International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 13 Issue:05 | May 2026
p-ISSN: 2395-0072
www.irjet.net
RescueTrack: An AI-Driven Real-Time Emergency Dispatch and Tracking System with Multimodal AI Assistance Yadav Tarun Kanhai1, Roshan Yadav2, Raj Kumar3, Mrs. Priya Tyagi4 (Assistant Professor, Department CSE) Department of Computer Science and Engineering, NITRA Technical Campus, Ghaziabad – 201002, Uttar Pradesh, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Imagine you witness a family member collapse at home from a suspected cardiac arrest. You call for an ambulance,
but you have no idea where it is, how long it will take, or what you should do in the meantime. That uncertainty those minutes of helplessness is precisely what Rescue Track was engineered to eliminate. This paper presents Rescue Track, a real-time emergency dispatch and tracking system that seamlessly connects patients, ambulance drivers, and hospital emergency departments through a shared, continuously updated operational picture. The system combines Firebase Realtime Database for low-latency data synchronization, GPS-based live tracking for all parties, and the Google Gemini Live AI API to provide voice-based first-aid guidance and emotionally calibrated support to patients while they await help. We evaluated the system across 250 simulated emergency sessions and a formal usability study with 45 participants drawn from all three stakeholder groups. End-to-end SOS notification latency averaged 1.82 seconds, GPS synchronization latency remained below 200ms at the median, and the AI assistant responded within 1.5 seconds of any patient query. Participants rated the system 84.3 out of 100 on the System Usability Scale, placing it firmly in the "Excellent" category. More meaningfully, 87% of patient participants described the AI assistant as reassuring, and 73% reported lower anxiety compared with a no-assistance control condition. These findings collectively demonstrate that the technology needed to make every emergency faster, better coordinated, and less frightening is not a future aspiration — it is deployable today. Key Words: Emergency Medical Services, Real-Time Tracking, Artificial Intelligence, Firebase, GPS, Large Language Models, Pre-Hospital Care, mHealth, Cloud Computing, Gemini API
1. INTRODUCTION Every year, cardiovascular disease claims approximately 17.9 million lives worldwide [1]. A significant portion of those deaths are not inevitable they occur because help arrived too slowly, or because the person waiting for it had no idea what to do in those critical minutes. The medical concept of the "golden hour" captures this reality with uncomfortable precision: in a cardiac arrest, every minute without intervention reduces survival probability by 7 to 10 percent [2]. When the average ambulance response time in urban India stretches to 14–18 minutes [3], the arithmetic becomes deeply troubling. It is worth pausing on what actually happens during those minutes. A person has called for help. A dispatcher has logged the call. An ambulance is theoretically on its way. But the patient's family has no visibility into any of this they cannot see the ambulance on a map, they do not know if it has even been dispatched, and they certainly receive no guidance on what to do while they wait. The sheer psychological weight of that helplessness compounds the physiological danger. Meanwhile, the receiving hospital has no advance warning about the patient en route, and the driver is navigating with minimal information. Each of these gaps, individually manageable, collectively produces a system that is slower, more stressful, and more fatal than it needs to be. None of the technologies required to close these gaps are new or exotic. Real-time GPS tracking, cloud-synchronized databases, push notifications, and conversational AI are all mature, widely available, and inexpensive to deploy at scale. What has been missing is their purposeful integration into a coherent, emergency-specific coordination platform designed around the actual workflows of patients, paramedics, and hospital staff. That is precisely what RescueTrack attempts to do not by inventing new technology, but by connecting existing technology in ways that serve human lives.
1.1 The Emergency Response Gap Before building anything, the development team spent considerable time understanding the real-world context. The research began with nine in-depth interviews with EMS practitioner’s paramedics, dispatchers, and emergency nurses across two hospitals in Bangalore. The team also observed four live emergency response episodes with full consent and analyzed incident reports covering 847 emergency calls from a regional ambulance service over a three-month period. Five non-negotiable design constraints emerged from that fieldwork: (1) End-to-end SOS latency from button press to hospital notification must be under three seconds on a normal mobile connection. (2) GPS updates must arrive at minimum every two seconds to support accurate ETA calculation. (3) The AI assistant must respond within two seconds of a voice or text query.
© 2026, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 107