ALGORITMA EKSTRAKSI ATURAN DARI JARINGAN SYARAF TIRUAN : SURVEI
Keywords:
jaringan syaraf tiruan, ekstraksi aturan jaringan syaraf tiruanAbstract
Jaringan syaraf tiruan (JST) telah berhasil diterapkan dalam berbagai bidang seperti ekonomi,
keuangan, pengenalan pola, prediksi, optimisasi, kendali, pemrosesan sinyal digital ,kedokteran. Namu n para
ahli tidak puas hanya dengan tingkat akurasi yang tinggi yang ditunjukkan JST. Hal ini karena cara penalaran
yang digunakan JST untuk mencari jawaban tidak dapat dilakukan dengan cepat, sehingga perlu untuk
mengekstrasi pengetahuan yang terdapat pada JST terlatih dan menunjukkannya secara simbolik untuk
menjustifikasi outputnya. Mengekstraksi aturan “IF-THEN” dari jaringan terlatih untuk menjelaskan penarikan
kesimpulan jawaban jaringan adalah teknik yang paling banyak digunakan. Dengan adanya aturan ini, akan
meningkatkan penerimaan ahli terhadap model koneksi yang lebih umum. Dalam beberapa tahun terakhir,
banyak penelitian tentang ekstraksi aturan dari JST yang terlatih. Terdapat tiga pendekatan ekstraksi aturan
JST, yaitu decompositional, pedagogical, dan eclectic. Pada penelitian ini dilakukan beberapa tinjauan
algoritma ekstraksi aturan JST dari ketiga pendekatan dan perbandingan beberapa algoritma tersebut. Aplikasi
diberbagai bidang juga telah diterapkan menggunakan algoritma ekstraksi JST tersebut.
References
Network Knowledge Extraction
Rev.Roum.Sci.Techn. - Électrotechn.et
Énerg. Bucharest. 1998 ; .,43, 1 , p
[2] Choe, W., Ersoy, O.K., , Detection of Rare
Events and Rule Extraction by Neural
Networks and Decision Trees. ECE
Technical Reports. 2000 ; Paper 18.
[3] Lisboa, P.J., Taktak, A.F.G. The Use of Artificial
Neural Networks in Decision Suport in
Cancer. Neural Networks 19. 2006; 408-415
[4] Sarhan, A.M., Abd El-Wahed, W.F., Danf, T.E.,
Tokhy, M. M., Developing a Rule Extraction
Methodology for Expert Sytems Based
Artificial Neural Network Ensembles. 2005
[5] Campos, P.G., Ludermir, T.B. Literal and
ProRulext : Algorithms for Rule Extraction of
ANNs. Proceedings of the 5th International
Conference on Hybrid Inteligence Systems.
2005
[6] Zhou, Z. Rule Extraction: Using Neural Networks
or For Neural Networks. National Laboratory
for Novel Software Technology, Nanjing
University, Nanjing 210093, China. 2003
[7] Augasta, M.A., Kathirvalavakumar, T. Rule
Extraction from Neural networks – a
Comparative Study, Proceedings of the
International Conference on Pattern
Recognition, Informatics and Medical
Engineering. 2012,
[8] Kamruzzaman, S.M., Islam, M.M. Extraction of
Symbolic Rules from ANN. Proceedings of
World Academy of science, Engineering and
Technology ISSN 1307-6884. 2005 ;Volume
10
[9] Hongchun, Y., Fanlun, X., Chao, D. Neural
Network Method for Extraction Evaluation
Rules of Soil Fertility. Project of National
Natural Foundations of China. 2000
[10] Steiner, M.T.A., Neto, P.J.S., Soma, N.Y.,
Shimizu, T., Nievola, J.C. Using Neural
Network Rule Extraction for Evaluation
Credit-Risk Evaluation. IJCSNS. 2006; Vol
6 No 5A
[11] Hudson, B.D., Whitley, D.C., Browne, A., Forda,
M.G. Extraction of Comprehensible Logical
Rules from Neural Networks : Application of
TREPAN in Bio and Chemoinformatics.
