A Predictive Pedestrian Crash Model Based on Artificial Intelligence Techniques
Every year in Italy, there are about 20,000 road accidents involving pedestrians, with a significant number of injuries and deaths. Out of these, about 30% occur at pedestrian crossings, where pedestrians should be protected the most. Here, we propose a new accident prediction model to improve pedes...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/23/11364 |
| _version_ | 1827675065883295744 |
|---|---|
| author | Monica Meocci Valentina Branzi Giulia Martini Roberto Arrighi Irene Petrizzo |
| author_facet | Monica Meocci Valentina Branzi Giulia Martini Roberto Arrighi Irene Petrizzo |
| author_sort | Monica Meocci |
| collection | DOAJ |
| description | Every year in Italy, there are about 20,000 road accidents involving pedestrians, with a significant number of injuries and deaths. Out of these, about 30% occur at pedestrian crossings, where pedestrians should be protected the most. Here, we propose a new accident prediction model to improve pedestrian safety assessments that allows us to accurately identify the sites with the largest potential safety improvements and define the best treatments to be applied. The accident prediction model was developed using the ISTAT dataset, including information about the fatal and injurious crashes that occurred in Italy in a 5-year period. The model allowed us to estimate the risk level of a road section through a machine-learning approach. Gradient Boosting seems to be an appropriate tool to fit classification models for its flexibility that allows us to capture non-linear relationships that would be difficult to detect via a classical approach. The results show the ability of the model to perform an accurate analysis of the sites included in the dataset. The locations analyzed have been classified based on the potential risk in the following three classes: High, medium, and low. The proposed model represents a solid and reliable tool for practitioners to perform accident analysis with pedestrian involvement. |
| first_indexed | 2024-03-10T04:56:56Z |
| format | Article |
| id | doaj.art-1b676d236aa84f0cb491dbf4ff7f3fe6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:56:56Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1b676d236aa84f0cb491dbf4ff7f3fe62023-11-23T02:06:57ZengMDPI AGApplied Sciences2076-34172021-12-0111231136410.3390/app112311364A Predictive Pedestrian Crash Model Based on Artificial Intelligence TechniquesMonica Meocci0Valentina Branzi1Giulia Martini2Roberto Arrighi3Irene Petrizzo4Department of Civil and Environmental Engineering, Università di Firenze, 50139 Firenze, ItalyDepartment of Civil and Environmental Engineering, Università di Firenze, 50139 Firenze, ItalyWorld Food Programme—Research Assessment and Monitoring, 00127 Roma, ItalyDepartment of Neuroscience, Psychology, Pharmacology and Child Health, Università di Firenze, 50139 Firenze, ItalyDepartment of Neuroscience, Psychology, Pharmacology and Child Health, Università di Firenze, 50139 Firenze, ItalyEvery year in Italy, there are about 20,000 road accidents involving pedestrians, with a significant number of injuries and deaths. Out of these, about 30% occur at pedestrian crossings, where pedestrians should be protected the most. Here, we propose a new accident prediction model to improve pedestrian safety assessments that allows us to accurately identify the sites with the largest potential safety improvements and define the best treatments to be applied. The accident prediction model was developed using the ISTAT dataset, including information about the fatal and injurious crashes that occurred in Italy in a 5-year period. The model allowed us to estimate the risk level of a road section through a machine-learning approach. Gradient Boosting seems to be an appropriate tool to fit classification models for its flexibility that allows us to capture non-linear relationships that would be difficult to detect via a classical approach. The results show the ability of the model to perform an accurate analysis of the sites included in the dataset. The locations analyzed have been classified based on the potential risk in the following three classes: High, medium, and low. The proposed model represents a solid and reliable tool for practitioners to perform accident analysis with pedestrian involvement.https://www.mdpi.com/2076-3417/11/23/11364pedestrian crashesmodellinggradient boosting |
| spellingShingle | Monica Meocci Valentina Branzi Giulia Martini Roberto Arrighi Irene Petrizzo A Predictive Pedestrian Crash Model Based on Artificial Intelligence Techniques Applied Sciences pedestrian crashes modelling gradient boosting |
| title | A Predictive Pedestrian Crash Model Based on Artificial Intelligence Techniques |
| title_full | A Predictive Pedestrian Crash Model Based on Artificial Intelligence Techniques |
| title_fullStr | A Predictive Pedestrian Crash Model Based on Artificial Intelligence Techniques |
| title_full_unstemmed | A Predictive Pedestrian Crash Model Based on Artificial Intelligence Techniques |
| title_short | A Predictive Pedestrian Crash Model Based on Artificial Intelligence Techniques |
| title_sort | predictive pedestrian crash model based on artificial intelligence techniques |
| topic | pedestrian crashes modelling gradient boosting |
| url | https://www.mdpi.com/2076-3417/11/23/11364 |
| work_keys_str_mv | AT monicameocci apredictivepedestriancrashmodelbasedonartificialintelligencetechniques AT valentinabranzi apredictivepedestriancrashmodelbasedonartificialintelligencetechniques AT giuliamartini apredictivepedestriancrashmodelbasedonartificialintelligencetechniques AT robertoarrighi apredictivepedestriancrashmodelbasedonartificialintelligencetechniques AT irenepetrizzo apredictivepedestriancrashmodelbasedonartificialintelligencetechniques AT monicameocci predictivepedestriancrashmodelbasedonartificialintelligencetechniques AT valentinabranzi predictivepedestriancrashmodelbasedonartificialintelligencetechniques AT giuliamartini predictivepedestriancrashmodelbasedonartificialintelligencetechniques AT robertoarrighi predictivepedestriancrashmodelbasedonartificialintelligencetechniques AT irenepetrizzo predictivepedestriancrashmodelbasedonartificialintelligencetechniques |