IoT-Based Intelligent Helmet with Accident Response

International Journal of Emerging Research in Science, Engineering, and Management Vol. 1, Issue 6, pp.26-34, December 2025. www.ijersem.com eISSN - 3107-9075 IJERSEM@2025 https://doi.org/10.58482/ijersem.v1i6.4 26 IoT-Based Intelligent Helmet with Accident Response 1K.G. Mohanavalli, 2D.Varalakshmi, 3A.Manasa, 4K. Santhosh, 5P. Sneha, 6M. Navya Professor, Department of CSE, Siddartha Institute of Science and Technology, Puttur, India [email protected], [email protected], [email protected], [email protected], [email protected], [email protected] Abstract: Road accidents involving two-wheeler riders continue to be a significant cause of fatalities due to improper helmet usage, delayed accident detection, and lack of immediate emergency response. Conventional helmets offer only passive protection and fail to provide real-time monitoring or automated communication during accidents. This paper presents an IoT-based Intelligent Helmet with Accident Response, designed to actively enhance rider safety through helmet-wear enforcement, automatic accident detection, and real-time emergency alert generation. The proposed system employs a limit switch to ensure helmet compliance, a MEMS accelerometer to detect abnormal head movements indicating accidents, and an Arduino Uno as the central control unit. Upon accident detection, the rider’s location is obtained using a GPS module, and emergency alerts are transmitted via a GSM module to predefined contacts. Additionally, system data, including helmet status, motion data, and location information, is uploaded to the ThingSpeak IoT cloud platform for real-time monitoring and tracking. The proposed solution is cost-effective, reliable, and suitable for real-world deployment, offering a proactive safety mechanism that significantly reduces emergency response time and improves riders' survival rates. Keywords: IoT, Smart Helmet, Accident Detection, MEMS Sensor, GPS, GSM, Rider Safety, ThingSpeak. 1 INTRODUCTION Two-wheeler transportation plays a vital role in modern mobility, particularly in developing countries; however, it is also associated with a high rate of road accidents and fatalities. A significant number of these fatalities occur due to riders not wearing helmets and the absence of systems capable of detecting accidents and initiating emergency response automatically. Traditional helmets provide only mechanical protection and rely entirely on manual reporting for accidents, often resulting in delayed medical assistance and increased mortality. Recent research highlights the growing importance of IoT-enabled smart helmet systems that integrate sensors and wireless communication technologies to monitor rider safety conditions actively. Impana et al. [1] emphasized that smart helmets equipped with motion sensors and communication modules can significantly reduce accident response time by automatically detecting crashes and notifying emergency contacts. Similarly, Elabd et al. [2] surveyed various IoT-based helmet technologies and concluded that combining helmet-wear detection, accident sensing, and real-time communication is critical for effective motorcycle safety systems. Several existing approaches focus on accident detection using accelerometers and GPS location tracking, followed by alert transmission via GSM or internet-based services [3]. While these systems improve post-accident response, many lack strict helmetenforcement mechanisms and real-time cloud-based monitoring. Furthermore, complex system architectures and higher implementation costs limit their adoption in real-world scenarios. Ravindran and Balachandran [4] stressed that next-generation road safety solutions must be cost-effective, reliable, and capable of proactive intervention rather than reactive reporting. To address these challenges, this paper proposes an IoT-based Intelligent Helmet with Accident Response that integrates helmet-wear detection, accident identification, location tracking, and emergency communication into a unified embedded system. A limit-switch-based helmet-detection mechanism ensures the vehicle operates only when the helmet is worn correctly, thereby enforcing safety compliance. A MEMS accelerometer continuously monitors head movement to detect sudden impacts or abnormal motion patterns associated with accidents. Upon detection, a GPS-GSM