Enhancing Driver Identification with a Crow Search-Optimized Stacking Ensemble

Anwar Mehmood Sohail; Khurram Shehzad Khattak; Zawar Hussain Khan; Ahmad Mustafa

Authors

Anwar Mehmood Sohail Department of Computer System Engineering, University of Engineering and Technology, Peshawar, Pakistan
Khurram Shehzad Khattak Department of Computer System Engineering, University of Engineering and Technology, Peshawar, Pakistan
Zawar Hussain Khan College of Computer Science and Engineering, University of Hail Hail, Saudi Arabia
Ahmad Mustafa Department of Computer System Engineering, University of Engineering and Technology, Peshawar, Pakistan

Keywords:

Crow Search Algorithm, Driver Identification, Stacking Optimization, Stacking Ensemble, Intelligent Transportation System

Abstract

Driver identification systems play a crucial role in enhancing vehicle security and delivering personalized experiences for drivers. Traditional identification methods typically use individual machine learning models, which often struggle to perform well due to their limited ability to adapt to diverse driving behaviors. In this study, we present a novel stacking ensemble framework optimized using the Crow Search Algorithm (CSA) to overcome these challenges. The CSA-optimized ensemble combines the strengths of several base models—Logistic Regression (LR), Naïve Bayes (NB), Random Forest (RF), and K-Nearest Neighbour (KNN)—with a meta-learner designed to boost both accuracy and robustness. CSA is used to fine-tune the ensemble’s hyperparameters, ensuring optimal performance. Experimental results on a driving dataset demonstrated that the proposed method significantly outperforms existing approaches in terms of identification accuracy, precision, and recall. This framework holds promise for a wide range of applications, including intelligent transportation systems and automotive cybersecurity.

References

A. M. Sohail, T. Y. Wah, N. A. Khan, Z. A. Khan, and A. Koubâa, “A Comprehensive Review: Analysis of Machine Learning, Deep Learning, and Large Language Model Techniques for Revolutionizing Driver Identification,” Authorea Prepr., Mar. 2024, doi: 10.36227/TECHRXIV.170974128.87339641/V1.

E. K. Pei-Yu Tseng, Po-Ching Lin, “Vehicle theft detection by generative adversarial networks on driving behavior,” Eng. Appl. Artif. Intell., vol. 117, p. 105571, 2023, doi: https://doi.org/10.1016/j.engappai.2022.105571.

S. Hernández Sánchez, R. F. Pozo, and L. A. H. Gómez, “Driver Identification and Verification from Smartphone Accelerometers Using Deep Neural Networks,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 1, pp. 97–109, Jan. 2022, doi: 10.1109/TITS.2020.3008210.

K. Gunapriya Balan, Singaravelan Arumugam, Suresh Muthusamy, Hitesh Panchal, Hossam Kotb, Mohit Bajaj, Sherif S. M. Ghoneim, “An Improved Deep Learning-Based Technique for Driver Detection and Driver Assistance in Electric Vehicles with Better Performance,” Int. Trans. Electr. Energy Syst., 2022, doi: https://doi.org/10.1155/2022/8548172.

K. A. N. Ayaz Shehzad, Khattak Khurram S, Khan Zawar H, Minallah Nasru, Khan Mushtaq A, “Sensing technologies for traffic flow characterization: From heterogeneous traffic perspective,” J. Appl. Eng. Sci., vol. 20, no. 1, pp. 29–40, 2022, [Online]. Available: https://scindeks.ceon.rs/Article.aspx?artid=1451-41172201029A

A. N. K. ALI ZEB, KHURRAM S. KHATTAK, AREEB AGHA, ZAWAR H.KHAN, M. ATHAR JAVED SETHI, “On-Board Diagnostic (OBD-II) Based Cyber Physical System for Road Bottlenecks Detection,” J. Eng. Sci. Technol., vol. 17, no. 2, pp. 0906–0922, 2022, [Online]. Available: https://jestec.taylors.edu.my/Vol 17 Issue 2 April 2022/17_2_07.pdf

Li, Z., “Driver identification in intelligent vehicle systems using machine learning algorithms,” IET Intell. Transp. Syst., vol. 13, no. 1, pp. 40–47, 2019, [Online]. Available: http://crossref.org/metadatamanager/publications/10.33411%2Fijasd/addarticle

Y. X. Huihuan Qian, Yongsheng Ou, Xinyu Wu, Xiaoning Meng, “Support Vector Machine for Behavior‐Based Driver Identification System,” J. Robot., 2010, doi: https://doi.org/10.1155/2010/397865.

X. Z. ZhenLong Li, HaoXin Wang, “Random forest–based feature selection and detection method for drunk driving recognition,” Sage Journals, 2020, doi: https://doi.org/10.1177/1550147720905234.

H. Zhang, S. Gao, and Y. Guo, “Driver Lane-Changing Intention Recognition Based on Stacking Ensemble Learning in the Connected Environment: A Driving Simulator Study,” IEEE Trans. Intell. Transp. Syst., vol. 25, no. 2, pp. 1503–1518, Feb. 2024, doi: 10.1109/TITS.2023.3314443.

R. F. Hongjia Zhang, Yingshi Guo, Chang Wang, “Stacking-based ensemble learning method for the recognition of the preceding vehicle lane-changing manoeuvre: A naturalistic driving study on the highway,” IET Intell. Transp. Syst., 2021, doi: https://doi.org/10.1049/itr2.12154.

Y. Chen and M. L. Wong, “Optimizing stacking ensemble by an ant colony optimization approach,” Genet. Evol. Comput. Conf. GECCO’11 - Companion Publ., pp. 7–8, 2011, doi: 10.1145/2001858.2001863;GROUPTOPIC:TOPIC:ACM-PUBTYPE>PROCEEDING;CTYPE:STRING:BOOK.

S. K. P. Shunmugapriya, “Optimization of stacking ensemble configurations through Artificial Bee Colony algorithm,” Swarm Evol. Comput., vol. 12, pp. 24–32, 2013, [Online]. Available: https://www.sciencedirect.com/science/article/abs/pii/S2210650213000199?via%3Dihub

A. Gupta and A. R. Thakkar, “Optimization of stacking ensemble Configuration based on various metahueristic algorithms,” Souvenir 2014 IEEE Int. Adv. Comput. Conf. IACC 2014, pp. 444–451, 2014, doi: 10.1109/IADCC.2014.6779365.

G. Priyadharshini and M. F. Ukrit, “Stacking optimized with artificial bee colony for driving style classification by feature reconstruction from OBD II data,” Soft Comput., vol. 27, no. 1, pp. 591–603, Jan. 2023, doi: 10.1007/S00500-022-07135-3/METRICS.

B. Il Kwak, J. Y. Woo, and H. K. Kim, “Know your master: Driver profiling-based anti-theft method,” 2016 14th Annu. Conf. Privacy, Secur. Trust. PST 2016, pp. 211–218, 2016, doi: 10.1109/PST.2016.7906929.

Alireza Askarzadeh, “A novel metaheuristic method for solving constrained engineering optimization problems: Crow search algorithm,” Comput. Struct., vol. 169, pp. 1–12, 2016, doi: https://doi.org/10.1016/j.compstruc.2016.03.001.