A novel Model to predict fertilizers requirement using hyperbolic Growing Cosine Unit in Multilayer Perceptron classifier

IJEP 44(1): 60-67 : Vol. 44 Issue. 1 (January 2024)

Juhi Reshma S.R.* and D. John Aravindhar

Hindustan Institute of Technology and Science, School of computing Sciences, Kelambakkam – 603 103, Tamil Nadu, India


The backbone of the Indian economy is agriculture, most of the rural populations are dependent on agricultural activities for their daily livelihood. Due to increased population, it is necessary to make use of available land more effectively and it is also essential to focus on soil quality. Overuse of fertilizers has become a growing concern, which can degrade the soil quality. The amount of NPK for each crop considering the soil nutrient values should be predicted and recommended to the farmers to prevent soil degradation. Different machine learning techniques were used in different scenarios to support agriculture and to bridge the gap between agriculture and technology. In this study, requirement of fertilizers is recommended using multilayer perceptron method. A hyperbolic growing cosine unit (GCU) is introduced in MLP to provide better accuracy when compared with multilayer perception (MLP) without hyperbolic GCU.


Multilayer perception, Hyperbolic, Growing cosine unit, Agriculture, Fertilizers, Machine learning


  1. Ertugrul, O.F. 2018. A novel type of activation function in artificial neural networks: Trained activation function. Neural Networks. 99:148-157.
  2. FAO, IFAD, UNICEF, WFP and WHO. 2021. The state of food security and nutrition in the world 2021. Transforming food systems for food security, improved nutrition and affordable healthy diets for all. Food and Agriculture Organization of the United Nations.
  3. Mehri, M., A. Rostamizadeh and A. Talwalkar. 2018. Foundations of machine learning. MIT Press.
  4. Choubin, B., et al. 2016. Multiple linear regression, multilayer perception network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signals. Hydrol. Sci. J., 61(6):1001-1009.
  5. Madaras, M. and M. Koubava. 2015. Potassium availability and soil extraction tests in agricultural soils with low exhangeable potassium conted. Plant Soil Env., 61(5):234-239.
  6. Parviz, L. 2020. Performance evaluation of remote sensing data with machine learning technique to determine soil colour. Polish J. Soil Sci., 53:(1):97.
  7. Pham, V., D.C. Weindort and T. Dang. 2021. Soil profile analysis using interactive visualizations machine learning and deep learning. Computers Electronics Agric., 191:106539.
  8. Pokrajac, D. and Z. Obradovic. 2001. Neural network-based software for fertilizer optimization in precision forming. LICNNO1 International Joint Conference on Neural network (Cat. no. 01CH37 222). Proceedings, vol. 3, pp 2110-215.
  9. Sivaramakrishnan, N., et al. 2021. A deep learning based hydbrid model for recommendation generation and ranking. Neural Computing Applications. 33:10719-10736.
  10. Wang, P., B.A. Hafshejani and D. Wang. 2021. An improved multilayer perception approach for detecting sugarcane yield production in IOT based smart agriculture. Microprocessors Microsys., 82: 1038 22.
  11. Kashinathan, T., D. Singaraju and S.R. Uyyala. 2021. Insect classification and detection in field crops using modern machine learning techniques. Inf. Processing Agric., 8(3): 446-457.
  12. Liakos, K.G., et al. 2018. Machine learning in agriculture: A review. Sensors. 18(8):2674.
  13. Konkel, R. 2014. The monetization of global poverty: The concept of poverty in World Bank history, 1944-90. J. Global History. 9(2):276-300.
  14. Standing, G. 1999. Global feminization through flexible labour: A theme revisited. World Develop., 27(3): 583-602.
  15. Tilak, J.B. 1982. Education priorities in the sixth five year plan in India. Rajasthan Eco. J., 6(2): 1-12.
  16. Venkatesh, P., V. Sangeetha and P. Singh. 2016. Relationship between food production and consumption diversity in India: Empirical evidences from cross section analysis. Agric. Eco. Review. 29: 139-148.
  17. Palanisami, K., et al. 2009. Diversification of agriculture in coastal districts of Tamil Nadu: A spatio-temporal analysis. Resilience project report.
  18. Li, Y. and X. Chao. 2020. ANN-based continual classification in agriculture. Agric., 10(5):178.
  19. Michelon, G.K., et al. 2018. Artificial neural networks to estimate the productivity of soybeans and corn by chlorophyll readings. J. Plant Nutrition. 41(10): 1285-1292.
  20. Vincent, D.R., et al. 2019. Sensors driven AI-based agriculture recommendation model for assessing land suitability. Sensors. 19(17):3667.
  21. Basilaia, G., et al. 2020. Replacing the classic learning form at universities as an immediate response to the Covid-19 virus infection in Georgia. Int. J. Res. Appl. Sci. Eng. Tech., 8(3):101-108.
  22. Nosratabadi, S., et al. 2021. Prediction of food production using machine learning algorithms of multiplayer perceptran and ANFIS. Agric., 11(5): 408.
  23. Farzad, A., H. Mashayekhi and H. Hasanpour. 2019. A comparative performance analysis of different activation functions in LSTM networks for classification. Neural Computing Applications. 37:2507-2521.
  24. Najah, A., et al. 2014. Performance of ANFIS vs MLP-NN dissolved oxygen prediction models in water quality monitoring. Env. Poll. Res., 21:1658-1670.
  25. Bolandnazar, E., A. Rohini and M. Taki. 2020. Energy consumption forecasting i agriculture by artificial intelligence and mathematical model. Energy Sources. Part A. Recovery utilization Env. Effects. 42(3):1618-1632.
  26. Penalver-Cruz, A. and F.G. Horgan. 2022. Interactions between rice resistance to plonthoppers and honey dew-related egg parasitism under varying levels of nitrogenous fertilizers. Insects. 13(3):251.
  27. Ramezanpour, M.R. and M. Farajpour. 2022. Application of artificial neural networks and genetic algorithm to predict and optimize greenhouse banana fruit yield through nitrogen, potassium and magnesium. Plos One. 17(2):e0264040.
  28. Wojcieszak, D., et al. 2021. Assessment of the content of dry matter and dry organic matter in compost with neural modelling methods. Agric., 11(4):307.
  29. Radhika, K. and D.M. Latha. 2019. Machine learning model for automation of soil texture classification. Indian J. Agric. Res., 53(1):78-82.
  30. Gomes, G.S.S., T.B. Ludermir and I.M. Lima. 2011. Comparison of new activation functions in neural network for forecasting financial time series. Neural Computing Application. 20:417-439.
  31. Kumar, Y., et al. 2022. Multiclass classification of nutrients deficiency of apple using deep neural network. Neural Computing Applications. 1-12.
  32. Latifi, Z. and H.S. Fami. 2022. Forecasting wheat production of Iran using time series technique and artificial neural network. J. Agric. Sci Tech., 24(2): 261-273.
  33. Sun, C., et al. 2019. Using of multi-source and multi-temporal remote sensing data improves crop-type mapping in the subtropical agriculture region. Sensors. 19(10):2401.