Issue

Vol. 11, No. 3, August 2026 (Article in Progress)

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

A Memory-Efficient and Gradient-Stable Lightweight ANFIS for Real-Time Humidity Prediction in Precision Agriculture

https://doi.org/10.22219/kinetik.v11i3.2700
Eddy Nurraharjo
Universitas Amikom Yogyakarta
Ema Utami
Universitas Amikom Yogyakarta
Kusrini
Universitas Amikom Yogyakarta
Kumara Ari Yuana
Universitas Amikom Yogyakarta

Corresponding Author(s) : Eddy Nurraharjo

eddynurraharjo@students.amikom.ac.id

Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, Vol. 11, No. 3, August 2026 (Article in Progress)

Abstract

Precision agriculture demands artificial intelligence solutions that are both accurate and deployable on resource-constrained hardware, yet conventional machine learning models require excessive memory while traditional ANFIS architectures suffer from training instability. This study developed a memory-efficient and gradient-stable lightweight Adaptive Neuro-Fuzzy Inference System (ANFIS) for real-time humidity prediction on microcontroller-class devices. The proposed architecture strategically reduced the rule base from 27 to only 4 interpretable fuzzy rules and limited membership functions to two per input, achieving an 85.2% reduction in learnable parameters. A gradient-stable training mechanism was introduced, combining physics-informed parameter initialization with adaptive gradient clipping to prevent gradient explosion. The model was trained and validated using 31,474 real-world greenhouse samples collected over 218 days, with 80% allocated for training and 20% for temporal testing. Experimental results demonstrated that the gradient-stable architecture successfully converged from a catastrophic R² of -64.08 to 0.9148, with a root mean square error of 1.32% and mean absolute error of 1.05%. The model required only 0.211 KB of memory, representing a 99.9% reduction compared to baseline Random Forest models, while achieving inference time of 8.2 milliseconds on Arduino UNO. The system was successfully deployed on three independent hardware modules, maintaining consistent performance with average RMSE of 1.99% over 168 hours of continuous operation. This study concludes that strategic simplification and stability-aware training enable interpretable neuro-fuzzy systems to operate effectively on ultra-low-resource devices, bridging the gap between predictive accuracy and hardware feasibility in embedded agricultural IoT applications.

