Granular Modelling - principles and the design environment

It is well accepted that modelling of complex systems involves transition from detailed numerical to more abstract, aggregated information processing. Granular computing is geared toward representing and processing aggregated chunks of information - information granules. These granules are collections of entities that are arranged together due to their similarity, functional adjacency, indistinguishability or alike. No matter how the information granulation proceeds and what fundamental technology becomes involved therein it is driven by an overreaching need to split the problem into more manageable subtasks and to provide a better insight into its nature. The rapid development of granular computing in the late 90's arises from the fact that unlike numeric computing, which is data-oriented, granular computing is knowledge-oriented, and as such, it underlies knowledge-inclined system modeling. I envisage that with the increased visibility of granular computing, granular models are about to come to existence in a broad spectrum of application domains. Consequently, development of a well-rounded design environment represents a challenging yet highly rewarding long-term target. There are many fundamental questions that will be asked: Are granular models preferred over some other approaches? How should a hierarchy of information granules be organized? How to validate the models against experimental and perception-driven evidence? What is the best means of communication between granular models? The motivation of this research is to make such investigation more structured and comprehensive. The detailed objectives that can be set in this research program are:
• Formulation and analysis of functional architectures of granular models.
• Design of hierarchies of granular models.
• Defining and quantifying interoperability and collaboration between various layers of information and granules derived at different levels of specificity.
• Investigation of logic-driven processing of information granules.

Publications

• Bargiela, A., Pedrycz, W., Granular computing: an introduction, Springer, 2003
• Bargiela, A., Pedrycz, W., (Eds.) Human-centric information processing through granular modelling, Studies in Computational Intelligence 182, Springer Berlin Heidelberg, 2009, (doi: 10.1007/978-3-540-92916-1)
• Bargiela A., Pedrycz W., Hirota K., Data granulation through optimization of similarity measure, Archives of Control Sciences, 12, 4, 469-491, 2002
• Pedrycz, W., Bargiela, A., Granular clustering: a granular signature of data, IEEE Trans. on Systems Man and Cybernetics, SMC-B, 32, 2, April 2002, 212-224, (doi: 10.1109/3477.990878 )
• Bargiela, A., Pedrycz, W., Recursive information granulation: Aggregation and interpretation issues, IEEE Trans. on Systems Man and Cybernetics SMC-B, 33, 1, 17, 2003, 96-112. (10.1109/TSMCB.2003.808190)
• Bargiela A., Pedrycz W., Hirota K., Granular prototyping in fuzzy clustering, IEEE Transactions on Fuzzy Systems, 12, 5, 2004, 697-709 (doi: 10.1109/TFUZZ.2004.834808)
• Bargiela, A., Pedrycz, W., Granular mappings, IEEE Transactions on Systems Man and Cybernetics SMC-A, vol. 35, 2, March 2005, 288-301 (doi: 10.1109/TSMCA.2005.843381)
• Bargiela, A., Pedrycz, W., A model of granular data: a design problem with the Tchebyschev FCM, Soft Computing, 9, 3, March 2005, 155-163 (doi: 10.1007/s00500-003-0339-2)
• Bargiela A., Homenda W., Information structuring in natural language communication Ð syntactical approach, Journal of Intelligent and Fuzzy Systems, 17(6), 2006, 575-582.
• Bargiela, A., Pedrycz, W., The roots of granular computing, Proceedings of 2006 IEEE International Conference on Granular Computing, 806-809
• Bargiela, A., Pedrycz, W., Toward a theory of Granular Computing for human-centred information processing, IEEE Trans. on Fuzzy Systems, vol. 16, 2, 2008, 320-330. (doi: 10.1109/TFUZZ.2007.905912)
• Pedrycz W., Bargiela A., Fuzzy clustering with semantically distinct families of variables: descriptive and predictive aspects, Pattern Recognition Letters, 31(13), 1952-1958, 2010. (doi: 10.1016/j.patrec.2010.06.016)
• Pedrycz, W., Bargiela, A., An Optimisation of allocation of information gramularity in the interpretation of data structures, IEEE Transactions on Systems Man and Cybernetics Part B , 42(3), 2012, 582-590 (doi: 10.1109/TSMCB.2011.2170067)
• Bargiela A., Pedrycz W., Optimised information abstraction in granular Min/Max clustering, in S. Ramanna, R.J. Howlett, L. Jain (ed.), Emerging Paradigms in Machine Learning, Springer, June 2012. ISBN 978-3-642-28698-8
• Bargiela A., Pedrycz W., Supervised and unsupervised information granulation: A study in hyperbox design, Chapter 3 in J.T.Yao (ed.), Novel developments in Granular Computing: Applications for Advanced Human Reasoning and Soft Computation, IGI Global, 2010.
• Bargiela, A., Pedrycz W., Self-organising maps for interactive information granulation, in Neural Network Applications in IT, In : D. Wang, N.K.Lee (eds.), University of Malasia Press, 1-19, 2004
• Bargiela, A. Pedrycz, W., Combined physical and mathematical model of Granular Computing, Proc. Int. Conf. On Soft Computing and Intelligent Systems SCIS2006, Tokyo, Japan, Sept. 2006