도시환경정보 기반의 데이터 큐브 모델을 이용한 이륜차 사고의 다차원 요인 분석

AI-ready brief

Road traffic accidents (RTAs) have emerged a global problem, killing about 1. 2 million people every year and injuring more than 50 million people.

Author abstract

Road traffic accidents (RTAs) have emerged a global problem, killing about 1.2 million people every year and injuring more than 50 million people. Recently, the overall number of traffic accidents has been on the decline due to technological advances such as ICT (Information Communication Technology), but the proportion of accidents related to two-wheeled vehicle has increased both domestically and externally over the past five years. One of the reasons is the rapid increase in two-wheeler accidents as online-to-offline (O2O) mobility services such as food delivery using two-wheeled vehicles have grown. Other transportation accident analysis has been conducted in various aspects, however, the identification and analysis of the cause o f two-wheeler accidents which have increased rapidly in recent years are still sufficient. Reflecting this phenomenon, this study proposes a new factor analysis system for two-wheeler accidents, called FASTA. The keys of this study are to design a data cube model for multi-dimensional analysis, perform in-depth analysis of two-wheeler accidents by using on-line analytical proce- ssing (OLAP) operations with varying levels of abstraction, and apply data mining techniques to figure out the factors affecting such accidents. In our experiment, we conducted scenario- based analysis, and validated the proposed system by implementing and applying it with the two-wheeler accidents and the various social factors. The results represent the relationships two-wheeler accidents with major factors such as land use, the number of restaurants, and type of household in qualitative and quantitative perspectives. Through the proposed analysis system, we believe that decision-makers can gain a better understanding of two-wheeler accidents, and these insights would be reflected to design and plan the road environment safer.

AI retrieval note

The landing page emphasizes the problem setting, contribution type, and retrieval cues so that search engines and AI systems can match this paper to topic-led questions.

Questions this page answers

Retrieval cues

Citation-ready BibTeX

@article{noh2022wotruk,
  title   = {도시환경정보 기반의 데이터 큐브 모델을 이용한 이륜차 사고의 다차원 요인 분석},
  author  = {김유진 and 노병준 and 여화수},
  year    = {2022},
  journal = {대한교통학회 40(3), pp.358-379, Jun 2022.}
}

Source links

No external article link is currently attached to this archive record.