A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network
Yıl: 2019 Cilt: 27 Sayı: 6 Sayfa Aralığı: 4246 - 4255 Metin Dili: İngilizce DOI: 10.3906/elk-1903-75 İndeks Tarihi: 22-05-2020
A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network
Öz: The random vector functional link (RVFL) has successfully been employed in many applications since 1989.RVFL has a single hidden layer feedforward structure that also has direct links between the input layer and the outputlayer. Although nonlinearity, high generalization capacity, and fast training ability can be provided in RVFL, it can befound from the literature that higher nonlinearity can be obtained by adding recurrent feedback to an artificial neuralnetwork. In this paper, the recurrent type of RVFL (R-RVFL), which has both outer feedbacks and also inner feedbacks,is proposed. In order to evaluate and validate the proposed approach, a total of 109 public datasets were employed.Obtained results showed that R-RVFL can be employed successfully in terms of obtained success rates.
Anahtar Kelime: Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık
- [1] McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bulletin Of Mathematical Biophysics 1943; 5 (4): 115–133. doi: 10.1007/BF02478259
- [2] Wang D. Editorial: Randomized algorithms for training neural networks. Information Sciences 2016; 364–365: 126–128. doi: 10.1016/j.ins.2016.12.007
- [3] Zhang L, Suganthan PN. A comprehensive evaluation of random vector functional link networks. Information Sciences 2016; 367–368: 1094–1105. doi: 10.1016/j.ins.2015.09.025
- [4] Zhang L, Suganthan PN. A survey of randomized algorithms for training neural networks. Information Sciences 2016; 364: 146–155. doi: 10.1016/j.ins.2016.01.039
- [5] Schmidt WF, Kraaijveld MA, Duin RPW. Feed forward neural networks with random weights. In: IEEE 11th International Conference on Pattern Recognition; The Hague, the Netherlands; 1992. pp. 1–4.
- [6] Pao YH, Park GH, Sobajic DJ. Learning and generalization characteristics of the random vector functional-link net. Neurocomputing 1994; 6 (2): 163–180. doi: 10.1016/0925-2312(94)90053-1
- [7] Li M, Wang D. Insights into randomized algorithms for neural networks: practical issues and common pitfalls. Information Sciences 2017; 382–383: 170–178. doi: 10.1016/j.ins.2016.12.007
- [8] Ho S, Xie M, Goh T. A comparative study of neural network and Box-Jenkins ARIMA modeling in time series prediction. Computers and Industrial Engineering 2002; 42 (2): 371–375. doi: 10.1016/S0360-8352(02)00036-0
- [9] Lukoševičius M, Jaeger H. Reservoir computing approaches to recurrent neural network training. Computer Science Review 2009; 3 (3): 127–149. doi: 10.1016/j.cosrev.2009.03.005
- [10] Kermanshahi B. Recurrent neural network for forecasting next 10 years loads of nine Japanese utilities. Neurocomputing 1998; 23 (1): 125–133. doi: 10.1016/S0925-2312(98)00073-3
- [11] Pai PF, Hong WC. Forecasting regional electricity load based on recurrent support vector machines with genetic algorithms. Electric Power Systems Research 2005; 74 (3): 417–425. doi: 10.1016/j.epsr.2005.01.006
- [12] Alanis AY, Sanchez EN, Loukianov AG, Hernandez EA. Discrete-time recurrent high order neural networks for nonlinear identification. Journal of the Franklin Institute 2010; 347 (7): 1253–1265. doi: 10.1016/j.jfranklin.2010.05.018
- [13] Li L, Haykin S. A cascaded recurrent neural network for real-time nonlinear adaptive filtering. In: IEEE International Conference on Neural Networks; San Francisco, CA, USA; 1993. pp. 857–62. doi: 10.1109/ICNN.1993.298670
- [14] Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: International Joint Conference on Artificial Intelligence; Montreal, Canada; 1995. pp. 1–7.
- [15] Xu QS, Liang YZ. Monte Carlo cross validation. Chemometrics and Intelligent Laboratory Systems 2001; 56 (1): 1–11. doi: 10.1016/S0169-7439(00)00122-2
- [16] Duin RP, Juszczak P, Paclik P, Pekalska E, De Ridder D. PR-Tools 4.0, A MATLAB Toolbox for Pattern Recognition. The Netherlands, 2004.
- [17] Arrieta O, Vilanova R, Balaguer P. Procedure for cascade control systems design: choice of suitable PID tunings. International Journal of Computers Communications and Control 2008; 3 (3): 235–248. doi: 10.15837/ijccc.2008.3.2392
- [18] Shinskey FG. Process-Control Systems: Application, Design, Adjustment. New York, NY, USA: McGraw-Hill, 1979.
- [19] Ertuğrul ÖF. A novel approach for extracting ideal exemplars by clustering for massive time-ordered datasets. Turkish Journal of Electrical Engineering and Computer Sciences 2017; 25 (4): 2614-2634. doi: 10.3906/elk-1602- 341
| APA | Ertuğrul Ö (2019). A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. , 4246 - 4255. 10.3906/elk-1903-75 |
| Chicago | Ertuğrul Ömer Faruk A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. (2019): 4246 - 4255. 10.3906/elk-1903-75 |
| MLA | Ertuğrul Ömer Faruk A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. , 2019, ss.4246 - 4255. 10.3906/elk-1903-75 |
| AMA | Ertuğrul Ö A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. . 2019; 4246 - 4255. 10.3906/elk-1903-75 |
| Vancouver | Ertuğrul Ö A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. . 2019; 4246 - 4255. 10.3906/elk-1903-75 |
| IEEE | Ertuğrul Ö "A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network." , ss.4246 - 4255, 2019. 10.3906/elk-1903-75 |
| ISNAD | Ertuğrul, Ömer Faruk. "A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network". (2019), 4246-4255. https://doi.org/10.3906/elk-1903-75 |
| APA | Ertuğrul Ö (2019). A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. Turkish Journal of Electrical Engineering and Computer Sciences, 27(6), 4246 - 4255. 10.3906/elk-1903-75 |
| Chicago | Ertuğrul Ömer Faruk A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. Turkish Journal of Electrical Engineering and Computer Sciences 27, no.6 (2019): 4246 - 4255. 10.3906/elk-1903-75 |
| MLA | Ertuğrul Ömer Faruk A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. Turkish Journal of Electrical Engineering and Computer Sciences, vol.27, no.6, 2019, ss.4246 - 4255. 10.3906/elk-1903-75 |
| AMA | Ertuğrul Ö A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. Turkish Journal of Electrical Engineering and Computer Sciences. 2019; 27(6): 4246 - 4255. 10.3906/elk-1903-75 |
| Vancouver | Ertuğrul Ö A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network. Turkish Journal of Electrical Engineering and Computer Sciences. 2019; 27(6): 4246 - 4255. 10.3906/elk-1903-75 |
| IEEE | Ertuğrul Ö "A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network." Turkish Journal of Electrical Engineering and Computer Sciences, 27, ss.4246 - 4255, 2019. 10.3906/elk-1903-75 |
| ISNAD | Ertuğrul, Ömer Faruk. "A novel randomized recurrent artificial neural network approach: recurrent random vector functional link network". Turkish Journal of Electrical Engineering and Computer Sciences 27/6 (2019), 4246-4255. https://doi.org/10.3906/elk-1903-75 |
