Forecasting of Giresun Hazelnut Quantity in Giresun Province Using Pi-Sigma Artificial Neural Networks

Abstract

Artificial neural networks are frequently used to solve many problems and give successful results. Artificial neural networks, which we frequently encounter in solving forecasting problems, attract the attention of researchers with the successful results they provide. Pi-sigma artificial neural network, which is a high-order artificial neural network, draws attention with its use of both additive and multiplicative combining functions in its architectural structure. This artificial neural network model offers successful forecasting results thanks to its high-order structures. In this study, the pi-sigma artificial neural network was preferred due to its superior performance properties, and the particle swarm optimization algorithm was used for training the pi-sigma artificial neural network. To evaluate the performance of this preferred artificial neural network, monthly ready-made manufacturer sale shelled hazelnut quantities in Giresun province was used and a comparison was made with many artificial neural network models available in the literature. It has been observed that this tested method has the best performance among other compared methods.

Keywords

• Pi-Sigma Artificial Neural Network
• Particle Swarm Optimization Algorithm
• Giresun Hazelnut Quantity
• Forecasting

References

1. [1] J. L. McClelland, D. E. Rumelhart, PDP Research Group, Parallel distributed processing, 2, 1986, 20-21, Cambridge, MA: MIT press.
2. [2] S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural computation, 9(8), 1997, 1735-1780.
3. [3] Y. Shin, J. Ghosh, The pi-sigma network: An efficient higherorder neural network for pattern classification and function approximation, In IJCNN91-Seattle international joint conference on neural networks, 1, Jul. 1991, 13-18, IEEE.
4. [4] J. Kennedy, R. Eberhart, Particle swarm optimization, In Proceedings of IEEE International Conference on Neural Networks, 4, 1995, 1942-1948.
5. [5] Y. Nie, W. Deng, A hybrid genetic learning algorithm for Pi-sigma neural network and the analysis of its convergence, In 2008 fourth international conference on natural computation, Vol. 3, pp. 19-23, Oct. 2008, IEEE.
6. [6] S. Panigrahi, A. K. Bhoi, Y. Karali, A modified differential evolution algorithm trained pi-sigma neural network for pattern classification, International Journal of Soft Computing and Engineering, 3(5), (2013), 133-136.
7. [7] J. T. Lalis, E. Maravillas, Dynamic forecasting of electric load consumption using adaptive multilayer perceptron (AMLP), In 2014 International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), pp. 1-7, Nov. 2014, IEEE.
8. [8] J. Nayak, B. Naik, H. S. Behera, A hybrid PSO-GA based Pi sigma neural network (PSNN) with standard back propagation gradient descent learning for classification, In 2014 international conference on control, instrumentation, communication and computational technologies (iccicct), pp. 878-885, Jul. 2014, IEEE.

