Improved metaheuristics with deep learning based object detector for intelligent control in autonomous vehicles

• Published in: Computers & electrical engineering Vol. 108; p. 108718
• Main Authors: Alasmari, Naif, Alohali, Manal Abdullah, Khalid, Majdi, Almalki, Nabil, Motwakel, Abdelwahed, Alsaid, Mohamed Ibrahim, Osman, Azza Elneil, Alneil, Amani A
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-05-2023
• Subjects: Artificial intelligence; Autonomous systems; Hyperparameter tuning; Intelligent control; Metaheuristics; Object detection; Autonomous systems; Metaheuristics; Artificial intelligence; Object detection; Intelligent control; Hyperparameter tuning
• ISSN: 0045-7906; 1879-0755
• DOI: 10.1016/j.compeleceng.2023.108718

•Develop an object detector for intelligent control in autonomous vehicles.•Propose a nadam optimizer with retinanet for object detection.•Apply improved dragonfly with elman neural network to classify object.•Validate the simulation results of proposed model on KITTI database.
In recent times, the autonomous systems have gained considerable interest due to their improved performance and lesser requirements for manual support. The autonomous systems have been extensively implemented in various domains such as logistics, industries, health care, finance, and so on. Intelligence control is the incorporation of autonomous and Artificial Intelligence (AI) systems that assist in critical decision-making steps. Autonomous driving is a new field in intelligent transportation systems that requires automated classification, detection, and the ranging of on-road difficulties. Therefore, the current study develops an Improved Metaheuristics technique with Deep Learning-based Object Detectors for Intelligent Control in Autonomous Vehicles (IMDLOD-ICAV). The presented technique mainly detects the objects to assist, in driving the autonomous vehicles. In the current research work, the RetinaNet model is applied as an object detector whereas the hyperparameter tuning process is executed with the help of the Nadam optimizer. Besides, the Elman Neural Network (ENN) model is also exploited to recognize the objects with a high accuracy. The parameter tuning process is performed with the help of the Improved Dragonfly Algorithm (IDFA). The authors conducted a comprehensive set of experiments to establish the superior performance of the proposed IMDLOD-ICAV technique. The outcomes confirmed the enhanced performance of the IMDLOD-ICAV technique with a maximum accuracy of 99.38%.
[Display omitted]