Citation :

Julaluk Watthananon, Prapas Thongruk, Pollawat Chintanaporn, Chollada Ploysongsri, "Design and Implementation of a Mobile-Based Accident Prediction System using Behavioural Data Mining," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 6, pp. 201-210, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I6P114

Abstract

Riding motorbikes on the roads and being involved in traffic accidents remains among the primary causes of injury and death, especially in developing nations. The problem and its impact on society drive this research to put forward a design and development of a mobile-based accident prediction system with a focus on data mining of behavioral patterns to predict accident proneness by using the combined capabilities of GPS and a gyroscope in smartphones and the K-Nearest Neighbor algorithm in RapidMiner. The designed mobile application not only identifies dangerous motorbike-riding behavior, but it also supports real-time alerts to improve user awareness to drive motorbikes safely in the future. The system was tested on a population of 300 users and exhibited a high level of accuracy and user satisfaction at 92.5%. The integration of machine learning with real-time mobile monitoring offers a scalable and effective approach to road safety enhancement.

Keywords

Accident Prediction, Driving Behavior, Data Mining, KNN, Software Engineering.

References

[1] Jittima Wongwuttiwat, Thacha Lawanna, and Tanakom Tantontrakul, “The State of Digital Technology and Innovation Development: The Comparative Position of Thailand in ASEAN,” The Electronic Journal of Information Systems in Developing Countries, vol. 90, no. 4, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Witaya Chadbunchachai et al., “Road Traffic Injuries in Thailand: Current Situation,” The Journal of Medical Association Thailand, vol. 95, no. 7, pp. 274-281, 2012.
[Google Scholar]

[3]  Padma Iyenghar, Emil Gracic, and Gregor Pawelke, “A Systematic Approach to Enhancing ISO 26262 with Machine Learning-Specific Life Cycle Phases and Testing Methods,” IEEE Access, vol. 12, pp. 179600-179627, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[4]  ISO, ISO/IEC/IEEE 29119-1:2013(en), Software and Systems Engineering — Software Testing — Part 1: Concepts and Definitions, ISO, 2022. [Online]. Available: https://www.iso.org/obp/ui/#iso:std:iso-iec-ieee:29119:-1:ed-1:v1:en

[5]  Rüdiger Wirth, and Jochen Hipp, “CRISP-DM: Towards a Standard Process Model for Data Mining,” Proceedings of the 4^th International Conference on the Practical Applications of Knowledge Discovery and Data Mining, vol. 1, pp. 1-11, 2000.
[Google Scholar]

[6] Karrouchi Mohammed et al., “Intelligent Driver Monitoring System: An Internet of Things-based System for Tracking and Identifying the Driving Behavior,” Computer Standards and Interfaces, vol. 84, 2023.
[CrossRef] [Google Scholar] [Publisher Link] 

[7] Alexey Kashevnik et al., “Cloud-based Driver Monitoring System using a Smartphone,” IEEE Sensors Journal, vol. 20, no. 12, pp. 6701-6715, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Renjia Wang et al., “Smartphone Sensors-based Abnormal Driving Behaviors Detection: Serial-Feature Network,” IEEE Sensors Journal, vol. 21, no. 14, pp. 15719-15728, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Ehsan Khosravi et al., “Safe Deep Driving Behavior Detection (S3D),” IEEE Access, vol. 10, pp. 113827-113838, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Junqing Li et al., “Road Roughness Detection based on Discrete Kalman Filter Model with Driving Vibration Data Input,” International Journal of Pavement Research and Technology, vol. 18, no. 2, pp. 480-492, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Rohith Vallabhaneni et al., “Secured Web Application based on CapsuleNet and OWASP in the Cloud,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 35, no. 3, pp. 1924-1932, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Preeti Agarwal, and Mansaf Alam, “A Lightweight Deep Learning Model for Human Activity Recognition on Edge Devices,” Procedia Computer Science, vol. 167, pp. 2364-2373, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Deepti Mehrotra et al., “Multiclass Classification of Mobile Applications as Per Energy Consumption,” Journal of King Saud University - Computer and Information Sciences, vol. 33, no. 6, pp. 719-727, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Ankita et al., “An Efficient and Lightweight Deep Learning Model for Human Activity Recognition using Smartphones,” Sensors, vol. 21, no. 11, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Hazilah Mad Kaidi et al., “IoE-Powered Smartphone Feedback for Real-time Driver Improvement,” International Journal of Integrated Engineering, vol. 16, no. 3, pp. 273-280, 2024.
[Google Scholar] [Publisher Link]

[16] Ian Warren et al., “Behavior Change for Youth Drivers: Design and Development of a Smartphone-based App (BackPocketDriver),” JMIR Formative Research, vol. 2, no. 2, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Sarven S. McLinton et al., “A ‘Living Intervention’: Evaluating A Real-Time Feedback System to Help Teams Co-Create Psychosocial Safety Climate,” Safety Science, vol. 190, pp. 1-11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Komal Lochan Behera et al., “Analyzing the Effectiveness of Real-Time Feedback Systems in Occupational Health,” Health Leadership and Quality of Life, vol. 2, 2023.
[Google Scholar]

[19] Lukasz Jedrzejczyk et al., “On the Impact of Real-Time Feedback on Users’ Behaviour in Mobile Location-Sharing Applications,” Proceedings of the Sixth Symposium on Usable Privacy and Security, Association for Computing Machinery, New York, NY, United States, pp. 1-12, 2010.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Gibrail Islam, and Tim Storer, “A Case Study of Agile Software Development for Safety-Critical Systems Projects,” Reliability Engineering and System Safety, vol. 200, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Mario Barbareschi et al., “Scrum for Safety: An Agile Methodology for Safety-Critical Software Systems,” Software Quality Journal, vol. 30, no. 4, pp. 1067-1088, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Suat Kasap, Ersin Elbasi, and Milan Dordevic, “Design, Development, and Evaluation of a Mobile Application for Safety Engineers,” Journal of Infrastructure, Policy and Development, vol. 8, no. 12, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Oyekunle Claudius Oyeniran et al., “5G Technology and its Impact on Software Engineering: New Opportunities for Mobile Applications,” Computer Science and IT Research Journal, vol. 4, no. 3, pp. 562-576, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[24]Yufeng Li et al., “Complying with ISO 26262 and ISO/SAE 21434: A Safety and Security Co-Analysis Method for Intelligent Connected Vehicle,” Sensors, vol. 24, no. 6, pp. 1-29, 2024.
        [CrossRef] [Google Scholar] [Publisher Link]