Smart ADAS for EVs: A Deep Learning Approach to Driver Detection and Safety Enhancement

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 9

Year of Publication : 2025

Authors : Prasanna Moorthy V, Manjusha M, Revathi R, Josephin Shermila P

10.14445/23488549/IJECE-V12I9P115

How to Cite?

Prasanna Moorthy V, Manjusha M, Revathi R, Josephin Shermila P, "Smart ADAS for EVs: A Deep Learning Approach to Driver Detection and Safety Enhancement," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 9, pp. 178-187, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I9P115

Abstract:

Electric Vehicle (EV) technology is an emerging field with several benefits, including lower running costs. Long-lasting batteries have always been the aim of EVs; thus, any additional hardware might significantly shorten battery life. Humans frequently make mistakes. As a result, driving habits like moderation and sports style may cause collisions and fatalities. Driver identification has emerged as a research hotspot in the fields of intelligent transportation and modern car development, and it is crucial to achieving personalized services for drivers and road traffic safety for electric vehicles. An enhanced deep learning-based method for identifying and supporting drivers in Better-performing electric vehicles was presented in this study. This method produces better results by utilizing a special real-world dataset that represents a variety of driving situations. ADAS is designed to increase vehicle efficiency and safety with features including autonomous braking, adaptive cruise control, and lane-keeping assistance. Thus, data-driven object recognition and localization methods are expected to be used in sophisticated driver assistance systems and self-driving automobiles. Specifically, deep neural networks demonstrated exceptional performance in object detection and classification from photos, frequently attaining superhuman levels of efficiency. The suggested ADAS model obtained 97.6% accuracy, 96.9% precision, 98.8% recall, and 99.3% sensitivity.

Keywords:

Electric Vehicles, Deep Learning, Detecting Driver, battery life, Data-driven, Advanced Driver Assistance Systems (ADAS).

References:

[1] Gunapriya Balan et al., “An Improved Deep Learning‐Based Technique for Driver Detection and Driver Assistance in Electric Vehicles with Better Performance,” International Transactions on Electrical Energy Systems, vol. 2022, no. 1, pp. 1-16, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Xiaolin Tang et al., “Visual Detection and Deep Reinforcement Learning-based Car Following and Energy Management for Hybrid Electric Vehicles,” IEEE Transactions on Transportation Electrification, vol. 8, no. 2, pp. 2501-2515, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Halid Kaplan, Kambiz Tehrani, and Mo Jamshidi, “A Fault Diagnosis Design based on Deep Learning Approach for Electric Vehicle Applications,” Energies, vol. 14, no. 20, pp. 1-14, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Guoyuan Wu et al., “Deep Learning–based Eco-Driving System for Battery Electric Vehicles,” UC Davis: National Center for Sustainable Transportation, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Chigozie Uzochukwu Udeogu, and Wansu Lim, “Improved Deep Learning-Based Energy Management Strategy for Battery-Supercapacitor Hybrid Electric Vehicle with Adaptive Velocity Prediction,” IEEE Access, vol. 10, pp. 133789-133802, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yang Xing et al., “Driver Activity Recognition for Intelligent Vehicles: A Deep Learning Approach,” IEEE Transactions on Vehicular Technology, vol. 68, no. 6, pp. 5379-5390, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Seyedeh Mahsa Sotoudeh, and Baisravan HomChaudhuri, “A Deep-Learning-based Approach to Eco-Driving-Based Energy Management of Hybrid Electric Vehicles,” IEEE Transactions on Transportation Electrification, vol. 9, no. 3, pp. 3742-3752, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Irfan Ullah et al., “A Comparative Performance of Machine Learning Algorithm to Predict Electric Vehicles Energy Consumption: A Path Towards Sustainability,” Energy & Environment, vol. 33, no. 8, pp. 1583-1612, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Kai Wang et al., “Analysis of Recent Deep-Learning-based Intrusion Detection Methods for in-Vehicle Network,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 2, pp. 1843-1854, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Liang Zhao et al., “Machine Learning-Based Method for Remaining Range Prediction of Electric Vehicles,” IEEE Access, vol. 8, pp. 212423-212441, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Seokjoon Hong et al., “Real Driving Cycle-Based State of Charge Prediction for EV Batteries using Deep Learning Methods,” Applied Sciences, vol. 11, no. 23, pp. 1-20, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Haochen Sun et al., “Driving-Behavior-Aware Optimal Energy Management Strategy for Multi-Source Fuel Cell Hybrid Electric Vehicles based on Adaptive Soft Deep-Reinforcement Learning,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 4, pp. 4127-4146, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Lulu Guo, Jin Ye, and Bowen Yang, “Cyberattack Detection for Electric Vehicles using Physics-Guided Machine Learning,” IEEE Transactions on Transportation Electrification, vol. 7, no. 3, pp. 2010-2022, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Pedro Maroto Estrada et al., “Deep Learning in the Development of Energy Management Strategies of Hybrid Electric Vehicles: A Hybrid Modeling Approach,” Applied Energy, vol. 329, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Zheng Chen, Chao Yang, and Shengnan Fang, “A Convolutional Neural Network-Based Driving Cycle Prediction Method for Plug-in Hybrid Electric Vehicles with Bus Route,” IEEE Access, vol. 8, pp. 3255-3264, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Bin Xu et al., “A Study of Vehicle Driving Condition Recognition Using Supervised Learning Methods,” IEEE Transactions on Transportation Electrification, vol. 8, no. 2, pp. 1665-1673, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Wangjie Lang et al., “Artificial Intelligence-Based Technique for Fault Detection and Diagnosis of EV Motors: A Review,” IEEE Transactions on Transportation Electrification, vol. 8, no. 1, pp. 384-406, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Yong Wang et al., “Hybrid Electric Vehicle Energy Management with Computer Vision and Deep Reinforcement Learning,” IEEE Transactions on Industrial Informatics, vol. 17, no. 6, pp. 3857-3868, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Jose del C. Julio-Rodríguez et al., “Environment Classification using Machine Learning Methods for Eco-Driving Strategies in Intelligent Vehicles,” Applied Sciences, vol. 12, no. 11, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Teng Liu et al., “Driving Conditions-Driven Energy Management Strategies for Hybrid Electric Vehicles: A Review,” Renewable and Sustainable Energy Reviews, vol. 151, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Sk. Tanzir Mehedi et al., “Deep Transfer Learning-Based Intrusion Detection System for Electric Vehicular Networks,” Sensors, vol. 21, no. 14, pp. 1-23, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Mohammed Almehdhar et al., “Deep Learning in the Fast Lane: A Survey on Advanced Intrusion Detection Systems for Intelligent Vehicle Networks,” IEEE Open Journal of Vehicular Technology, vol. 5, pp. 869-906, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Yijie Xun et al., “Automobile Driver Fingerprinting: A New Machine Learning based Authentication Scheme,” IEEE Transactions on Industrial Informatics, vol. 16, no. 2, pp. 1417-1426, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Abdollah Kavousi-Fard et al., “An Evolutionary Deep Learning-Based Anomaly Detection Model for Securing Vehicles,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 7, pp. 4478-4486, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Hsiao-Chung Lin et al., “Using Deep Learning Networks to Identify Cyber-Attacks on Intrusion Detection for in-Vehicle Networks,” Electronics, vol. 11, no. 14, pp. 1-18, 2022.
[CrossRef] [Google Scholar] [Publisher Link]