Edge-based intelligent and smart health monitoring on PYNQ-Z2 using lightweight protocol and integration of machine learning models

Basu, Samik; Ray, Rajdeep; Maitra, Arkadip; Banerjee, Pritha; Chakrabarti, Amlan

doi:10.2478/ijssis-2025-0056

Abstract

This study presents a smart health monitoring system that integrates information and communication technology (ICT) with machine learning (ML) for efficient, real-time healthcare delivery. The system is designed for elderly and chronically ill patients, using sensor-based data acquisition (heart rate [HR], blood oxygen saturation [SpO₂], temperature) and self-powered, remote monitoring via personal health devices (PHDs). It employs the message queuing telemetry transport (MQTT) protocol for lightweight messaging, with sensor data collected through an ESP32-based microcontroller, working as an MQTT client, and a Raspberry Pi (RPI) acting as the MQTT broker, enabling seamless health data accessibility over the internet. An intelligent health prediction module is designed to classify health conditions based on key physiological parameters, such as HR, SpO₂, and body temperature. Health conditions are classified using ML algorithms (support vector machine [SVM], K-nearest neighbors [KNN], decision tree [DT]) trained on real-time datasets. The models are deployed on a PYNQ-Z2 FPGA board, ensuring high-speed, low-power, and cost-effective operation. This scalable and intelligent framework supports accessible and reliable e-health monitoring.

