Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways [version 2; peer review: 1 approved, 2 approved with reservations]
Background: Road accidents claim around 1.35 million lives annually, with countries like India facing a significant impact. In 2019, India reported 449,002 road accidents, causing 151,113 deaths and 451,361 injuries. Accident severity modeling helps understand contributing factors and develop preven...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
F1000 Research Ltd
2023-10-01
|
| Series: | F1000Research |
| Subjects: | |
| Online Access: | https://f1000research.com/articles/12-494/v2 |
| _version_ | 1797356193900920832 |
|---|---|
| author | Humera Khanum Mir Iqbal Faheem Anshul Garg |
| author_facet | Humera Khanum Mir Iqbal Faheem Anshul Garg |
| author_sort | Humera Khanum |
| collection | DOAJ |
| description | Background: Road accidents claim around 1.35 million lives annually, with countries like India facing a significant impact. In 2019, India reported 449,002 road accidents, causing 151,113 deaths and 451,361 injuries. Accident severity modeling helps understand contributing factors and develop preventive strategies. AI models, such as random forest, offer adaptability and higher predictive accuracy compared to traditional statistical models. This study aims to develop a predictive model for traffic accident severity on Indian highways using the random forest algorithm. Methods: A multi-step methodology was employed, involving data collection and preparation, feature selection, training a random forest model, tuning parameters, and evaluating the model using accuracy and F1 score. Data sources included MoRTH and NHAI. Results: The classification model had hyperparameters ‘max depth’: 10, ‘max features’: ‘sqrt’, and ‘n estimators’: 100. The model achieved an overall accuracy of 67% and a weighted average F1-score of 0.64 on the training set, with a macro average F1-score of 0.53. Using grid search, a random forest Classifier was fitted with optimal parameters, resulting in 41.47% accuracy on test data. Conclusions: The random forest classifier model predicted traffic accident severity with 67% accuracy on the training set and 41.47% on the test set, suggesting possible bias or imbalance in the dataset. No clear patterns were found between the day of the week and accident occurrence or severity. Performance can be improved by addressing dataset imbalance and refining model hyperparameters. The model often underestimated accident severity, highlighting the influence of external factors. Adopting a sophisticated data recording system in line with MoRTH and IRC guidelines and integrating machine learning techniques can enhance road safety modeling, decision-making, and accident prevention efforts. |
| first_indexed | 2024-03-08T14:23:02Z |
| format | Article |
| id | doaj.art-41ea6ead658248a48b99021442763279 |
| institution | Directory Open Access Journal |
| issn | 2046-1402 |
| language | English |
| last_indexed | 2024-03-08T14:23:02Z |
| publishDate | 2023-10-01 |
| publisher | F1000 Research Ltd |
| record_format | Article |
| series | F1000Research |
| spelling | doaj.art-41ea6ead658248a48b990214427632792024-01-14T01:00:02ZengF1000 Research LtdF1000Research2046-14022023-10-0112157426Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways [version 2; peer review: 1 approved, 2 approved with reservations]Humera Khanum0https://orcid.org/0000-0003-2689-6370Mir Iqbal Faheem1Anshul Garg2School of Civil Engineering, Lovely Professional University, Phagwara, Punjab, 1444411, IndiaCivil Engineering Department, Deccan College of Engineering and Technology, Hyderabad, Telangana, 500001, IndiaSchool of Civil Engineering, Lovely Professional University, Phagwara, Punjab, 1444411, IndiaBackground: Road accidents claim around 1.35 million lives annually, with countries like India facing a significant impact. In 2019, India reported 449,002 road accidents, causing 151,113 deaths and 451,361 injuries. Accident severity modeling helps understand contributing factors and develop preventive strategies. AI models, such as random forest, offer adaptability and higher predictive accuracy compared to traditional statistical models. This study aims to develop a predictive model for traffic accident severity on Indian highways using the random forest algorithm. Methods: A multi-step methodology was employed, involving data collection and preparation, feature selection, training a random forest model, tuning parameters, and evaluating the model using accuracy and F1 score. Data sources included MoRTH and NHAI. Results: The classification model had hyperparameters ‘max depth’: 10, ‘max features’: ‘sqrt’, and ‘n estimators’: 100. The model achieved an overall accuracy of 67% and a weighted average F1-score of 0.64 on the training set, with a macro average F1-score of 0.53. Using grid search, a random forest Classifier was fitted with optimal parameters, resulting in 41.47% accuracy on test data. Conclusions: The random forest classifier model predicted traffic accident severity with 67% accuracy on the training set and 41.47% on the test set, suggesting possible bias or imbalance in the dataset. No clear patterns were found between the day of the week and accident occurrence or severity. Performance can be improved by addressing dataset imbalance and refining model hyperparameters. The model often underestimated accident severity, highlighting the influence of external factors. Adopting a sophisticated data recording system in line with MoRTH and IRC guidelines and integrating machine learning techniques can enhance road safety modeling, decision-making, and accident prevention efforts.https://f1000research.com/articles/12-494/v2Traffic Accidents Accident Severity Road Safety Accident Prediction Modeling Random Forest eng |
| spellingShingle | Humera Khanum Mir Iqbal Faheem Anshul Garg Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways [version 2; peer review: 1 approved, 2 approved with reservations] F1000Research Traffic Accidents Accident Severity Road Safety Accident Prediction Modeling Random Forest eng |
| title | Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_full | Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_fullStr | Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_full_unstemmed | Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_short | Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_sort | accident severity prediction modeling for road safety using random forest algorithm an analysis of indian highways version 2 peer review 1 approved 2 approved with reservations |
| topic | Traffic Accidents Accident Severity Road Safety Accident Prediction Modeling Random Forest eng |
| url | https://f1000research.com/articles/12-494/v2 |
| work_keys_str_mv | AT humerakhanum accidentseveritypredictionmodelingforroadsafetyusingrandomforestalgorithmananalysisofindianhighwaysversion2peerreview1approved2approvedwithreservations AT miriqbalfaheem accidentseveritypredictionmodelingforroadsafetyusingrandomforestalgorithmananalysisofindianhighwaysversion2peerreview1approved2approvedwithreservations AT anshulgarg accidentseveritypredictionmodelingforroadsafetyusingrandomforestalgorithmananalysisofindianhighwaysversion2peerreview1approved2approvedwithreservations |