⚡ electrical engineering

ALERT: Adaptive Lane Emergency Routing andTraffic Signal Optimization – A Pilot Implementationof a Smart Green Corridor System in SignalizedUrban Intersections

This paper proposes and simulates an automated, scalable "Green Corridor" system that utilizes geotags, GPS, and camera-based detection to preemptively optimize traffic signals for emergency vehicles without requiring hardware installation, achieving a 65% reduction in response times and enhancing hospital preparedness through real-time alerts.

Original authors: Jerline Sheebha Anni Dhanaraj, Chin-Shiuh Shieh, Mong-Fong Horng, prabu Mohandas

Published 2026-06-29

📖 4 min read☕ Coffee break read

CC BY 4.0

Original authors: Jerline Sheebha Anni Dhanaraj, Chin-Shiuh Shieh, Mong-Fong Horng, prabu Mohandas

Original paper licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). ✨ This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer

Imagine a city as a giant, busy kitchen during the dinner rush. The roads are crowded with cars, buses, and scooters all trying to get to their destinations. Now, imagine an ambulance is like a chef who needs to rush a critical order (a patient) to the hospital, but the kitchen is a total mess. Usually, the chef has to wait for the traffic police (the human managers) to shout at everyone to move, or for a traffic light operator to manually flip a switch. This takes time, and in a medical emergency, time is the most precious ingredient.

This paper introduces ALERT, a new "Smart Green Corridor" system designed to clear a path for emergency vehicles automatically, without needing a human to press a button. Think of it as a magical "VIP lane" that appears instantly whenever an ambulance needs it.

Here is how the system works, broken down into simple steps:

1. The "Early Warning" System (Geotagging)

Instead of waiting until the ambulance is right at the traffic light to change it, the system acts like a 200-meter head-start.

How it works: Imagine invisible "flags" (geotags) placed 200 meters before every intersection. As soon as the ambulance crosses the first flag, the system knows, "Oh, an ambulance is coming!"
The Benefit: This gives the traffic lights enough time to prepare and turn green before the ambulance even arrives, so the chef doesn't have to stop at the door.

2. The "Double-Check" Security (Cameras + GPS)

Sometimes, GPS can get confused, or a big truck might block the signal. To make sure the system doesn't get tricked by a fake ambulance or a broken signal, it uses a two-step verification process.

The Analogy: It's like a bouncer at a club who checks your ID (GPS) and looks at your face (Camera).
The Tech: The system uses a super-smart camera AI (called YOLOv11) that can "see" the ambulance even in bad weather, heavy traffic, or at night. If the GPS says "ambulance coming" and the camera sees "ambulance coming," the system is 100% sure and turns the light green. If only one says yes, it waits to be sure.

3. The "Traffic Conductor" (Adaptive Signals)

Once the system is sure an ambulance is coming, it acts like a conductor directing an orchestra.

Dynamic Adjustments: It doesn't just turn one light green; it calculates the whole path. If the ambulance gets stuck in a jam or has to take a detour because of a roadblock, the system instantly recalculates the route and turns the lights green along the new path.
Patient Priority: The system also knows how sick the patient is. If the patient is in critical condition (like a heart attack), the system treats the ambulance as the "VIP of VIPs," clearing the path even faster.

4. The "Hospital Headset" (Real-Time Alerts)

While the ambulance is racing through the city, the system is also talking to the hospital.

The Analogy: It's like a runner texting the finish line, "I'm 5 minutes away, and I'm carrying a heavy box."
The Result: The hospital team gets a notification with the patient's condition and the exact time of arrival. They can prepare the operating room or the trauma team before the ambulance even pulls up, saving crucial minutes.

5. What Happens if the System Breaks? (Fail-Safe)

The authors know technology can fail, so they built a backup plan.

The Backup: If the main computer crashes or the internet goes down, a smaller, simpler backup board (called a Vega board) takes over. It switches the traffic lights to a simple, pre-set pattern (like a standard timer) so traffic doesn't freeze completely. It's like having a manual crank on an elevator if the power goes out.

The Results: A Faster Kitchen

The researchers tested this system using a computer simulation (a digital twin of a real city intersection in Kozhikode, India).

Before the system: Ambulances were stuck in traffic, waiting an average of 10 minutes at junctions.
After the system: The average wait time dropped to 5.5 minutes.
The Bottom Line: This represents a 45% to 65% reduction in response time. In the real world, this means the "Golden Hour" (the critical first hour after an injury) is used more effectively, giving patients a much better chance of survival.

In summary: ALERT is a smart, automated traffic manager that uses "invisible flags" and "smart eyes" to clear a green path for ambulances, ensuring they reach the hospital faster while keeping the rest of the city moving smoothly. It removes the guesswork and human delay from saving lives.

Technical Summary: ALERT – Adaptive Lane Emergency Routing and Traffic Signal Optimization

Problem Statement

Urban traffic congestion significantly impedes the response times of emergency services, particularly ambulances. In critical medical scenarios, such as heart attacks or major accidents, delays of even a few minutes can drastically reduce patient survival rates (the "Platinum ten minutes" and "Golden hour"). Existing traffic management systems in India and similar developing nations face several limitations:

Manual Dependency: Current "Green Corridor" implementations rely heavily on human intervention by traffic police or control room operators to manually adjust signals. This process is prone to human error, lacks scalability during simultaneous emergencies, and is slow to react to dynamic traffic conditions.
Technological Limitations: Existing automated solutions often rely on single technologies like RFID or V2X. RFID systems can fail due to signal interference or infrastructure gaps, while V2X requires widespread vehicle adoption which is currently infeasible in many regions. Furthermore, fixed-time traffic signals cannot adapt to fluctuating traffic densities or unexpected roadblocks.
Rigidity: Pre-planned routes restrict flexibility; if an ambulance encounters a roadblock, the system often fails to dynamically recalculate the path and adjust signals accordingly.

