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.
Driver-assistance systems have become an indispensable component of modern vehicles, serving as a crucial element in enhancing safety for both drivers and passengers. Among the fundamental aspects of these systems, object detection stands out, posing significant challenges in low-light scenarios, particularly during nighttime. In this research paper, we propose an innovative and advanced approach for detecting objects during nighttime in driver-assistance systems. Our proposed method leverages thermal vision and incorporates You Only Look Once version 5 (YOLOv5), which demonstrates promising results. The primary objective of this study is to comprehensively evaluate the performance of our model, which utilizes a combination of stochastic gradient descent (SGD) and Adam optimizer. Moreover, we explore the impact of different activation functions, including SiLU, ReLU, Tanh, LeakyReLU, and Hardswish, on the efficiency of nighttime object detection within a driver assistance system that utilizes thermal imaging. To assess the effectiveness of our model, we employ standard evaluation metrics including precision, recall, and mean average precision (mAP), commonly used in object detection systems.
Plant disease identification at an early stage plays a crucial role in ensuring efficient management of the diseases and crop protection. The occurrence of plant ailments can result in substantial reductions in both crop yield and quality, which may cause financial setbacks for farmers and lead to food shortages for consumers. Traditional methods of disease detection rely on visual observation, which can consume a significant amount of time, be a labor-intensive, and often be inaccurate. Automated disease detection systems, based on techniques for machine learning have the potential to greatly improve the precision and speed of disease detection. This article presents a model for classifying plant diseases that combines the output of two transfer learning models, EfficientNetB0 and MobileNetV2, to improve disease classification accuracy. The PlantVillage Dataset was used to train and test the model under consideration, which contains 54,305 photos of 38 different plant disease classes, achieving an accuracy rate of 99.77% in disease classification. The use of an ensemble of deep learning models in this study shows promising results, indicating that the technique can enhance the accuracy of plant disease classification. Besides, this study contributes to the development of accurate and reliable automated disease detection systems, thereby supporting sustainable agriculture and global food security.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.