This paper presents a new type of endocrine neural network (ENN). ENN utilizes artificial glands which enable the network to be adaptive to external disturbances. Sensitivity is controlled by the hormone decay rate and the value of the sensitivity parameter. The network presented in this paper is improved by making the sensitivity parameter self-tuning and implementing orthogonal activation functions inside the network structure. Automatic tuning is performed on the basis of the biological principle of postsynaptic potentials by implementing inhibitory and excitatory glands inside the standard backpropagation learning algorithm of developed orthogonal ENN. These additional network functionalities enable extra sensitivity to external conditions and an additional network feature of activation sharpening. The network was tested on real-time series of experimental data with a purpose to forecast exchange rate of the three widely used international currencies.
Issue Section:
Research Papers
References
1.
Philip
, A. A.
, Taofiki
, A. A.
, and Bidemi
, A. A.
, 2011
, “Artificial Neural Network Model for Forecasting Foreign Exchange Rate
,” World Comput. Sci. Inf. Technol. J.
, 1
(3
), pp. 110
–118
.2.
Erdogan
, O.
, and Goksu
, A.
, 2014
, “Forecasting Euro and Turkish Lira Exchange Rates With Artificial Neural Networks (ANN)
,” Int. J. Acad. Res. Accounting, Finance Manage. Sci.
, 4
(4
), pp. 307
–316
.3.
Zhang
, G.
, and Berardi
, V.
, 2001
, “Time Series Forecasting With Neural Network Ensembles: An Application for Exchange Rate Prediction
,” J. Operational Res. Soc.
, 52
(6
), pp. 652
–664
.4.
Yu
, L.
, Wang
, S.
, and Lai
, K.
, 2005
, “Adaptive Smoothing Neural Networks in Foreign Exchange Rate Forecasting
,” 5th International Conference, Computational Science—
ICCS 2005
, Atlanta, GA, May 22–25, pp. 523
–530
.5.
Chen
, A.
, Hsu
, Y.
, and Hu
, K.
, 2008
, “A Hybrid Forecasting Model for Foreign Exchange Rate Based on a Multi-Neural Network
,” 4th International Conference on Natural Computation
, ICNC
, Oct. 18–20, Vol. 5
, pp. 293
–298
.6.
Chen
, Y.
, Peng
, L.
, and Abraham
, A.
, 2006
, “Exchange Rate Forecasting Using Flexible Neural Trees
,” Advances in Neural Networks
(Lecture Notes in Computer Science), J.
Wang
, Z.
Yi
, J. M.
Zurada
, B.-L.
Lu
, and H.
Yin
, eds., Vol. 3973
, Springer
, Berlin
, pp. 518
–523
.7.
Gomes
, G. S. D. S.
, Ludermir
, T. B.
, and Lima
, L. M.
, 2010
, “Comparison of New Activation Functions in Neural Network for Forecasting Financial Time Series
,” Neural Comput. Appl.
, 20
(3
), pp. 417
–439
.8.
Tenti
, P.
, 1996
, “Forecasting Foreign Exchange Rates Using Recurrent Neural Networks
,” Appl. Artif. Intell.
, 10
(6
), pp. 567
–582
.9.
Pino
, R.
, Parreno
, J.
, Gomez
, A.
, and Priore
, P.
, 2008
, “Forecasting Next-Day Price of Electricity in the Spanish Energy Market Using Artificial Neural Networks
,” Eng. Appl. Artif. Intell.
, 21
(1
), pp. 53
–62
.10.
Božić
, J.
, and Babić
, D.
, 2015
, “EUR/RSD Exchange Rate Forecasting Using Hybrid Wavelet-Neural Model: A Case Study
,” Comput. Sci. Inf. Syst.
, 12
(2
), pp. 487
–508
.11.
Sa'Adah
, U.
, Seno
, S.
, Guritno
, S.
, and Suhartono
, S.
, 2015
, “Wavelet Neural Network Model Selection for Nonlinear-Seasonal Time Series Forecasting
,” Global J. Pure Appl. Math.
, 11
(1
), pp. 137
–148
.12.
Li
, A.
, and Wu
, J.
, 2012
, “Modeling and Prediction With Wavelet Neural Network in the On-Linear Time Series
,” Int. Rev. Comput. Software
, 7
(7
), pp. 3617
–3621
.13.
Timmis
, J.
, Neal
, M.
, and Thorniley
, J.
, 2009
, “An Adaptive Neuro-Endocrine System for Robotic Systems
,” IEEE
Workshop on Robotic Intelligence in Informationally Structured Space
, Nashville, TN, Mar. 30–Apr. 2, Vol. 1
, pp. 129
–136
.14.
Timmis
, J.
, Murray
, L.
, and Neal
, M.
, 2010
, “A Neural-Endocrine Architecture for Foraging in Swarm Robotic Systems
,” Gonzales
, J. R.
, Pelta
, D. A.
, Cruz
, C.
, Terrazas
, G.
, and Krasnogor
, N.