Keywords

Agricultural IoT Embedded AI Humidity Prediction Lightweight ANFIS Resource-Constrained Devices
Nurraharjo, E., Utami, E., Kusrini, & Ari Yuana, K. (2026). A Memory-Efficient and Gradient-Stable Lightweight ANFIS for Real-Time Humidity Prediction in Precision Agriculture . Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 11(3). https://doi.org/10.22219/kinetik.v11i3.2700
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
References
  1. M. J. Navarro, J. Carrasco, and F. J. Gea, “The role of water content in the casing layer for mushroom crop production and the occurrence of fungal diseases,” Agronomy, vol. 11, no. 10, Oct. 2021, doi: 10.3390/agronomy11102063.
  2. S. Adebayo, H. O. Aworinde, O. O. Olufemi, C. O. Osueke, A. E. Adeniyi, and O. Julius Aroba, “Understanding mushroom farm environment using TinyML-based monitoring devices,” Environ Res Commun, vol. 7, no. 4, Apr. 2025, doi: 10.1088/2515-7620/adc5cd.
  3. M. Rukhiran, C. Sutanthavibul, S. Boonsong, and P. Netinant, “IoT-Based Mushroom Cultivation System with Solar Renewable Energy Integration: Assessing the Sustainable Impact of the Yield and Quality,” Sustainability (Switzerland), vol. 15, no. 18, Sep. 2023, doi: 10.3390/su151813968.
  4. H. H. Nguyen, D. Y. Shin, W. S. Jung, T. Y. Kim, and D. H. Lee, “An Integrated IoT Sensor-Camera System toward Leveraging Edge Computing for Smart Greenhouse Mushroom Cultivation,” Agriculture (Switzerland), vol. 14, no. 3, Mar. 2024, doi: 10.3390/agriculture14030489.
  5. D. I. Săcăleanu, M. G. Matache, Ștefan G. Roșu, B. C. Florea, I. P. Manciu, and L. A. Perișoară, “IoT-Enhanced Decision Support System for Real-Time Greenhouse Microclimate Monitoring and Control,” Technologies (Basel), vol. 12, no. 11, Nov. 2024, doi: 10.3390/technologies12110230.
  6. M. H. Lee, M. H. Yao, P. Y. Kow, B. J. Kuo, and F. J. Chang, “An Artificial Intelligence-Powered Environmental Control System for Resilient and Efficient Greenhouse Farming,” Sustainability (Switzerland), vol. 16, no. 24, Dec. 2024, doi: 10.3390/su162410958.
  7. T. H. Chen, M. H. Lee, I. W. Hsia, C. H. Hsu, M. H. Yao, and F. J. Chang, “Develop a Smart Microclimate Control System for Greenhouses through System Dynamics and Machine Learning Techniques,” Water (Switzerland), vol. 14, no. 23, Dec. 2022, doi: 10.3390/w14233941.
  8. S. Bellahirich, D. Mezghani, and A. Mami, “Design and implementation of an intelligent anfis controller on a raspberry pi nano-computer for photovoltaic pumping intended for drip irrigation,” Energies (Basel), vol. 14, no. 17, Sep. 2021, doi: 10.3390/en14175217.
  9. M. Mardani Najafabadi, A. Mirzaei, H. Azarm, and S. Nikmehr, “Managing Water Supply and Demand to Achieve Economic and Environmental Objectives: Application of Mathematical Programming and ANFIS Models,” Water Resources Management, vol. 36, no. 9, pp. 3007–3027, Jul. 2022, doi: 10.1007/s11269-022-03178-1.
  10. M. E. Akiner and M. Ghasri, “Comparative assessment of deep belief network and hybrid adaptive neuro-fuzzy inference system model based on a meta-heuristic optimization algorithm for precise predictions of the potential evapotranspiration,” Environmental Science and Pollution Research, vol. 31, no. 30, pp. 42719–42749, Jun. 2024, doi: 10.1007/s11356-024-33987-3.
  11. H. Hamidane et al., “Application analysis of ANFIS strategy for greenhouse climate parameters prediction: Internal temperature and internal relative humidity case of study,” in E3S Web of Conferences, EDP Sciences, Sep. 2021. doi: 10.1051/e3sconf/202129701041.
  12. H. J. Ma, X. B. Jin, Z. M. Li, and Y. T. Bai, “Fuzzy adaptive-normalized deep encoder-decoder network: Medium and long-term predictor of temperature and humidity in smart greenhouses,” Comput Electron Agric, vol. 226, Nov. 2024, doi: 10.1016/j.compag.2024.109480.
  13. C. E. Lachouri, K. Mansouri, and M. M. Lafifi, “Greenhouse Climate Modeling Using Fuzzy Neural Network Machine Learning Technique,” Revue d’Intelligence Artificielle, vol. 36, no. 6, pp. 925–930, Dec. 2022, doi: 10.18280/ria.360614.
