IoT Meets Accessibility: A Machine Learning Based Solution for the Visually Impaired

Visually impaired people confront tremendous obstacles in navigating their surroundings safely and freely, underscoring the importance of improved assistive devices. This study describes an IoT-enabled device intended to improve obstacle identification, environmental awareness, and caregiver connectivity. The system combines ultrasonic, infrared, and water level sensors with a microcontroller kit and ESP8266 module to provide exact real-time hazard detection. Sensor data is sent to the Blynk IoT platform. This allows important updates about the user's environment to be sent to caregivers. The proposed solution will deliver a secured, affordable, reliable, and easy-to-use assistive technology for supporting visually impaired individuals to become more independent contributing to the emerging field of machine learning-based IoT assistive devices. The data used in the system is secured by using machine learning algorithms. The results show that the proposed model has achieved approximately 95% accuracy with a 5% error rate, making it robust and reliable.