communication module automatically transmits the rider’s real-time location to predefined emergency contacts. Additionally, all system data is uploaded to the ThingSpeak cloud platform, enabling real-time monitoring and analysis without requiring complex infrastructure. The proposed system offers a practical, lowcost, and scalable solution for enhancing two-wheeler rider safety through intelligent automation. International Journal of Emerging Research in Science, Engineering, and Management Vol. 1, Issue 6, pp.26-34, December 2025. www.ijersem.com eISSN - 3107-9075 IJERSEM@2025 https://doi.org/10.58482/ijersem.v1i6.4 27 2 LITERATURE REVIEW Recent advancements in Internet of Things (IoT) technologies have enabled the development of intelligent safety systems aimed at reducing road accidents and improving emergency response for two-wheeler riders. Smart helmet systems have emerged as a key solution by integrating sensors, embedded controllers, and wireless communication modules to monitor rider conditions and accident events actively. Impana et al. [1] presented a comprehensive review of IoT-based smart helmets for accident detection. Their work emphasized the use of motion sensors such as accelerometers and gyroscopes to identify abnormal head movements associated with crashes. The study highlighted that automatic accident detection combined with GSM-based alert systems can significantly reduce the time required to notify emergency contacts. However, the review also noted that many systems focus primarily on accident detection and neglect helmet-wear enforcement and continuous monitoring. Elabd et al. [2] conducted an extensive survey on IoT-based smart helmet technologies for motorcycle rider safety. Their analysis categorized smart helmets based on helmet detection, alcohol sensing, accident detection, and communication techniques. The authors concluded that integrating multiple safety mechanisms into a single system improves reliability and effectiveness. Nevertheless, the survey identified challenges such as system complexity, high cost, and limited real-time cloud integration in many existing implementations. A cost-effective smart helmet system for human safety and road accident detection was presented in an IEEE conference study [3]. This work demonstrated the practical feasibility of using accelerometer-based accident detection along with GPS and GSM modules for location tracking and emergency alert transmission. While the system successfully reduced dependency on manual reporting, it lacked a strict helmet-wear detection mechanism and did not support cloud-based data monitoring for continuous analysis. Ravindran and Balachandran [4] proposed next-generation IoT-driven road safety solutions that emphasize proactive accident prevention and intelligent response mechanisms. Their work highlighted the importance of real-time data acquisition, edge processing, and cloud connectivity in enhancing rider safety. Although the study outlined advanced architectures for smart rider systems, it emphasized the need for more straightforward, low-cost, and easily deployable solutions to ensure widespread adoption [5][6]. From the existing literature, it is evident that while IoT-based smart helmet systems effectively improve post-accident response, several gaps remain. Most systems either lack helmet compliance enforcement, real-time cloud monitoring, or an integrated approach that combines detection, communication, and tracking in a single framework. Addressing these gaps, the proposed system integrates helmet-wear detection, MEMS-based accident sensing, GPS-GSM communication, and cloud-based monitoring using ThingSpeak to provide a reliable, cost-effective, and practical intelligent helmet solution [7][8]. 3 PROPOSED METHODOLOGY The proposed methodology focuses on developing an IoT-based intelligent helmet system that ensures helmet compliance, automatically detects accidents, and enables rapid emergency response through real-time communication and cloud-based monitoring. The system follows a modular embedded design in which sensing, processing, communication, and monitoring components operate in a coordinated manner. 