Crash risk factor identification using association rules in Nagpur city, Maharashtra, India

Dalai, Bahuguna; Landge, Vishrut S.

doi:10.18520/cs/v123/i6/781-790

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Weng et al investigated the characteristics and contributing factors of work zone crash casualties at a work zone in Michigan with association rules [17]. A similar study Comparative analysis of regional variations in road traffic accident patterns with association rule mining 3 was found for the case in Nagpur city, Maharashtra, India, with the analysis of RTA characteristics performed on three different zones (high, medium, and low) in terms of the RTA occurrence risk [18]. The Apriori algorithm was used for each zone to identify the hidden RTA characteristics.…”

Section: Related Workmentioning

confidence: 99%

“…A review of the state-of-the-art application of ARM showed that the amount of data available is a challenge to discovering the pattern and relationships between the attributes of RTAs. It was suggested that future research is necessary to include more data or useful attributes in mining the association rules for a more comprehensive interpretation of RTA patterns and relationships with contributing factors [8], [9], [11], [14], [18], [19]. In addition, the reviewed studies mostly applied the Apriori algorithm to generate the association rules.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Comparative analysis of regional variations in road traffic accident patterns with association rule mining

Chai,

Lau,

Tee

et al. 2023

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

INTRODUCTION: Road Traffic Accidents (RTAs) patterns discovery is vital to formulate mitigation strategies based on the characteristics of RTAs.OBJECTIVES: Various studies have utilised Apriori algorithm for RTA pattern discovery. Hence, this work aimed to explore the applicability of FP-Growth algorithm to discover and compare the RTA patterns in several regions.METHODS: Orange data mining toolkit is used to discover RTA patterns from the open-access RTA datasets from Addis Ababa city (12,317 samples), Finland (371,213 samples), Berlin city-state (50,119 samples), New Zealand (776,878 samples), the UK (1,048,575 samples), and the US (173,829 samples).RESULTS: There are similarities and differences in RTA patterns among the six regions. The five common factors contributing to RTAs are road characteristics, type of road users or objects involved, environment, driver’s profile, and characteristics of RTA location. These findings could be beneficial for the authorities to formulate strategies to reduce the risk of RTAs.CONCLUSION: Discovery of RTA patterns in different regions is beneficial and future work is essential to discover the RTA patterns from different perspectives such as seasonal or periodical variations of RTA patterns.

show abstract

Section: Related Workmentioning

confidence: 99%