AcciAid: IoT-Driven Real-Time Accident Detection and Emergency

Alert System

Balaji Morasa

, Pavan Kumar Naik M

, Hemalatha K

, Murali Naik K

, Santhosh Kumar M

and Yasmin Begum A

Department of ECE, Mohan Babu University, Tirupati, Andhra Pradesh, India

Department of ECE, Sree Vidyanikethan Engineering College, Tirupati, Andhra Pradesh, India

Keywords: Safety, Alert, Accident, Nodemcu, GSM.

Abstract: The "AcciAid: IoT-Driven Real-Time Accident Detection and Emergency Alert System"offers a life-saving

solution for real-time accident detection and quick communication with emergency services. The system

integrates various sensors, including MEMS, force, and vibration sensors, with an Arduino microcontroller

to detect accidents. The GPS module tracks the exact location (longitude and latitude), while the GSM

module sends SMS alerts to emergency contacts and hospitals. The data is uploaded to ThingSpeak web

server, which is then accessed by an Android application to fetch real-time data. This enables automatic

notifications and emergency calls, ensuring timely intervention. The system is designed with IoT

connectivity, using a NodeMCU Wi-Fi module for efficient data transmission, providing an integrated,

reliable, and cost-effective solution for accident detection and immediate response in emergencies.

1 INTRODUCTION

In modern transportation systems, real-time accident

detection and monitoring play a crucial role in

enhancing road safety and reducing response times

for emergency services. This system utilizes a MEMS

accelerometer to detect sudden impacts or collisions,

triggering an immediate alert. Integrated with GPS

tracking, it ensures precise location identification,

enabling rapid assistance in the event of an accident.

The wireless communication module transmits

critical data, including impact intensity and location,

to relevant authorities or emergency contacts. By

providing real-time accident monitoring and data

logging, this approach enhances post-accident

analysis, improves emergency response efficiency,

and contributes to overall road safety (

Gunadal A et al.,

2015)

Enhancing road safety through proactive accident

prevention is a critical advancement in modern

transportation. This system integrates IoT technology

with machine learning to analyze real-time data from

various sensors, identifying potential hazards before

they lead to accidents. By continuously monitoring

parameters such as vehicle speed, environmental

conditions, and driver behavior, the system predicts

risks and provides timely alerts to prevent collisions.

With intelligent data processing and adaptive

learning, it improves decision-making for both

drivers and automated safety mechanisms. This

approach not only minimizes accidents but also

contributes to a more efficient and secure

transportation ecosystem (

Alnashwan Raghad A., et al.,

2023)

Road safety and accident response are critical

concerns in modern transportation. This system

utilizes advanced sensors to continuously monitor

vehicle parameters, detecting sudden impacts or

collisions in real time. By integrating GPS tracking, it

ensures accurate location reporting, enabling swift

emergency response. The collected data, including

speed, impact force, and environmental conditions, is

stored for post-accident analysis, helping authorities

and insurance agencies determine the cause of

incidents. With its ability to provide real-time alerts

and comprehensive accident documentation, this

technology enhances road safety, improves

emergency response times, and supports effective

incident investigation (

Josephinshermila P., Priya S.

Sharon, et al., 2023)

570

Morasa, B., M., P. K. N., Hemalatha, K., K., M. N., M., S. K. and A., Y. B.

AcciAid: IoTâ

SDriven Realâ

STime Accident Detection and Emergency Alert System.

DOI: 10.5220/0013886600004919

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies (ICRDICCT‘25 2025) - Volume 2, pages

570-578

ISBN: 978-989-758-777-1

Efficient vehicle monitoring is essential for

enhancing security and operational management.

This system integrates GPS, GSM, and Arduino

technology to provide real-time tracking and

communication. The GPS module accurately

determines the vehicle’s location, while the GSM

module enables wireless data transmission to

designated recipients. Arduino serves as the central

controller, processing location data and transmitting

alerts in case of unauthorized movement or

emergencies. This approach ensures continuous

monitoring, enhances security measures, and enables

prompt responses through remote tracking and

communication capabilities (

Mahmood Firas M. Z et al.,

2022)

Ensuring rapid emergency response is critical in

modern transportation. This system leverages IoT

technology to detect accidents in real time and

securely transmit essential driver information.