References

Al-Fuqaha A., et al., “Internet of things: “A survey on enabling technologies, protocols, and applications,” IEEE Communications Surveys and Tutorials, vol. 17, no. 4, pp. 2347–2376, 2015.
Search in Google Scholar Back to article
Tiwari D, Prasad D, Guleria K, and Ghosh P., “IoT based Smart Healthcare Monitoring Systems: A Review,” 2021 6th International Conference on Signal Processing, Computing and Control (ISPCC), Solan, India, 2021, pp. 465–469, doi: 10.1109/ISPCC53510.2021.9609393.
Open DOI Search in Google Scholar Back to article
Verma Himanshu, Chauhan Naveen, Awasthi Lalit Kumar, “A Comprehensive review of “Internet of Healthcare Things”: Networking aspects, technologies, services, applications, challenges, and security concerns, Computer Science Review, Volume50,2023,100591, ISSN 1574–0137, https://doi.org/10.1016/j.cosrev.2023.100591.
Search in Google Scholar Back to article
Medvediev I., et al., “IoT solutions for health monitoring: analysis and case study,” 2018 IEEE 9th International Conference on Dependable Systems, Services and Technologies (DESSERT), IEEE, 2018.
Search in Google Scholar Back to article
Tonello S., et al., “Design and in vitro Characterization of a Wearable Multi-sensing System for Hydration Monitoring,” in IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1–11, 2024, doi: 10.1109/TIM.2024.3369161.
Open DOI Search in Google Scholar Back to article
Sharma G, Joshi A. M., Yadav D, and Mohanty S. P., “A Smart Healthcare Framework for Accurate Detection of Schizophrenia Using Multichannel EEG,” in IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1–9, 2023, Art no. 3523409, doi: 10.1109/TIM.2023.3293544.
Open DOI Search in Google Scholar Back to article
Zhang H, Wang Z, Teng C, Kumar S, Li X, and Min R., “Wearable Cardiorespiratory Sensor for Real-Time Monitoring With Smartphone Integration,” in IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1–10, 2024, Art no. 7000710, doi: 10.1109/TIM.2023.3338709.
Open DOI Search in Google Scholar Back to article
Priya A. D., and Sundar S., “Health Monitoring System using IoT,” 2019 International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN), Vellore, India, 2019, pp. 1–3, doi: 10.1109/ViTECoN.2019.8899434.
Open DOI Search in Google Scholar Back to article
Pardeshi V., et al. “Health monitoring systems using IoT and Raspberry Pi—a review,” 2017 International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), IEEE, 2017.
Search in Google Scholar Back to article
Divakaran S., et al., “IOT clinic-Internet based patient monitoring and diagnosis system,” 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), IEEE, 2017.
Search in Google Scholar Back to article
Uddin M. S., Alam J. B., and Banu S., “Real time patient monitoring system based on Internet of Things,” 2017 4th International Conference on Advances in Electrical Engineering (ICAEE), IEEE, 2017.
Search in Google Scholar Back to article
Bouslama A., Laaziz Y., Tali A., and Eddabbah M., “AWS and IoT for real-time remote medical monitoring,” International Journal of Intelligent Enterprise, vol. 6, no. 2–4, pp. 369–381, 2019.
Search in Google Scholar Back to article
Stradolini F., et al., “Live demonstration: An IoT smartwatch-based system for intensive care monitoring,” 2017 IEEE Biomedical Circuits and Systems Conference (BioCAS), IEEE, 2017.
Search in Google Scholar Back to article
Zilani K. A., et al., “R3 HMS, An IoT Based Approach for Patient Health Monitoring,” 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), IEEE, 2018.
Search in Google Scholar Back to article
Alshammari Hamoud H., “The internet of things healthcare monitoring system based on MQTT protocol”. Alexandria Engineering Journal, Volume 69, 2023, Pages 275–287, ISSN 1110-0168, https://doi.org/10.1016/j.aej.2023.01.065.
Search in Google Scholar Back to article
Maxim Integrated. MAX30100 Pulse Oximeter and Heart-Rate Sensor IC for Wearable Health, Rev 0 (2014), https://datasheets.maximintegrated.com/en/ds/MAX30100.pdf
Search in Google Scholar Back to article
Kaur A., and Jasuja A., “Health monitoring based on IoT using Raspberry Pi”. 2017, International Conference on Computing, Communication and Automation (ICCCA), 1335–1340. doi: 10.1109/CCAA.2017.8230004
Open DOI Search in Google Scholar Back to article
