BibTex RIS Cite

COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS

Year 2013, Volume: 14 Issue: 3, 315 - 328, 04.05.2015

Abstract

In the literature, artificial neural networks have been frequently used for the problem of time series forecasting. There are many types of artificial neural networks in prediction of time series. Single multiplicative neuron model is firstly proposed in literature by Yadav et al. (2007). Single multiplicative neuron model uses single multiplicative aggregation function unlike the other artificial neuron models. Single neuron which uses single multiplicative neuron model was shown that in Yadav et al. (2007) successful results were obtained in time series forecasting problem of artificial neural network by using well-known time series in literature. It has known that single neuron and feed forward neural networks based on single multiplicative neuron model obtained quite successful results in time series prediction. In this study, Istanbul gold exchange and Index 100 for the stocks and bonds

References

  • Aladağ, C.H. (2011). Defining Fuzzy Relations with Multiplicative Neuron Model. The Second International Fuzzy Systems Symposium (FUZZYSS’11) Proceedings, 29-33.
  • Alpaslan, F., Eğrioglu, E., Aladağ, C.H. ve Tiring, E. (2012). A Statistical Research on Feed Forward Neural Networks for Forecasting Time Series. American Journal of Intelligence Systems 2(3), 21-25.
  • Avcı, G. (2011). Gerçek Zamanlı Uygulamalar için ABC Algoritmasının FPGA üzerinde Gerçeklenmesi. Yüksek Lisans Tezi, Niğde Üniversitesi, Niğde.
  • Gunay, S., Eğrioglu, E. ve Aladag, C.H. (2007). Introduction to Single Variable Time Series Analysis. Hacettepe University Press.
  • İlter, D. (2012). Tek Çarpımsal Sinir Hücresi Modelinin Eğitiminde Yapay Arı Kolonisi Algoritmasının Performansının Değerlendirilmesi. Yüksek Lisans Tezi, Ondokuz Mayıs Üniversitesi, Samsun, 43-44.
  • İ.M.K.B. (2012). Fiyat Endeksi. http://www.imkb.gov.tr/Data/StocksData.aspx (18.06.2012).
  • İstanbul Altın Borsası, (2012). Altın Verileri. http://www.iab.gov.tr/veriler.asp (18.06.2012).
  • Karaboğa, D. (2005). An Idea Based on Honey bee Swarm for Numerical Optimization. Technical Report-TR06, Erciyes University, Engineering Faculty, Computer Engineering Department.
  • Karaboğa, D. (2011). Yapay Zeka Optimizasyon Algoritmaları. Nobel Yayın Dağıtım, Ankara, 231s.
  • Karaboğa, D. ve Akay, B. (2007). Yapay Arı Koloni (Artificial Bee Colony, ABC) Algoritması ile Yapay Sinir Ağlarının Eğitilmesi. Sinyal İşleme ve İletişim Uygulamaları (SIU 2007). IEEE 15th, 1 – 4.
  • Karaboğa, D., Akay B., Öztürk, C. (2007). Artificial Bee Colony (ABC) Optimization Algorithm for Training Feed-Forward Neural Networks, LNCS: Modeling Decisions for Artificial Intelligence, 4617, 318-329.
  • Karaboğa, D. ve Öztürk, C. (2009). Neural Networks Training by Artificial Bee Colony Algorithm on Pattern Classification. Neural Network World 19(3), 279-292.
  • Kumbhar, P.Y. ve Krishnan, S. (2011). Use of Artificial Bee Colony (ABC) Algorithm in Artificial Neural Network Synthesis. Internatıonal Journal of Advanced Engineering Sciences And Technologies 11(1), 162-171.
  • Mammadov, M. ve Taş, E. (2006). An Improved Version of Backpropagation Algorithm with Effective Dynamic Learning Rate and Momentum. WSEAS Transactions on Mathematics 7(5), 872-877.
  • Mammadov, M., Taş, E., Omay, R.E. (2008). Accelerating Backpropagation using Effective Parameters at Each Step and An Experimental Evaluation. Journal of Statistical Computation and Simulation 78(11), 1055-1064.
  • Öztürk, C. ve Karaboğa, D. (2011). Hybrid Artificial Bee Colony Algorithm for Neural Network Training. Evolutionary Computation (CEC), 2011 IEEE Congress on, 5-8 June 2011, 84-88.
  • Samanta, B. (2011). Prediction of Chaotic Time Series using Computational Intelligence. Expert Systems with Applications 38(9), 11406-11411.
  • Şen, Z. (2004). Yapay Sinir Ağları İlkeleri. Su Vakfı Yayınları, İstanbul, 183.
  • Tsai, P-W., Pan, J-S., Liao, B-Y. ve Chu, S-C. (2009). Enhanced Artificial Bee Colony Optimization. International Journal of Innovative Computing, Information and Control 5(12), 5081-5092.
  • Yadav, R.N., Kalra, P.K. ve John, J. (2007). Time Series Prediction with Single Multiplicative Neuron Model. Applied Soft Computing 7, 1157-1163.
  • Zhang, G., Patuwo, B.E. ve Hy, Y.M. (1998). Forecasting with Artificial Neural Networks: The State of The Art. International Journal of Forecasting 14, 35-62.
  • Zhao, L. ve Yang, Y. (2009). PSO-based Single Multiplicative Neuron Model for Time Series Prediction. Expert Systems with Applications 36, 2805-2812.