Equipped with smart sensors, it identifies collisions

and collects vital data, including impact force and

location. The integrated communication module

ensures that emergency contacts and relevant

authorities receive immediate alerts, enabling swift

assistance. By prioritizing data security and

reliability, this approach enhances accident detection,

improves response efficiency, and contributes to safer

transportation through real-time monitoring and

automated reporting (

Alkhaiwani A. Hussain., 2023)

2 LITERATURE SURVEY

In today's fast-paced world, road safety remains a

major concern due to increasing traffic incidents

caused by human error and negligence. This paper

introduces an IoT-based system designed for real-

time vehicle tracking, accident detection, and

prevention. By utilizing GPS, accelerometers, and

various IoT sensors, the system continuously

monitors vehicle movement and driving patterns to

detect potential hazards. If an abnormal event such as

a sudden impact or erratic driving behavior is

identified, the system processes the data and

determines the likelihood of an accident. Once an

accident is detected, the IoT framework enables

instant communication with emergency services by

transmitting the precise location coordinates via a

GSM module. Additionally, the system can send

automated alerts to nearby vehicles and traffic

management centers, allowing for swift intervention

and traffic regulation. By integrating cloud-based

storage, accident data is logged and analyzed to

improve predictive analytics, helping authorities

identify high-risk areas and implement preventive

measures. This intelligent system not only enhances

road safety but also contributes to smart city

initiatives by reducing emergency response time and

minimizing accident-related congestion. The

automation of accident detection and reporting

eliminates the reliance on bystanders, ensuring that

critical incidents are addressed without delays.

Through continuous monitoring and real-time data

transmission, this IoT-powered solution offers a

proactive approach to accident prevention and

enhances overall vehicular safety (

K. Poorani et al.,

2017)

Ensuring road safety and minimizing accident

response time are crucial in modern transportation

systems. This paper introduces an IoT-based

approach for detecting, reporting, and navigating

vehicle collisions in real time. The system integrates

various sensors, including accelerometers and GPS,

to continuously monitor vehicle dynamics and

identify sudden impacts. Upon detecting a collision,

the system processes sensor data and determines the

severity of the accident using predefined algorithms.

This minimizes false alarms while ensuring accurate

detection of critical incidents. Once an accident is

confirmed, the system automatically transmits alert

messages to emergency responders and nearby

vehicles. The notification includes real-time location

details, allowing rescue teams to navigate efficiently

to the accident site. Additionally, the system

leverages IoT connectivity to communicate with

traffic management centers, helping to reduce

congestion by rerouting vehicles away from affected

areas. By ensuring rapid and precise accident

reporting, this approach enhances emergency

response efficiency. Furthermore, the system utilizes

cloud-based data storage and analysis to identify

accident-prone zones and improve road safety

strategies. Historical data can be analyzed to predict

high-risk areas and develop preventive measures. By

integrating IoT with intelligent navigation and

accident reporting, this solution contributes to

building a smarter and safer transportation ecosystem

(

Nasr E et al., 2016)

In modern smart cities IoT and deep learning-

powered AI system designed for real-time accident

detection and automated alert generation. The system

integrates multiple sensors, including accelerometers,

GPS, and cameras, to monitor vehicular movements

and detect collisions. Upon detecting an anomaly, the

system processes data using deep learning algorithms

to confirm an accident, minimizing false alerts. The

IoT framework enables seamless data transmission,

ensuring that emergency responders receive instant

AcciAid: IoTâ

SDriven Realâ

STime Accident Detection and Emergency Alert System

571

notifications with precise accident location details,

improving response efficiency. By leveraging AI and

deep learning, the proposed system can analyze

accident patterns, predict high-risk zones, and

enhance overall urban traffic safety. The integration

of cloud computing and IoT networks facilitates real-

time data sharing across smart city infrastructures,

aiding traffic management systems in reducing

congestion caused by accidents. The automated alert

system reduces human intervention, ensuring swift

medical assistance and potentially saving lives. This

research demonstrates how AI-driven IoT solutions

can revolutionize accident detection and emergency

response in smart city environments (

Pathik Nikhlesh

Y., Gupta Rajeev K., et al., 2022)