  14. B. van Oostendorp, E. Zander, and B. Bede, “Deep Learning ANFIS Architectures,” in Fuzzy Information Processing 2023, K. Cohen, N. Ernest, B. Bede, and V. Kreinovich, Eds., Cham: Springer Nature Switzerland, 2023, pp. B. van Oostendorp, E. Zander, and B. Bede, “Deep Learning ANFIS Architectures,” in Fuzzy Information Processing 2023, K. Cohen, N. Ernest, B. Bede, and V. Kreinovich, Eds., Cham: Springer Nature Switzerland, 2023, pp. 141–148. doi: 10.1007/978-3-031-46778-3_13.
  15. Ahmad Abu Hanifah, Eni Sumarni, Ardiansyah, and Yeny Pusvyta, “Performance Comparison of Adaptive Neuro-Fuzzy Inference System (ANFIS) and Fuzzy Logic Based Microclimate Control System in Plant Factory,” Jurnal Keteknikan Pertanian, vol. 13, no. 2, pp. 340–361, Jul. 2025, doi: https://doi.org/10.19028/jtep.013.2.340-361.
  16. S. J. Soheli, N. Jahan, M. B. Hossain, A. Adhikary, A. R. Khan, and M. Wahiduzzaman, “Smart Greenhouse Monitoring System Using Internet of Things and Artificial Intelligence,” Wirel Pers Commun, vol. 124, no. 4, pp. 3603–3634, Jun. 2022, doi: 10.1007/s11277-022-09528-x.
  17. P. Kitcharoen, S. Chookaew, and S. Howimanporn, “Implementation of an AIoT-Based Intelligent Water Resources Control System for Smart Farm,” IEEE Access, vol. 12, pp. 156878–156892, 2024, doi: 10.1109/ACCESS.2024.3482088.
  18. M. A. M. Ariffin et al., “Enhanced iot-based climate control for oyster mushroom cultivation using fuzzy logic approach and nodemcu microcontroller,” Pertanika J Sci Technol, vol. 29, no. 4, pp. 2863–2885, Oct. 2021, doi: 10.47836/PJST.29.4.34.
  19. A. Al-Ali and U. Qidwai, “Rule-Based Modeling of Low-Dimensional Data with PCA and Binary Particle Swarm Optimization (BPSO) in ANFIS,” Feb. 2025, doi: 10.48550/arXiv.2502.03895.
  20. R. Raj and M. M. Bosukonda, “Mathematical Modelling and Analysis of the Simplest Fuzzy TwoInput Two-Output Two-Term Controller of Takagi−Sugeno Type,” Fuzzy Information and Engineering, vol. 15, no. 1, pp. 36–54, Mar. 2023, doi: 10.26599/FIE.2023.9270004.
  21. D. Wu, “MBGD-RDA Training and Rule Pruning for Concise TSK Fuzzy Regression Models,” Mar. 2020, doi: 10.48550/arXiv.2003.00608.
  22. Z. Shi, D. Wu, C. Guo, C. Zhao, Y. Cui, and F. Y. Wang, “FCM-RDpA: TSK fuzzy regression model construction using fuzzy C-means clustering, regularization, Droprule, and Powerball Adabelief,” Inf Sci (N Y), vol. 574, pp. 490–504, Oct. 2021, doi: 10.1016/j.ins.2021.05.084.
  23. Y. Lu, W. Li, and H. Wang, “A Batch Variable Learning Rate Gradient Descent Algorithm with the Smoothing L1/2 Regularization for Takagi-Sugeno Models,” IEEE Access, vol. 8, pp. 100185–100193, 2020, doi: 10.1109/ACCESS.2020.2997867.
  24. W. F. Gemechu and W. Sitek, “Application of Adaptive Neuro-Fuzzy Inference System models in estimating steel hardenability,” Journal of Achievements in Materials and Manufacturing Engineering, vol. 127, no. 2, pp. 49–59, Dec. 2024, doi: 10.5604/01.3001.0054.9783.
  25. M. Babanezhad, A. T. Nakhjiri, A. Marjani, and S. Shirazian, “Pattern recognition of the fluid flow in a 3D domain by combination of Lattice Boltzmann and ANFIS methods,” Sci Rep, vol. 10, no. 1, Dec. 2020, doi: 10.1038/s41598-020-72926-3.
  26. A. Sahoo, M. Bar, S. Bhattacharya, and S. Baitalik, “Impact of Membership Functions on the Performance of AI-Assisted Neuro-Fuzzy System for Analysis of Anion-Responsive Behaviours of Polypyridyl-Imidazole Based Ru(II) Receptors,” Chem Asian J, vol. 20, no. 6, p. e202401346, Mar. 2025, doi: https://doi.org/10.1002/asia.202401346.
  27. P. Zanineli, M. Z. Monteiro, V. Wasques, F. S. P. Simões, and G. Schleder, “Fuzzy Neural Network Performance and Interpretability of Quantum Wavefunction Probability Predictions,” p., 2025, doi: 10.48550/arXiv.2511.05261.
  28. A. Abdurohman, M. Siregar, C. Olivia Sereati, S. Windasari, and MM. L. W. Pandjaitan, “Implementation and Analysis of Fuzzy Inference System (FIS) and Adaptive Neuro-Fuzzy Inference System (ANFIS) for Irrigation,” International Journal of Engineering Continuity, vol. 4, no. 1, pp. 210–231, Aug. 2025, doi: 10.58291/ijec.v4i1.399.