TEK ÇARPIMSAL SİNİR HÜCRELİ YAPAY SİNİR AĞI MODELİNİN EĞİTİMİ İÇİN ABC VE BP YÖNTEMLERİNİN KARŞILAŞTIRILMASI

Year 2013, Volume: 14 Issue: 3, 315 - 328, 04.05.2015

Abstract

Yapay sinir ağları literatürde zaman serisi öngörü problemi için sıklıkla kullanılmaktadır. Yapay sinir ağlarının, zaman serisi öngörüsü için kullanılan birçok türü vardır. Literatürde ilk kez Yadav vd. (2007) tarafından tek çarpımsal sinir hücresi model önerilmiştir. Tek çarpımsal sinir hücresi model, diğer yapay sinir hücresi modellerinden farklı olarak tek çarpımsal bir birleştirme fonksiyonu kullanmaktadır. Tek çarpımsal sinir hücresi modelini kullanan tek sinir hücresinin, yapay sinir ağının zaman serisi öngörü probleminde başarılı sonuçlar verdiği literatürde iyi bilinen bazı zaman serileri kullanılarak Yadav vd. (2007)’de gösterilmiştir. Tek çarpımsal sinir hücresi modeline dayalı tek hücreli ve ileri beslemeli bir yapay sinir ağının zaman serilerini tahmin etmede oldukça başarılı sonuçlar ürettiği bilinmektedir. Bu çalışmada İstanbul Altın Borsası ve İMKB 100 endeksi zaman serileri tek çarpımsal sinir hücresi model yapay sinir ağı ile çözümlenmiştir. Çözümlemede tek çarpımsal sinir hücresinin eğitimi için yapay arı kolonisi algoritması ve geri yayılım öğrenme algoritması yöntemleri kullanılarak, elde edilen sonuçlar karşılaştırılmıştır.