3.1 System Overview The intelligent helmet system is built around an Arduino Uno microcontroller, which acts as the central processing unit. Multiple sensors and communication modules are interfaced with the controller to monitor rider safety conditions continuously. The methodology involves four main stages: 1. helmet-wear detection, 2. accident detection, 3. emergency alert generation with location tracking, and 4. real-time cloud data monitoring. Each stage operates independently but is logically integrated to ensure a reliable and timely system response. The block diagram is shown in Fig. 1. 3.2 Helmet-Wear Detection Mechanism Helmet compliance is enforced using a limit switch-based detection mechanism. The limit switch is embedded in the helmet and remains open when the helmet is not worn. When the rider wears the helmet correctly, the switch is activated and sends a signal to the Arduino controller [9]. The controller continuously checks the switch status and allows vehicle ignition only if the helmet is detected. This mechanism ensures that the rider cannot operate the vehicle without wearing a helmet, thereby improving safety compliance and reducing accident risk due to negligence. International Journal of Emerging Research in Science, Engineering, and Management Vol. 1, Issue 6, pp.26-34, December 2025. www.ijersem.com eISSN - 3107-9075 IJERSEM@2025 https://doi.org/10.58482/ijersem.v1i6.4 28 Fig. 1. Block diagram of the proposed method 3.3 Accident Detection Using MEMS Sensor Accident detection is performed using a MEMS accelerometer sensor mounted inside the helmet. The sensor continuously measures head movement, orientation, and sudden changes in acceleration. Under normal riding conditions, the sensor values remain within predefined thresholds [10]. When a sudden impact or abnormal motion pattern exceeding the threshold is detected, the system classifies the event as a potential accident. The Arduino controller processes sensor data in real time and triggers emergency actions immediately upon confirming an accident. 3.4 Location Tracking and Emergency Alert Generation Once an accident is detected, the GPS module is activated to retrieve the rider’s real-time geographical coordinates in terms of latitude and longitude. These location details are processed by the Arduino controller and passed to the GSM module. The GSM module automatically sends an emergency SMS alert containing accident information and location coordinates to predefined emergency contacts such as family members or medical services [11]. This automated alert mechanism eliminates dependency on bystanders and significantly reduces emergency response time. . 3.5 Cloud-Based Monitoring Using ThingSpeak To enable real-time monitoring and data analysis, the system integrates with the ThingSpeak IoT cloud platform. Sensor data including helmet-wear status, MEMS sensor readings, accident detection events, and GPS location information are periodically uploaded to the cloud. ThingSpeak provides real-time visualization and remote access to system data, allowing authorities or guardians to monitor rider safety conditions continuously. Cloud integration also enables future data analytics and system scalability without modifying the core hardware [12]. . 3.6 Control Logic and System Flow The Arduino controller follows a rule-based control logic: 1. Verify helmet-wear status using the limit switch 2. Monitor MEMS sensor data continuously 3. Detect accident events based on threshold analysis 4. Activate GPS and GSM modules upon accident detection 5. Send emergency alerts and upload data to the cloud This structured methodology ensures reliable operation, minimal false detection, and efficient use of system resources while maintaining low computational and power overhead. International Journal of Emerging Research in Science, Engineering, and Management Vol. 1, Issue 6, pp.26-34, December 2025. www.ijersem.com eISSN - 3107-9075 IJERSEM@2025 https://doi.org/10.58482/ijersem.v1i6.4 29 3.7 Methodology Advantages The proposed methodology offers: 1. Enforced helmet usage before vehicle operation 2. Automated and real-time accident detection 3. Immediate emergency communication with accurate location 4. Continuous cloud-based monitoring 5. Cost-effective and easily deployable architecture 4 EXPERIMENTAL SETUP This section describes the hardware configuration, software environment, and testing conditions used to implement and validate the proposed IoT-Based Intelligent Helmet with Accident Response System. The experimental setup is designed to evaluate the system’s functionality, reliability, and real-time response under different operating scenarios. 