Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction
Traffic accidents are one of the most important concerns of the world, since they result in numerous casualties, injuries, and fatalities each year, as well as significant economic losses. There are many factors that are responsible for causing road accidents. If these factors can be better understo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/10/12/157 |
| _version_ | 1797505728603226112 |
|---|---|
| author | Daniel Santos José Saias Paulo Quaresma Vítor Beires Nogueira |
| author_facet | Daniel Santos José Saias Paulo Quaresma Vítor Beires Nogueira |
| author_sort | Daniel Santos |
| collection | DOAJ |
| description | Traffic accidents are one of the most important concerns of the world, since they result in numerous casualties, injuries, and fatalities each year, as well as significant economic losses. There are many factors that are responsible for causing road accidents. If these factors can be better understood and predicted, it might be possible to take measures to mitigate the damages and its severity. The purpose of this work is to identify these factors using accident data from 2016 to 2019 from the district of Setúbal, Portugal. This work aims at developing models that can select a set of influential factors that may be used to classify the severity of an accident, supporting an analysis on the accident data. In addition, this study also proposes a predictive model for future road accidents based on past data. Various machine learning approaches are used to create these models. Supervised machine learning methods such as decision trees (DT), random forests (RF), logistic regression (LR), and naive Bayes (NB) are used, as well as unsupervised machine learning techniques including DBSCAN and hierarchical clustering. Results show that a rule-based model using the C5.0 algorithm is capable of accurately detecting the most relevant factors describing a road accident severity. Further, the results of the predictive model suggests the RF model could be a useful tool for forecasting accident hotspots. |
| first_indexed | 2024-03-10T04:22:50Z |
| format | Article |
| id | doaj.art-5ebd57ff8cf44fd6b51a90dfefc9f8e8 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T04:22:50Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-5ebd57ff8cf44fd6b51a90dfefc9f8e82023-11-23T07:46:36ZengMDPI AGComputers2073-431X2021-11-01101215710.3390/computers10120157Machine Learning Approaches to Traffic Accident Analysis and Hotspot PredictionDaniel Santos0José Saias1Paulo Quaresma2Vítor Beires Nogueira3Informatics Departament, University of Évora, 7002-554 Évora, PortugalInformatics Departament, University of Évora, 7002-554 Évora, PortugalInformatics Departament, University of Évora, 7002-554 Évora, PortugalInformatics Departament, University of Évora, 7002-554 Évora, PortugalTraffic accidents are one of the most important concerns of the world, since they result in numerous casualties, injuries, and fatalities each year, as well as significant economic losses. There are many factors that are responsible for causing road accidents. If these factors can be better understood and predicted, it might be possible to take measures to mitigate the damages and its severity. The purpose of this work is to identify these factors using accident data from 2016 to 2019 from the district of Setúbal, Portugal. This work aims at developing models that can select a set of influential factors that may be used to classify the severity of an accident, supporting an analysis on the accident data. In addition, this study also proposes a predictive model for future road accidents based on past data. Various machine learning approaches are used to create these models. Supervised machine learning methods such as decision trees (DT), random forests (RF), logistic regression (LR), and naive Bayes (NB) are used, as well as unsupervised machine learning techniques including DBSCAN and hierarchical clustering. Results show that a rule-based model using the C5.0 algorithm is capable of accurately detecting the most relevant factors describing a road accident severity. Further, the results of the predictive model suggests the RF model could be a useful tool for forecasting accident hotspots.https://www.mdpi.com/2073-431X/10/12/157machine learningdata analysisroad accident dataclusteringdecision treesrandom forests |
| spellingShingle | Daniel Santos José Saias Paulo Quaresma Vítor Beires Nogueira Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction Computers machine learning data analysis road accident data clustering decision trees random forests |
| title | Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction |
| title_full | Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction |
| title_fullStr | Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction |
| title_full_unstemmed | Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction |
| title_short | Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction |
| title_sort | machine learning approaches to traffic accident analysis and hotspot prediction |
| topic | machine learning data analysis road accident data clustering decision trees random forests |
| url | https://www.mdpi.com/2073-431X/10/12/157 |
| work_keys_str_mv | AT danielsantos machinelearningapproachestotrafficaccidentanalysisandhotspotprediction AT josesaias machinelearningapproachestotrafficaccidentanalysisandhotspotprediction AT pauloquaresma machinelearningapproachestotrafficaccidentanalysisandhotspotprediction AT vitorbeiresnogueira machinelearningapproachestotrafficaccidentanalysisandhotspotprediction |