Traffic accidents are one of the leading causes of fatalities and severe injuries, endangering the lives and health of individuals. These accidents might have a variety of reasons, some internal to the driver while others are external. When there is low visibility because of unfavorable weather conditions like rain, clouds, and fog, driving can be challenging and even dangerous. Using algorithmic machine learning and approaches for clustering, this project aims to provide a summary of advanced methods for traffic accident predicting. The rising global vehicle accident rate has profound implications for all aspects of human life. Despite their importance, factors including causality assessment, traffic features, and the connections between different contributing components have typically been ignored. Moreover, the majority of the data on traffic accidents that is now accessible is used for data extraction and basic statistical analysis, which offers limited understanding of patterns and statistics. Through the identification of significant contributing factors and the development of preventative methods, this road accident information category seeks to lessen the severity of subsequent accidents. Machine learning algorithms are used to analyze data, identify hidden patterns, predict the impact of an event, and swiftly disseminate this information.
Introduction
The World Health Organization reports a high number of road fatalities globally each year, with traffic volumes increasing rapidly and causing more accidents. Predicting road accidents is a critical area of transportation safety research due to the many factors influencing accidents, such as road geometry, traffic patterns, driver behavior, weather, and visibility. However, there is no standard method for identifying accident-prone zones.
Machine learning and data mining techniques, especially clustering and classification algorithms, have shown promise in analyzing large accident datasets to detect patterns, identify hazardous locations, and predict accident frequency. Various studies have applied algorithms like XGBoost, Naïve Bayes, Decision Trees, Random Forest, and Logistic Regression to improve accident prediction accuracy.
The methodology in this research involved collecting accident data from sources like Kaggle, preprocessing it using Python libraries (Pandas and NumPy), and applying k-means clustering for unsupervised categorization of accident zones into high and low risk. Logistic regression was then used to predict accident likelihood with an accuracy of 86%. Visualization of results helped interpret patterns such as accident frequency during different times of the day.
Conclusion
Road Accidents are caused by various factors. By going through all the research papers it can be concluded that Road Accident cases are hugely affected by the factors such as types of vehicles, age of the driver, age of the vehicle, weather condition, road structure and so on. Thus we have build an application which gives efficient prediction of road accidents based on the above mentioned factors.
The classification algorithm of the entire dataset. In the Road Accident prediction final result is to find the percentage of accident in particular area. Having lower number of features helps the algorithm to converge faster and increases accuracy. In the Road Accident prediction final result is to find the percentage of accident in particular area. Then we apply logistic regression on these features and obtain the least error
Since k-means clustering is an unsupervised learning technique used for unlabeled data, the data in this article are not labelled into any particular cluster. Additionally, regression analysis with a sizable accident data set was employed in this work to determine the causes of traffic accidents. Plotting of the identified contributing elements to the accident is done through analysis and is shown as a graph. This provides a great deal of insight into accident situations and causes. And in the end, this aids the government in modifying road safety regulations to account for various accident and circumstance kinds.
References
[1] Sachin Kumar, Durga Toshniwal, \"A data mining approach to characterize road accident locations”, J. Mod. Transport. 24(1):62–72.
[2] Tessa K. Anderson, “Kernel density estimation and K-means clustering to profile road accident hotspots”, Accident Analysis and Prevention 41,359–364.
[3] Shristi Sonal and Saumya Suman “A Framework for Analysis of Road Accidents” Proceedings of International Conference on Emerging Trends and Innovations in Engineering and Technological Research (ICETIETR)
[4] Analysis of road accidents in India using data mining classification algorithms- E. Suganya,S.Vijayrani.
[5] Hao, W., Kamga, C., Yang, X., Ma, J., Thorson, E., Zhong, M., & Wu, C., (2016), Driver injury severity study for truck involved accidents at highway-rail grade crossings in the United States, Transportation research part F: traffic psychology and behavior, 43, 379-386.
