Adaptive Neuro-Fuzzy Inference Systems for Predictive Analytics: Opportunities, Challenges, and Future Directions
Keywords:
Adaptive Neuro-Fuzzy Inference System (ANFIS), Fuzzy logic, Hybrid intelligence models, Neural networks, Neuro-adaptive learning, Predictive analytics, Sustainability forecasting, Takagi–Sugeno fuzzy inference modelAbstract
Predictive analytics revolutionizing decision-making in every industry, but traditional models often fail to accommodate uncertainty, nonlinear relationships and the need for visibility. Adaptive Neuro-Fuzzy Inference Systems (ANFIS) is an artificial neural network model combined with the fuzzy logic, which is widely used for predictive analytics due to the fact that it is highly adaptive for learning purposes and easy to understand the relations between the input and output parameters. Formulated from the Takagi– Sugeno fuzzy model, ANFIS uses a five-stage mechanism fuzzification, rule assessment, normalization, defuzzification, and output combination to emulate complicated, under-determined, and or higher order systems and/or systems of nonlinear character and noisy data effectively. It is particularly good at performing tasks such as time series forecasting, classification, regression, and control in various domains. It is observed from literature that ANFIS is very often found to be more effective than conventional models such as ANN and ARIMA in terms of accuracy and flexibility, but its performance is influenced by membership function selection and rule complexity. To be deployed ethically, transparency, bias mitigation, privacy, and accountability need to be considered. Future works are investigating synergy with deep learning, scalability, and explainability. However, ANFIS does have limitations such as high computational cost, rule explosion, and lack of interpretability as the model complexity grows. It aims at connecting human reasoning and machine learning for trustworthy predictions and application, and its practice brings better decision making, adaptable control and green innovation, thought requires careful design and conceptual remedies to prevent the weaknesses.
References
M. N. M. Salleh, N. Talpur, and K. Hussain, “Adaptive Neuro-Fuzzy Inference System: Overview, Strengths, Limitations, and Solutions,” Data Mining and Big Data, pp. 527–535, 2017, doi: https://doi.org/10.1007/978-3-319-61845-6_52
A. Azad, H. Karami, S. Farzin, A. Saeedian, H. Kashi, and F. Sayyahi, “Prediction of Water Quality Parameters Using ANFIS Optimized by Intelligence Algorithms (Case Study: Gorganrood River),” KSCE Journal of Civil Engineering, vol. 22, no. 7, pp. 2206–2213, Sep. 2017, doi: https://doi.org/10.1007/s12205-017-1703-6
A. Chieh, C. Jiang, B. Fan, “Real-time forecasting of COVID-19 spread according to protective behaviour and vaccination: autoregressive integrated moving average models,” BMC Public Health, vol. 23, no. 1, Aug. 2023, doi: https://doi.org/10.1186/s12889-023-16419-8
S. N. Sivanandam, S. Sumathi, and S. N. Deepa, Introduction to Fuzzy Logic using MATLAB. Berlin, Heidelberg: Springer Berlin Heidelberg, 2007. doi: https://doi.org/10.1007/978-3-540-35781-0
S. Haykin, Neural Networks. 1994.
F.-J. Chang and Y.-T. Chang, “Adaptive neuro-fuzzy inference system for prediction of water level in reservoir,” Advances in Water Resources, vol. 29, no. 1, pp. 1–10, Jan. 2006, doi: https://doi.org/10.1016/j.advwatres.2005.04.015
L.-X. Wang and J. M. Mendel, “Generating fuzzy rules by learning from examples,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 22, no. 6, pp. 1414–1427, Nov. 1992, doi: https://doi.org/10.1109/21.199466
J.-S. R. Jang, “ANFIS: adaptive-network-based fuzzy inference system,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 3, pp. 665–685, 1993, doi: https://doi.org/10.1109/21.256541
L. A. Zadeh, “Fuzzy sets,” Information and Control, vol. 8, no. 3, pp. 338–353, Jun. 1965, doi: https://doi.org/10.1016/s0019-9958(65)90241-x
V. Nourani, F. Sadikoglu, and N. J. Paknezhad, “Prediction Intervals for the Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) via the LUBE Method,” Advances in Intelligent Systems and Computing, pp. 1–9, Jan. 2021, doi: https://doi.org/10.1007/978-3-030-68004-6_1