Basu S., Saha S., Pandit S., and Barman S., “Smart health monitoring system for temperature, blood oxygen saturation, and heart rate sensing with embedded processing and transmission using IoT platform,” Computational Intelligence in Pattern Recognition: Proceedings of CIPR 2019, Springer Singapore, https://doi.org/10.1007/978-981-13-9042-5_8
Search in Google Scholar Back to article
Basu S., Ghosh M., and Mandal S. B., “Intelligent remote health monitoring system,” International Journal of Information Technology, Communications and Convergence (IJITCC), vol. 3, no. 4, pp. 259–275, https://doi.org/10.1504/IJITCC.2020.112453
Search in Google Scholar Back to article
Basu S., Ghosh M., and Barman S., “Raspberry PI 3B+ based smart remote health monitoring system using IoT platform,” Proceedings of the 2nd International Conference on Communication, Devices and Computing: ICCDC 2019, Springer Singapore, https://doi.org/10.1007/978-981-15-0829-5_46
Search in Google Scholar Back to article
Jana J., Basu S., Tripathi S., Chakrabarti A., and Bhaumik J., “Design and Implementation of IoT-Based System for Tracking and Monitoring of Suspected COVID-19 Patient,” Advances in VLSI and Embedded Systems: Select Proceedings of AVES 2021, Springer Nature Singapore, doi:10.1007/978-981-19-6780-1_14
Open DOI Search in Google Scholar Back to article
Jana J., Tripathi S., Bhattacharya A., Chowdhury R. S., Karmakar A., Ranjan D., and Bhaumik J., “An Android-Application-Controlled Car for Human Safety Against COVID-19,” Internet of Things and Its Applications: Select Proceedings of ICIA 2020, Springer Nature Singapore, 2022.
Search in Google Scholar Back to article
Chooruang K., and Mangkalakeeree P., “Wireless Heart Rate Monitoring System Using MQTT,” Procedia Computer Science, vol. 86, pp. 160–163, 2016.
Search in Google Scholar Back to article
Hussain H. M., Benkrid K., and Seker H., “An adaptive implementation of a dynamically reconfigurable K-nearest neighbour classifier on FPGA,” 2012 NASA/ESA Conference on Adaptive Hardware and Systems (AHS), pp. 205–212, June 2012.
Search in Google Scholar Back to article
Vieira J., Duarte R. P., and Neto H. C., “knnstuff: knn streaming unit for fpgas,” IEEE Access, vol. 7, pp. 170 864–170 877, 2019.
Search in Google Scholar Back to article
Samiee A., Huang Y., and Bai Y., “Frldm: Empowering K-nearest neighbor (knn) through FPGA-based reduced-rank local distance metric,” 2018 IEEE International Conference on Big Data (Big Data), pp. 4742–4746, Dec 2018.
Search in Google Scholar Back to article
Danopoulos D., Kachris C., and Soudris D., “FPGA acceleration of approximate knn indexing on high-dimensional vectors,” 2019 14th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC), pp. 59–65, July 2019.
Search in Google Scholar Back to article
Wang L-H, Hsiao Y-M, Xie X-Q and Lee S-Y, “An Outdoor Intelligent Healthcare Monitoring Device for the Elderly”, IEEE Trans. on Consumer Electronics, vol. 62, no. 2, pp. 128–135, May 2016.
Search in Google Scholar Back to article
Bharadwaj H. K., et al., “A Review on the Role of Machine Learning in Enabling IoT Based Healthcare Applications,” in IEEE Access, vol. 9, pp. 38859–38890, 2021, doi: 10.1109/ACCESS.2021.3059858.
Open DOI Search in Google Scholar Back to article
Mullick A., and Senguptta S., “Machine Learning-Based Analysis of IoT Healthcare Data: A Review of Contemporary Research,” 2024 International Conference on Computer, Electrical & Communication Engineering (ICCECE), pp. 1–9, 2024.
Search in Google Scholar Back to article
Jha S. K., Sagar S., Kumar R., and Narayan U., “Smart Health Monitoring System – A Comparative Study,” 2023 5th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), pp. 119–124, 2023.
Search in Google Scholar Back to article
Gupta P., et al., “IoT based smart healthcare kit,” 2016 International Conference on Computational Techniques in Information and Communication Technologies (ICCTICT), IEEE, 2016.
Search in Google Scholar Back to article
Vimal S. P., Vadivel M., Baskar V. V., Sivakumar V. G., and Srinivasan C., “Integrating IoT and Machine Learning for Real-Time Patient Health Monitoring with Sensor Networks,” 2023 4th International Conference on Smart Electronics and Communication (ICOSEC), pp. 574–578, 2023.
Search in Google Scholar Back to article
