Authors

Chigozi Wali

Department of Computer Science, Rivers State University, Port Harcourt, Nigeria

Onate Taylor

Department of Computer Science, Rivers State University, Port Harcourt, Nigeria

Victor Emmah

Department of Computer Science, Rivers State University, Port Harcourt, Nigeria

Abstract

Ubiquitous healthcare monitoring systems generate continuous streams of sensitive patient data from wearable sensors, mobile devices, and Internet of Medical Things environments, but existing privacy approaches often protect isolated stages of the data lifecycle while leaving analytical processing, adaptive parameter selection, and patient transparency insufficiently addressed. This paper developed a privacy-preserving model for ubiquitous healthcare monitoring systems by integrating sensitivity-guided data masking, adaptive differential privacy, unified lifecycle policy enforcement, and a Flask-based privacy transparency dashboard. The model classified health attributes as highly sensitive, moderately sensitive, or routine, masked attributes whose disclosure risk met the selected threshold, and applied context-aware differential privacy using epsilon values of 0.5 for highly sensitive attributes, 3.0 for moderately sensitive attributes, and 2.0 for routine attributes. A policy engine coordinated protection across collection, transmission, storage, and analysis stages, while the dashboard presented protection status, sensitivity summaries, privacy metrics, policy settings, and lifecycle audit records. The system was implemented in Python and evaluated using three public healthcare datasets: Diabetes Health, Heart Disease, and Physical Activity. Results showed that the proposed model achieved 100.00% re-identification resistance for Diabetes Health, 98.89% for Heart Disease, and 100.00% for Physical Activity, exceeding the 95% privacy target across all datasets. Analytical accuracy retention was 95.03%, 90.52%, and 93.88%, respectively, while relative mean absolute error remained below 10% for all datasets. Processing time stayed below two seconds per 1,000 records and peak memory consumption remained far below the 4 GB threshold. The findings demonstrate that combining data masking, adaptive differential privacy, policy enforcement, and dashboard transparency can provide strong privacy protection while preserving useful analytical value for healthcare monitoring data.

Keywords

Ubiquitous Healthcare Monitoring Internet of Medical Things Data Masking Adaptive Differential Privacy Privacy Policy Engine Privacy Transparency Dashboard Re-Identification Resistance

Citation of this Article

Chigozi Wali, Onate Taylor, & Victor Emmah. (2026). A Technique for Privacy-Preservation in Ubiquitous Healthcare Monitoring. Journal of Artificial Intelligence and Emerging Technologies (JAIET). 3(9), 10-19. Article DOI: https://doi.org/10.47001/JAIET/2026.309002 

Licence Copyright (c) 2026 Journal of Artificial Intelligence and Emerging Technologies. This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International Licence.

