Vision Health Monitoring System for Pilots

Maintaining optimal vision health among pilots during high-altitude flights is paramount for aviation safety. Vision disturbances, often attributed to retinal refraction deviations and fluctuating blood glucose levels, can compromise a pilot's ability to operate an aircraft safely. Diabetic Retinopathy (DR), a serious eye condition, poses a particular concern as it can lead to irreversible vision impairment if not promptly diagnosed and treated. In this study, we introduce an innovative solution tailored to aviation professionals. Leveraging IoT integration and deep learning methodologies, we present a hybrid approach designed for precise and real-time identification of diabetic retinopathy among pilots. Our methodology harnesses the power of deep Convolutional Neural Networks (CNNs) for feature extraction from fundus images, further enhancing accuracy through optimization with the Grey Wolf Optimizer (GWO) algorithm. Additionally, we incorporate Internet of Things (IoT) devices for continuous monitoring and immediate diabetic retinopathy identification. Experimental evaluation using publicly available datasets demonstrates the effectiveness of our approach, achieving an exceptional accuracy rate of 98.6%. Our research addresses a critical need within the aviation industry by providing a robust mechanism for accurate and instantaneous detection of diabetic retinopathy in pilots. This advancement is poised to significantly enhance aviation safety and the well-being of aviation professionals operating at high altitudes.