Scopus
YÖKSİS ISSN Eşleşti
SJR Q1
Rule extraction from trained adaptive neural networks using artificial immune systems
Expert Systems with Applications · Ocak 2009
YÖKSİS Kayıtları — ISSN Eşleşmesi
Game-theoretic DEA Optimization for Sustainable Agricultural Carbon Trading: Evidence from Türkiye’s Maize Production
2026 ISSN: 0957-4174 SCI-Expanded Q1
Prof. Dr. ZEKİ BAYRAMOĞLU →
Web based medical decision support system application of Coronary Heart Disease diagnosis with Boolean functions minimization method
2011 ISSN: 09574174 SCI
Prof. Dr. FATİH BAŞÇİFTÇİ →
Modeling and prediction of surface roughness in turning operations using artificial neural network and multiple regression method
2011 ISSN: 09574174 SCI-Expanded
Prof. Dr. MEHMET ÇUNKAŞ →
A fuzzy clustering approach for finding similar documents using a novel similarity measure
2007 ISSN: 0957-4174 SCI-Expanded 22 atıf
Doç. Dr. KEMAL TÜTÜNCÜ →
A new approach on search for similar documents with multiple categories using fuzzy clustering
2008 ISSN: 0957-4174 SCI-Expanded
Doç. Dr. KEMAL TÜTÜNCÜ →
Organizational strategy development in distribution channel management using fuzzy AHP and hierarchical fuzzy TOPSIS
2012 ISSN: 09574174 SCI-Expanded
Prof. Dr. NİMET YAPICI PEHLİVAN →
Artificial neural network and fuzzy expert system comparison for prediction of performance and emission parameters on a gasoline engine
2011 ISSN: 09574174 SCI-Expanded
Prof. Dr. ŞAKİR TAŞDEMİR →
Artificial neural network and fuzzy expert system comparison for prediction of performance and emission parameters on a gasoline engine
2011 ISSN: 0957-4174 SCI-Expanded 4 atıf
Prof. Dr. MURAT CİNİVİZ →
Fuzzy expert system design for operating room air-condition control systems
2009 ISSN: 0957-4174 SCI-Expanded 29 atıf Q1
Prof. Dr. İSMAİL SARITAŞ →
Prognosis of prostate cancer by artificial neural networks
2010 ISSN: 0957-4174 SCI-Expanded 30 atıf Q1
Prof. Dr. İSMAİL SARITAŞ →
Prediction of diesel engine performance using biofuels with artificial neural network
2010 ISSN: 0957-4174 SCI-Expanded 53 atıf Q1
Prof. Dr. İSMAİL SARITAŞ →
The effects of fuzzy control of magnetic flux on magnetic filter performance and energy consumption
2010 ISSN: 0957-4174 SCI-Expanded 5 atıf Q1
Prof. Dr. İSMAİL SARITAŞ →
Artificial neural network and fuzzy expert system comparison for prediction of performance and emission parameters on a gasoline engine
2011 ISSN: 0957-4174 SCI-Expanded 24 atıf Q1
Prof. Dr. İSMAİL SARITAŞ →
Anesthetic gas control with neuro fuzzy system in anesthesia
2010 ISSN: 09574174 SCI-Expanded
Prof. Dr. RÜŞTÜ GÜNTÜRKÜN →
An Adaptive Network Based Fuzzy Inference System ANFIS for the prediction of stock market return The case of the Istanbul Stock Exchange
2010 ISSN: 09574174 SCI-Expanded
Prof. Dr. MELEK ACAR →
Predicting direction of stock price index movement using artificial neural networks and support vector machines The sample of the Istanbul Stock Exchange
2011 ISSN: 09574174 SCI-Expanded
Prof. Dr. MELEK ACAR →
Predicting bank financial failures using neural networks support vector machines and multivariate statistical methods A comparative analysis in the sample of savings deposit insurance fund SDIF transferred banks in Turkey
2009 ISSN: 09574174 SCI-Expanded
Prof. Dr. MELEK ACAR →
The design of ultrasonic therapy device via fuzzy logic
2011 ISSN: 09574174 SCI-Expanded
Öğr. Gör. SEMA YILDIRIM →
Assessment of exercise stress testing with artificial neural network in determining coronary artery disease and predicting lesion localization
2009 ISSN: 09574174 SCI-Expanded
Prof. Dr. NAZİF AYGÜL →
Design of a hybrid system for the diabetes and heart diseases
2008 ISSN: 0957-4174 SCI-Expanded 85 atıf Q1
Prof. Dr. HUMAR KAHRAMANLI ÖRNEK →
Makale Bilgileri
ISSN09574174
Yayın TarihiOcak 2009
Cilt / Sayfa36 · 1513-1522
Scopus ID2-s2.0-56349096960
Özet
Although artificial neural network (ANN) usually reaches high classification accuracy, the obtained results sometimes may be incomprehensible. This fact is causing a serious problem in data mining applications. The rules that are derived from ANN are needed to be formed to solve this problem and various methods have been improved to extract these rules. Activation function is critical as the behavior and performance of an ANN model largely depends on it. So far there have been limited studies with emphasis on setting a few free parameters in the neuron activation function. ANN's with such activation function seem to provide better fitting properties than classical architectures with fixed activation function neurons [Xu, S., & Zhang, M. (2005). Data mining - An adaptive neural network model for financial analysis. In Proceedings of the third international conference on information technology and applications]. In this study a new method that uses artificial immune systems (AIS) algorithm has been presented to extract rules from trained adaptive neural network. Two real time problems data were investigated for determining applicability of the proposed method. The data were obtained from University of California at Irvine (UCI) machine learning repository. The datasets were obtained from Breast Cancer disease and ECG data. The proposed method achieved accuracy values 94.59% and 92.31% for ECG and Breast Cancer dataset, respectively. It has been observed that these results are one of the best results comparing with results obtained from related previous studies and reported in UCI web sites. © 2007 Elsevier Ltd. All rights reserved.
Yazarlar (2)
1
Humar Kahramanli
2
Novruz Allahverdi
Anahtar Kelimeler
Adaptive neural networks
Artificial immune systems
Backpropagation
Opt-aiNET
Optimization
Rule extraction
Kurumlar
Selçuk Üniversitesi
Selçuklu Turkey
Scimago Dergi (ISSN Eşleşmesi)
Expert Systems with Applications
Q1
SJR Skoru1,854
H-Index290
YayıncıElsevier Ltd
ÜlkeUnited Kingdom
Artificial Intelligence (Q1)
Computer Science Applications (Q1)
Engineering (miscellaneous) (Q1)
Metrikler
61
Atıf
2
Yazar
6
Anahtar Kelime