References

  • Aladağ, C.H. (2011). Defining Fuzzy Relations with Multiplicative Neuron Model. The Second International Fuzzy Systems Symposium (FUZZYSS’11) Proceedings, 29-33.
  • Alpaslan, F., Eğrioglu, E., Aladağ, C.H. ve Tiring, E. (2012). A Statistical Research on Feed Forward Neural Networks for Forecasting Time Series. American Journal of Intelligence Systems 2(3), 21-25.
  • Avcı, G. (2011). Gerçek Zamanlı Uygulamalar için ABC Algoritmasının FPGA üzerinde Gerçeklenmesi. Yüksek Lisans Tezi, Niğde Üniversitesi, Niğde.
  • Gunay, S., Eğrioglu, E. ve Aladag, C.H. (2007). Introduction to Single Variable Time Series Analysis. Hacettepe University Press.
  • İlter, D. (2012). Tek Çarpımsal Sinir Hücresi Modelinin Eğitiminde Yapay Arı Kolonisi Algoritmasının Performansının Değerlendirilmesi. Yüksek Lisans Tezi, Ondokuz Mayıs Üniversitesi, Samsun, 43-44.
  • İ.M.K.B. (2012). Fiyat Endeksi. http://www.imkb.gov.tr/Data/StocksData.aspx (18.06.2012).
  • İstanbul Altın Borsası, (2012). Altın Verileri. http://www.iab.gov.tr/veriler.asp (18.06.2012).
  • Karaboğa, D. (2005). An Idea Based on Honey bee Swarm for Numerical Optimization. Technical Report-TR06, Erciyes University, Engineering Faculty, Computer Engineering Department.
  • Karaboğa, D. (2011). Yapay Zeka Optimizasyon Algoritmaları. Nobel Yayın Dağıtım, Ankara, 231s.
  • Karaboğa, D. ve Akay, B. (2007). Yapay Arı Koloni (Artificial Bee Colony, ABC) Algoritması ile Yapay Sinir Ağlarının Eğitilmesi. Sinyal İşleme ve İletişim Uygulamaları (SIU 2007). IEEE 15th, 1 – 4.
  • Karaboğa, D., Akay B., Öztürk, C. (2007). Artificial Bee Colony (ABC) Optimization Algorithm for Training Feed-Forward Neural Networks, LNCS: Modeling Decisions for Artificial Intelligence, 4617, 318-329.
  • Karaboğa, D. ve Öztürk, C. (2009). Neural Networks Training by Artificial Bee Colony Algorithm on Pattern Classification. Neural Network World 19(3), 279-292.
  • Kumbhar, P.Y. ve Krishnan, S. (2011). Use of Artificial Bee Colony (ABC) Algorithm in Artificial Neural Network Synthesis. Internatıonal Journal of Advanced Engineering Sciences And Technologies 11(1), 162-171.
  • Mammadov, M. ve Taş, E. (2006). An Improved Version of Backpropagation Algorithm with Effective Dynamic Learning Rate and Momentum. WSEAS Transactions on Mathematics 7(5), 872-877.
  • Mammadov, M., Taş, E., Omay, R.E. (2008). Accelerating Backpropagation using Effective Parameters at Each Step and An Experimental Evaluation. Journal of Statistical Computation and Simulation 78(11), 1055-1064.
  • Öztürk, C. ve Karaboğa, D. (2011). Hybrid Artificial Bee Colony Algorithm for Neural Network Training. Evolutionary Computation (CEC), 2011 IEEE Congress on, 5-8 June 2011, 84-88.
  • Samanta, B. (2011). Prediction of Chaotic Time Series using Computational Intelligence. Expert Systems with Applications 38(9), 11406-11411.
  • Şen, Z. (2004). Yapay Sinir Ağları İlkeleri. Su Vakfı Yayınları, İstanbul, 183.
  • Tsai, P-W., Pan, J-S., Liao, B-Y. ve Chu, S-C. (2009). Enhanced Artificial Bee Colony Optimization. International Journal of Innovative Computing, Information and Control 5(12), 5081-5092.
  • Yadav, R.N., Kalra, P.K. ve John, J. (2007). Time Series Prediction with Single Multiplicative Neuron Model. Applied Soft Computing 7, 1157-1163.
  • Zhang, G., Patuwo, B.E. ve Hy, Y.M. (1998). Forecasting with Artificial Neural Networks: The State of The Art. International Journal of Forecasting 14, 35-62.
  • Zhao, L. ve Yang, Y. (2009). PSO-based Single Multiplicative Neuron Model for Time Series Prediction. Expert Systems with Applications 36, 2805-2812.
There are 22 citations in total.

Details

Primary Language English
Journal Section Articles
Authors

Faruk Alpaslan

Erol Eğrioğlu

Çağdaş Aladağ

Damla İlter

Ali Dalar

Publication Date May 4, 2015
Published in Issue Year 2013 Volume: 14 Issue: 3

Cite

APA Alpaslan, F., Eğrioğlu, E., Aladağ, Ç., İlter, D., et al. (2015). COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS. Anadolu University Journal of Science and Technology A - Applied Sciences and Engineering, 14(3), 315-328.
AMA Alpaslan F, Eğrioğlu E, Aladağ Ç, İlter D, Dalar A. COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS. AUJST-A. May 2015;14(3):315-328.
Chicago Alpaslan, Faruk, Erol Eğrioğlu, Çağdaş Aladağ, Damla İlter, and Ali Dalar. “COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS”. Anadolu University Journal of Science and Technology A - Applied Sciences and Engineering 14, no. 3 (May 2015): 315-28.
EndNote Alpaslan F, Eğrioğlu E, Aladağ Ç, İlter D, Dalar A (May 1, 2015) COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS. Anadolu University Journal of Science and Technology A - Applied Sciences and Engineering 14 3 315–328.
IEEE F. Alpaslan, E. Eğrioğlu, Ç. Aladağ, D. İlter, and A. Dalar, “COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS”, AUJST-A, vol. 14, no. 3, pp. 315–328, 2015.
ISNAD Alpaslan, Faruk et al. “COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS”. Anadolu University Journal of Science and Technology A - Applied Sciences and Engineering 14/3 (May 2015), 315-328.
JAMA Alpaslan F, Eğrioğlu E, Aladağ Ç, İlter D, Dalar A. COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS. AUJST-A. 2015;14:315–328.
MLA Alpaslan, Faruk et al. “COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS”. Anadolu University Journal of Science and Technology A - Applied Sciences and Engineering, vol. 14, no. 3, 2015, pp. 315-28.
Vancouver Alpaslan F, Eğrioğlu E, Aladağ Ç, İlter D, Dalar A. COMPARISON OF SINGLE MULTIPLICATIVE NEURON ARTIFICIAL NEURAL NETWORK MODELS USING ABC AND BP TRAINING ALGORITHMS. AUJST-A. 2015;14(3):315-28.