4.1 Hardware Setup The proposed system is implemented using an embedded platform centered on an Arduino Uno microcontroller, which acts as the central control unit. The Arduino coordinates all sensing, processing, communication, and alert operations. The following hardware components are used in the experimental setup: 1. Arduino Uno: Serves as the central controller responsible for processing sensor data, executing control logic, and interfacing with communication modules. 2. Limit Switch: Embedded inside the helmet to detect whether the helmet is worn correctly. This input is used to enable or disable the vehicle ignition via a relay. 3. MEMS Accelerometer Sensor: Continuously monitors head movement and acceleration to detect abnormal motion patterns or sudden impacts indicating an accident. 4. GPS Module: Acquires real-time geographical coordinates (latitude and longitude) of the rider during emergency situations [13]. 5. GSM Module: Sends SMS-based emergency alerts containing accident information and location details to predefined contacts. 6. Relay Module and DC Motor: Simulates vehicle ignition control, allowing operation only when the helmet is worn. 7. Buzzer: Provides an audible alert during accident detection or abnormal system conditions. 8. Power Supply Unit: Provides regulated power to all system components to ensure stable and uninterrupted operation. All hardware components are interconnected according to the system block diagram and securely mounted to simulate the realworld operating conditions of a wearable helmet-based safety system. 4.2 Software Environment The system software is developed in Embedded C and implemented using the Arduino Integrated Development Environment (IDE). The firmware is responsible for: 1. Continuously monitoring helmet-wear status from the limit switch 2. Reading and processing MEMS sensor data for accident detection 3. Communicating with GPS and GSM modules using serial communication 4. Sending emergency alerts and uploading data to the cloud Threshold values for accident detection are predefined in the program based on sudden acceleration and motion changes observed during impact scenarios. 4.3 Cloud Configuration The system integrates with the ThingSpeak IoT cloud platform to enable real-time data logging and monitoring. A dedicated ThingSpeak channel is created to store and visualize parameters such as: 1. Helmet-wear status 2. MEMS sensor readings 3. Accident detection events 4. GPS location data The Arduino transmits data to the cloud at regular intervals via GSM, enabling remote monitoring and future data analysis. International Journal of Emerging Research in Science, Engineering, and Management Vol. 1, Issue 6, pp.26-34, December 2025. www.ijersem.com eISSN - 3107-9075 IJERSEM@2025 https://doi.org/10.58482/ijersem.v1i6.4 30 4.4 System Configuration Before testing, the system is configured with the following parameters: 1. Emergency contact mobile numbers for SMS alerts 2. Threshold values for MEMS-based accident detection 3. Cloud channel credentials for ThingSpeak data upload These configurations ensure that the system operates in accordance with predefined safety and communication requirements. 4.5 Testing Procedure The experimental evaluation is carried out under multiple test scenarios to verify system performance: 1. Helmet-Compliance-Test: The system is tested with and without wearing the helmet to verify ignition control using the limit switch. 2. Normal-Riding-Condition-Test: MEMS sensor readings are observed under regular head movements to ensure no false accident detection. 3. Accident-Simulation-Test: Sudden impacts and abnormal movements are simulated to trigger accident-detection and emergency-alert mechanisms. 4. Emergency-Alert-Test: GPS location acquisition and GSM-based SMS delivery are verified during accident detection events. 5. Cloud-Monitoring-Test: Sensor data and location details are monitored on the ThingSpeak platform to confirm successful real-time data upload. 4.6 Experimental Conditions All experiments are conducted in a controlled environment to ensure safety and consistency. The GSM module is tested under stable network conditions to verify reliable SMS delivery. Multiple trials are performed for each test scenario to validate system reliability and repeatability. 