The research led me to collect useful journals to answer the questions proposed. Then, it was gathered in a table to easily find the patterns and assemble into a single refection, which support me to guide the research in the right direction. Therefore, it was found that the information collected shows that different drivers’ driving behaviours vary depending on a range of factors, to classify those factors Azadani & Boukerche, 2021 research classified algorithms into three categories Threshold-Based and Fuzzy Logic Algorithms, Classical Machine Learning Algorithms, Deep Learning Algorithms to determine driving events applied for ITS. Several algorithms for different applications were deeply studied by Meiring & Myburgh, 2015, Wahlström et al., 2017, Chan et al., 2019, and Abou Elassad et al., 2020 fill in those categories, where Abou Elassad et al., 2020 indicated that Support vector machines (SVM), Neural networks (NN), Bayesian learners (BL), and ensemble learners (EL) are generally the four most popular models; they were all adopted by 72% of participants in the study, and NN, IB, BL, and SVM are the most accurate Machine learning (ML) models for the analysis of the dimension of the Driving event. It also concluded that the most model metrics performance used is Accuracy with 65%, recall at 35% and specificity at 32%. Deep learning algorithms are not very often used as suggested by Khodairy & Abosamra, 2021 that used LSTM for driver identification, but Azadani & Boukerche, 2021 uncovered Deep neural networks (DNN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) for processing. On the other hand, The challenges and limitations in this area are associated with the collection, quality, and processing of the data before applying the models as proposed by Mantouka et al., 2021. Another challenge is the smartphone positioning to read the accelerometer data this is addressed in Vlahogianni & Barmpounakis, 2017 which employed a dynamic reposition. Additionally, although smartphone sensors are improving their quality through the years, is difficult to determine the variability in values between mobile phones and sensors from different generations, as well the sensor fusion may influence its functionality of itself as indicated by Kanarachos et al., 2018. Finally, several applications were identified by Aghayari et al., 2021 associated with health and road safety, Rachad et al., 2021 identified driving assistance mobile applications for driving, and Azadani & Boukerche, 2021 for ITS showing the applicability across different sectors of society, and demonstrating the interest on road safety.
References
Abou Elassad, Z. E., Mousannif, H., Al Moatassime, H., & Karkouch, A. (2020). The application of machine learning techniques for driving behavior analysis: A conceptual framework and a systematic literature review. Engineering Applications of Artificial Intelligence, 87, 103312.
Aghayari, H., Kalankesh, L. R., Sadeghi-Bazargani, H., & Feizi-Derakhshi, M.-R. (2021). Mobile applications for road traffic health and safety in the mirror of the Haddon’s matrix. BMC medical informatics and decision making, 21(1), 1-12.
Azadani, M. N., & Boukerche, A. (2021). Driving behavior analysis guidelines for intelligent transportation systems. IEEE Transactions on Intelligent Transportation Systems.
Chan, T. K., Chin, C. S., Chen, H., & Zhong, X. (2019). A comprehensive review of driver behavior analysis utilizing smartphones. IEEE Transactions on Intelligent Transportation Systems, 21(10), 4444-4475.
Kanarachos, S., Christopoulos, S.-R. G., & Chroneos, A. (2018). Smartphones as an integrated platform for monitoring driver behaviour: The role of sensor fusion and connectivity. Transportation research part C: emerging technologies, 95, 867-882.
Khodairy, M. A., & Abosamra, G. (2021). Driving behavior classification based on oversampled signals of smartphone embedded sensors using an optimized stacked-LSTM neural networks. IEEE Access, 9, 4957-4972.
Mantouka, E., Barmpounakis, E., Vlahogianni, E., & Golias, J. (2021). Smartphone sensing for understanding driving behavior: Current practice and challenges. International journal of transportation science and technology, 10(3), 266-282.
Meiring, G. A. M., & Myburgh, H. C. (2015). A review of intelligent driving style analysis systems and related artificial intelligence algorithms. Sensors, 15(12), 30653-30682.
Rachad, T., Idri, A., & Zellou, A. (2021). Gamified Mobile Applications for Improving Driving Behavior: A Systematic Mapping Study. Mobile Information Systems, 2021.
Vlahogianni, E. I., & Barmpounakis, E. N. (2017). Driving analytics using smartphones: Algorithms, comparisons and challenges. Transportation research part C: emerging technologies, 79, 196-206.
Wahlström, J., Skog, I., & Händel, P. (2017). Smartphone-based vehicle telematics: A ten-year anniversary. IEEE Transactions on Intelligent Transportation Systems, 18(10), 2802-2825.