Croatica Chemica Acta, CCACAA. 2006 ;78 (4) :561
[12] Liu, Y., Liu, H. , Zhang, B., Wu, G. Extraction If-Then Rules from Trained Neural Network
and Its Application to Earthquake Prediction,
Proceedings of the Third IEEE International
Conference on Cogitive Informatics. 2004
[13] Sarhan, A.M., Abd El-Wahed, W.F., Danf, T.E.,
Tokhy, M. M. Developing a Rule Extraction
Methodology for Expert Sytems Based
Artificial Neural Network Ensembles. 2005
[14] Franco, L., Subirats, J.L., Molina, I., Alba, E.,
Jerez, J.M. Early Breast Cancer Prognosis
Prediction andRule Extraction Using a New
Constructive Neural Network Algorithm.
2007
[15] Dias, S.M., Nogueira, B.M., Z´arate, L.E.
Adaptation of FCANN Method to Extract and
Represent Comprehensible Knowledge from
Neural Networks. New Chall. in Appl. Intel.
Tech., SCI. 2008 ; 134, pp. 163–172
[16] Kahramanli, H., Allahverdi, N. Rule extraction
from trained adaptive neural networks using
artificial immune systems, Expert Systems
with Applications. 2009 ; 36 1513–1522
[17] Weckman G.R., Millie D., Ganduri, C.,
Rangwala, M., Young, W., Rinder, M.,
Fahnenstiel G.L. Knowledge Extraction from
the Neural ‘Black Box’ in Ecological
Monitoring. Journal of Industrial and
Systems Engineering. 2009; Vol. 3, No. 1,
pp 38-55
[18] Sheikhan, M., Khalili, A Rule Extraction from
Dynamic Cell Structure Neural Networks.
World Applied Sciences Journal 7 (Special
Issue of Computer & IT). 2009; 54-58
[19] Ozbakir, L., Baykasoğlu, A., Kulluk, S. Rule
extraction from artificial neural networks to
discover causes of quality defects in fabric
production. Neural Computing and
Applications, Springer-Verlag London
Limited. 2010
[20] Ma, J. Guo, D., Liu, M., Ma, Y., Chen, S. Rules
Extraction from ANN Based on Clustering.
International Conference on Computational
Intelligence and Natural Computing. , 2009
[21] Shen, J., Wang, L. Configuration Rules
Acquisition for Product Extension Services
Using Local Cluster Neural Network and
RULEX Algorithm, International Conference
on Artificial Intelligence and Computational
Intelligence. 2010
[22] Setiono, R., Tanaka, M. Neural network rule
extraction and the LED display recognition
problem. 22nd International Conference on
Tools with Artificial Intelligence. 2010
[23] Silva, A.A., Gerhardt, G.J.L., Echeverrigaray, S.
Rules extraction from neural networks
applied to the prediction and recognition of
prokaryotic promoters. Genetics and
Molecular Biology Springer-Verlag Berlin
Heidelberg. 2011; 34, 2, 353-360
[24] Kamruzzaman, S.M., Islam, M.M. Extraction of
Symbolic Rules from ANN, Proceedings of
World Academy of science. Engineering and
Technology ISSN 1307-6884. 2005 ;Volume
10
[25] El Alami, M.E. Destructive Algorithm for Rule
Extraction based on a Trained Neural
Network. International Journal of Computer
Applications (0975 – 8887). 2012 ; Volume
42– No.21
[26] Godara, S., Gupta, R., 2013, Neural Networks
for Iris Recognition: Comparisons between
[27] Hawickhorst, B.A., Zahorian, S.A., Rajagopal,
R., -, A Comparison of Three Neural
Network Architectures for Automatic Speech
Recogniton, Old Dominion University,
Norfolk, VA 23529
[28] Azis, A., Hartati, S., Ekstraksi JST LVQ dengan
Algoritma C4.5. Prosiding Sentia 2012,
Politeknik Negeri Malang, Indonesia. 2012