Soni Dipa, and Makwana Ashwin., “A SURVEY ON MQTT: A PROTOCOL OF INTERNET OF THINGS(IOT)”. (ICTPACT – April, 2017).
Search in Google Scholar Back to article
Bhuvana J., Kumar S., Deepa M., Pavithra G., and Anandkumar V., “AI Innovations in IoT and Machine Learning for Health Prediction Systems,” 2023 International Conference on Inventive Computation Technologies (ICICT), pp. 1432–1435, 2023.
Search in Google Scholar Back to article
Orpa Tasnim, Ahnaf Adil, Ovi Tareque, and Rizu Mubdiul, “An IoT Based Intelligent Healthcare Solution With ESP32 Using Machine Learning Model”. (2023). 10.1109/STI56238.2022.10103231
Open DOI Search in Google Scholar Back to article
Maxim Integrated.: DS18B20 Programmable Resolution 1-Wire Digital Thermometer, Rev4(2015), https://datasheets.maximintegrated.com/en/ds/DS18B20.pdf
Search in Google Scholar Back to article
Kumar N, Sharma A, and Singh R, “K-Nearest Neighbor Based Early Warning System for Health Monitoring,” IEEE Transactions on Information Technology in Biomedicine, vol. 24, no. 3, pp. 519–528, May 2020. DOI: 10.1109/TITB.2020.2955478
Open DOI Search in Google Scholar Back to article
Zhang X., Zhao Y., and Li M., “Support Vector Machine-Based Classification of Heart Disease Using Wearable Sensor Data,” IEEE Access, vol. 9, pp. 78465–78475, Jul. 2021. DOI: 10.1109/ACCESS.2021.3085029
Open DOI Search in Google Scholar Back to article
Wang L., Chen Z., and Zhang H., “Decision Tree Approach for Diabetes Prediction in Real-Time Health Monitoring Systems,” IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 4, pp. 1248–1257, Apr. 2021. DOI: 10.1109/JBHI.2021.3051115
Open DOI Search in Google Scholar Back to article
Singh A., and Gupta P. K., “Hybrid Machine Learning Models Using KNN, SVM, and Decision Tree for Wearable Health Monitoring Systems,” IEEE Sensors Journal, vol. 22, no. 5, pp. 4843–4850, Mar. 2022. DOI: 10.1109/JSEN.2022.3142256
Open DOI Search in Google Scholar Back to article
Sokolova S., and Lapalme G., “A Systematic Analysis of Performance Measures for Classification Tasks,” Information Processing & Management, vol. 45, no. 4, pp. 427–437, Jul. 2009. DOI: 10.1016/j.ipm.2009.03.002
Open DOI Search in Google Scholar Back to article
Thingspeak.: IoT Analytics. Accessed on 15.10.2024. https://thingspeak.com
Search in Google Scholar Back to article
PYNQ-Z2 FPGA Board. Datasheet Accessed on 10.11.2024. https://www.amd.com/en/corporate/university-program/aup-boards/pynq-z2.html#specs
Search in Google Scholar Back to article
Zhang X., Xiong Y., and Lin T., “Accelerated Neural Network Inference for Biomedical Signal Processing Using PYNQ-Z2 FPGA,” IEEE Access, vol. 9, pp. 12345–12357, 2021 DOI:10.1109/ACCESS.2021.3059876
Open DOI Search in Google Scholar Back to article
Xiang Y., and Oniga S., “FPGA-Based Hardware Accelerator for EEG Signal Patterns Recognition,” Sensors, vol. 22, no. 5, pp. 1–16, 2024. DOI: 10.3390/s22051475
Open DOI Search in Google Scholar Back to article
Tallapaneni N. S., Jayanthi M. and Venkatesan M., “IoT based Smart Health care system monitoring using Machine Learning Techniques,” 2021 International Conference on System, Computation, Automation and Networking (ICSCAN), Puducherry, India, 2021, pp. 1–6, doi: 10.1109/ICSCAN53069.2021.952644
Open DOI Search in Google Scholar Back to article
K-Nearest Neighbor algorithm: https://github.com/fahadmuslim/KNN; Accessed on 21.07.2025
Search in Google Scholar Back to article
Afifi S., Hosseini H. G., Sinha R., “A system on chip for melanoma detection using FPGA-based SVM classifier”, Microprocessors and Microsystems, Volume 65, 2019, Pages 57–68, ISSN 0141-9331, https://doi.org/10.1016/j.micpro.2018.12.005
Search in Google Scholar Back to article
Laxmisagar H.S., Hanumantharaju M.C, “FPGA implementation of breast cancer detection using SVM linear classifier”. Multimed Tools Appl 82, 41105–41128 (2023). https://doi.org/10.1007/s11042-023-15121-6
Search in Google Scholar Back to article
Mhaouch A., Gtifa W., Machhout M., “FPGA Hardware Acceleration of AI Models for Real-Time Breast Cancer Classification”. AI. 2025; 6(4):76. https://doi.org/10.3390/ai6040076
Search in Google Scholar Back to article

Edge-based intelligent and smart health monitoring on PYNQ-Z2 using lightweight protocol and integration of machine learning models

Abstract

Paradigm

My account