IoT-based accident detection and alert system

designed to improve response times and enhance road

safety. The system utilizes sensors such as

accelerometers and GPS modules to monitor vehicle

movement and detect sudden impacts. Upon detecting

an accident, the system automatically sends real-time

alerts, including the precise location coordinates, to

emergency responders and predefined contacts

through a GSM module. This rapid notification

system ensures timely medical assistance, potentially

reducing casualties. The system's ability to operate

without human intervention enhances efficiency,

particularly in remote or low-surveillance areas.

Additionally, the collected data can be analyzed to

identify accident-prone zones, helping authorities

implement preventive measures. This research

highlights the potential of IoT solutions in creating

safer road networks and improving emergency

response mechanisms (

B. M. Nandish, R. J. Ekanth

Babu, S. S. Ganeshanaik, et al., 2022) With a focus on

cutting-edge developments, the journal publishes

high-quality research articles, reviews, and case

studies that address challenges in modern intelligent

systems. Topics such as smart healthcare,

environmental monitoring, autonomous systems, and

industrial automation are explored through novel

sensor networks and AI-driven solutions. The journal

aims to contribute to technological advancements by

bridging the gap between theoretical research and

practical implementations, making it a valuable

resource for academics and practitioners alike (

Ezil S.

L. and Dhanlakshmi., 2017)

IoT-enabled system for real-time vehicle crash

detection and automated alert generation. The system

integrates sensors such as accelerometers and GPS to

monitor vehicle motion and identify sudden impacts.

Upon detecting a crash, the system processes the data

and immediately sends an alert message containing

the accident's exact location to emergency responders

and relevant authorities. By leveraging IoT

connectivity, the system ensures seamless

communication, reducing response time and

increasing the chances of saving lives. Additionally,

the proposed mechanism enhances road safety by

minimizing human intervention in accident reporting.

The system's real-time monitoring and automated

notifications enable faster decision-making and

improve emergency response efficiency. Integration

with cloud-based platforms allows for data storage

and analysis, helping to identify accident-prone areas

and develop preventive measures. This IoT-driven

solution contributes to smarter and safer

transportation networks by providing a reliable,

efficient, and scalable approach to accident detection

and response (

Sharma S., 2019) An automated accident

detection and alert system that leverages IoT and

sensor-based technology to improve accident

response time. The system integrates an

accelerometer, GPS, and GSM module to detect

sudden vehicle impacts and immediately transmit

accident location details to emergency contacts. By

utilizing real-time data processing, the system

minimizes response delays, ensuring timely medical

assistance and potentially saving lives. The proposed

solution is designed to operate efficiently in various

environments, providing accurate accident detection

while reducing false alarms. When a collision occurs,

the system automatically sends an alert message

containing the GPS coordinates of the accident site,

allowing emergency services to respond quickly. This

approach enhances road safety by streamlining

communication between vehicles and rescue teams,

making it a valuable addition to intelligent

transportation systems (

C.k.Gomathy et al., 2022)

Road accidents remain a significant global

concern, often resulting in severe injuries or fatalities

due to delayed emergency response. This paper

presents a crash identification and alert system that

leverages GSM, GPS, and GPRS technologies to

ensure timely accident detection and notification. The

system integrates an accelerometer to detect sudden

vehicle impacts and immediately triggers an alert

mechanism. Upon detecting a crash, the GPS module

captures the exact location coordinates, while the

GSM module sends automated alerts to predefined

emergency contacts, including medical services and

authorities. By utilizing GPRS, the system enables

real-time data transmission, allowing continuous

monitoring and instant updates on accident scenarios.

This technology ensures that emergency responders

receive accurate crash location details, improving

response efficiency. Additionally, the system

minimizes false alerts through sensor calibration and

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

572

threshold-based accident detection, enhancing

itsreliability in real-world conditions. The integration

of multiple communication technologies ensures

seamless connectivity, even in remote areas, where

immediate assistance is often critical.