9. [9] J. Nayak, D. P. Kanungo, B. Naik, H. S. Behera, A higher order evolutionary Jordan Pi-Sigma neural network with gradient descent learning for classification, In 2014 International Conference on High Performance Computing and Applications (ICHPCA), pp. 1-6, Dec. 2014, IEEE.
10. [10] Y. Todo, H. Tamura, K. Yamashita, Z. Tang, Unsupervised learnable neuron model with nonlinear interaction on dendrites, Neural Networks, 60, 2014, 96-103.
11. [11] J. Szoplik, Forecasting of natural gas consumption with artificial neural networks, Energy, 85, (2015), 208-220.
12. [12] D. P. Kanungo, J. Nayak, B. Naik, H. S. Behera, Non-linear classification using higher order pi-sigma neural network and improved particle swarm optimization: an experimental analysis, In Computational Intelligence in Data Mining—Volume 2: Proceedings of the International Conference on CIDM, 5-6 Dec. 2015, pp. 507-518, 2016, Springer India.
13. [13] U. Akram, R. Ghazali, M. F. Mushtaq, A comprehensive survey on Pi-Sigma neural network for time series prediction, Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(3-3), (2017), 57-62.
14. [14] E. Bas, C. Grosan, E. Egrioglu, U. Yolcu, High order fuzzy time series method based on pi-sigma neural network, Engineering Applications of Artificial Intelligence, 72, (2018), 350-356.
15. [15] E. Akdeniz, E. Egrioglu, E. Bas, U. Yolcu, An ARMA type pi-sigma artificial neural network for nonlinear time series forecasting, Journal of Artificial Intelligence and Soft Computing Research, 8(2), (2018), 121-132.
16. [16] E. Egrioglu, U. Yolcu, E. Bas, Intuitionistic high-order fuzzy time series forecasting method based on pi-sigma artificial neural networks trained by artificial bee colony, Granular Computing, 4, (2019), 639-654.
17. [17] K. Yan, W. Li, Z. Ji, M. Qi, Y. Du, A hybrid LSTM neural network for energy consumption forecasting of individual households, Ieee Access, 7, (2019), 157633-157642.
18. [18] J. Q. Wang, Y. Du, J. Wang, LSTM based long-term energy consumption prediction with periodicity, Energy, 197, (2020), 117197.
19. [19] E. Bolandnazar, A. Rohani, M. Taki, Energy consumption forecasting in agriculture by artificial intelligence and mathematical models, Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 42(13), (2020), 1618-1632.
20. [20] S. C. Nayak, A fireworks algorithm based Pi-Sigma neural network (FWA-PSNN) for modelling and forecasting chaotic crude oil price time series, EAI Endorsed Transactions on Energy Web, 7(28), (2020), e2-e2.
21. [21] H. Swapna Rekha, J. Nayak, H. S. Behera, Pi-sigma neural network: Survey of a decade progress, In Computational Intelligence in Pattern Recognition: Proceedings of CIPR 2020, pp. 429-441, 2020, Springer Singapore.
22. [22] C. Kocak, A. Z. Dalar, O. Cagcag Yolcu, E. Bas, E. Egrioglu, A new fuzzy time series method based on an ARMA-type recurrent Pi-Sigma artificial neural network, Soft Computing, 24, (2020), 8243-8252.
23. [23] E. Bas, E. Egrioglu, O. Karahasan, A Pi-Sigma artificial neural network based on sine cosine optimization algorithm, Granular Computing, (2021), 1-8.
24. [24] O. Yılmaz, E. Bas, E. Egrioglu, The training of Pi-Sigma artificial neural networks with differential evolution algorithm for forecasting, Computational Economics, 59(4), (2022), 1699-1711.
25. [25] E. Bas, E. Egrioglu, E. Kolemen, A novel intuitionistic fuzzy time series method based on bootstrapped combined pi-sigma artificial neural network, Engineering Applications of Artificial Intelligence, 114, (2022), 105030.
26. [26] R. Kumar, A Lyapunov-stability-based context-layered recurrent pi-sigma neural network for the identification of nonlinear systems, Applied Soft Computing, 122, (2022), 108836.
27. [27] E. Bas, E. Egrioglu, E. Kolemen, Training simple recurrent deep artificial neural network for forecasting using particle swarm optimization, Granular Computing, 7(2), (2022), 411–420.
28. [28] E. Egrioglu, E. Bas, T. Cansu, M. A. Kara, A new nonlinear causality test based on single multiplicative neuron model artificial neural network: a case study for Turkey’s macroeconomic indicators, Granular Computing, 8(2), (2023), 391-396.
