Scholarlink

<p>Innovative wearable neurotechnology offers new methods to enhance user capabilities and provide insights into cognitive processes. These brain-computer interfaces, increasingly accessible, have the potential to become commonplace, necessitating proactive consideration of their societal and sector-specific impacts—including traffic and transportation. However, their development presents two major risks: potential misuse of cognitive data and challenges in user trust and acceptance. This paper proposes a novel approach to improve road safety through the integration of wearable sensor technology and Explainable Artificial Intelligence (XAI). The primary goal is to monitor drivers’ cognitive load in real-time to mitigate the dangers of distracted driving. Wearable sensors, such as EEG headbands and heart rate monitors, continuously capture physiological signals, which are then processed using advanced machine learning algorithms, including XAI models, to yield interpretable assessments of driver cognitive states. The proposed system offers several advantages over traditional methods, including non-intrusiveness, real-time operation, and the capacity for personalized intervention. By developing explainable deep learning models, the system fosters transparency and trust among users and regulatory bodies, encouraging adoption. Ultimately, the integration of this cognitive monitoring system into smart road infrastructure aims to reduce road accidents caused by distraction and promote safer journeys for all road users.</p>

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

Enhancing Road Safety Through Wearable Sensor Technology and Explainable Artificial Intelligence: A Novel Approach To Cognitive Load Monitoring in Driving

  • 期刊论文

  • 发表日期：

    2025年10月4日

查看全文
  • Bharathiraja Nagu,
  • Sellakumar Subramanian,
  • Raj Gaurang Tiwari,
  • Ayodeji Olalekan Salau

摘要

Innovative wearable neurotechnology offers new methods to enhance user capabilities and provide insights into cognitive processes. These brain-computer interfaces, increasingly accessible, have the potential to become commonplace, necessitating proactive consideration of their societal and sector-specific impacts—including traffic and transportation. However, their development presents two major risks: potential misuse of cognitive data and challenges in user trust and acceptance. This paper proposes a novel approach to improve road safety through the integration of wearable sensor technology and Explainable Artificial Intelligence (XAI). The primary goal is to monitor drivers’ cognitive load in real-time to mitigate the dangers of distracted driving. Wearable sensors, such as EEG headbands and heart rate monitors, continuously capture physiological signals, which are then processed using advanced machine learning algorithms, including XAI models, to yield interpretable assessments of driver cognitive states. The proposed system offers several advantages over traditional methods, including non-intrusiveness, real-time operation, and the capacity for personalized intervention. By developing explainable deep learning models, the system fosters transparency and trust among users and regulatory bodies, encouraging adoption. Ultimately, the integration of this cognitive monitoring system into smart road infrastructure aims to reduce road accidents caused by distraction and promote safer journeys for all road users.