This research highlights the importance of intelligent

crash detection systems in reducing accident-related

fatalities. By providing an automated and efficient

alert mechanism, the proposed system enhances road

safety and emergency response effectiveness. The

combination of GSM, GPS, and GPRS enables a cost-

effective and scalable solution that can be

implemented across various transportation

infrastructures, contributing to smarter and safer road

networks (

Jalil J et al.,)

3 EXISTING METHOD

Traditional accident detection and emergency

response systems primarily rely on manual reporting

methods, which can be slow and inefficient. In

conventional systems, accidents are usually reported

by eyewitnesses or by the driver themselves, which

may not be possible if the driver is unconscious or in

critical condition. Some vehicles are equipped with

basic airbag deployment sensors that trigger alerts,

but these systems lack precise accident detection

capabilities and do not provide real-time location

tracking. Additionally, older emergency response

methods depend on centralized call centers, which

may delay the dispatch of medical assistance due to

miscommunication or a lack of accurate location

details. The absence of automation in these methods

results in longer response times, reducing the chances

of timely medical intervention. Another common

limitation of existing systems is the lack of

integration with IoT and mobile applications. Many

traditional systems do not store accident data for

future analysis, making it difficult to improve road

safety measures. Additionally, emergency contacts

are not always automatically notified, requiring

manual calls that may be delayed or missed. Without

real-time GPS tracking and automated messaging,

responders struggle to locate accident sites quickly,

especially in remote areas. Furthermore, most

conventional methods do not offer features like live

monitoring or cloud-based data storage, limiting

accessibility and real-time decision-making. These

drawbacks highlight the need for a more advanced,

IoT-enabled accident detection system that integrates

GPS, GSM, and an Android application to ensure

immediate and effective emergency response.

4 PROPOSED METHOD

The proposed system integrates IoT and mobile

technology to enable real-time accident detection and

emergency response. It consists of various hardware

components, an Android application, and a cloud-

based data management system to ensure seamless

communication and rapid assistance in critical

situations.

4.1 Hardware Implementation

4.1.1 Sensor Integration

● MEMS Sensor: Detects sudden vehicle tilts

and impacts.

● Vibration Sensor: Identifies abnormal

vibrations caused by collisions.

● Force Sensor: Measures force impact to

assess accident severity.

● GPS Module: Provides real-time location

coordinates (latitude & longitude).

● GSM Module: Sends SMS alerts to

emergency contacts.

4.1.2 Microcontroller & Communication

● Arduino Microcontroller: Processes sensor

data and detects accidents.

● NodeMCU (Wi-Fi Module): Transmits

collected sensor data to the ThingSpeak cloud.

4.1.3 Alert Mechanism

● Buzzer: Generates an alert sound upon

accident detection.

● LED Indicator: Provides a visual alert signal.

● GSM Notifications: Sends emergency

messages with location details.

4.2 Cloud & Data Management5

4.2.1 Data Transmission to ThingSpeak

● Sensor values are continuously sent to the

ThingSpeak server for real-time monitoring.

● The stored data can be accessed for analysis

and system performance evaluation.

4.2.2 Data Processing & Analysis

● The system analyzes sensor thresholds to

distinguish between normal vibrations and

actual accidents.

AcciAid: IoTâ

SDriven Realâ

STime Accident Detection and Emergency Alert System

573

● If an accident is detected, an automatic alert is

generated.

4.3 Android Application Integration

4.3.1 Real-Time Data Monitoring

● The Android app fetches live sensor data from

the cloud.

● Users can view vehicle status, accident alerts,

and historical data.

4.3.2 Emergency Contact Management

● Users can pre-configure emergency contacts

and favorite numbers in the app.

● Contacts include family, friends, and medical

responders.

4.3.3 Automated Emergency Notification

● When an accident is detected, the app

automatically sends messages with GPS

coordinates to stored contacts.

● Push notifications alert the user about

abnormal conditions.

4.3.4 SOS Feature

● The app includes an SOS button for manual

emergency alerts.

● Voice command integration can trigger

emergency messages.

4.4 System Workflow

• Data Collection: Sensors continuously

monitor vehicle conditions.

• Accident Detection: The microcontroller

analyzes sensor values and determines

accident severity.