  29. R. Saatchi, “Fuzzy Logic Concepts, Developments and Implementation,” Information (Switzerland), vol. 15, no. 10, Oct. 2024, doi: 10.3390/info15100656.
  30. Dr. M. Kalpana, Dr. B. Sivasankari, Dr. P. Prema, and Dr. R. Vasanthi, “Rice yield prediction using adaptive Neuro-fuzzy inference system (ANFIS),” Int J Chem Stud, vol. 8, no. 1, pp. 1638–1640, Jan. 2020, doi: 10.22271/chemi.2020.v8.i1x.8497.
  31. M. F. R. Juston, S. R. Dekhterman, W. R. Norris, D. Nottage, and A. Soylemezoglu, “Hierarchical Rule-Base Reduction-Based ANFIS With Online Optimization Through DDPG,” IEEE Transactions on Fuzzy Systems, vol. 32, no. 11, pp. 6350–6362, 2024, doi: 10.1109/TFUZZ.2024.3449147.
  32. J. Blanchet, P. Cui, J. Li, and J. Liu, “Stability Evaluation via Distributional Perturbation Analysis,” May 2024, doi: 10.48550/arXiv.2405.03198.
  33. Anindita A Khade, Dhaval K Powle, and Gaurav M Keshari, “A Novel Technique for Chronic Kidney Disease Prediction using Glowworm Swarm Algorithm with Adaptive Neuro Fuzzy Inference System,” Journal of Electronics, Electromedical Engineering, and Medical Informatics, vol. 7, no. 2, pp. 391–403, Apr. 2025, doi: https://doi.org/10.35882/jeeemi.v7i2.623.
  34. M. Mamuda and S. Sathasivam, “The development of Adaptive Neuro-Fuzzy Inference System model to diagnosis diabetes disease data set,” 2017. doi: 10.11113/matematika.v33.n1.957.
  35. N. Lazarieva, “Parametric Optimization of the Hierarchical Fuzzy Model of Control with Transfer of Fuzzy Values of Intermediate Data,” Electronics and Control Systems, p., 2025, doi: 10.18372/1990-5548.84.20190.
  36. S. Troha, M. Milovančević, and A. Dimov, “Adaptive Neuro-Fuzzy Optimization for Enhanced Precision in Laser Micro-Machining Operations,” Journal of Engineering Management and Systems Engineering, vol. 2, no. 2, pp. 134–139, Jun. 2023, doi: 10.56578/jemse020205.
  37. A. Bansal, K. Balaji, and Z. Lalani, “Temporal Encoding Strategies for Energy Time Series Prediction,” Mar. 2025, doi: 10.48550/arXiv.2503.15456.
  38. L. Semmelmann, O. Resch, S. Henni, and C. Weinhardt, “Privacy-preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering,” IET Smart Grid, vol. 7, no. 2, pp. 172–185, Apr. 2024, doi: 10.1049/stg2.12137.
  39. N. Alkhulaifi et al., “Machine Learning Pipeline for Energy and Environmental Prediction in Cold Storage Facilities,” IEEE Access, vol. 12, pp. 153935–153951, 2024, doi: 10.1109/ACCESS.2024.3482572.
  40. K. Zhang, W. Hao, X. Yu, and T. Shao, “A Symmetrical Fuzzy Neural Network Regression Method Coordinating Structure and Parameter Identifications for Regression,” Symmetry (Basel), vol. 15, no. 9, Sep. 2023, doi: 10.3390/sym15091711.
  41. P. D. Bharathi, A. N. Velu, and B. S. Palaniappan, “Design and Enhancement of a Fog-Enabled Air Quality Monitoring and Prediction System: An Optimized Lightweight Deep Learning Model for a Smart Fog Environmental Gateway,” Sensors, vol. 24, no. 15, Aug. 2024, doi: 10.3390/s24155069.
  42. S. Kumar Vishwakarma and V. Kumar, “Hybrid SNN-ANFIS Framework for Predicting Crop Yields Under Climate Change Scenarios: a Case Study of Maharashtra, India,” 2025. doi: 10.64252/2ybpa102.
  43. Y. Ren, Y.-C. Chang, T. Do, Z. Cao, and C.-T. Lin, “A Self-Constructing Multi-Expert Fuzzy System for High-dimensional Data Classification.” doi: 10.48550/arXiv.2410.13390.
  44. Y. Hang, X. Meng, and Q. Wu, “Application of Improved Lightweight Network and Choquet Fuzzy Ensemble Technology for Soybean Disease Identification,” IEEE Access, vol. 12, pp. 25146–25163, 2024, doi: 10.1109/ACCESS.2024.3365829.
  45. M. Hassan and E. Beshr, “Predicting soil cone index and assessing suitability for wind and solar farm development in using machine learning techniques,” Sci Rep, vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-52702-3.
  46. R. Maurya, S. Mahapatra, and L. Rajput, “A Lightweight Meta-Ensemble Approach for Plant Disease Detection Suitable for IoT-Based Environments,” IEEE Access, vol. 12, pp. 28096–28108, 2024, doi: 10.1109/ACCESS.2024.3367443.
Read More
Author biographies is not available.
Download this PDF file
Statistic
Read Counter : 0

Downloads

Download data is not yet available.