29. [29] M. Hekimoğlu, A. İ. ÇETİN, B. E. Kaya, Evaluation of Various Machine Learning Methods to Predict Istanbul’s Freshwater Consumption, International Journal of Environment and Geoinformatics, 10(2), (2023), 1-11.
30. [30] A. O. Amole, S. Oladipo, D. Ighravwe, K. A. Makinde, J. Ajibola, Comparative analysis of deep learning techniques based COVID-19 impact assessment on electricity consumption in distribution network, Nigerian Journal of Technological Development, 20(3), (2023), 23-46.
31. [31] E. Egrioglu, E. Bas, Modified pi sigma artificial neural networks for forecasting, Granular Computing, 8(1), (2023), 131-135.
32. [32] E. Bas, E. Eğrioğlu, A new recurrent pi‐sigma artificial neural network inspired by exponential smoothing feedback mechanism, Journal of Forecasting, 42(4), (2023), 802-812.
33. [33] S. Shan, H. Ni, G. Chen, X. Lin, J. Li, A Machine Learning Framework for Enhancing Short-Term Water Demand Forecasting Using Attention-BiLSTM Networks Integrated with XGBoost Residual Correction, Water, 15(20), (2023), 3605.
34. [34] T. Cansu, E. Kolemen, Ö. Karahasan, E. Bas, E. Egrioglu, A new training algorithm for long short-term memory artificial neural network based on particle swarm optimization, Granular Computing, (2023), 1-14.
35. [35] E. Egrioglu, E. Bas, O. Karahasan, Winsorized dendritic neuron model artificial neural network and a robust training algorithm with Tukey’s biweight loss function based on particle swarm optimization, Granular Computing, 8(3), (2023), 491-501.
36. [36] E. Bas, E. Egrioglu, U. Yolcu, M. Y. Chen, A Robust Learning Algorithm Based on Particle Swarm Optimization for Pi-Sigma Artificial Neural Networks, Big Data, 11(2), (2023), 105-116.
37. [37] R. Dash, R. Rautray, R. Dash, Utility of a Shuffled Differential Evolution algorithm in designing of a Pi-Sigma Neural Network based predictor model, Applied Computing and Informatics, 19(1/2), (2023), 22-40.
38. [38] Y. D. Jhong, C. S. Chen, B. C. Jhong, C. H. Tsai, S. Y. Yang, Optimization of LSTM parameters for flash flood forecasting using genetic algorithm, Water Resources Management, (2024), 1-24.
39. [39] Y. Xu, T. Liu, P. Du, Volatility forecasting of crude oil futures based on Bi-LSTM-Attention model: The dynamic role of the COVID-19 pandemic and the Russian-Ukrainian conflict, Resources Policy, 88, (2024), 104319.
40. [40] J. Zhang, H. Liu, W. Bai, X. Li, A hybrid approach of wavelet transform, ARIMA and LSTM model for the share price index futures forecasting, The North American Journal of Economics and Finance, 69, (2024), 102022.
41. [41] P. K. Kollu, T. S. Janjanam, K. S. Siram, Comparative analysis of cloud resources forecasting using deep learning techniques based on VM workload traces, Transactions on Emerging Telecommunications Technologies, 35(1), (2024), e4933.
42. [42] E. M. de Moraes Sarmento, I. F. Ribeiro, P. R. N. Marciano, Y. G. Neris, H. R. de Oliveira Rocha, V. F. S., Mota, R. da Silva Villaça, Forecasting energy power consumption using federated learning in edge computing devices, Internet of Things, 25, (2024), 101050.
43. [43] A. M. Sharma, S. Baby, V. Raghu, Forecasting High Speed Diesel Demand in India with Econometric and Machine Learning Methods, International Journal of Energy Economics and Policy, 14(1), (2024), 496.
44. [44] O. Karahasan, E. Bas, E. Egrioglu, New deep recurrent hybrid artificial neural network for forecasting seasonal time series, Granular Computing, 9(1), (2024), 19.
45. [45] G. F. Fan, Y. Y. Han, J. W. Li, L. L. Peng, Y. H. Yeh, W. C. Hong, A hybrid model for deep learning short-term power load forecasting based on feature extraction statistics techniques, Expert Systems with Applications, 238, (2024), 122012.
46. [46] E. Kolemen, E. Egrioglu, E. Bas, M. Turkmen, A new deep recurrent hybrid artificial neural network of gated recurrent units and simple seasonal exponential smoothing, Granular Computing, 9(1), (2024), 7.
47. [47] U. Rajasekaran, G. K. Sriram, A. Malini, V. Sharma, Hybrid Explainable SRNN-LSTM Architecture for Irradiance, Temperature and Wind Speed Forecasting, (2023).
48. [48] E. Bas, E. Egrioglu, T. Cansu, Robust training of median dendritic artificial neural networks for time series forecasting, Expert Systems with Applications, 238, (2024), 122080.