This research analyzes a driving monitoring system built with hybrid technologies like yolo, cnn, haar cascade by integrating IoT sensors, computer vision, AI, and embedded systems to assess the driver's actions alongside vehicular and environmental conditions in real- time. By leveraging AI-based deep learning techniques such as CNN and Haar Cascade, the system accurately detects driver fatigue, drowsiness, and distraction. IoT sensors enhance accuracy by capturing physiological and vehicular movement patterns, employing both wearable and non-wearable methods to comprehensively analyze driver behaviour and issue proactive accident- prevention measures. The study explores emerging AI-driven driver monitoring technologies, emphasizing the benefits of AI-embedded detection models with Arduino Uno for efficient sensor data processing. Additionally, it addresses challenges related to data quality, computational power, and system integration while discussing potential solutions.           The      conclusion            provides recommendations for further research in developing advanced real-time monitoring systems to enhance road safety.