• Data Transmission: Sensor readings are

sent to ThingSpeak for cloud storage.

• Android App Alert: The application

retrieves data and informs the user.

• Emergency Notification: If an accident is

detected, the app automatically notifies pre-

stored contacts with location details.

• Assistance Activation: Emergency

responders and nearby contacts receive

alerts and respond accordingly.

This method ensures efficient accident detection,

rapid emergency response, and real-time monitoring,

ultimately enhancing road safety and reducing

fatalities. Figure 1 shows the block diagram

representing embedded design.

5 BLOCK DIAGRAMS

Figure 1: Block Diagram representing embedded

design.

6 METHODOLOGY

6.1 System Overview

The proposed accident detection and emergency alert

system aims to improve road safety by identifying

accidents in real-time and immediately notifying

emergency contacts. It integrates IoT technology,

embedded systems, cloud computing, and an Android

application to ensure effective monitoring and rapid

response.

The system consists of multiple sensors, including

MEMS, vibration, and force sensors, which detect

accidents with high accuracy. An Arduino

microcontroller processes sensor data, while a GPS

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

574

module determines the exact accident location. A

GSM module sends SMS alerts to emergency

contacts and nearby hospitals. The NodeMCU Wi-Fi

module uploads real-time data to the ThingSpeak

cloud, enabling remote monitoring.

An Android application fetches real-time accident

information from ThingSpeak and automatically

sends emergency notifications to pre-configured

contacts. This multi-layered approach ensures rapid

emergency response and increases the chances of

survival for accident victims.

6.2 Working Principle

The system functions in three key stages:

• Data acquisition using sensors and the

microcontroller

• Data processing and communication using

embedded systems and cloud storage

• User interaction through the Android

application and emergency notification

system.

6.2.1 Data Acquisition

Sensors for accident detection: The system uses

multiple sensors to accurately detect accidents:

● MEMS accelerometer sensor detects sudden

motion changes, acceleration, or tilting of the

vehicle, which indicates a possible crash.

● Vibration sensor detects abnormal vibrations

or shocks caused by a collision.

● Force sensor measures impact force to confirm

the severity of an accident.

These sensors are connected to an Arduino

microcontroller, which continuously monitors their

output and applies threshold values to determine if an

accident has occurred.

GPS module for location tracking: Once an

accident is detected, the GPS module retrieves the

vehicle’s precise latitude and longitude. This location

data is then included in the emergency alert message

to enable faster rescue operations.

GSM module for emergency alerts: The GSM

module sends SMS alerts containing accident details,

including the location, to emergency contacts. The

alert is also sent to hospitals and emergency response

teams to facilitate a quick response.

6.2.2 Data Processing and Transmission

Role of the arduino microcontroller

The Arduino microcontroller continuously processes

sensor inputs and determines whether an accident has

occurred based on predefined thresholds. When an

accident is detected, it triggers the GPS and GSM

modules to send emergency alerts.

Nodemcu and thingspeak cloud integration: The

NodeMCU Wi-Fi module transmits all collected

sensor data to the ThingSpeak cloud server. This

ensures real-time data visualization and remote

monitoring of the vehicle’s status.

6.2.3 Android Application Integration

1) How the android application works

• The Android application fetches real-time

sensor values from the ThingSpeak cloud.

• It displays accident information, including

the location and vehicle status.

• In case of an accident, the application

automatically notifies emergency contacts

stored within it.

• The app includes an SOS button that allows

users to manually trigger an emergency

alert.

6.3 Flowchart Explanation

The flowchart represents the overall functioning of

the system:

• The sensors continuously monitor the

vehicle’s movement and impact force.

• The microcontroller processes the data and

determines if an accident has occurred.

• If an accident is detected, the GPS module

retrieves the exact location.

• The GSM module sends an emergency SMS

to pre-stored contacts.

• The NodeMCU Wi-Fi module uploads the

accident data to the cloud.

• The Android application fetches real-time

data and notifies emergency contacts.

• Users can manually trigger an SOS alert if

needed.

AcciAid: IoTâ

SDriven Realâ

STime Accident Detection and Emergency Alert System

575

6.4 Embedded System and Python

Integration

1) Embedded system components

The embedded system consists of an Arduino

microcontroller and a NodeMCU Wi-Fi module.