References

  1. Pantelopoulos, A., & Bourbakis, N. G. (2010). A survey on wearable sensor-based systems for health monitoring and prognosis. IEEE Transactions on Systems, Man, and Cybernetics, Part C, 40(1), 1-12.
  2. Dias, D., & Cunha, J. P. S. (2018). Wearable health devices: Vital sign monitoring, systems and technologies. Sensors, 18(8), Article 2414. https://doi.org/10.3390/s18082414
  3. Nabha, R., Laouiti, A., & Samhat, A. E. (2025). Internet of Things-based healthcare systems: An overview of privacy-preserving mechanisms. Applied Sciences, 15(7), Article 3629. https://doi.org/10.3390/app15073629
  4. Aboshosha, B. W., Zayed, M. M., Khalifa, H. S., & Ramadan, R. A. (2025). Enhancing Internet of Things security in healthcare using a blockchain-driven lightweight hashing system. Beni-Suef University Journal of Basic and Applied Sciences, 14(1), Article 56. https://doi.org/10.1186/s43088-025-00644-8
  5. Shenoy, D., Bhat, R., & Prakasha, K. K. (2025). Exploring privacy mechanisms and metrics in federated learning. Artificial Intelligence Review, 58(8), Article 223. https://doi.org/10.1007/s10462-025-11170-5
  6. Haripriya, A. P., Khare, N., & Pandey, V. (2025). Privacy-preserving federated learning for collaborative medical data mining in multi-institutional settings. Scientific Reports, 15(1), Article 12482. https://doi.org/10.1038/s41598-025-97565-4
  7. Sifaoui, A., & Eastin, M. S. (2024). “Whispers from the Wrist”: Wearable Health Monitoring Devices and Privacy Regulations in the U.S.: The Loopholes, the Challenges, and the Opportunities. Cryptography, 8(2), 26.
  8. Irshad, R. R., Sohail, S. S., Hussain, S., Madsen, D. O., Zamani, A. S., Ahmed, A. A. A., Alattab, A. A., Badr, M. M., & Alwayle, I. M. (2023). Towards enhancing security of IoT-enabled healthcare system. Heliyon, 9(11), Article e22336. https://doi.org/10.1016/j.heliyon.2023.e22336
  9. Mudassar, B., Tahir, S., Khan, F., Shah, S. A., Shah, S. I., & Abbasi, Q. H. (2024). Privacy-preserving data analytics in Internet of Medical Things. Future Internet, 16(11), Article 407. https://doi.org/10.3390/fi16110407
  10. Kalodanis, K., Feretzakis, G., Anastasiou, A., Rizomiliotis, P., Anagnostopoulos, D., & Koumpouros, Y. (2025). A privacy-preserving and attack-aware AI approach for high-risk healthcare systems under the EU AI Act. Electronics, 14(7), 1385.
  11. Cheon, J. H., Kim, A., Kim, M., & Song, Y. (2017). Homomorphic encryption for arithmetic of approximate numbers. Advances in Cryptology-ASIACRYPT 2017, 409-437.
  12. Fang, M., Cao, X., Jia, J., & Gong, N. (2023). Local model poisoning attacks to Byzantine-robust federated learning. USENIX Security Symposium, 1605-1622.
  13. Kumar, S., Gupta, R., & Singh, A. (2023). Configurable encryption and decryption architectures for CKKS-based homomorphic encryption. Sensors, 23(17), 7389.
  14. Ballhausen, H., Corradini, S., Belka, C., Bogdanov, D., Boldrini, L., Bono, F., Goelz, C., Landry, G., Panza, G., Parodi, K., Talviste, R., Tran, H. E., Gambacorta, M. A., & Marschner, S. (2024). Privacy-friendly evaluation of patient data with secure multiparty computation in a European pilot study. npj Digital Medicine, 7(1), Article 275. https://doi.org/10.1038/s41746-024-01293-4
  15. Naresh, V. S., Raju, A. V., & Rao, O. S. (2025). Secure multiparty computation for privacy-preserving machine learning in healthcare: A comprehensive survey. WIREs Computational Statistics, e70046.
  16. Brückner, S., Dridi, A., Deshmukh, A., Kirsten, T., Lauber-Rönsberg, A., Riedel, R., Hetmank, S., Welzel, C., & Gilbert, S. (2025). A user-driven consent platform for health data sharing in digital health applications. npj Digital Medicine, 8(1), Article 699. https://doi.org/10.1038/s41746-025-02147-3
  17. Kaabachi, B., Despraz, J., Meurers, T., Otte, K., Halilovic, M., Kulynych, B., Prasser, F., & Raisaro, J. L. (2025). A scoping review of privacy and utility metrics in medical synthetic data. npj Digital Medicine, 8, 60.
  18. Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004). Design science in information systems research. MIS Quarterly, 28(1), 75-105. https://doi.org/10.2307/25148625
  19. Peffers, K., Tuunanen, T., Rothenberger, M. A., & Chatterjee, S. (2007). A design science research methodology for information systems research. Journal of Management Information Systems, 24(3), 45-77. https://doi.org/10.2753/MIS0742-1222240302
  20. Booch, G., Rumbaugh, J., & Jacobson, I. (2007). The unified modelling language user guide (2nd ed.). Addison-Wesley.
  21. Sommerville, I. (2016). Software engineering (10th ed.). Pearson.
  22. Van Rossum, G., & Drake, F. L. (2009). Python 3 reference manual. CreateSpace.