K. Nait Khachat, A. Mesabahi, M. Khafallah, and A. Nouaiti, “Enhancing Energy Consumption Predictions Using ANFIS method,” 2025 5th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), pp. 1–4, May 2025, doi: https://doi.org/10.1109/iraset64571.2025.11008163
S. Palaniappan and R. Awang, “Intelligent heart disease prediction system using data mining techniques,” 2008 IEEE/ACS International Conference on Computer Systems and Applications, Mar. 2008, doi: https://doi.org/10.1109/aiccsa.2008.4493524
N. K. Dewangan, N. Pandey, R. Gautam, A. K. Goswami, “A novel healthcare decision support system using IoT and ANFIS,” International Journal of Information Technology, vol. 16, no. 8, pp. 5421–5427, Aug. 2024, doi: https://doi.org/10.1007/s41870-024-02159-4
N. Talpur, S. J. Abdulkadir, H. Alhussian, M. H. Hasan, N. Aziz, and A. Bamhdi, “A comprehensive review of deep neuro-fuzzy system architectures and their optimization methods,” Neural Computing and Applications, vol. 34, no. 3, pp. 1837–1875, Jan. 2022, doi: https://doi.org/10.1007/s00521-021-06807-9
C. R. Kavitha, M. Varalatchoumy, H. R. Mithuna, K. Bharathi, and N. M. Geethalakshmi, “Energy Monitoring and Control in the Smart Grid,” Advances in Bioinformatics and Biomedical Engineering Book Series, pp. 290–316, Oct. 2023, doi: https://doi.org/10.4018/978-1-6684-6577-6.ch014
A. Subasi, “EEG signal classification using wavelet feature extraction and a mixture of expert model,” Expert Systems with Applications, vol. 32, no. 4, pp. 1084–1093, May 2007, doi: https://doi.org/10.1016/j.eswa.2006.02.005
H. Vitaliyivna Denysyuk et al., “Algorithms for automated diagnosis of cardiovascular diseases based on ECG data: A comprehensive systematic review,” Heliyon, A Cell Press Journals, vol. 9, no. 2, pp. e13601–e13601, Feb. 2023, doi: https://doi.org/10.1016/j.heliyon.2023.e13601
A. Seifi, M. Ehteram, V. P. Singh, and A. Mosavi, “Modeling and Uncertainty Analysis of Groundwater Level Using Six Evolutionary Optimization Algorithms Hybridized with ANFIS, SVM, and ANN,” Sustainability, vol. 12, no. 10, p. 4023, May 2020, doi: https://doi.org/10.3390/su12104023
M. Jafari, H. Ojaghlou, M. Zare, and G. Schumann, “Application of a Novel Hybrid Wavelet-ANFIS/Fuzzy C-Means Clustering Model to Predict Groundwater Fluctuations,” Artificial Intelligence and Machine Learning: Application in Predictive Hydrological Models, vol. 12, no. 1, pp. 9–9, Dec. 2020, doi: https://doi.org/10.3390/atmos12010009
S. Vakili and S. M. Mousavi, “Rainfall-Runoff modeling using adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm (GA),” Water Supply, Sep. 2022, doi: https://doi.org/10.2166/ws.2022.318
A. Kaur, Y. Singh, and L. G., “A Novel ANFIS based Algorithm for Fault Detection in Power Transformers,” International Journal of Computer Applications, vol. 179, no. 12, pp. 34–41, Jan. 2018, doi: https://doi.org/10.5120/ijca2018916142
M. Shirdar et al., “Advanced manufacturing/Mechanical engineering, UTM, Skudai, Malaysia-81310 6 Advanced manufacturing/Mechanical engineering,” Journal of Theoretical and Applied Information Technology, vol. 15, no. 1, p. 81310, 2011, [Online]. Available: https://www.jatit.org/volumes/Vol33No1/10Vol33No1.pdf
A. K. Srivastava and M. M. Islam, “Prediction of tool wear and surface finish using ANFIS modelling during turning of Carbon Fiber Reinforced Plastic (CFRP) composites,” Manufacturing Letters, vol. 41, pp. 658–669, Oct. 2024, doi: https://doi.org/10.1016/j.mfglet.2024.09.084
T. Singh, T. Glory, and P. Sudheerkumar, “Adaptive Neuro-Fuzzy Inference System (ANFIS) for Predicting Stock Market Trends: A Comparison with Traditional Financial Models,” 2024. [Online]. Available: https://jespublication.com/specialissue/2024-V15I11025(S).pdf
J. K. Bharath and V. Deepa, “Stock Market Prediction Using ANFIS Machine Learning Approach,” International Journal of Advance Research and Innovative Ideas in Education, vol. 7, no. 2, pp. 541–546, 2021, [Online]. Available: https://ijariie.com/FormDetails.aspx?MenuScriptId=212752
J. K. Roy and L. Vasa, “Transforming credit risk assessment: A systematic review of AI and machine learning applications,” Journal of Infrastructure Policy and Development, vol. 9, no. 1, pp. 9652–9652, Jan. 2025, doi: https://doi.org/10.24294/jipd9652
B. Van Oostendorp, E. Zander, and B. Bede, “Deep Learning ANFIS Architectures,” Lecture Notes in Networks and Systems, pp. 141–148, Jan. 2023, doi: https://doi.org/10.1007/978-3-031-46778-3_13
