An Integrated Smart Traffic and Emergency Communication System for Ambulance and Hospitals Using Deep Learning and IoT
Nikith J*1, Parkavi A2, Pushpalatha M N3
1Nikith J, Department of Computer Science and Engineering, M S Ramaiah Institute of Technology, Bangalore (Karnataka), India.
2Dr. Parkavi A, Department of Computer Science and Engineering, M S Ramaiah Institute of Technology, Bangalore (Karnataka), India.
3Dr. Pushpalatha M. N, Department of Information Science and Engineering, M S Ramaiah Institute of Technology, Bangalore (Karnataka), India.
Manuscript received on 24 April 2026 | First Revised Manuscript received on 06 May 2026 | Second Revised Manuscript received on 09 July 2026 | Manuscript Accepted on 15 August 2026 | Manuscript published on 30 August 2026 | PP: 7-12 | Volume-13 Issue-8, August 2026 | Retrieval Number: 100.1/ijies.E114913050526 | DOI: 10.35940/ijies.E1149.13050526
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: If ambulances are delayed at urban traffic junctions, patient survival chances during medical emergencies can drop. Previous systems used single-modality vehicular detection for both ambulances and traffic police. Communication was similarly limited to a single channel among the various actors, namely, traffic police, ambulance crew, and hospital. This led to missed detections, poor coordination, avoidable delays, and so on. This project aims to design an intelligent system that authenticates ambulances in real time and controls traffic signals via IoT-based technology. It will also provide a platform for simultaneous communication between police, hospitals, and other concerned parties. By fusing a visual detection model with an audio-based siren classifier, the system uses a confidence-based adaptive decision mechanism for reliable detection in challenging scenarios involving occlusion, low light, and high ambient noise. When detection is confirmed, an IoT edge device triggers real-time traffic signal preemption to create a green corridor. This will work without any changes to ambulance hardware. Moreover, a cross-platform mobile application can help ambulance staff and police communicate with hospital staff. It allows manual SOS signals, signal override, patient information sharing, and telemedicine. The system includes an in-ambulance patient monitoring module that detects critical clinical conditions and sends real-time alerts to the hospital before arrival. Based on experimental results, the system achieved 98.4% video accuracy and 97.9% audio accuracy with low latency. The proposed framework improved the efficiency and coordination of emergency response and pre-arrival patient care in urban environments.
Keywords: Ambulance Detection, Deep Learning, Emergency Communication, IoT, Signal Preemption, YOLOv11, CNN, Multimodal Fusion.
Scope of the Article: Computer Science and Engineering