[Paper Review] Real-time accident detection and physiological signal monitoring to enhance motorbike safety and emergency response

Syed Md. Siam, Khadiza Islam Sumaiya+5 more|arXiv (Cornell University)|Mar 28, 2024

IoT and GPS-based Vehicle Safety Systems4 citations

TL;DR

This paper proposes an IoT-based smart helmet system integrating accelerometer, GPS, GSM, and physiological sensors (pulse rate and SpO2) for real-time motorbike accident detection and emergency response. The system detects collisions via accelerometer thresholds, transmits GPS location and vital signs to emergency contacts via SMS, and achieved 100% accident detection accuracy in testing with real-time alerts within 5 seconds.

ABSTRACT

Rapid urbanization and improved living standards have led to a substantial increase in the number of vehicles on the road, consequently resulting in a rise in the frequency of accidents. Among these accidents, motorbike accidents pose a particularly high risk, often resulting in serious injuries or deaths. A significant number of these fatalities occur due to delayed or inadequate medical attention. To this end, we propose a novel automatic detection and notification system specifically designed for motorbike accidents. The proposed system comprises two key components: a detection system and a physiological signal monitoring system. The detection system is integrated into the helmet and consists of a microcontroller, accelerometer, GPS, GSM, and Wi-Fi modules. The physio-monitoring system incorporates a sensor for monitoring pulse rate and SpO$_{2}$ saturation. All collected data are presented on an LCD display and wirelessly transmitted to the detection system through the microcontroller of the physiological signal monitoring system. If the accelerometer readings consistently deviate from the specified threshold decided through extensive experimentation, the system identifies the event as an accident and transmits the victim's information -- including the GPS location, pulse rate, and SpO$_{2}$ saturation rate -- to the designated emergency contacts. Preliminary results demonstrate the efficacy of the proposed system in accurately detecting motorbike accidents and promptly alerting emergency contacts. We firmly believe that the proposed system has the potential to significantly mitigate the risks associated with motorbike accidents and save lives.

Motivation & Objective

• Address the high fatality rate in motorbike accidents due to delayed emergency response.
• Develop a low-cost, real-time system to detect accidents and notify emergency contacts automatically.
• Integrate physiological monitoring (pulse rate, SpO2) with accident detection for comprehensive rider safety.
• Improve emergency response by providing real-time location and health data to responders.
• Create an affordable, scalable solution suitable for high-density urban areas like Bangladesh.

Proposed method

• Deploy an ESP-8266 microcontroller with ADXL345 accelerometer, Ublox Neo-6M GPS, and SIM800L GSM module in a helmet for real-time accident detection.
• Use accelerometer data to detect abnormal motion patterns (e.g., sudden deceleration, high G-force) exceeding predefined thresholds.
• Implement a Wi-Fi-connected D1 Mini Pro microcontroller to collect and transmit pulse rate and SpO2 data from a MAX30100 sensor.
• Store and display physiological and location data on an LCD screen and wirelessly relay to the detection system.
• Trigger SMS alerts to emergency contacts when sustained accelerometer deviations exceed thresholds for 5 seconds.
• Embed GPS coordinates in a Google Maps link within the alert to enable real-time location tracking.

Experimental results

Research questions

• RQ1 Can real-time accelerometer-based detection reliably identify motorbike accidents with minimal false positives?
• RQ2 How effectively can integrated physiological monitoring (pulse rate and SpO2) enhance post-accident emergency response?
• RQ3 To what extent does the system reduce emergency response time compared to conventional methods?
• RQ4 What is the cost-effectiveness and scalability of the proposed system in low-resource urban environments?
• RQ5 How accurate is the real-time GPS tracking and data transmission in dynamic riding conditions?

Key findings

• The system successfully detected a simulated accident when accelerometer values on the Y-axis remained below -200 for 5 consecutive seconds, triggering an alert.
• An SMS alert was sent to emergency contacts exactly 5 seconds after the threshold was met, confirming real-time notification capability.
• Pulse rate and SpO2 data were continuously monitored and transmitted alongside the accident alert, enabling medical personnel to assess the rider’s condition.
• The system provided real-time GPS coordinates with a Google Maps link, allowing precise location tracking of the injured rider.
• The total cost of the prototype was $31.02 USD (BDT 3130), demonstrating high economic viability for large-scale deployment.
• The system achieved 100% accuracy in detecting the test accident event, with no false positives or missed detections in the evaluation.