This study investigates convolutional neural network (CNN) architectures for predicting steering angles in self-driving vehicles navigating unstructured roads, using road-facing image data. Two complementary experiments are conducted. First, the impact of three activation functions—Exponential Linear Unit (ELU), Rectified Linear Unit (ReLU), and Leaky ReLU—is evaluated on a baseline CNN model. Trained on 14,754 images and validated on 3,585 images, the model with ELU activation achieves the lowest validation mean squared error (MSE) compared to ReLU and Leaky ReLU, demonstrating superior convergence and generalization. Second, the effect of model complexity is examined using ELU activati... More >

Road accidents have become a critical concern in recent years, particularly due to unmanaged road conditions and challenging geographical terrains, leading to a significant rise in fatalities. Timely detection and rapid response to such incidents are crucial to reducing casualties. This paper presents the design and development of an electronic system, “Vehicle Accident Detection and SMS Conveyor,” which automatically detects accident locations and communicates the incident to relevant authorities via SMS. The system integrates multiple sensors and modules, including an MPU-6050 (gyroscope and accelerometer), ESP32 microcontroller, GSM module, and GPS module. The MPU-6050 monitors vehicl... More >