Scholarlink

Driver drowsiness is a critical safety concern in the realm of road transportation, potentially leading to severe accidents and fatalities. This research presents an Internet of Things (IoT)-based Driver Drowsiness System designed specifically for electric vehicles (EVs). The proposed system employs a combination of camera as sensor and Deep CNN algorithms to monitor the driver’s vital signs and detect signs of drowsiness or fatigue. The integration of IoT technology enables real-time monitoring and immediate intervention to mitigate potential risks and enhance road safety. In this system, camera and sensor are strategically placed within the vehicle to capture vital signals such as heart rate, facial expressions, and steering behavior. These data points are continuously collected and transmitted wirelessly to a central processing unit, hosted in the cloud. MobileNetV2 Deep Convolutional Neural Networks algorithms are utilized to analyze and interpret the collected data, identifying patterns indicative of drowsiness. Through this IoT-based Driver Drowsiness System, electric vehicle operators can significantly reduce the risks associated with driver fatigue, promoting a safer and more secure driving experience. The integration of emerging technologies and real-time monitoring capabilities is a promising step toward enhancing road safety and advancing the evolution of electric vehicle technology.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Efficient Deep-Learning Approach for the Driver Drowsiness System in Electric Vehicles Using IoT

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • B. Ramasubramanian,
  • Sriram Anbalagan,
  • E. Raja,
  • R. Sathishkumar,
  • Atchaya

摘要

Driver drowsiness is a critical safety concern in the realm of road transportation, potentially leading to severe accidents and fatalities. This research presents an Internet of Things (IoT)-based Driver Drowsiness System designed specifically for electric vehicles (EVs). The proposed system employs a combination of camera as sensor and Deep CNN algorithms to monitor the driver’s vital signs and detect signs of drowsiness or fatigue. The integration of IoT technology enables real-time monitoring and immediate intervention to mitigate potential risks and enhance road safety. In this system, camera and sensor are strategically placed within the vehicle to capture vital signals such as heart rate, facial expressions, and steering behavior. These data points are continuously collected and transmitted wirelessly to a central processing unit, hosted in the cloud. MobileNetV2 Deep Convolutional Neural Networks algorithms are utilized to analyze and interpret the collected data, identifying patterns indicative of drowsiness. Through this IoT-based Driver Drowsiness System, electric vehicle operators can significantly reduce the risks associated with driver fatigue, promoting a safer and more secure driving experience. The integration of emerging technologies and real-time monitoring capabilities is a promising step toward enhancing road safety and advancing the evolution of electric vehicle technology.