE9Z18_vP9y-bG4-XR1fXlxU2gJQypqMyGiqbtBGqARe4ndONVdPm3ShJ3UlRmnvkasdF2JlhAlVqOAsW2awUB9zt6cfPfBf98oJrXaqGlZ0JHfospxCdkMom8z-vofdPZbyCEdqT77CeiaTIkTpYOPMdCk9sGuGA5KgDp2o2aVu1HHbhQMKneTNa8enLdxJfNX8aeMDLw7AZSj-GEpqKgtOU3GBtJJGW__Y_8bStCiXg</recordid><startdate>20201201</startdate><enddate>20201201</enddate><creator>Jiang, Feifeng</creator><creator>Yuen, Kwok Kit Richard</creator><creator>Lee, Eric Wai Ming</creator><general>Elsevier Ltd</general><general>Elsevier Science Ltd</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7T2</scope><scope>C1K</scope><scope>K9.</scope><scope>7X8</scope></search><sort><creationdate>20201201</creationdate><title>Analysis of motorcycle accidents using association rule mining-based framework with parameter optimization and GIS technology</title><author>Jiang, Feifeng ; Yuen, Kwok Kit Richard ; Lee, Eric Wai Ming</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c409t-3dfaaad3794d0eba84a7bf37437fcea74c2dbf83aa2c3216eaa4a2b10b6559d03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Accidents</topic><topic>Accidents, Traffic - statistics & numerical data</topic><topic>Accurate and Efficient Classification Based on Multiple Class-Association Rules (CMAR)</topic><topic>Adult</topic><topic>Aged</topic><topic>Aged, 80 and over</topic><topic>Association Rule Mining (ARM)</topic><topic>Data mining</topic><topic>Data Mining - standards</topic><topic>Data processing</topic><topic>Decision making</topic><topic>Female</topic><topic>Geographic Information System (GIS)</topic><topic>Geographic information systems</topic><topic>Geographic Information Systems - statistics & numerical data</topic><topic>Humans</topic><topic>Identification methods</topic><topic>Injury analysis</topic><topic>Injury prevention</topic><topic>Key Factors</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Mining accidents & safety</topic><topic>Motorcycle Accidents</topic><topic>Motorcycles</topic><topic>Optimization</topic><topic>Parameters</topic><topic>Performance enhancement</topic><topic>Remote sensing</topic><topic>Spatial analysis</topic><topic>Technology assessment</topic><topic>threshold determination</topic><topic>Thresholds</topic><topic>Traffic accidents</topic><topic>Traffic accidents & safety</topic><topic>Traffic safety</topic><topic>Victoria</topic><topic>Young Adult</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jiang, Feifeng</creatorcontrib><creatorcontrib>Yuen, Kwok Kit Richard</creatorcontrib><creatorcontrib>Lee, Eric Wai Ming</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Health and Safety Science Abstracts (Full archive)</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>MEDLINE - Academic</collection><jtitle>Journal of safety research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jiang, Feifeng</au><au>Yuen, Kwok Kit Richard</au><au>Lee, Eric Wai Ming</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Analysis of motorcycle accidents using association rule mining-based framework with parameter optimization and GIS technology</atitle><jtitle>Journal of safety research</jtitle><addtitle>J Safety Res</addtitle><date>2020-12-01</date><risdate>2020</risdate><volume>75</volume><spage>292</spage><epage>309</epage><pages>292-309</pages><issn>0022-4375</issn><eissn>1879-1247</eissn><abstract>•An ARM-based framework is proposed to analyze motorcycle accidents.•Parameter optimization and rule analysis in ARM are addressed for better analysis.•Five individual key factors and four boosting factors are related to fatal injury.•Hot spots of motorcycle accidents related to fatal factors are presented in GIS maps.•The framework has been validated to have better performance on severity analysis.
Analyzing key factors of motorcycle accidents is an effective method to reduce fatalities and improve road safety. Association Rule Mining (ARM) is an efficient data mining method to identify critical factors associated with injury severity. However, the existing studies have some limitations in applying ARM: (a) Most studies determined parameter thresholds of ARM subjectively, which lacks objectiveness and efficiency; (b) Most studies only listed rules with high parameter thresholds, while lacking in-depth analysis of multiple-item rules. Besides, the existing studies seldom conducted a spatial analysis of motorcycle accidents, which can provide intuitive suggestions for policymakers. Method: To address these limitations, this study proposes an ARM-based framework to identify critical factors related to motorcycle injury severity. A method for parameter optimization is proposed to objectively determine parameter thresholds in ARM. A method of factor extraction is proposed to identify individual key factors from 2-item rules and boosting factors from multiple-item rules. Geographic information system (GIS) is adopted to explore the spatial relationship between key factors and motorcycle injury severity. Results and conclusions: The framework is applied to a case study of motorcycle accidents in Victoria, Australia. Fifteen attributes are selected after data preprocessing. 0.03 and 0.7 are determined as the best thresholds of support and confidence in ARM. Five individual key factors and four boosting factors are identified to be related to fatal injury. Spatial analysis is conducted by GIS to present hot spots of motorcycle accidents. The proposed framework has been validated to have better performance on parameter optimization and rule analysis in ARM. Practical applications: The hot spots of motorcycle accidents related to fatal factors are presented in GIS maps. Policymakers can refer to those maps straightforwardly when decision making. This framework can be applied to various kinds of traffic accidents to improve the performance of severity analysis.</abstract><cop>United States</cop><pub>Elsevier Ltd</pub><pmid>33334488</pmid><doi>10.1016/j.jsr.2020.09.004</doi><tpages>18</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0022-4375 |
| ispartof | Journal of safety research, 2020-12, Vol.75, p.292-309 |
| issn | 0022-4375 1879-1247 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2471459186 |
| source | MEDLINE; Access via ScienceDirect (Elsevier) |
| subjects | Accidents Accidents, Traffic - statistics & numerical data Accurate and Efficient Classification Based on Multiple Class-Association Rules (CMAR) Adult Aged Aged, 80 and over Association Rule Mining (ARM) Data mining Data Mining - standards Data processing Decision making Female Geographic Information System (GIS) Geographic information systems Geographic Information Systems - statistics & numerical data Humans Identification methods Injury analysis Injury prevention Key Factors Male Middle Aged Mining accidents & safety Motorcycle Accidents Motorcycles Optimization Parameters Performance enhancement Remote sensing Spatial analysis Technology assessment threshold determination Thresholds Traffic accidents Traffic accidents & safety Traffic safety Victoria Young Adult |
| title | Analysis of motorcycle accidents using association rule mining-based framework with parameter optimization and GIS technology |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T18%3A39%3A16IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Analysis%20of%20motorcycle%20accidents%20using%20association%20rule%20mining-based%20framework%20with%20parameter%20optimization%20and%20GIS%20technology&rft.jtitle=Journal%20of%20safety%20research&rft.au=Jiang,%20Feifeng&rft.date=2020-12-01&rft.volume=75&rft.spage=292&rft.epage=309&rft.pages=292-309&rft.issn=0022-4375&rft.eissn=1879-1247&rft_id=info:doi/10.1016/j.jsr.2020.09.004&rft_dat=%3Cproquest_cross%3E2471459186%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2486551075&rft_id=info:pmid/33334488&rft_els_id=S0022437520301109&rfr_iscdi=true |