Crop Yield Prediction from Soil Parameters through Neupper Rule Established Algorithm

  • Authors

    • S Manimekalai
    • K Nandhini
    https://doi.org/10.14419/ijet.v7i3.34.19587
  • Agriculture, crop yield prediction, feature selection, classification.
  • Agriculture is considered as the backbone of the Indian economy. Soil classification is used to maintain and enhance its productivity, to avoid soil degradation and to overcome environmental damage. Repeated Incremental Pruning to Produce Error Reduction (Ripper) was used for crop yield prediction. Though the computational cost of this method is very much decreased, the accuracy is not much increased for prediction of crop yield. Artificial Neural Network (ANN) was widely used technique for yield prediction of crop. But with a large number of hidden layers and nodes, the training time will increase and leads to over fitting of networks. Sometimes, it comes out with hardly interpretation results. Counter Propagation ANN (CP-ANN) was a technique which combining features of both supervised and unsupervised learning technique which effectively predicted the crop yield. However, the prediction accuracy of this method is still poor. In order to overcome the above problems and to improve the crop yield prediction accuracy, a Neupper rule based algorithm is proposed in this paper. The proposed algorithm combines ANN and Ripper classifier algorithms. The soil parameters such as phosphorus (P), potassium (K), sulphur (S), calcium (C), magnesium (Mg), zinc (Zn), copper (Cu), iron (Fe) and manganese (Mn) are given as input to ANN which returns weight of each soil parameter. Then, a decision tree is constructed based on weight values. After this, rules are generated based on the building and optimization stage of Ripper algorithm. The proposed Neupper rule based algorithm improves the accuracy of crop yield prediction by combining ANN and Ripper. Finally, the experiments are carried out in terms of accuracy, precision and Root Mean Square Error (RMSE) to prove the effectiveness of the proposed crop yield prediction method.

     

  • References

    1. [1] V. Lamba, and V. S. Dhaka, “Wheat yield prediction using artificial neural network and crop prediction techniques (A Survey)â€, International Journal for Research in Applied Science and Engineering Technology, vol. 2, pp. 330-341, 2014.

      [2] S. Vijayarani, and M. Divya, “An efficient algorithm for generating classification rulesâ€, International Journal of Computer Science and Technology, vol. 2, no. 4, pp. 512- 515, 2011.

      [3] S. Khairunniza-Bejo, S. Mustaffha, and W. I. W. Ismail, “Application of artificial neural network in predicting crop yield: A reviewâ€, Journal of Food Science and Engineering, vol. 4, no. 1, pp. 1-9, 2014.

      [4] X. E. Pantazi, D. Moshou, T. Alexandridis, R. L. Whetton, and A. M. Mouazen, “Wheat yield prediction using machine learning and advanced sensing techniquesâ€, Computers and Electronics in Agriculture, vol. 121, pp. 57-65s, 2016.

      [5] P. K. Devi, and S. Shenbagavadivu, “Enhanced Crop Yield Prediction and Soil Data Analysis using Data Miningâ€, International Journal of Modern Computer Science (IJMCS), vol. 4, no. 6, pp. 1-7, 2016.

      [6] M. Paul, S. K. Vishwakarma, and A. Verma, “Analysis of Soil Behaviour and Prediction of Crop Yield using Data Mining Approachâ€, IEEE 2015 International Conference on Computational Intelligence and Communication Networks (CICN), pp. 766-771, 2015.

      [7] M. Blagojević, M. Blagojević, and V. LiÄina, “Web-based intelligent system for predicting apricot yields using artificial neural networksâ€, Scientia Horticulturae, vol. 213, pp. 125-131, 2016.

      [8] S. S. Dahikar, and S. V. Rode, “Agricultural crop yield prediction using artificial neural network approachâ€, International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering, vol. 2, no. 1, pp. 683-686, 2014.

      [9] N. Gandhi, L. J. Armstrong, and O. Petkar, “Proposed decision support system (DSS) for Indian rice crop yield predictionâ€, In Technological Innovations in ICT for Agriculture and Rural Development (TIAR), 2016 IEEE, pp. 13-18, 2016.

      [10] A. Manjula, and G. Narsimha, “XCYPF: A flexible and extensible framework for agricultural Crop Yield Predictionâ€, 2015 IEEE 9th International Conference on Intelligent Systems and Control (ISCO), IEEE, pp. 1-5, 2015.

  • Downloads

  • How to Cite

    Manimekalai, S., & Nandhini, K. (2018). Crop Yield Prediction from Soil Parameters through Neupper Rule Established Algorithm. International Journal of Engineering & Technology, 7(3.34), 908-912. https://doi.org/10.14419/ijet.v7i3.34.19587