All Issue

2020 Vol.38, Issue 3 Preview Page

Article

Pattern Classification of Taxi Drivers Based on Work and Living Conditions for Commercial Vehicle Safety Management System

운수안전경영시스템을 위한 근무 및 생활환경 기반 택시 운수종사자 패턴 분류

Seolyoung LEE1
,
Eunsol CHO2
,
Cheol OH3*
,
Sunwha KANG4
,
Byongho CHOE5
이 설영1
,
조 은솔2
,
오 철3*
,
강 선화4
,
최 병호5
1Ph.D., Transportation and Logistics Engineering, Hanyang University, Gyeonggi 15588, Korea
2Master Course, Transportation and Logistics Engineering, Hanyang University, Gyeonggi 15588, Korea
3Professor, Transportation and Logistics Engineering, Hanyang University, Gyeonggi 15588, Korea
4Associate, Transport Safety Research Office, Korea Transportation Safety Authority, Gimcheon 39660, Korea
5Head, Transport Safety Research Office, Korea Transportation Safety Authority, Gimcheon 39660, Korea
1한양대학교 교통 ‧ 물류공학과 박사
2한양대학교 교통 ‧ 물류공학과 석사과정
3한양대학교 교통 ‧ 물류공학과 교수
4한국교통안전공단 교통안전연구처 연구원
5한국교통안전공단 교통안전연구처장
* Corresponding Author
30 June 2020. pp. 218-231
PDF XML Citation
Abstract

The in-depth crash causes analysis for commercial vehicles is necessary to develop more effective safety countermeasures because the crash severity due to commercial vehicles is much higher than other vehicle types. A viable countermeasure to cope with commercial vehicle crashes is to conduct a traffic safety consulting for commercial vehicle drivers. The purpose of this study is to classify the pattern of taxi drivers, which is a fundamental to developing a customized consulting program. A two-stage clustering methodology is adopted to recognize the pattern of taxi drivers based on driver’s intrinsic characteristics underlying the cause of the crash occurrence that include working, health, and living conditions. Results show that it is desirable to classify taxi drivers into four groups such as ‘overworking’, ‘life-imbalanced’, ‘work and life-balanced’, and ‘unspecified-normal’. Discussions on how to use four driver patterns in conducting the safety consulting are presented. In addition, an example of consulting method is presented, which is expected to be used for developing effective consulting programs.

Keywords
driver’s pattern
commercial vehicle safety management system
intrinsic characteristics
mixed clustering
survey
taxi

사업용자동차 중 교통사고 발생 비율이 가장 높은 택시 교통사고의 예방을 위해서는 운수종사자를 대상으로 한 심층적인 원인조사를 통한 운수안전경영시스템이 필요하다. 현재의 교통사고 원인조사 체계에서 수집하는 자료는 사고 발생 현장의 도로교통시설결함과 운수종사자의 위험운전행동에 초점이 맞춰져 있어 택시사고에 가장 비중이 큰 운전자요인에 영향을 미치는 근무환경, 생활패턴, 건강특성과 같은 사고발생 기저에 있는 본질적인 요인과 관련된 자료의 수 집에 한계가 있다. 본 연구의 목적은 택시 운수종사자의 근무 및 생활환경, 건강특성 등을 토대로 운수종사자의 유형을 진단하여 인적요인 기반 운수안전경영관리의 새로운 방향을 제시하는 것이다. 본 연구에서는 법인택시 운수종사자 993명을 대상으로 수행한 심층 면담조사를 통하여 본질적 기저요인 자료를 수집하였으며, 혼합 클러스터링 기법을 적용하여 법인택시 운수종사자의 유형을 분석하였다. 혼합 클러스터링 분석을 통하여 법인택시 운수종사자를 ‘근로과다형’, ‘생활불균형형’, ‘불특정다수형’, ‘워라밸지향형’ 4개의 패턴으로 분류 및 정의하였다. 또한 자료 수집 항목 중 첨단운전자지원시스템 필요성, 일주일 근로시간, 직무스트레스 정도, 신체적 및 정신적 건강상태, 사고심각도 등 패턴의 특성을 파악할 수 있는 총 21개의 유의변수를 도출하였다. 본 연구에서는 운수종사자 안전경영시스템의 새로운 방향을 제시하였으며 연구결과를 활용하여 운수종사자 진단 및 관리를 위한 기초자료로 활용될 수 있을 것으로 기대된다.