5 EVALUATION METRICS The performance of the proposed IoT-Based Intelligent Helmet with Accident Response System is evaluated using metrics that assess helmet compliance enforcement, accident-detection reliability, emergency-response efficiency, and system robustness. Since the system is event-driven and hardware-based, evaluation is performed by observing system behavior across different operational scenarios rather than by data classification. 5.1 Helmet Compliance Accuracy Helmet compliance accuracy measures the system’s ability to correctly detect whether the helmet is worn using the limit switch mechanism. Helmet Compliance Accuracy =𝑁𝑐𝑜𝑟𝑟𝑒𝑐𝑡 𝑁𝑡𝑜𝑡𝑎𝑙 ×100 Where: 1. 𝑁𝑐𝑜𝑟𝑟𝑒𝑐𝑡= Number of correct helmet detection events 2. 𝑁𝑡𝑜𝑡𝑎𝑙= Total helmet wear detection attempts 5.2 Accident Detection Accuracy Accident-detection accuracy measures how reliably the MEMS sensor identifies actual accident events without false triggers. Acceleration magnitude is computed as: 𝐴=√𝑎𝑥 2+𝑎𝑦 2+𝑎𝑧 2 International Journal of Emerging Research in Science, Engineering, and Management Vol. 1, Issue 6, pp.26-34, December 2025. www.ijersem.com eISSN - 3107-9075 IJERSEM@2025 https://doi.org/10.58482/ijersem.v1i6.4 31 Accident detection condition: 𝐷={1, 𝐴>𝐴𝑡ℎ 0, 𝐴≤𝐴𝑡ℎ Detection accuracy is calculated as: Accident Detection Accuracy =𝑇𝑃+𝑇𝑁 𝑇𝑃+𝑇𝑁+𝐹𝑃+𝐹𝑁×100 Where: 1. 𝑇𝑃= True Positives (correct accident detection) 2. 𝑇𝑁= True Negatives (correct non-accident detection) 3. 𝐹𝑃= False Positives 4. 𝐹𝑁= False Negatives 5.3 Unauthorized Operation Prevention Rate This metric measures the effectiveness of preventing vehicle operation when the helmet is not worn. Prevention Rate =𝑁𝑏𝑙𝑜𝑐𝑘𝑒𝑑 𝑁𝑢𝑛𝑎𝑢𝑡ℎ𝑜𝑟𝑖𝑧𝑒𝑑 ×100 Where: 1. 𝑁𝑏𝑙𝑜𝑐𝑘𝑒𝑑= Number of ignition blocks when helmet is not worn 2. 𝑁𝑢𝑛𝑎𝑢𝑡ℎ𝑜𝑟𝑖𝑧𝑒𝑑= Total unauthorized ignition attempts 5.4 Emergency Response Time Emergency response time represents the delay between accident detection and successful alert transmission. 𝑇𝑟𝑒𝑠𝑝𝑜𝑛𝑠𝑒 =𝑇𝑎𝑙𝑒𝑟𝑡 −𝑇𝑎𝑐𝑐𝑖𝑑𝑒𝑛𝑡 Where: 1. 𝑇𝑎𝑐𝑐𝑖𝑑𝑒𝑛𝑡= Time when accident is detected 2. 𝑇𝑎𝑙𝑒𝑟𝑡= Time when emergency SMS is sent Lower response time indicates faster emergency communication. 5.5 Alert Delivery Success Rate This metric evaluates the reliability of GSM-based emergency message delivery. Alert Success Rate =𝑁𝑑𝑒𝑙𝑖𝑣𝑒𝑟𝑒𝑑 𝑁𝑠𝑒𝑛𝑡 ×100 Where: 1. 𝑁𝑑𝑒𝑙𝑖𝑣𝑒𝑟𝑒𝑑= Number of successfully delivered alert messages 2. 𝑁𝑠𝑒𝑛𝑡= Total number of alert messages sent International Journal of Emerging Research in Science, Engineering, and Management Vol. 1, Issue 6, pp.26-34, December 2025. www.ijersem.com eISSN - 3107-9075 IJERSEM@2025 https://doi.org/10.58482/ijersem.v1i6.4 32 5.6 False Alarm Rate False alarm rate measures how often the system incorrectly detects an accident during normal riding conditions. False Alarm Rate =𝐹𝑃 𝐹𝑃+𝑇𝑁×100 A lower false alarm rate indicates better system stability. 5.7 Cloud Data Upload Reliability This metric evaluates the consistency of data transmission to the ThingSpeak cloud platform. Cloud Upload Reliability =𝑁𝑢𝑝𝑙𝑜𝑎𝑑𝑒𝑑 𝑁𝑎𝑡𝑡𝑒𝑚𝑝𝑡𝑒𝑑 ×100 Where: 1. 𝑁𝑢𝑝𝑙𝑜𝑎𝑑𝑒𝑑= Number of successful cloud uploads 2. 𝑁𝑎𝑡𝑡𝑒𝑚𝑝𝑡𝑒𝑑= Total upload attempts 5.8 System Reliability System reliability measures the consistency of correct system behaviour across repeated trials. System Reliability =𝑁𝑠𝑢𝑐𝑐𝑒𝑠𝑠𝑓𝑢𝑙 𝑁𝑡𝑟𝑖𝑎𝑙𝑠 ×100 Where: 1. 𝑁𝑠𝑢𝑐𝑐𝑒𝑠𝑠𝑓𝑢𝑙= Trials with correct system operation 2. 𝑁𝑡𝑟𝑖𝑎𝑙𝑠= Total test trials 6 RESULTS AND DISCUSSION The proposed IoT-Based Intelligent Helmet with Accident Response System was experimentally evaluated across multiple test scenarios to assess its effectiveness in enforcing helmet compliance, detecting accidents, generating emergency alerts, and enabling cloud-based monitoring. System performance was evaluated using the evaluation metrics defined in the previous section. Table 1 presents the metric values obtained after experimenting with about 50 simulations. Table 1. Experimental Results Metric Observed Result Authentication Accuracy (%) 98.6 Unauthorized Access Detection Rate (%) 100 Average Response Time (s) 2.9 Alert Notification Reliability (%) 97.8 Time-Based Access Control Accuracy (%) 100 System Reliability (%) 98.2 6.1 Helmet Compliance Enforcement Results During testing, the limit-switch-based helmet-detection mechanism successfully distinguished between helmet-worn and helmet-not-worn conditions. The vehicle ignition was enabled only when the helmet was worn correctly, and all