Development of the basic module of the fuzzy artmap algorithm in operating systems for decision making and intelligent data analysis
DOI:
https://doi.org/10.15276/opu.2.72.2025.15Keywords:
machine learning, classification and clustering algorithms, artificial neural fuzzy inverse systems (ANFIS), operating systems (OS), input vector normalization, preprocessing, postprocessing, network learning speed, complementation method, similarity criterion, data fuzzificationAbstract
In decision support systems for organizational management, simple and understandable models are often used in practice, such as decision-making rules based on well-known fuzzy logic methods, linear or logistic regression, and classification and regression tree methods. The value and practical significance of such algorithms lie in their important ability to understand and explain their internal decision-making logic, but their disadvantage is their low accuracy. More accurate neural network algorithms, as a rule, do not have the property of interpretability. However, the algorithm proposed in this study combines a sufficiently high accuracy in the analysis of monitoring information and, at the same time, it explains the resulting decisions well. ART neural networks are best suited for developing methods and algorithms for intelligent support of management decision-making when processing monitoring information, as they are characterized by stable and fast data attribution, and at the same time are flexible for storing new information. Based on the use of ART family networks, a general approach to solving monitoring data clustering problems has been proposed. Since a well-known disadvantage of ART family networks is their dependence on the initial initialization of hyperparameters, the type and nature of this dependence in monitoring data clustering problems have been investigated. A genetic algorithm has been proposed for the automatic tuning of the hyperparameters of the Fuzzy ARTMAP network in order to overcome this drawback. Such an algorithm allows for the improvement of methods for obtaining and processing information for organizational system management tasks. Since monitoring information can generate large data flows, an algorithm for using an ensemble of Fuzzy ARTMAP networks for parallel processing and structuring of stream data is proposed. Parallel and high-performance computing technology is developing, and computing resources are becoming increasingly accessible, new opportunities are emerging for parallelizing neural network models in terms of better processing of calculations and increasing the intensity of data processing, and, consequently, increasing the speed of management decisions based on operational data, which is especially important in management tasks in organizational systems. This article develops and investigates an algorithm for training a Fuzzy ARTMAP network to solve classification problems in conditions of overlapping classes. Such a task often arises when analyzing monitoring information in management decision support systems, since noise and errors often occur when collecting operational data, which blurs the boundaries between the classes into which the values of the input monitoring indicators are divided. A modified selection function that provides such classification is proposed for this algorithm, and its properties are mathematically justified.
Downloads
References
Amis, G. P., & Carpenter, G. A. (2010). Self-supervised ARTMAP. Neural Networks, 23, 265–282.
Brito da Silva, L. E., Elnabarawy, I., & Wunsch, D. C., 2nd. (2019). Dual vigilance fuzzy adaptive resonance theory. Neural Networks, 109, 1–5.
Nandwani, P., & Verma, R. (2021). A review on sentiment analysis and emotion detection from text. Social Network Analysis and Mining, 11(81). https://doi.org/10.1007/s13278-021-00776-6.
Carpenter, G. A., Grossberg, S., Markuzon, N., Reynolds, J. H., & Rosen, D. B. (1992). Fuzzy ARTMAP: An adaptive resonance architecture for incremental learning of analog maps. Proceedings of the International Joint Conference on Neural Networks, 1992.
Acheampong, F. A., Wenyu, C., & Nunoo-Mensah, H. (2020). Text-based emotion detection: Advances, challenges, and opportunities. Engineering Reports. https://doi.org/10.1002/eng2.12189.
Maruf, A. A., Khanam, F., Haque, M. M., Jiyad, Z. M., Mridha, M. F., & Aung, Z. (2024). Challenges and opportunities of text-based emotion detection: A survey. IEEE Access, 12, 18416–18450. https://doi.org/10.1109/ACCESS.2024.3356357.
Chu, K. L., Liew, W., Seera, M., & Lim, E. (2014). Probabilistic ensemble Fuzzy ARTMAP optimization using hierarchical parallel genetic algorithms. Neural Computing and Applications, 26, 263–276.
French, R. M. (1999). Catastrophic forgetting in connectionist networks. Trends in Cognitive Sciences, 3, 128–135.
Acheampong, F. A., Nunoo-Mensah, H., & Chen, W. (2021). Transformer models for text-based emotion detection: A review of BERT-based approaches. Artificial Intelligence Review, 54, 5789–5829. https://doi.org/10.1007/s10462-021-09958-2.
