AI-Driven Smart Cockpit: Monitoring of Sudden Illnesses, Health Risk Intervention, and Future Prospects

Area of Science:

• Human-computer interaction
• Artificial intelligence in healthcare
• Automotive technology

Background:

• Intelligent driving cabins are becoming a "third living space" integrating AI for perception, analysis, decision-making, and intervention.
• Real-time monitoring of physiological indicators like heart rate and blood pressure is achievable through multimodal biosignal acquisition.

Purpose of the Study:

• To develop an AI platform for intelligent driving cabins that integrates multimodal biosignal acquisition for real-time health monitoring.
• To leverage vehicle domain controllers and edge computing for reduced latency and enhanced AI processing.
• To create personalized health baselines and high-precision risk prediction models using machine learning.

Main Methods:

• Utilizing flexible and non-contact biosensing technologies for physiological data acquisition.
• Implementing domain controllers and edge computing for efficient data processing and reduced latency.
• Employing machine learning models, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), for risk prediction.

Main Results:

• The AI platform can integrate internal and external cabin data for comprehensive analysis.
• Tailored health baselines and accurate risk prediction models (e.g., CNN, LSTM) are established.
• Multi-level interventions are initiated, including environmental adjustments, health recommendations, and ADAS-assisted emergency parking with telemedicine.

Conclusions:

• Intelligent driving cabins offer a novel approach to continuous health monitoring and proactive intervention.
• Key challenges include sensor precision, AI interpretability, data privacy, and legal liability.
• Future directions involve cognitive digital twins, autonomous driving integration, advanced biomedical sensors, and smart city medical ecosystems.