Autosoft Journal

Online Manuscript Access

Using Iceberg Concept Lattices and Implications Rules to Extract Knowledge from Ann



Nowadays, Artificial Neural Networks are being widely used in the representation of physical processes. Once trained, the networks are capable of solving unprecedented situations, keeping tolerable errors in their outputs. However, humans cannot assimilate the knowledge kept by these networks, since such knowledge is implicitly represented by their structure and connection weights. Recently, the FCANN method, based on Formal Concept Analysis, has been proposed as a new approach to extract, represent and understand the behavior of the processes based on rules. However, the extraction of those rules set is not an easy task. In this work, two main proposals to improve the FCANN method are presented and discussed: 1) the building of concept lattice using frequent item sets, which provides a threshold on the formal concepts number, and 2) the extraction of implications rules from the concept lattice, which provides clearer and more direct rules, thus facilitating the learning of the process by the user. As a case study, the new approach will be applied in a solar energy system – thermosiphon.



Total Pages: 12
Pages: 361-372


Manuscript ViewPdf Subscription required to access this document

Obtain access this manuscript in one of the following ways

Already subscribed?

Need information on obtaining a subscription? Personal and institutional subscriptions are available.

Already an author? Have access via email address?


Volume: 19
Issue: 3
Year: 2013

Cite this document


Andrews R. Neurocomputing

Benítez J. M. IEEE transactions on neural networks

Craven, Mark W. & Shavlik, Jude W. (1995). Extracting comprehensible concept representations from trained neural networks. In Working Notes on the IJCAI ’95 Workshop on Comprehensibility in M.L (pp. 61–75)

Tarca, A. L., and J. E. K. Cooke. "A Robust Neural Networks Approach for Spatial and Intensity-Dependent Normalization of cDNA Microarray Data." Bioinformatics 21.11 (2005): 2674-2683. Crossref. Web.

Towell Geoffrey G. Machine learning 13.1 (1993)

Vimieiro, Renato, Zárate, Luis E., Silva, J. P. D., Pereira, E. M. D. & Diniz, A. S. C. (2004). Rule extraction from trained neural networks via formal concept analysis. In 8th IASTED Inter. Conf. on Arti. Intelli. and Soft Comp (pp. 334–339). IEEE express

Davey B. Introduction to lattices and order

Vimieiro, Renato, Zárate, Luiz E., Pereira, Elizabeth M. D. & Vieira, Newton J. (2005, June). Using the nextclosure algorithm to extract rules from trained neural networks application in solar energy systems. In IEEE mid-summer workshop on soft computing in industrial applications SMCia (pp. 184– 189). New York

Ganter Bernhard Formal concept analysis: mathematical foundations

Stumme G. Data and Knowledge Engineering 42.34 (2002)

Carpineto C. Concept data analysis: Theory and applications

Roth, Camille, Obiedkov, Sergei, & Kourie, Derrick G. (2006). Towards concise representation for taxonomies of epistemic communities. In CLA 4th International Conference on Concept Lattices and their Applications, Tunis, Facultédes Sciences de Tunis (pp. 205–218)

Cheung Karen S. K. Information Retrieval 8.2 (2005)

Dias, Sérgio M., and Newton J. Vieira. "Applying the JBOS Reduction Method for Relevant Knowledge Extraction." Expert Systems with Applications 40.5 (2013): 1880-1887. Crossref. Web.

Aswani Kumar, Ch., and S. Srinivas. "Concept Lattice Reduction Using Fuzzy K-Means Clustering." Expert Systems with Applications 37.3 (2010): 2696-2704. Crossref. Web.

Kumar Ch. Aswani Journal of biological systems 18.4 (2010)

Taouil, R. Stumme, G. Data and Knowledge Engineering 42.34 (2002)

Dias, Sérgio M. (2010). Algoritmos para geração de reticulados conceituais (Master”s thesis). Federal University of Minas Gerais (UFMG), Department of Computer Science, Belo Horizonte, MG, Brazil. In portuguese

Zárate Luiz. E. Neurocomputing

Maier David The theory of relational databases

Zárate, Luis E., Pereira, E. M. D., Oliveira, L. A. R., Gil, V. P., Santos, T. R. A., Nogueira, B. M. (2006). Techniques for training sets selection in the representation of a thermosiphon system via ann (pp. 2736–2741). Proc IJCNN

Morrison G. L. Solar Energy

Haykin, S. (2001). Redes Neurais – Princípios e prática. Porto Alegre, Brasil: Bookman. In portuguese

Rudolph, S. (2007). Some notes on pseudo-closed sets. ICFCA, 151–165

Hecht-Nielsen, R. (1987). Kolmogorov”s mapping neural networks existence theorem. Proc. IEEE inter. conf. on neural networks 3, 11–13

Hecht-Nilsen, R. (1990, September). Neurocomputing. Reading, MA: Addison-Wesley

Altincay, H., Demirekler, M. (2002). Why does output Normalization create problems in multiple classifier systems? Proc. ICPR, 775–778


ISSN PRINT: 1079-8587
ISSN ONLINE: 2326-005X
DOI PREFIX: 10.31209
10.1080/10798587 with T&F
IMPACT FACTOR: 0.652 (2017/2018)
Journal: 1995-Present


TSI Press
18015 Bullis Hill
San Antonio, TX 78258 USA
PH: 210 479 1022
FAX: 210 479 1048