Road traffic accidents prediction modelling: An analysis of Anambra State, Nigeria

Eskandari

2021

HDQ

Background: Road accidents are among the most important causes of death and severe personal and financial injuries. Also, its profound social, cultural, and economic effects threaten human societies. This study aimed to estimate the trend of traffic accident victims in Yazd Province, Iran, to predict the number of traffic accident victims in this province. Materials and Methods: Based on traffic casualty statistics referred to forensic medicine in Yazd Province within April 1989 and March 2017 referred to Forensic Medicine of Yazd Province and using an artificial neural network to predict the number of injured for 12 months ending in 2020 has been paid. The neural network used in this study had 12 inputs, one output, and 5 hidden layers. The network predicts the relationship between data after training and learning. The network is considered the MSE benchmark. Results: The number of injured in traffic accidents in Yazd Province in 2020 was equal to 7052 people, with the highest number in December with 832 people and the lowest in June with 414 people. The exact method of use was equal to 92 cases. Conclusion: The trend of traffic accident casualties in Yazd Province in 2020 will be declining. For future research, the exact method designed in this study can be examined with other methods for the best response level.

Section: Discussionmentioning

confidence: 51%

Using Artificial Neural Network to Destroy the Process of Traffic Accident Victims in Yazd Province

Eskandari

2021

HDQ

“…Chukwutoo et al compared the accuracy of ARIMA and ARIMAX methods for predicting car accidents in Nigeria that occurred between 2007 and 2015. Their comparison showed that the ARIMAX model was better than the ARIMA model in predicting car accidents [17]. Liue et al reported that if the Box-Jenkins time series is combined with other methods, its prediction accuracy could be increased [18].…”

Section: Discussionmentioning

confidence: 99%

“…Bahadori Monfared et al reported the reducing trend of traffic accidents in Iran [14]. Omidi et al also reported the reduced rate of traffic accidents in Zanjan Province; however, Chukwutoo et al reported an increasing trend of accidents in Nigeria in the future [13,17].…”

Section: Discussionmentioning

confidence: 99%

Providing an Appropriate Prediction Model for Traffic Accidents: A Case Study on Accidents in Golestan, Mazandaran, Guilan, and Ardebil Provinces

Eskandari

Raissi

et al. 2019

HDQ

Background: Road traffic accidents in Iran are a critical issue that hinders economic development and one of the main threats to the health and safety of people in the community. The statistics indicate that after cardiovascular diseases, traffic accidents are the second leading cause of death in different age groups, which reflects the necessity of prediction in this area. Materials and Methods: The present study investigated the data of the traffic-accident injured people between April 2009 and March 2012 in Golestan, Mazandaran, Guilan, and Ardebil provinces, presented to forensic medicine. We used the Box-Jenkins method as one of the most advanced methods in prediction and future studies in the field of health systems, to estimate the number of injuries by province, for the years 2016 to 2019. Results: The obtained results suggested the appropriate time series patterns for predicting injured people in Golestan Province with Autoregressive Integrated Moving Average (ARIMA)

“…Reference [33] confirmed that traffic accidents and injuries on Slovenian roads were caused by a combination of factors, the most important of which being human error, or more precisely, speeding and driving in the wrong lane. Reference [34] revealed that a combination of human, vehicle and environmental factors led to road traffic crashes.…”

Section: Million In 2015mentioning

confidence: 99%

Feature Recognition of Urban Road Traffic Accidents Based on GA-XGBoost in the Context of Big Data

Lin

et al. 2019

IEEE Access

The identification of the characteristics of urban road traffic accidents is of great significance for reducing traffic accidents and the corresponding losses. In the context of big data, to accurately understand the characteristics of traffic accidents, the feature set of urban road traffic accidents is proposed, the XGBoost model is used to classify traffic accidents into minor accidents, general accidents, major accidents and serious accidents, and a GA-XGBoost feature recognition model is built. The GA-XGBoost feature recognition model is based on the genetic algorithm (GA) as a factor search algorithm and is verified by applying the big data of traffic accidents in a Chinese city from 2006 to 2016; in addition, the model is compared with the GA-RF, GA-GBDT and GA-LightGBM models. The results show that the GA-XGBoost model can accurately identify the features of the traffic accidents in 7 cities, including driving experience, illegal driving behavior, vehicle age, road intersection type, weather conditions, traffic flow and time interval. Compared with the GA-RF, GA-GBDT and GA-LightGBM models, the recognition features are more accurate, and the performance is better. INDEX TERMS Urban traffic, feature recognition, traffic accidents, XGBoost algorithm, genetic algorithm (GA).