Year: 2025
Type: article
Abstract: Timely and informed response in emergency medical services (EMS) can significantly increase survival rates. Conventional ambulance services encounter delays in recognizing patients, accessing medical records, and coordinating communication between on-site teams and medical facilities. This study introduces an AI-driven ambulance system that incorporates real-time facial recognition, GPS tracking, and retrieval of patient information through biometric authentication. A compact machine learning model (MobileFaceNet) is implemented on Android using TensorFlow Lite, allowing for instantaneous facial recognition. The mobile application captures the patient's identity, connects with a backend to retrieve medical history, and synchronizes GPS information for adaptive routing and notifications to hospitals. The findings show a decrease in the time taken for patient identification, enhanced readiness of hospitals, and improved responsiveness in emergencies.
Institution: Ajeenkya DY Patil University
Language: English
Subfield: Mechanical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410240499