Methodology

The paper proposes ALERT (Adaptive Lane Emergency Routing and Traffic Signal Optimization), an integrated, automated Green Corridor system designed for signalized urban intersections. The system operates without human intervention and is designed to be hardware-light for the ambulance itself (requiring no special onboard hardware beyond standard GPS).

Core Components

Multi-Layer Verification System:
- Geotagging: Critical zones are defined 200 meters upstream of intersections. When an ambulance enters this zone, the system triggers a pre-alert.
- Dual Verification: To ensure accuracy and prevent false positives, the system combines GPS geotagging with YOLOv11 (You Only Look Once) computer vision. Cameras at intersections visually verify the presence of the ambulance and its direction, even in adverse weather or heavy congestion.
Adaptive Signal Control:
- Real-Time Optimization: The system utilizes Binary Particle Swarm Optimization (BPSO) and Multi-Level Priority Dynamic Scheduling (MLPDS). BPSO calculates optimal green light configurations, while MLPDS prioritizes routes based on vehicle type, traffic density, and patient severity.
- Dynamic Timing: Using Webster's formula, the system calculates optimal cycle lengths. If an ambulance is delayed by traffic density, the green light duration is extended by 20 seconds. If the ambulance clears the junction within 25 seconds, signals revert to normal; otherwise, the system extends the green phase based on real-time GPS tracking.
Communication and Notification:
- LoRaWAN: A Long-Range Wide Area Network protocol facilitates communication between the mobile application, central server, and traffic controllers, ensuring low latency (10–50 ms) and high reliability (99.8%).
- Stakeholder Alerts: Real-time notifications regarding patient severity levels and Estimated Time of Arrival (ETA) are sent simultaneously to traffic controllers, police booths, and the destination hospital to facilitate preparation.
Route Recalculation:
- The system dynamically recalculates routes in response to diversions or roadblocks. It updates geotagged zones along the new path to ensure continuous signal prioritization.
- ETA Calculation: The system adjusts the ETA based on a congestion factor ( $X$ ) derived from real-time traffic density, modifying the effective speed of the ambulance for accurate arrival predictions.

Failure Handling

The system includes a robust fail-safe mechanism. In the event of a controller or server failure, a Vega board acts as a backup, reverting to predefined static signal timings to prevent gridlock. It utilizes locally cached geotagging data (updated every 2 seconds) to continue prioritizing emergency vehicles within a 200-meter radius even if the central server is unreachable.

Key Contributions

Hybrid Intelligent System: Integration of BPSO and MLPDS to identify ambulances 200 meters in advance and control signals in real-time based on congestion and patient severity, eliminating human intervention.
Dual Verification Mechanism: A novel combination of geotagging and YOLOv11 camera detection to accurately identify ambulances under challenging conditions (e.g., fog, heavy traffic) and adapt routes dynamically.
Real-Time Stakeholder Coordination: Automated notifications providing patient severity levels and ETA to hospitals and traffic stations, enhancing preparedness and reducing delays.
Scalability and Hardware Independence: The system supports all classes of emergency vehicles without requiring hardware installations on the vehicles themselves, making it scalable for diverse urban environments.

Results and Performance

The system was evaluated using the SUMO (Simulation of Urban Mobility) framework, simulating the Kalluthankadavu junction network in Kozhikode, India. The dataset included 40,000 images of various traffic conditions (fog, peak hours, night) annotated for 10 vehicle classes.

Response Time Reduction: The simulation demonstrated a 65% reduction in response time for emergency vehicles.
- Specific Data Point: Before implementation, the mean delay per ambulance was 10 minutes (totaling 700 minutes for 70 ambulances). After implementation, the mean delay dropped to 5.5 minutes (totaling 315 minutes), representing a 45% decrease in total delay time for the specific test case.
Traffic Flow: The system significantly reduced signal wait times and ambulance travel times while maintaining minimal disruption to non-emergency traffic flow.
Reliability: The dual verification system ensured zero false positives in vehicle identification, and the LoRaWAN communication protocol maintained 99.8% transmission reliability.
Comparative Analysis: The paper notes that while manual systems offered a 12.5% improvement and RFID-based systems offered 23.5%, the proposed integrated approach achieved the highest reduction (65%) compared to existing technologies.

Significance and Claims

The paper claims that ALERT represents a significant advancement in emergency traffic management by solving the issues of scalability, human error, and rigidity inherent in current Green Corridor implementations. By leveraging existing infrastructure (cameras, GPS) and advanced AI (YOLOv11, BPSO), the system provides a reliable, automated solution that can be deployed in complex, mixed-traffic urban environments like those in India.

The authors emphasize that the system is not limited to organ transplant scenarios but is designed to support all emergency services. The integration of real-time patient severity data allows for a tiered response, ensuring that the most critical cases receive the highest priority. While the paper acknowledges challenges such as high vehicle density and transmission delays, it posits that the proposed adaptive framework offers a robust foundation for improving public safety and emergency response efficiency in congested urban areas.