Pemeliharaan Prediktif Berbasis ANFIS untuk Perangkat EKG Portabel Menggunakan Masukan Multi-Sensor

Agus Supriyanto; Arief Marwanto

doi:10.59485/yj0ty525

Authors

Agus Supriyanto Sultan Agung Islamic University
Arief Marwanto Sultan Agung Islamic University

DOI:

https://doi.org/10.59485/yj0ty525

Keywords:

ANFIS, predictive maintenance, portable ECG, multi-sensor

Abstract

The development of portable medical equipment such as Electrocardiograph (ECG) in Type C Hospitals faces significant challenges in terms of preventive maintenance due to limited historical data and the inability of conventional methods to model the non-linear relationship between operational parameters and failure risk. This study proposes a predictive maintenance framework based on Adaptive Neuro-Fuzzy Inference System (ANFIS) with multi-sensor integration that includes temperature, humidity, usage duration, and device age. Synthetic data amounting to 230 samples (30 historical + 200 synthetic) were generated using a sigmoid membership function to overcome data scarcity. The ANFIS model was trained with a 5-layer architecture using a generalized bell membership function and a hybrid algorithm of backpropagation and least squares. The evaluation results showed that the model accuracy reached 98.67% on the test data, with a precision of 92.3%, a recall of 98.2%, and an F1-score of 95.2%. Comparisons with the Mamdani Fuzzy Logistics (96.67%), Random Forest (91.5%), and SVM (88.3%) methods demonstrate the significant superiority of ANFIS in handling complex multivariable data. An AUC value of 0.978 confirms the model's excellent discrimination ability. This framework contributes to the development of adaptive, accurate, and interpretable predictive systems for medical equipment management in resource-constrained healthcare facilities.

Downloads

Download data is not yet available.

References

. Cheol Hui Lee dan Seong Han Kim, “ECG Measurement System for Vehicle Implementation and Heart Disease Classification Using Machine Learning.,” IEEE Access, vol. 4, no. 3, pp. 17968–17982, Mar. 2023.

2. M. Hundur, L. Spahić, F. Bećirović, L. Gurbeta Pokvić, and A. Badnjević, “Advancement of post-market surveillance of medical devices leveraging artificial intelligence: ECG devices case study,” Technology and Health Care, vol. 33, no. 4, pp. 1818–1826, 2025.

3. S. Sabah, M. Moussa, and A. Shamayleh, “Predictive maintenance application in healthcare,” in 2022 Annual Reliability and Maintainability Symposium (RAMS), IEEE, 2022, pp. 1–9.

4. N. R. Nangare, M. Gulhane, J. K. M, N. Rakesh, M. B. Mane, and A. Gupta, “Predictive maintenance of biomedical devices using AI,” in AIP Conference Proceedings, AIP Publishing LLC, 2026, p. 020114.

5. O. Manchadi, F.-E. Ben-Bouazza, and B. Jioudi, “Predictive maintenance in healthcare system: a survey,” IEEE Access, vol. 11, pp. 61313–61330, 2023.

6. Jyh-Shing Roger Jang, “ANFIS: adaptive-network-based fuzzy inference system,” IEEE Trans. Syst. Man Cybern., vol. 23, no. 3, pp. 665–685, 1993.

7. M. , A. M. , A. M. M. , M. W. , A. S. , A. S. A. , S. S. , & B. W. Alqahtani, “An improved salp swarm algorithm (ISSA),” Alexandria Engineering Journal, vol. 3, no. 4, pp. 56–65, Jul. 2025.

8. B. Sadanandan, B. A. Nobar, and V. Behzadan, “Comparative Study of Generative Models for Early Detection of Failures in Medical Devices,” arXiv preprint arXiv:2505.04845, 2025.

9. K. S. I. Camacho, M. L. P. Roque, R. R. P. Vicerra, and N. T. Bugtai, “Predictive Maintenance Algorithm for Machine Failure Using Fuzzy Logic Techniques,” International Exchange and Innovation Conference on Engineering & Sciences, 2025.