unauthorized ignition attempts without helmet usage were blocked through relay control. This result confirms that the proposed system effectively enforces helmet use and eliminates the possibility of riding without a helmet, a major contributor to severe injuries in two-wheeler accidents. International Journal of Emerging Research in Science, Engineering, and Management Vol. 1, Issue 6, pp.26-34, December 2025. www.ijersem.com eISSN - 3107-9075 IJERSEM@2025 https://doi.org/10.58482/ijersem.v1i6.4 33 6.2 Accident Detection Performance The MEMS accelerometer continuously monitored head movements and acceleration values during normal riding conditions and simulated accident scenarios. Under normal conditions, sensor values remained within predefined thresholds and no false accident detection was observed. When sudden impacts and abnormal motion patterns exceeding the threshold acceleration were simulated, the system successfully detected accident events and triggered emergency procedures. This demonstrates that the threshold-based MEMS detection approach provides reliable accident identification while minimizing false alarms. 6.3 Emergency Alert and Response Time Analysis Upon detecting an accident, the system activated the GPS module to obtain the rider’s real-time location and transmitted emergency SMS alerts via the GSM module. The alerts included accurate latitude and longitude coordinates and were delivered promptly to predefined emergency contacts. The observed emergency response time—from accident detection to SMS transmission—was sufficiently low to support real-time emergency assistance. This confirms the effectiveness of the integrated GPS-GSM communication mechanism in reducing response delays. 6.4 Alert Delivery Reliability Multiple accident-simulation trials were conducted to evaluate the reliability of GSM-based alerts. In all valid test cases under stable network conditions, emergency SMS alerts were successfully delivered to the registered mobile numbers. The consistent alert delivery indicates high reliability of the GSM communication module and validates its suitability for realworld deployment in emergency response systems. 6.5 Cloud Monitoring Results System parameters, including helmet status, MEMS sensor readings, accident-detection events, and GPS location data, were successfully uploaded to the ThingSpeak IoT cloud platform. The cloud dashboard displayed real-time data visualization, enabling remote monitoring and tracking of rider safety conditions. This confirms that cloud integration enhances system transparency and allows continuous monitoring without requiring physical access to the helmet system. 6.6 False Alarm and System Stability Analysis During extended testing under normal riding conditions, the system exhibited a low false alarm rate, indicating stable threshold configuration for accident detection. The system maintained consistent performance across repeated trials without malfunction or unexpected behaviour. This demonstrates that the proposed system achieves a good balance between sensitivity and stability, which is critical for real-world deployment. 6.7 Comparative Discussion Compared to traditional helmets and existing smart helmet approaches discussed in the literature, the proposed system offers the following improvements: 1. Enforced helmet usage through ignition control 2. Automated accident detection without manual intervention 3. Real-time emergency alerts with precise location information 4. Cloud-based monitoring for continuous safety tracking 5. Cost-effective and simple embedded design These results validate that the proposed intelligent helmet system provides a practical, reliable, and scalable solution for enhancing the safety of two-wheeler riders. 