SAFETYLIT WEEKLY UPDATE

We compile citations and summaries of about 400 new articles every week.
RSS Feed

HELP: Tutorials | FAQ
CONTACT US: Contact info

Search Results

Journal Article

Citation

Naseem M, Sami A, Ashraf S, Hashmi SA. Inj. Prev. 2022; 28(Suppl 1): A41.

Copyright

(Copyright © 2022, BMJ Publishing Group)

DOI

10.1136/injuryprev-2022-SAVIR.105

PMID

unavailable

Abstract

SAVIR 2022 Conference Abstracts

Statement of Purpose Road traffic accidents are responsible for 1.3 million deaths each year, contributing to significant morbidity and mortality worldwide. Artificial intelligence (AI), with its ability to process massive amounts of data is an accurate, reliable and cost-effective solution to tackle the ever increasing problems of today's complex transport systems. Through this study, we attempt to determine the utility of various AI based methods for improved road safety.

Methods/Approach The literature search for this scoping review was conducted through the PubMed database using keywords: (AI OR artificial intelligence OR neural network OR machine learning) AND (RTA OR road traffic accident OR RTI OR road traffic injuries OR RTC OR road traffic crashes OR road traffic crash OR road traffic injury prevention). 68 articles were identified and screened for eligibility and 42 were included in the final review. All the items of this Scoping review are reported using guidelines for PRISMA extension for scoping reviews (PRISMA-ScR).

Results Results were synthesized and reported under 7 themes (a) Predicting Injury Severity (b) Risk factors for crash among elderly drivers (c) Intelligent Transport Systems (d) Crash Prediction (e) Modifying Driver's Behavior using AI (f) Road Infrastructure and weather prediction (g) Urban Planning/Smart Cities using AI. Most of the AI based modelling techniques were based on Artificial Neural Network (ANN), Convoluted Neural Network (CNN), Support Vector Machine (SVM), Fuzzy Neural Network (FNN). Further modification and development of hybrid models and spatiotemporal prediction techniques such as Long short-term memory using traffic data of different temporal resolutions (LSTMDTR), Fuzzy Cellular Automata (FCA) model, Novel Decision Tree-based revised Fuzzy Logic model were identified as more accurate predictors of road traffic crash injuries.

Significance Artificial intelligence can be used to identify high-risk areas and predict collisions leading to improved road safety and efficient transport systems which can assist in increasing passenger safety, reducing traffic congestion, accidents, and minimize financial expenditures.


Language: en

NEW SEARCH


All SafetyLit records are available for automatic download to Zotero & Mendeley
Print