Classification-Oriented Neural Networks with Granular Processing

Authors

DOI:

https://doi.org/10.31181/jscda412026105

Keywords:

Granular Computing, Neural Network, Allocation of Information Granules, Interval Analysis

Abstract

This paper presents a classification framework of granular neural networks (GNNs) designed for classification tasks. Built upon conventional neural network architectures, the framework introduces interval-valued (granular) connections, where each interval forms an information granule around a numeric weight. This design is proposed to utilize a granular approach in classification tasks. This representation provides a quantifiable measure of uncertainty and interpretability in classification decisions. By optimally distributing information granularity across network connections, the proposed model seeks to maximize classification confidence while preserving specificity. To achieve this objective, a single-objective particle swarm optimization (PSO) algorithm is employed, guided by classification coverage and specificity criteria. The proposed approach is validated using benchmark datasets and evaluated through multiple performance indices derived from the Interval Neutrosophic Set (INS) and granular computing domains.

Downloads

Download data is not yet available.

References

Song, M. L., & Pedrycz, W. (2013). Granular neural networks: Concepts and development schemes. IEEE Transactions on Neural Networks and Learning Systems, 24(4), 542–553. https://doi.org/10.1109/TNNLS.2013.2237787

Liu, Y., Zhao, J., Wang, D., & Pedrycz, W. (2021). Prediction intervals for granular data streams based on evolving type-2 fuzzy granular neural network dynamic ensemble. IEEE Transactions on Fuzzy Systems, 29(4), 874–888. https://doi.org/10.1109/TFUZZ.2020.2966172

Al-Hmouz, R., Pedrycz, W., Balamash, A. S., & Morfeq, A. (2014). Description and classification of granular time series. Soft Computing, 19(4), 1003–1017. https://doi.org/10.1007/s00500-014-1311-z

Panoutsos, G., & Mahfouf, M. (2010). A neural-fuzzy modelling framework based on granular computing: Concepts and applications. Fuzzy Sets and Systems, 161(21), 2808–2830. https://doi.org/10.1016/j.fss.2010.06.004

Ishibuchi, H., Tanaka, H., & Okada, H. (1993). An architecture of neural networks with interval weights and its application to fuzzy regression analysis. Fuzzy Sets and Systems, 57(1), 27–39. https://doi.org/10.1016/0165-0114(93)90118-2

Song, M. L., Jing, Y., & Pedrycz, W. (2019). Granular neural networks: A study of optimizing allocation of information granularity in input space. Applied Soft Computing, 77, 67–75. https://doi.org/10.1016/j.asoc.2019.01.013

Song, M. L., & Jing, Y. (2020). Granular neural networks: The development of granular input spaces and parameters spaces through a hierarchical allocation of information granularity. Information Sciences, 517, 148–166. https://doi.org/10.1016/j.ins.2019.12.081

Balamash, A. S., Pedrycz, W., Al-Hmouz, R., & Morfeq, A. (2015). Granular classifiers and their design through refinement of information granules. Soft Computing, 21(10), 2745–2759. https://doi.org/10.1007/s00500-015-1978-9

Akhoundi, E. (2014). Optimal allocation of information granularity to the inputs of granular neural networks [Master's dissertation, University of Alberta]. https://doi.org/10.7939/r3j960j49

Al-Hmouz, R., Pedrycz, W., Balamash, A. S., & Morfeq, A. (2013). Granular representation schemes of time series: A study in an optimal allocation of information granularity. In 2013 IEEE Symposium on Foundations of Computational Intelligence (FOCI). https://doi.org/10.1109/FOCI.2013.6602454

Lu, W., Ma, C., Pedrycz, W., & Yang, J. (2021). Design of granular model: A method driven by hyper-box iteration granulation. IEEE Transactions on Cybernetics, 53(5), 2899–2913. https://doi.org/10.1109/TCYB.2021.3124235

Arun Kumar, D., Meher, S., Kanhar, D., & Padma Kumari, K. (2016). Unified granular neural networks for pattern classification. Neurocomputing, 216, 109–125. https://doi.org/10.1016/j.neucom.2016.07.034

Zhu, X., Pedrycz, W., & Li, Z. (2019). Development and analysis of neural networks realized in the presence of granular data. IEEE Transactions on Neural Networks and Learning Systems, 31(9), 3606–3619. https://doi.org/10.1109/TNNLS.2019.2945307

Song, M. L., Li, Y., & Pedrycz, W. (2023). Time series prediction with granular neural networks. Neurocomputing, 546, 126328. https://doi.org/10.1016/j.neucom.2023.126328

Dong, L., Li, G., Wang, D., Yu, Z., Nasr, E. A., Abdelgawad, A. E., & Fararah, E. (2022). Granular data modeling and analysis based on optimized subsets of data. Measurement and Control, 56(1–2), 34–48. https://doi.org/10.1177/00202940221083263

Loia, V., Parente, M., Pedrycz, W., & Tomasiello, S. (2018). A granular functional network with delay: Some dynamical properties and application to the sign prediction in social networks. Neurocomputing, 321, 61–71.

