An Approach to Hyperparameter Tuning in Transfer Learning for Driver Drowsiness Detection Based on Bayesian Optimization and Random Search

Abstract

Driver drowsiness is a critical factor in road safety, and developing accurate models for detecting it is essential. Transfer learning has been shown to be an effective technique for driver drowsiness detection, as it enables models to leverage large, pre-existing datasets. However, the optimization of hyperparameters in transfer learning models can be challenging, as it involves a large search space. The core purpose of this research is on presenting an approach to hyperparameter tuning in transfer learning for driving fatigue detection based on Bayesian optimization and Random search algorithms. We examine the efficiency of our approach on a publicly available dataset using transfer learning models with the MobileNetV2, Xception, and VGG19 architectures. We explore the impact of hyperparameters such as dropout rate, activation function, the number of units (the number of dense nodes), optimizer, and learning rate on the transfer learning models' overall performance. Our experiments show that our approach improves the performance of the transfer learning models, obtaining cutting-edge results on the dataset for all three architectures. We also compare the efficiency of Bayesian optimization and Random search algorithms in terms of their ability to find optimal hyperparameters and indicate that Bayesian optimization is more efficient in finding optimal hyperparameters than Random search. The results of our study provide insights into the importance of hyperparameter tuning for transfer learning-based driver drowsiness detection using different transfer learning models and can guide the selection of hyperparameters and models for future studies in this field. Our proposed approach can be applied to other transfer learning tasks, making it a valuable contribution to the field of ML.

Multi-layer perceptron hyperparameter optimization using Jaya algorithm for disease classification

“…This adaptability in learning rate and momentum enables Adam to expedite convergence and diminish the likelihood of getting stuck in local optima, particularly in intricate optimization landscapes characterized by a substantial number of parameters, as is often encountered in deep learning models [30], [31]. The fact that different datasets have different optimized hyperparameters emphasises how crucial hyperparameter tuning is to get the best results on tasks [32]. Table 7 shows average accuracy and execution time comparison from 10 experiments.…”

Deep Learning-Based Lane-Keeping Assist System for Self-Driving Cars Using Transfer Learning and Fine Tuning

“…Initially, rule-based strategies dominated autonomous driving research with a strong emphasis on image processing. These approaches treated perception and control as separate modules, operating independently [1][2][3][4][5][6][7][8][9][10]. However, the emergence of deep learning has led to a significant shift towards end-to-end vehicle control as a prominent research area in autonomous driving [11,12].…”

Advanced Night time Object Detection in Driver-Assistance Systems using Thermal Vision and YOLOv5

“…This poses a considerable challenge for autonomous vehicles navigating roads at night or in poorly lit environments. To address these challenges [6], [7], [8], researchers have turned to Convolutional Neural Networks (CNNs), a powerful deep learning technique that has revolutionized various fields, including computer vision. CNNs have shown great promise for object detection, providing a robust framework for training models that can learn and extract meaningful features from image data.…”