키워드
운수종사자 유형
운수안전경영시스템
본질적 기저요인
혼합 클러스터링
심층면담조사
택시
References
1
Bae W. S., Roh S. W. (2005), A Study on K-means Clustering, Commun. Stat. Appl. Methods, 12(2), The Korean Statistical Society, 497-508.
10.5351/CKSS.2005.12.2.497
2
Bulduk E. Ö., Bulduk S., Süren T., Ovalı F. (2014), Assessing Exposure to Risk Factors for Work-related Musculoskeletal Disorders Using Quick Exposure Check (QEC) in Taxi Drivers, Int. J. Ind. Ergon., 44(6), Elsevier, 817-820.
10.1016/j.ergon.2014.10.002
3
Burgel B. J., Gillen M., White M. C. (2012), Health and Safety Strategies of Urban Taxi Drivers, J. Urban Health, 89(4), Springer, 717-722.
10.1007/s11524-012-9685-722669644PMC3535147
4
Caliński T., Harabasz J. (1974), A Dendrite Method for Cluster Analysis, Commun. Stat. Theory Methods, 3(1), Taylor & Francis, 1-27.
10.1080/03610927408827101
5
Charlton S. G., Baas P. H., Alley B. D., Luther R. E. (2003), Analysis of Fatigue Levels in New Zealand Taxi and local-route truck drivers, TERNZ, 22-32.
6
Chen J. C., Chang W. R., Chang W., Christiani D. (2005), Occupational Factors Associated with Low Back Pain in Urban Taxi Drivers, Occup. Med., 55(7), Oxford University Press, 535-540.
10.1093/occmed/kqi12516141293
7
Cheong D. H., Oh K. J. (2014), Using Cluster Analysis and Genetic Algorithm to Develop Portfolio Investment Strategy Based on Investor Information, Journal of the Korean Data And Information Science Society (KDISS), 25(1), The Korean Data and Information Science Society, 107-117.
10.7465/jkdi.2014.25.1.107
8
Cho J. H., Jang K. T., Shim J. S., Oh C. S. (2015), An Analysis of Dangerous Driving Behaviors in Commercial Vehicles using eTAS, J. Korean Soc. Transp., 72, Korean Society of Transportation, 158-163.
9
Evers C. (2009), Effects of Loads and Stress on the Traffic Behavior of Truck Drivers (Doctoral Dissertation), Rheinische Friedrich-Wilhelms-University, Germany.
10
Government of Victoria (2019), Fatigue Management Guidelines, Commercial Passenger Vehicles Victoria (CPVV), 1-7.
11
Halkidi M., Batistakis Y., Vazirgiannis M. (2001), On Clustering Validation Techniques, J. Intell. Inf. Syst., 17(2-3), Kluwer Academic Publishers, 107-145.
10.1023/A:1012801612483
12
Kim Y. W., Kang J. G. (2015), Implementation of Real-time Dangerous Driving Behavior Analysis Utilizing the Digital Tachograph, Journal of The Korea Society of Computer and Information, 20(2), The Korean Society of Computer and Information, 55-62.
10.9708/jksci.2015.20.2.055
13
Korea Occupational Safety & Health Agency (2012), Taxi Driver's Occupational Health Guideline, 88.
14
Kwon O. H., Park S. H., Kim D. W. (2019), Case Studies Using Taxi DTG Data: Analysis of Relationship between Traffic Crashes and Risky Driving Behavior & Effect Analysis of Safe Driving Training Programs, 2019 Korea ITS Society Spring Conference, The Korea Institute of Intelligent Transport Systems, 32.
15
Kwon S. Y. (2018), Risk Factors Associated with Traffic Accidents among Occupational Drivers Based on Fatigue and Sleep Assessment (Doctoral Dissertation), Yonsei University, Korea.
16
La Q. N., Lee A. H., Meuleners L. B., Van Duong D. (2013), Prevalence and Factors Associated with Road Traffic Crash among Taxi Drivers in Hanoi, Vietnam, Accid. Anal. Prev., 50, Elsevier, 452-455.
10.1016/j.aap.2012.05.02222683278
17
