Despite the rapid advances in deep learning (DL) for object detection, existing techniques still face several challenges. In particular, object detection in adverse weather conditions (AWCs) requires complex and computationally costly models to achieve high accuracy rates. Furthermore, the generalization capabilities of these methods struggle to show consistent performance under different conditions. This work focuses on improving object detection using You Only Look Once (YOLO) versions 5, 7, and 9 in AWCs for autonomous vehicles. Although the default values of the hyperparameters are successful for images without AWCs, there is a need to find the optimum values of the hyperparameters in AWCs. Given the many numbers and wide range of hyperparameters, determining them through trial and error is particularly challenging. In this study, the Gray Wolf Optimizer (GWO), Artificial Rabbit Optimizer (ARO), and Chimpanzee Leader Selection Optimization (CLEO) are independently applied to optimize the hyperparameters of YOLOv5, YOLOv7, and YOLOv9. The results show that the preferred method significantly improves the algorithms’ performances for object detection. The overall performance of the YOLO models on the object detection for AWC task increased by 6.146%, by 6.277% for YOLOv7 + CLEO, and by 6.764% for YOLOv9 + GWO.

Our research aims to predict students' academic performance by considering the variables affecting academic performance in science courses using the deep learning method from machine learning algorithms and to determine the importance of independent variables affecting students' academic performance in science courses. 445 students from 5th, 6th, 7th, and 8th grades attending a school in Central Anatolian City in Turkey, participated in this study in the 2022-2023 school year. Data was collected with a. A deep learning method called deep neural network, one of the ways of machine learning, was used in data analysis. The average number of books read per year had the highest importance among the variables affecting academic performance in science courses. In addition, deep learning predicted students' final science scores with 90% accuracy. According to the results of this study, the percentage of the academic achievement prediction might be raised by reproducing the required data set for the data analysis method with deep learning. A forecast of the student’s academic achievement with artificial intelligence and detecting the importance of variables’ percentage might be researched for other courses in addition to the Science course.