Abstract
This research mainly based on multilayer perceptron (MLP) neural networks technique of data mining to forecast the wheat crop yield at the district level. There are many statistical and simulation models available, but the proposed algorithm with new activation function provides promising results in a shorter time with more accuracy. Sigmoid and hyperbolic tangent activation functions are widely used in the neural network. The activation functions play an important role in the neural network learning algorithm. The main objective of the proposed work is to develop an amended MLP neural network with new activation function and revised random weights and bias values for crop yield estimation by using the different weather parameter datasets. MLP model has been tested by existing activation functions and newly created activation functions with different cases including weights and bias values. In this research study, we evaluate the result of different activation functions and recommend some new simple activation functions, named DharaSig, DharaSigm and SHBSig, to improve the performance of neural networks and accurate results. Also, three new activation functions created with little variations in the DharaSig function named DharaSig1, DharaSig2 and DharaSig3. In this research study, variable numbers of hidden layers are tested with the variable number of neurons per hidden layer for the agriculture dataset. Variable values of momentum, seed and learning rate are also used in this study. Experiments show that newly created activation functions provide better results compared to ‘sigmoid’ default neural network activation function for agriculture datasets.
Similar content being viewed by others
Abbreviations
- DM:
-
Data mining
- SMW:
-
Standard Meteorological Week
- WEKA:
-
Waikato Environment for Knowledge Analysis
- MLP:
-
Multilayer perceptron
- MAE:
-
Mean absolute error
- MSE:
-
Mean squared error
- RMSE:
-
Root mean squared error
- MAPE:
-
Mean absolute percentage error
- RAE:
-
Relative absolute error
- RRSE:
-
Root relative squared error
- BSS:
-
Basic sun shine hours
- MAXT:
-
Maximum temperature
- MINT:
-
Minimum temperature
- RH1:
-
Morning relative humidity (%)
- RH2:
-
Afternoon relative humidity (%)
- VP1:
-
Morning vapour pressure
- VP2:
-
Afternoon vapour pressure
- AF:
-
Activation function
- DA:
-
Direction accuracy
References
Aditya Shastry K, Sanjay HA, Deshmukh A (2016) A parameter based customized artificial neural network model for crop yield prediction. J Artif Intell 9(1–3):23–32. https://doi.org/10.3923/jai.2016.23.32
Bhojani SH, Bhatt N (2018) Wheat crop yield forecasting using WEKA time series data mining technique. Int J Sci Res Comput Sci Appl Manag Stud 7(5):2–3
Muradkhanli L (2018) Neural networks for prediction of oil production. ELSEVIER IFAC Papers OnLine 51(30):415–417
Stastny J, Konecny V, Trenz O (2011) Agricultural data prediction by means of neural network. Agric Econ Czech 57(7):356–361
Paswan RP, Begum SA, Neog B (2018) Comparison of abilities of different activation functions of artificial neural network to predict crop area and crop production. Int J Pure Appl Biosci 6(6):212–220. https://doi.org/10.18782/2320-7051.7145
da Gomes GSS, Ludermir TB, Lima LMMR (2011) Comparison of new activation functions in neural network for forecasting financial time series. Neural Comput Appl 20:417–439. https://doi.org/10.1007/s00521-010-0407-3
Dudek G (2019) Generating random weights and biases in feedforward neural networks with random hidden nodes. Information sciences. arXiv:1908.05864 [cs.LG], pp 33–56
Dudek G (2017) A method of generating random weights and biases in feedforward neural networks with random hidden nodes. arXiv:1710.04874 [cs.NE]
Nwankpa C, Ijomah W, Gachagan A, Marshall S (2018) Activation functions: comparison of trends in practice and research for deep learning. arXiv:1811.03378 [cs.LG]
Usha TM, Appavu Alias Balamurugan S (2016) Seasonal based electricity demand forecasting using time series analysis. Circuits Syst 7:3320–3328
Niedbała G, Kozłowski R (2019) Application of artificial neural networks for multi-criteria yield prediction of winter wheat. J Agric Sci Technol 21:51–61
Ganatra A, Kosta YP, Panchal G, Gajjar C (2011) Initial classification through back propagation in a neural network following optimization through GA to evaluate the fitness of an algorithm. Int J Comput Sci Inf Technol 3(1):98–116
Bhojani SH, Bhatt N (2018) Application of data mining technique for wheat crop yield forecasting for districts of Gujarat state. Int J Sci Res Public 8(7):302–306
Garg B, Aggarwal S, Sokhal J (2018) Crop yield forecasting using fuzzy logic and regression model. Elsevier Comput Electr Eng 67:383–403
Jayaram MA, Marad N (2012) Fuzzy inference systems for crop yield prediction. J. Intell. Syst. 21:363–372. https://doi.org/10.1515/jisys-2012-0016
Pabuccu H (2017) Time series forecasting with neural network and fuzzy logic. IASSR E-BWN Publication
Menaka K, Yuvaraj N (2016) A survey on crop yield prediction models. Indian J Innov Dev 5(12)
Acknowledgements
I am thankful to the Directorate of Agriculture, Gandhinagar, and Agro-meteorology Department, Anand Agricultural University, Anand, Gujarat, for providing the datasets for my research work.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
No conflicts of interest to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Shital H. Bhojani is a Research Scholar, RK University, Rajkot, Gujarat, India and Assistant Professor, AAU, Anand, Gujarat, India; Nirav Bhatt is a Associate Professor, MCA Department, RK University, Rajkot, Gujarat, India.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Bhojani, S.H., Bhatt, N. Wheat crop yield prediction using new activation functions in neural network. Neural Comput & Applic 32, 13941–13951 (2020). https://doi.org/10.1007/s00521-020-04797-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-04797-8