• The Arduino acts as the central processing

unit, continuously analyzing sensor inputs

and triggering alerts when necessary.

• The NodeMCU module ensures seamless

cloud integration by uploading accident data

to ThingSpeak.

• The GSM module is responsible for sending

emergency SMS alerts.

2) Role of python

• Python is used for data processing and

integration with the ThingSpeak API.

• It enables real-time data visualization and

ensures seamless communication between

the cloud and the Android application.

• Python is also used to enhance the accuracy

of accident detection algorithms.

6.5 Android Application

1) Features of the android app

• Displays real-time sensor data and accident

alerts

• Sends automatic notifications to emergency

contacts

• Tracks accident location using Google Maps

• Allows users to store and manage

emergency contacts

• Includes an SOS button for manual

emergency alerts

2) Working of the android app

• The application retrieves real-time sensor

data from ThingSpeak.

• It displays sensor readings and accident

alerts on the dashboard.

• When an accident is detected, it

automatically sends notifications to

emergency contacts.

• The accident location is displayed on a map

for tracking.

• Users can manually send an SOS alert if

needed.

7 RESULTS AND DISCUSSION

Figure 1: Data Plots in Thingspeak for analysis.

Figure 2: Addition of Zonal details in software.

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

576

Sensor data from MEMS, force, and vibration

sensors, along with latitude and longitude coordinates

from the GPS module, are uploaded to ThingSpeak as

shown in Figure 1. The data is stored in designated

fields and displayed in a graphical format for real-

time monitoring and analysis.

Figure 2 displays the user's name and essential

details. It also provides a section to add family

members and favorite contacts for quick access in

case of emergencies.

In Figure 4 We have integrated phone numbers

along with location details and other relevant

information into the application. This ensures that in

case of an accident, emergency contacts receive

accurate location data and necessary details for a

quick response.

Figure 4: Displying details of added contacts.

Figure 5: Message alert when accident is detected.

Figure 5 shows the message sent to registered

mobile numbers, including the GPS location for

accurate tracking and emergency response.

Figure 6: Tracked accident location.

Figure 6 displays the Google Maps location

within the application, allowing users to view real-

time positioning seamlessly. This Figure 7 displays

the complete hardware setup of the system,

showcasing all integrated components and their

connections. It provides a clear overview of the

assembled kit used for accident detection and

emergency response.

Figure 7: Hardware setup.

8 CONCLUSIONS

In conclusion, the proposed accident detection and

emergency alert system offers an effective solution

for enhancing road safety through real-time

monitoring and rapid communication. By integrating

various sensors with the Arduino microcontroller, the

system accurately detects accidents and unusual

impacts. The combination of GPS and GSM modules

AcciAid: IoTâ

SDriven Realâ

STime Accident Detection and Emergency Alert System

577

ensures that emergency contacts receive immediate

notifications along with the precise location of the

incident. The incorporation of IoT technology

through the NodeMCU Wi-Fi module enables

seamless data transmission to the ThingSpeak web

server, allowing for continuous monitoring and quick

decision-making. With its automated functionality,

cost-effectiveness, and reliability, the system

provides a practical and efficient approach to

minimizing response times, ultimately increasing the

chances of saving lives in emergency situations.

REFERENCES

Gunadal A., Koujalagi A., Karavade S., and Konnuri S.,

“MEMS Accelerometer-Based Wireless Black Box

with GPS Tracking for Vehicle Accident Monitoring,”

Project Reference No.: 37S0430, S.G. Balekundri

Institute of Technology, Belgaum, 2015.

Alnashwan Raghad A., et al., “Machine Learning-Based

IoT System for Accident Prevention,” College of

Computer and Information Sciences, King Saud

University, February 2023.

Josephinshermila P., Priya S. Sharon, et al., “Smart

Automotive Black-Box Monitoring System for

Accident Detection,” ELSEVIER, Measurement:

Sensors, Vol. 27, 100721, 2023, pp. 1-8.

Alkhaiwani A. Hussain, Alsamani B. Soliman, “An IoT-

Enabled Framework for Secure Accident Detection and

Driver Information Reporting,” Sustainability, Vol. 15,

pp. 01-26, 2023.