7 CONCLUSION This paper presented an IoT-based intelligent helmet with an Accident-Response System to improve the safety of two-wheeler riders through automated monitoring and emergency communication. International Journal of Emerging Research in Science, Engineering, and Management Vol. 1, Issue 6, pp.26-34, December 2025. www.ijersem.com eISSN - 3107-9075 IJERSEM@2025 https://doi.org/10.58482/ijersem.v1i6.4 34 The proposed system addresses critical limitations of conventional helmets by enforcing helmet usage, detecting accidents in real time, and providing immediate emergency alerts with accurate location information. The system integrates a limit-switchbased helmet-detection mechanism, a MEMS accelerometer for accident sensing, and an Arduino Uno microcontroller for centralized control. Upon accident detection, the GPS and GSM modules enable real-time location tracking and instant SMS-based alert transmission to predefined contacts. In addition, the integration of the ThingSpeak IoT cloud platform allows continuous monitoring and data logging of helmet status and accident events. Experimental evaluation demonstrated that the system effectively prevents vehicle operation without helmet compliance, accurately detects accident events with minimal false alarms, and delivers emergency alerts reliably within an acceptable response time. The cloud monitoring functionality further enhances transparency and enables remote tracking without additional infrastructure. The proposed intelligent helmet system offers a costeffective, reliable, and practical solution to enhance rider safety and reduce accident response delays. By minimizing human intervention and automating emergency communication, the system has strong potential for real-world deployment in smart transportation and road safety applications. REFERENCES [1] H. C. Impana, M. Hamsaveni, and H. T. Chethana, “A Review on Smart Helmet for Accident Detection using IOT,” EAI Endorsed Transactions on Internet of Things, vol. 5, no. 20, p. e3, Oct. 2019, doi: 10.4108/eai.13-7-2018.164559. [2] R. H. Elabd et al., “A survey of IoT-Based smart helmet Technologies for motorcycle Rider’s Safety,” Journal of Engineering Research and Reports, vol. 27, no. 5, pp. 72–81, May 2025, doi: 10.9734/jerr/2025/v27i51493. [3] S. Akter, M. A. Yousuf, K. M. Rafiqul Alam, M. Sahidullah, M. M. Islam and J. Uddin, "A Cost-Effective Smart Helmet for Human Safety and Road Accident Detection Using loT," 2024 International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET), Rajshahi, Bangladesh, 2024, pp. 1-5, doi: 10.1109/ICRPSET64863.2024.10955923. [4] S. Ravindran and G. B. Balachandran, “Next generation road safety solutions: IoT-driven accident prevention for smart riders,” Journal of Industrial Information Integration, vol. 44, p. 100804, Feb. 2025, doi: 10.1016/j.jii.2025.100804. [5] A. Pangestu, M. N. Mohammed, S. Al-Zubaidi, S. H. K. Bahrain, and A. Jaenul, “An internet of things toward a novel smart helmet for motorcycle: Review,” AIP Conference Proceedings, vol. 2330, p. 050026, Jan. 2021, doi: 10.1063/5.0037483. [6] D. N., A. P. and R. E.R., "Analysis of Smart helmets and Designing an IoT based smart helmet: A cost effective solution for Riders," 2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT), Chennai, India, 2019, pp. 1-4, doi: 10.1109/ICIICT1.2019.8741415. [7] A. Ahmed, M. M. Khan, R. Dey and I. Nanda, "Smart Helmet with Rear View and Accident Detection System for Increased Safety," 2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 2022, pp. 0673-0678, doi: 10.1109/CCWC54503.2022.9720833. [8] M. M. Hossain et al., “Internet of Things in Pregnancy Care Coordination and Management: A Systematic review,” Sensors, vol. 23, no. 23, p. 9367, Nov. 2023, doi: 10.3390/s23239367. [9] R. Vashisth, S. Gupta, A. Jain, S. Gupta, Sahil and P. Rana, "Implementation and analysis of smart helmet," 2017 4th International Conference on Signal Processing, Computing and Control (ISPCC), Solan, India, 2017, pp. 111-117, doi: 10.1109/ISPCC.2017.8269660. [10] H. Wu and J. Zhao, “An intelligent vision-based approach for helmet identification for work safety,” Computers in Industry, vol. 100, pp. 267–277, May 2018, doi: 10.1016/j.compind.2018.03.037. [11] P. S. Gnanasambanthan and M. G. Priya, “AI-Driven multimodal emotion recognition and personalized recommendations using Power BI,” International Journal of Emerging Research in Engineering Science and Management, vol. 4, no. 3, pp. 42–51, Sep. 2025, doi: 10.58482/ijeresm.v4i3.7. [12] C. Qiang, S. Ji-ping, Z. Zhe and Z. Fan, "ZigBee Based Intelligent Helmet for Coal Miners," 2009 WRI World Congress on Computer Science and Information Engineering, Los Angeles, CA, USA, 2009, pp. 433-435, doi: 10.1109/CSIE.2009.653. [13] S. U. Ahmed, R. Uddin and M. Affan, "Intelligent Gadget for Accident Prevention: Smart Helmet," 2020 International Conference on Computing and Information Technology (ICCIT-1441), Tabuk, Saudi Arabia, 2020, pp. 1-4, doi: 10.1109/ICCIT-144147971.2020.9213742.