, eds., Nature Inspired Cooperative Strategies for Optimization (NICSO 2010)
(Studies in Computational Intelligence), Springer
, Berlin
, Vol. 284
, pp. 319
–330
.15.
Chen
, D.
, Wang
, J.
, Zou
, F.
, Yuan
, W.
, and Hou
, W.
, 2014
, “Time Series Prediction With Improved Neuro-Endocrine Model
,” Neural Comput. Appl.
, 24
(6
), pp. 1465
–1475
.16.
Sauze
, C.
, and Neal
, M.
, 2013
, “Artificial Endocrine Controller for Power Management in Robotic Systems
,” IEEE Trans. Neural Networks Learn. Syst.
, 24
(12
), pp. 1973
–1985
.17.
French
, R.
, 1991
, “Using Semi-Distributed Representations to Overcome Catastrophic Forgetting in Connectionist Networks
,” 13th Annual Cognitive Science Society Conference
, Vol. 1
, pp. 173
–178
.18.
Jian
, B.
, Yi
, Y.
, and Bin
, Z.
, 2009
, “Research on Real-Time Image Sharpening Methods Based on Optimized Neural Network
,” 5th International Conference on Natural Computation
, Vol. 2
, pp. 424
–428
.19.
Ans
, B.
, and Rousset
, S.
, 2000
, “Neural Networks With a Self-Refreshing Memory: Knowledge Transfer in Sequential Learning Tasks Without Catastrophic Forgetting
,” Connect. Sci.
, 12
(1
), pp. 1
–19
.20.
Billings
, S.
, Jamaluddin
, H.
, and Chen
, S.
, 1991
, “A Comparison of the Backpropagation and Recursive Prediction Error Algorithms for Training Neural Networks
,” Mech. Syst. Signal Process.
, 5
(3
), pp. 233
–255
.21.
Kumar
, K.
, 1992
, “Backpropagation Algorithm for a Generalized Neural Network Structure
,” IEEE S Southeastcon
, Apr. 12–15, Vol. 2
, pp. 646
–649
.22.
Nikolić
, S. S.
, Antić
, D. S.
, Milojković
, M. T.
, Milovanović
, M. B.
, Perić
, S. L.
, and Mitić
, D. B.
, 2016
, “Application of Neural Networks With Orthogonal Activation Functions in Control of Dynamical Systems
,” Int. J. Electron.
, 103
(4
), pp. 667
–685
.23.
Milojković
, M.
, Antić
, D.
, Milovanović
, M.
, Nikolić
, S. S.
, Perić
, S.
, and Almawlawe
, M.
, 2015
, “Modeling of Dynamic Systems Using Orthogonal Endocrine Adaptive Neuro-Fuzzy Inference Systems
,” ASME J. Dyn. Syst. Meas. Control
, 137
(9
), p. 091013
.24.
Perić
, S.
, Antić
, D.
, Milovanović
, M.
, Mitić
, D.
, Milojković
, M.
, and Nikolić
, S.
, 2016
, “Quasi-Sliding Mode Control With Orthogonal Endocrine Neural Network-Based Estimator Applied in Anti-Lock Braking System
,” IEEE/ASME Trans. Mech.
, 21
(2
), pp. 754
–764
.25.
Rumelhart
, D.
, Hinton
, G.
, and Williams
, R.
, 1986
, “Learning Internal Representations by Error Propagation
,” Parallel Distributed Processing
, D.
Rumelhart
and J.
McClelland
, eds., Vol. 1
, MIT Press
, Cambridge, MA
.26.
Antweiler, W.,
2015
, “Service for Academic Research and Teaching
,” University of British Columbia, Vancouver, Canada, accessed Apr. 11, 2015, http://fx.sauder.ubc.ca/27.
Kaastra
, I.
, and Boyd
, M.
, 1996
, “Designing a Neural Network for Forecasting Financial and Economic Time Series
,” Neurocomputing
, 10
(3
), pp. 215
−236
.28.
Zhu
, X.
, Chen
, J.
, and Zhong
, M.
, 2015
, “Dynamic Interacting Relationships Among International Oil Prices, Macroeconomic Variables and Precious Metal Prices
,” Trans. Nonferrous Met. Soc. China
, 25
(2
), pp. 669
−676
.29.
Imandoust
, S.
, and Fahimifard
, S.
, 2010
, “Application of NNRAX to Agricultural Economic Variables Forecasting
,” J. Appl. Sci.
, 10
(13
), pp. 1263
–1270
.30.
Lee
, C.
, Chung
, P.
, Tsai
, J.
, and Chang
, C.
, 1999
, “Robust Radial Basis Function Neural Networks
,” IEEE Trans. Syst. Man Cybern.
, 29
(6
), pp. 674
−685
.31.
Gardner
, W.
, and Dorling
, S. R.
, 1998
, “Artificial Neural Networks (The Multilayer Perceptron)—A Review of Applications in the Atmospheric Sciences
,” Atmos. Environ.
, 32
(14−15
), pp. 2627
–2636
.Copyright © 2017 by ASME
You do not currently have access to this content.