Liu, Y., & Song, M. L. (2021). Few samples learning based on granular neural networks. Granular Computing, 7(3), 577–589. https://doi.org/10.1007/s41066-021-00285-z

Song, M. L., & Liu, Y. (2021). A development framework of granular prototypes with an allocation of information granularity. Information Sciences, 573, 154–170. https://doi.org/10.1016/J.INS.2021.06.001

Qin, J., Martinez, L., Pedrycz, W., Ma, X. Y., & Liang, Y. (2023). An overview of granular computing in decision-making: Extensions, applications, and challenges. Information Fusion, 98, 101833. https://doi.org/10.1016/j.inffus.2023.101833

Song, M. L., & Wang, Y. (2016). A study of granular computing in the agenda of growth of artificial neural networks. Granular Computing, 1(4), 247–257. https://doi.org/10.1007/s41066-016-0020-7

Smarandache, F. (2006). A unifying field in logics: Neutrosophic logic. In Neutrosophic Probability (5th ed., p. 157). Zenodo. https://doi.org/10.48550/arXiv.math/0101228

Qasim, A. R., Abbas, S., Jumaah, H. N., Hussein, K. M., & Khalid, E. H. (2025). A neutrosophic approach to improving sentiment classification accuracy in social media analytics. Zenodo. https://doi.org/10.5281/zenodo.15825643

Marcheco, Chacon, E., Washington Eduardo, Y. P., Cueva Salazar, N. M., Toro Molina, B. M., Silva Deley, L. M., & Dekhkonov, B. (2025). A proposed SWOT analysis method for integrating indeterminate Likert scale with the neutrosophic AHP. International Journal of Neutrosophic Science (IJNS), 25(1). https://doi.org/10.54216/ijns.250142

Smarandache, F. (2020). The score, accuracy, and certainty functions determine a total order on the set of neutrosophic triplets (T, I, F). Infinite Study. https://doi.org/10.48550/arXiv.2012.10208

Khatter, K. (2021). Interval valued trapezoidal neutrosophic set: Multi-attribute decision making for prioritization of non-functional requirements. Journal of Ambient Intelligence and Humanized Computing, 12(1), 1039–1055. https://doi.org/10.1007/s12652-020-02130-8

Kennedy, J., & Eberhart, R. (2002). Particle swarm optimization. In Proceedings of ICNN'95 - International Conference on Neural Networks (Vol. 4, pp. 1942–1948).

Pedrycz, W., & Homenda, W. (2013). Building the fundamentals of granular computing: A principle of justifiable granularity. Applied Soft Computing, 13(10), 4209–4218. https://doi.org/10.1016/j.asoc.2013.06.017

Pedrycz, W. (2021). The principle of justifiable granularity. Springer International Publishing. https://doi.org/10.1007/978-3-030-52800-3_10

Wolberg, W., Mangasarian, O., Street, N., & Street, W. (1993). Breast Cancer Wisconsin (Diagnostic) [Data set]. https://doi.org/10.24432/c5dw2b

Fisher, R. A. (1936). The use of multiple measurements in taxonomic problems. Annals of Eugenics, 7(2), 179–188. https://doi.org/10.1111/j.1469-1809.1936.tb02137.x

Nakai, K., & Kanehisa, M. (1991). Expert system for predicting protein localization sites in gram-negative bacteria. Proteins: Structure, Function, and Bioinformatics, 11, 95–110. https://doi.org/10.1002/prot.340110203

MathWorks. (2017). Data sets for deep learning - MATLAB and Simulink. https://www.mathworks.com/help/deeplearning/ug/data-sets-for-deep-learning.html

Janosi, & Detrano, R. (1989). Heart Disease [Data set]. UCI Machine Learning Repository. https://doi.org/10.24432/c52p4x

Thabtah, F. (2017). Autism Screening Adult [Data set]. UCI Machine Learning Repository. https://doi.org/10.24432/C5F019

Narayan, N. (2024). Weather Type Classification [Data set]. Kaggle. https://www.kaggle.com/datasets/nikhil7280/weather-type-classification

Bhagat, A. M. (2024). Crop Recommendation Dataset [Data set]. Kaggle. https://www.kaggle.com/datasets/madhuraatmarambhagat/crop-recommendation-dataset

Nakai, K. (1996). Ecoli [Data set]. UCI Machine Learning Repository. https://doi.org/10.24432/C5388M

Matiz, S., & Barner, K. E. (2019). Inductive conformal predictor for convolutional neural networks: Applications to active learning for image classification. Pattern Recognition, 90, 172–182. https://doi.org/10.1016/j.patcog.2019.01.035

Li, M., Klamkin, M., Tanneau, M., Zandehshahvar, R., & Van Hentenryck, P. (2025). Conformal prediction with upper and lower bound models. arXiv preprint arXiv:2503.04071. https://doi.org/10.48550/arXiv.2503.04071

Sadinle, M., Lei, J., & Wasserman, L. (2019). Least ambiguous set-valued classifiers with bounded error levels. Journal of the American Statistical Association, 114(525), 223–234. https://doi.org/10.1080/01621459.2017.1395341

Downloads

Published

2026-10-26

Issue

Vol. 4 No. 1 (2026): Journal of Soft Computing and Decision Analytics

Section

Articles

License

Copyright (c) 2026 Inas Shadoul, Rami Al-Hmouz, Majdi Mansouri, Mostefa Mesbah (Author)

Creative Commons License

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

How to Cite

Shadoul, I., Al-Hmouz, R., Mansouri, M., & Mesbah, M. (2026). Classification-Oriented Neural Networks with Granular Processing. Journal of Soft Computing and Decision Analytics, 4(1), 236-258. https://doi.org/10.31181/jscda412026105