Mahmood Firas M. Z., “GPS, GSM, and Arduino-Based

Vehicle Monitoring System,” CIC-COCOS 2022:

International Conferences on Communication Engineering

and Computer Science, pp. 157-161.

Belhadi A., Djenouri Y., et al., “Enhanced Regional

Convolutional Neural Network for Vehicle Detection in

Smart Road Accident Prevention,” Pattern Recognition

Letters, ELSEVIER, Vol. 158, 2022, pp. 42-47.

Pathik Nikhlesh Y., Gupta Rajeev K., et al., “IoT and Deep

Learning-Based AI System for Smart City Accident

Detection and Alerts,” Sustainability, 2022, Vol. 14,

Issue 7701, pp. 1-24.

B. M. Nandish, R. J. Ekanth Babu, S. S. Ganeshanaik, et al.,

“IoT-Based System for Accident Detection and

Emergency Response,” International Journal of

Engineering Research & Technology (IJERT), Vol. 10,

Issue 11, ICEI - 2022 Conference Proceedings, ISSN:

2278-0181, pp. 636-640.

Sharma S., “IoT-Enabled Vehicle Crash Identification and

Alert Mechanism for Common Road Incidents,”

*International Journal of Computer and Electrical

Engineering*, vol. 5, Oct. 2019.

Dr. C.k.Gomathy, K Rohan, Bandi Mani Kiran Reddy,

Dr.V Geetha“ Accident Detection And Alert

System.May 2022.

Ezil S. L. and Dhanlakshmi, “Real-Time Vehicle Tracking

and Surveillance Utilizing IoT with Arduino,”

*International Journal of Intelligent Systems and Smart

Sensing*, Sept. 2017

K. Poorani et al., “Real-Time Vehicle Tracking, Crash

Detection, and Prevention Using IoT,” *International

Journal of Engineering Research and Recent Trends*,

March 2017.

Nasr E., Kfoury E., and Khoury D., “IoT-Based Method for

Detecting, Reporting, and Navigating Vehicle

Collisions,” *IEEE International Conference on

Multidisciplinary Engineering and Technology*, 2016.

Jalil J., Amin M. S., and Reaz M. B. I., “Crash Identification

and Alert System Utilizing GSM, GPS, and GPRS

Technologies,” *IEEE/OSAIAPR International

Conference on Vision, Electronics, and Informatics*.

S. Akriti et al., “IoT and Cloud-Based Smart Accident

Detection and Response System,” *Proceedings of the

2nd International Conference on Emerging Next-Gen

Computing Technologies*, October 2016.

Patel A., Kumar B., and Gupta C., “IoT-Enabled Smart

Helmet for Instant Crash Detection,” *IEEE Sensors

Journal*, vol. 15, no. 6, pp. 2900-2910, 2019.

S. Singh, K. Verma, and R. Sharma, “Development and

Deployment of an Intelligent Helmet for Ensuring

Worker Safety in Industrial Settings,” *IEEE Access*,

vol. 7, pp. 102550-102562, 2019.

H. Kim and M. Lee, “Smart Helmet Utilizing IoT for

Enhancing Construction Worker Safety,” *IEEE

Journal of Internet of Things*, vol. 5, no. 2, pp. 1234-

1245, 2020.

S. Das, A. Ghosh, R. Dutta, M. Lee, and H. Kim, “Smart

Helmet System for Motorcycle Safety Using IoT,”

*IEEE Transactions on Intelligent Transportation

Systems*, vol. 20, no. 5, pp. 2000–2012, 2021.

Gupta N., Kumar P., and Sharma S., “Comparative

Analysis of Wireless Communication Protocols for

IoT-Enabled Smart Helmets,” *IEEE Wireless

Communications Letters*, vol. 9, no. pp. 456-468, 202.

Tiwari A., Choudhary S., and Singh P., “IoT-Integrated

Smart Helmet for Accident Detection Utilizing

Machine Learning,” *IEEE Transactions on Intelligent

Systems*, vol. 25, no. 1, pp. 50-62, 2022.

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

578