10. A. H. Zamzam, K. Hasikin, and A. K. A. Wahab, “Integrated failure analysis using machine learning predictive system for smart management of medical equipment maintenance,” Eng. Appl. Artif. Intell., vol. 125, p. 106715, 2023.

11. P. E. Alfa et al., “A Hybrid SVM-Bayesian-Fuzzy Logic Framework for Predictive Maintenance,” NIPES JSTR SPECIAL ISSUE-PREPRINT PLATFORM, vol. 7, no. 1, pp. 1768–1773, 2025.

12. E. Safikou, K. R. Pattipati, and G. M. Bollas, “Fault diagnosis and prognosis with inferential sensors: a hybrid approach integrating symbolic regression and information theory,” IEEE Access, vol. 13, pp. 78555–78570, 2025.

13. B. Yenisari and S. Seker, “Feasibility of a hybrid ANFIS-PSO model to predict medical waste: case study for Istanbul,” IEEE Access, vol. 13, pp. 148330–148352, 2025.

14. A. Alimuddin, R. Arafiyah, I. Saraswati, R. Alfanz, P. Hasudungan, and T. Taufik, “Development and performance study of temperature and humidity regulator in baby incubator using fuzzy-pid hybrid controller,” Energies (Basel)., vol. 14, no. 20, p. 6505, 2021.

15. M. N. M. Sunny, M. B. H. Sakil, J. Atayeva, Z. S. Munmun, M. S. Mollick, and M. O. Faruq, “Predictive healthcare: An iot-based anfis framework for diabetes diagnosis,” Engineering, vol. 16, no. 10, pp. 325–336, 2024.

16. R. Jeya, H. B. A. Karim, B. Muruganantham, S. B. Mansor, and T. Y. Fei, “Soft Computing-Based Heart Disease Prediction Framework (SC-HDP) Using ANFIS,” Journal of Internet Services and Information Security (JISIS), vol. 16, no. 2, pp. 227–244, 2026.

17. C. K. Lau, K. Ghosh, M. A. Hussain, and C. R. C. Hassan, “Fault diagnosis of Tennessee Eastman process with multi-scale PCA and ANFIS,” Chemometrics and Intelligent Laboratory Systems, vol. 120, pp. 1–14, 2013.

18. S. Patnaik, “Design of ANFIS Based E-Health Care System for Cardio Vascular Disease Detection,” 2017.

19. L. Sarangi, M. N. Mohanty, and S. Patnaik, “Design of ANFIS based e-health care system for cardio vascular disease detection,” in International Conference on Intelligent and Interactive Systems and Applications, Springer, 2016, pp. 445–453.

20. M. A. Khan and F. Algarni, “A healthcare monitoring system for the diagnosis of heart disease in the IoMT cloud environment using MSSO-ANFIS,” IEEE access, vol. 8, pp. 122259–122269, 2020.

21. M. G. K. , T. L. K. , & B. F. C. Machesa, “Predicting Oscillatory Heat Transfer Coefficient in Thermoacoustic Refrigerators Using Hybrid ANFIS-PSO and ANFIS-GA Models.,” in In ASME 2025 International Mechanical Engineering Congress and Exposition, Volume 8: Heat Transfer and Thermal Engineering; Mechanics of Solids, Structures and Fluids. American Society of Mechanical Engineers. V008T12A034., Washington: ASME, Apr. 2025, pp. 3–15.

22. R. K. Jha et al., “Neural Fuzzy Hybrid Rule‐Based Inference System with Test Cases for Prediction of Heart Attack Probability,” Math. Probl. Eng., vol. 2022, no. 1, p. 3414877, 2022.

23. A. B. , S. S. , & A. A. Makokha, “A Comparative Study of Hybridized Machine Learning Models for Short-Term Load Prediction in Medium-Voltage Electricity Networks.,” Electricity, vol. 7, no. 1, p. 21, Jun. 2026.