International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Multi-Organ Failure Detection System Using Biomedical Signals and Machine Learning |
|---|---|
| ABSTRACT | Multi-Organ Failure (MOF) is a severe and life-threatening medical condition characterized by the simultaneous or sequential failure of multiple organ systems, requiring immediate and continuous monitoring for effective diagnosis and treatment; therefore, early detection plays a crucial role in reducing mortality rates and improving patient outcomes. To address this challenge, the proposed system presents a portable, cost-effective, and intelligent healthcare monitoring solution that integrates biomedical signal acquisition, machine learning, and Internet of Things (IoT) technologies into a unified framework. The system continuously collects physiological signals such as Electrocardiogram (ECG) for monitoring cardiac activity, Electromyography (EMG) for assessing muscle function, Electroencephalography (EEG) for analyzing brain activity, Electrooculography (EOG) for tracking eye movements and neurological responses, and Photoplethysmography (PPG) for measuring blood volume changes and oxygen saturation levels, thereby providing a comprehensive view of multiple organ functions. These signals are captured using appropriate sensors and processed by the ESP32 microcontroller, which is selected for its low power consumption, high processing capability, and built-in wireless communication features such as Wi-Fi and Bluetooth. The ESP32 performs essential tasks including signal conditioning, noise filtering, amplification, analog-to-digital conversion, feature extraction, and real-time data analysis to convert raw sensor inputs into meaningful physiological parameters. Furthermore, advanced machine learning algorithms are implemented to analyze patterns within the extracted features and classify the patient’s condition as normal or abnormal, enabling intelligent decision-making and reducing the dependency on constant human supervision. The integration of IoT technology allows seamless transmission of processed data to a cloud-based platform, where it is stored, analyzed, and visualized through an interactive dashboard accessible to healthcare professionals from remote locations. This remote monitoring capability is further enhanced with automated alert mechanisms that generate notifications or alarms when abnormal conditions are detected, ensuring timely medical intervention. In addition, the system is designed to be scalable, user-friendly, and suitable for both hospital and home-care environments, making it highly beneficial in rural and resource-limited settings where access to advanced medical facilities is limited. Overall, the proposed solution significantly improves early diagnosis, continuous monitoring, accessibility, and efficiency in modern healthcare systems by leveraging the combined power of embedded systems, data analytics, machine learning, and IoT technologies, thereby contributing to smarter and more proactive patient care. |
| AUTHOR | DR.P.N.PALANISAMY, SENTAMIZHSELVAN S, RATHINAKUMAR M, RAHUL A, VISHAL P Associate Professor, Dept. of ECE, Mahendra College of Engineering, Salem, Tamil Nadu, India UG Student, Dept. of ECE, Mahendra College of Engineering, Salem, Tamil Nadu, India |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404132 |
| pdf/132_Multi-Organ Failure Detection System Using Biomedical Signals and Machine Learning.pdf | |
| KEYWORDS | |
| References | 1. J. G. Webster, Medical Instrumentation: Application and Design, 4th ed., Wiley, 2009. 2. L. Cromwell et al., Biomedical Instrumentation and Measurements, Pearson, 2011. 3. R. S. Khandpur, Handbook of Biomedical Instrumentation, McGraw-Hill, 2014. 4. P.N.Palanisamy, Secure Routing In Mobile Adhoc Networks (MANET)* International Journal of Innovative Research in Computer and Communication Engineering (IJIRCCE) 2(7) 2320-9801 (2014). 5. U. R. Acharya et al., “Automated identification of epileptic EEG signals,” Int. J. Neural Systems, 2011. 6. G. B. Moody and R. G. Mark, “MIT-BIH arrhythmia database,” IEEE Eng. Med. Biol., 2001. 7. S. M. Pincus, “Approximate entropy,” PNAS, 1991. 8. A. Pantelopoulos and N. G. Bourbakis, “Wearable sensor-based health monitoring,” IEEE Systems, 2010. 9. Lin Bai et al., “Epileptic Seizure Detection Using Machine Learning: A Systematic Review and Meta-Analysis,” Brain Sciences, 2025. 10. Y. Paul, “Various epileptic seizure detection techniques using biomedical signals,” Brain Informatics, 2018. 11. G. Liu et al., “Minireview of Epilepsy Detection Techniques Based on EEG Signals,” Frontiers, 2021. 12. I. Ahmad et al., “EEG-Based Epileptic Seizure Detection via Machine Learning,” 2022. 13. P. Boonyakitanont et al., “Feature extraction in EEG seizure detection,” 2019. 14. P.N.Palanisamy, Performance Analysis of Wireless Sensor Networks in Different Terrain Areas using DSR Routing Protocol in NS2 Simulation * International Journal of Innovative Research in Computer and Communication Engineering (IJIRCCE) 2320-9801 (2016). |