Lee H. J. (2009), A Study on the Relation between Perceived Social Support and Career Attitude Maturity with Career Preparation Behavior of an Undergraduate (Masters dissertation), Ewha Womans University, Seoul.
18
Lee Y. S., An M. Y. (2003), A Comparison of Clustering Algorithm in Data Mining, Journal of the Korean Data And Information Science Society (KDISS), 14(2), The Korean Data and Information Science Society, 19-25.
19
Li X., Zhang Q., Peng Z., Wang A., Wang W. (2019), A Data-driven Two-level Clustering Model for Driving Pattern Analysis of Electric Vehicles and a Case Study, J. Clean Prod., 206, Elsevier, 827-837.
10.1016/j.jclepro.2018.09.184
20
MacQueen J. (1967), Some Methods for Classification and Analysis of Multivariate Observations, In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1(14), 281-297.
21
Mahajan K., Velaga N. R., Kumar A., Choudhary A., Choudhary P. (2019), Effects of Driver Work-rest Patterns, Lifestyle and Payment Incentives on Long-haul Truck Driver Sleepiness, Transp. Res. Part F Traffic Psychol. Behav., 60, Elsevier, 366-382.
10.1016/j.trf.2018.10.028
22
Meng F., Li S., Cao L., Li M., Peng Q., Wang C. et al. (2015), Driving Fatigue in Professional Drivers: A Survey of Truck and Taxi Drivers. Traffic inj. prev., 16(5), Taylor & Francis, 474-483.
10.1080/15389588.2014.97394525357206
23
Meng F., Wong S. C., Yan W., Li Y. C., Yang L. (2019), Temporal Patterns of Driving Fatigue and Driving Performance among Male Taxi Drivers in Hong Kong: A Driving Simulator Approach, Accid. Anal. Prev., 125, Elsevier, 7-13.
10.1016/j.aap.2019.01.02030690275
24
Park J. W., Kim E. (2017), Runtime Prediction of Parallel Applications with Workload-aware Clustering, J. Supercomput., 73(11), Kluwer Academic Publishers, 4635-4651.
10.1007/s11227-017-2038-2
25
Raanaas R. K., Anderson D. (2008), A Questionnaire Survey of Norwegian Taxi Drivers' Musculoskeletal Health, and Work-related Risk Factors, Int. J. Ind. Ergon., 38(3-4), Elsevier, 280-290.
10.1016/j.ergon.2007.10.017
26
SAS Institute (2016), SAS/STAT® 14.2 User's Guide.
27
Shin Y. C. (2003), A Study on the Method of Measurement and Application of the Inter-regional Linkage and Urbanization Level for Delimiting the Regional Territory (Masters Dissertation), Dankook University, Yongin.
28
Song M. K., Chang H. (2010), Charaterization of Cities in Seoul Metropolitan Area by Cluster Analysis, Journal of Korean Society for Geospatial Information System, 18(1), Korea Spatial Information Society, 83-88.
29
The Australian Federal Office of Road Safety(1998), Taxi Drivers and Road Safety, 34-120.
30
Williamson A., Lombardi D. A., Folkard S., Stutts J., Courtney T. K., Connor J. L. (2011), The Link between Fatigue and Safety, Accid. Anal. Prev., 43(2), Elsevier, 498-515.
10.1016/j.aap.2009.11.01121130213
31
Yi S. K., Hong S. E., Park S. H. (2006), A Similar Price Zone Determination of Public Land Price Using a Hybrid Clustering Technique, Journal of the Korean Geographical Society, 41(1), The Korean Geographical Society, 121-135.
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 38
  • No :3
  • Pages :218-231
  • Received Date : 2020-04-23
  • Revised Date : 2020-05-12
  • Accepted Date : 2020-05-21
  • DOI :https://doi.org/10.7470/jkst.2020.38.3.218
Journal Informaiton Journal of Korean Society of Transportation Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close