Zhang, X., Mao, R., & Cambria, E. (2024). Multilingual emotion recognition: Discovering the variations of lexical semantics between languages. International Joint Conference on Neural Networks (IJCNN), 1–9. https://doi.org/10.1109/IJCNN60899.2024.10651409.
Ghosh, J., & Acharya, A. (2011). Cluster ensembles. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1(4), 305–315.
Grossberg, S. (2019). The resonant brain: How attentive conscious seeing regulates action sequences that interact with attentive cognitive learning, recognition, and prediction. Attention, Perception, & Psychophysics, 81, 2237–2264.
De León Languré, A., & Zareei, M. (2024). Improving text emotion detection through comprehensive dataset quality analysis. IEEE Access, 12, 70489–70500. https://doi.org/10.1109/ACCESS.2024.3491856.
Kharchenko, V., Fesenko, H., & Illiashenko, O. (2022). Quality models for artificial intelligence systems: Characteristic-based approach, development and application. Sensors, 22(13), 4865. https://doi.org/10.3390/s22134865.
Marco, V., Taylor, B., Wang, Z., & Elkhatib, Y. (2020). Optimizing deep learning inference on embedded systems through adaptive model selection. ACM Transactions on Embedded Computing Systems, 19(1), 1–28. https://doi.org/10.1145/3371154.
Haupt, S. E., Pasini, A., & Marzban, C. (2009). Environmental optimization: Applications of genetic algorithms. In Artificial Intelligence Methods in the Environmental Sciences (pp. 379–395).
Keskin, G. A., & Ozkan, C. (2009). An alternative evaluation of FMEA: Fuzzy ART algorithm. Quality and Reliability Engineering International, 25(6), 647–661.
Kirkpatrick, J., Pancanu, R., Rabinowitz, N., Veness, J., Desjarkins, G., Rusu, A. A., ... & Hadsell, R. (2017). Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences, 114, 3521–3526.
Kuncheva, L. I., & Whitaker, C. J. (2003). Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Machine Learning, 51, 181–207.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444.
Massey, L. (2005). Real-world text clustering with adaptive resonance theory neural networks. Proceedings of 2005 International Joint Conference on Neural Networks.
Martinez-Zarzuela, M., Diaz Pernas, F. J., Diez Higuera, J. F., & Rodriguez, M. A. (2007). Fuzzy ART neural network parallel computing on the GPU. In Computational and Ambient Intelligence (pp. 463–470).
Meng, L., Tan, A.-H., & Wunsch, D. C. (2013). Vigilance adaptation in adaptive resonance theory. 2013 IEEE International Joint Conference on Neural Networks (IJCNN), 1–7.
Oong, T. H., & Isa, N. A. M. (2014). Feature-based ordering algorithm for data presentation of Fuzzy ARTMAP ensembles. IEEE Transactions on Neural Networks and Learning Systems, 25, 812–819.
Rosenberg, A., & Hirschberg, J. (2007). Detecting pitch accent using pitch-corrected energy-based predictors. Interspeech 2007, 2777–2780.
Rousseeuw, P. J. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53–65.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
Seto, K. C., & Liu, W. (2003). Comparing ARTMAP neural network with the maximum-likelihood classifier for detecting urban change. Photogrammetric Engineering & Remote Sensing, 69(9), 981–990.
Solyanik, S. A., & Kravets, O. J. (2020). Development of distributed management complexes for territorial information systems data flows. Science Book Publishing House LLC.
Skovajsova, L., & Rojcek, M. (2011). Soft clustering algorithms based on neural networks. 2011 IEEE 12th International Symposium on Computational Intelligence and Informatics, 439–442.
Wasserman, P. D. (1989). Neural computing: Theory and practice. Van Nostrand Reinhold Co.
Versace, M., Kozma, R. T., & Wunsch, D. C. (2012). Adaptive resonance theory design in mixed memristive-fuzzy hardware. In Advances in Neuromorphic Memristor Science and Applications (pp. 133–153).
Xu, R., & Wunsch, D. C., 2nd. (2005). Survey of clustering algorithms. IEEE Transactions on Neural Networks, 16(3), 645–678.
Zhang, X., Nakhai, M. R., Zheng, G., Lambotharan, S., & Ottersten, B. (2019). Calibrated learning for online distributed power allocation in small-cell networks. IEEE Transactions on Signal Processing, 67(11), 8124–8136.
