Utilization of Artificial Neural Networks (Ann) in Predicting Accidents Within Maharlika Highway San Pablo City, Laguna

Patrick Louie Jay R. Federizo, Marriel Bondad-Baet, Arhgy L. Batarlo, Paul Andrei Enriquez, Jimuel Edmon V. Landicho and Juliana Marie B. Pareja
Additional contact information
Patrick Louie Jay R. Federizo: Asst. Professorial Lecturer, School of Environment and Design – Architecture Program, De La Salle – College of Saint Benilde, Inc., Taft Avenue, Manila
Marriel Bondad-Baet: Faculty, Laguna College, San Pablo City, Laguna
Arhgy L. Batarlo: Student, Civil Engineering Department, Laguna College, San Pablo City, Laguna
Paul Andrei Enriquez: Student, Civil Engineering Department, Laguna College, San Pablo City, Laguna
Jimuel Edmon V. Landicho: Student, Civil Engineering Department, Laguna College, San Pablo City, Laguna
Juliana Marie B. Pareja: Student, Civil Engineering Department, Laguna College, San Pablo City, Laguna

International Journal of Latest Technology in Engineering, Management & Applied Science, 2025, vol. 14, issue 6, 447-459

Abstract: This study presents an accident prediction model for three different segments along Maharlika Highway, San Pablo City, Laguna, which utilizes an Artificial Neural Network (ANN) to analyze accident-related data from the area. The dataset included parameters such as vehicle type, driver’s age, license type, gender, month of occurrence, DUI of alcohol, time and day of accidents, traffic volume, and road characteristics that were used for feature selection. Before the study creation, data preprocessing was conducted to clean and organize the data. These data were trained to predict the likelihood of RTAs based on these features. The results showed that the most relevant features based on their contribution to accidents were vehicle type with 20%, age of driver with 16%, and license with 14%. The study also predicted accidents for 2024-2028 using the ANN-LSTM Prediction. The data were divided for testing, training, and validation. Segment 1 and Segment 3 showed the lowest MSE values of 1.92 and 1.95, respectively, with an epoch of 1100, while Segment 2 showed the lowest MSE of 1.81 with 600 epochs. The LSTM prediction demonstrated different accident trends for the three segments. For Segment 1 and Segment 2, there was an increase in accidents in 2025 before peaking in 2026 and 2027, respectively, followed by a decline in the following years. For Segment 3, there was a potential drop in 2025 before peaking in 2026 with 28 predicted accidents. The predicted trends implied a possible rise in accidents in the next few years, followed by a decline.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.ijltemas.in/DigitalLibrary/Vol.14Issue6/447-459.pdf (application/pdf)
https://www.ijltemas.in/papers/volume-14-issue-6/447-459.html (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bjb:journl:v:14:y:2025:i:6:p:447-459

Access Statistics for this article

International Journal of Latest Technology in Engineering, Management & Applied Science is currently edited by Dr. Pawan Verma

More articles in International Journal of Latest Technology in Engineering, Management & Applied Science from International Journal of Latest Technology in Engineering, Management & Applied Science (IJLTEMAS)
Bibliographic data for series maintained by Dr. Pawan Verma ().