[6] Li, L., Shrestha, S., & Hu, G., (2017), Analysis of road traffic fatal accidents using data mining techniques, In Software Engineering Research, Management and Applications (SERA), IEEE 15th International Conference on (pp. 363-370). IEEE.
[7] El Tayeb, A. A., Pareek, V., & Araar, A. (2015). Applying association rules mining algorithms for traffic accidents in Dubai. International Journal of Soft Computing and Engineering.
[8] Bahram Sadeghi Bigham ,(2014),ROAD ACCIDENT DATA ANALYSIS: A DATA MINING APPROACH, Indian Journal Of Scientific Research 3(3):437-443.
[9] Divya Bansal, Lekha Bhambhu, \"Execution of Apriori algorithm of data mining directed towards tumultuouscrimesconcerningwomen\", International Journal of AdvancedResearch in Computer Science and Software Engineering, vol. 3, no. 9, September 2013.
[10] S. Krishnaveni, M. Hemalatha, \"A perspective analysis of traffic accident using data mining techniques\", International Journal of Computer Applications, vol. 23, no. 7, pp. 40-48, June 2011.
[11] Masashi Toyoda, Daisaku Yokoyama, Junpei Komiyama, Masahiko “Itoh 2017 IEEE International Conference on Big Data,” Boston, MA, 11-14. 2017
[12] Jonardo R. Asor, Gene Marck B. Catedrilla, ”A study on the road accidents using data Investigation and visualization in Los Baños, Laguna, Philippines” 2018 International Conference on Information and Communications Technology (ICOIACT) Yogyakarta, Indonesia. Page s: 96 – 101. 6 March 2018
[13] Sadiq Hussain, L. J. Muhammad, F. S. Ishaq, Atomsa Yakubu and I. A. Mohammed “Performance Evaluation of Various Data MiningAlgorithms on Road Traffic Accident Dataset” Information and Communication Technology for Intelligent Systems pp 67-78, 30 December 2018.
[14] TibebeBeshahTesema, Ajith Abraham, Dejene Ejigu, Learning the Classification of Traffic Accident Types”2012 Fourth International Conference on Intelligent Networking and Collaborative Systems. Page s: 463 – 468, 19-21Sept. 2012
[15] Tibebe Beshah Tesema, Dejene Eijigu, Ajith Abraham, “Knowledge Discovery from Road Traffic Accident Data In Ethiopia” 2011 World Congress on Information and Communication Technologies Page s: 1241 – 1246.Year: 2011
[16] Girija Narasimhan, Ben George Ephrem, et al, “Predictive Analytics of Road Accidents in Oman using Machine Learning Approach”2017 International Conference on Intelligent Computing, Instrumentation, and Control technologies (ICICICT) Page s: 1058 - 1065 July 2017
[17] Li, L, Shrestha, S, and Hu, G, “Analysis of Road Traffic Fatal Accidents using Data Mining Techniques,” 2017IEEE 15th International Conference on Software Engineering Research, Management and Applications (SERA) Page s: 363 – 370, Year: 2017
[18] Ms. Nidhi. R, Ms. Kanchana V, “Analysis of Road Accidents Using Data Mining Techniques” International Journal of Engineering & Technology, Volume 7 (3.10) page 40-44, (2018)
[19] Sadiq Hussain “Survey on Current Trends and Techniques of Data Mining Research “London Journal of Research in Computer Science and Technology Volume 17 | Issue 1 | Compilation 1.0 (March 2017)
[20] Jesus Alcal ´ a-Fdez, Rafael Alcal ´ a, and Francisco Herrera “A Fuzzy Association Rule-Based Classification Model for High-Dimensional Problems With Genetic Rule Selection and Lateral Tuning” IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL. 19,NO. 5, OCTOBER 2011
[21] Niklas Donges Machine learning-blog.com Tutorials and explanations about applied Machine Learning “The Random Forest Algorithm,” 06 February 2016.