Abstract
Higher Order Neural Networks (HONN) with backpropagation algorithm is conducted for predicting the time series event, which is a challenging problem under investigation. Many factors can affect the results of time series prediction. One of the most important factors is the architecture of a HONN which consists of layer, network’s order and output layer. In this study, we are focusing on the numbers of network’s order (or hidden nodes for ordinary Neural Network). Other factors are kept unchanged. The network is also tested with few other metaheuristic learning algorithms and compared to Multilayer Perceptron. Experimental results demonstrate that the effects of the numbers of network’s order on time series prediction are significant. Together with proper network’s order setup, practical analysis of results shows that 5-5-1 for PSNN-MCMC and 6-4-1 for FLNN-MCMC are the optimal network combination of input-hidden-output. The accuracy rate for both network models is around 0.037% to 0.498%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gershenfeld, N.A., Weigend, A.S.: The future of time series: learning and understanding. In: (eds.) Pattern Formation in the Physical and Biological Sciences, pp. 349–429. CRC Press (2018)
Husaini, N.A., Ghazali, R., Nawi, N.M., Ismail, L.H.: Jordan pi-sigma neural network for temperature prediction. In: Proceedings of the International Conference on Ubiquitous Computing and Multimedia Applications, pp. 547–558. Springer (2011)
Selvanambi, R., Natarajan, J., Karuppiah, M., Islam, S.H., Hassan, M.M., Fortino, G.: Lung cancer prediction using higher-order recurrent neural network based on glowworm swarm optimization. Neural Comput. Appl. 32(9), 4373–4386 (2020)
Husaini, N.A., Ghazali, R., Nawi, N.M., Ismail, L.H.: The effect of network parameters on pi-sigma neural network for temperature forecasting. Int. J. Modern Phys. Conf. Ser. World Sci. Publishing Company 9, 440–447 (2012)
Ghazali, R., Al-Jumeily, D.: Application of pi-sigma neural networks and ridge polynomial neural networks to financial time series prediction. In: (eds.) Artificial Higher Order Neural Networks for Economics and Business, pp. 271–293. IGI Global (2009)
Hassim, Y.M.M., Ghazali, R.: Optimizing functional link neural network learning using modified bee colony on multi-class classifications. In: (eds.) Advances in Computer Science and its Applications, pp. 153–159. Springer (2014)
Nolte, M., Gal, E., Markram, H., Reimann, M.W.: Impact of higher order network structure on emergent cortical activity. Network Neurosci. 4(1), 292–314 (2020)
Morris, C., et al.: Weisfeiler and leman go neural: Higher-order graph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33(1), pp. 4602–4609 (2019)
Pao, Y.-H., Takefuji, Y.: Functional-link net computing: theory, system architecture, and functionalities. Computer 25(5), 76–79 (1992)
Husaini, N.A., Ghazali, R., Yanto, I.T.R.: Enhancing modified cuckoo search algorithm by using MCMC random walk. In: Proceedings of the 2016 2nd International Conference on Science in Information Technology (ICSITech), pp. 306–311. IEEE (2016)
Weigend, A.S., Gershenfeld, N.A. (eds.): Time Series Prediction. Addison Wesley (1994)
Li, C.-Y., Guo, J.-C., Cong, R.-M., Pang, Y.-W., Wang, B.: Underwater image enhancement by dehazing with minimum information loss and histogram distribution prior. IEEE Trans. Image Process. 25(12), 5664–5677 (2016)
Makridakis, S.: Accuracy measures: theoretical and practical concerns. Int. J. Forecast. 9(4), 527–529 (1993)
Acknowledgment
The authors would like to thank Universiti Tun Hussein Onn Malaysia for funding this research activity under the Multi-disciplinary Research Grant, Vote No. H494.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Husaini, N.A., Ghazali, R., Arbaiy, N., Lasisi, A. (2022). Effects of the Number of Network’s Order Used in a Higher Order Neural Network on Time Series Prediction. In: Mahyuddin, N.M., Mat Noor, N.R., Mat Sakim, H.A. (eds) Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications. Lecture Notes in Electrical Engineering, vol 829. Springer, Singapore. https://doi.org/10.1007/978-981-16-8129-5_102
Download citation
DOI: https://doi.org/10.1007/978-981-16-8129-5_102
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8128-8
Online ISBN: 978-981-16-8129-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)