A Novel Borda Count based Feature Ranking and Feature Fusion Strategy to Attain Effective Climatic Features for Rice Yield Prediction
An attempt has been made in the agricultural field to predict the effect of climatic variability based on rice crop production and climatic features of three coastal regions of Odisha, a state of India. The novelty of this work is Borda Count based fusion strategy on the ranked features obtained from various ranking methodologies. The proposed prediction model works in three phases; in the first phase, three feature ranking approaches such as; Random Forest, Support Vector Regression-Recursive Feature Elimination (SVR-RFE) and F-Test are applied individually on the two datasets of three coastal areas and features are ranked as per their algorithm. In the second phase; Borda Count as a fusion method has been implemented on those ranked features from the above phase to obtain the top five best features. The multi quadratic activation function based Extreme Learning Machine (ELM) has been used to predict the rice crop yield using those ranked features obtained from fusion-based raking strategy and the number of varying features are obtained which gives prediction accuracy above 99% in the third phase of experimentation. Finally, the statistical paired T-test has been used to evaluate and validate the significance of the proposed fusion based ranking prediction model. This prediction model not only predicts the rice yield per hector but also able to obtain the significant or most affecting features during Rabi and Kharif seasons. From the observations made during experimentation, it has been found that; relative humidity is playing a vital role along with the minimum and maximum temperature for rice crop yield during Rabi and Kharif seasons.
Central Soil and water Conservation Research & Training Institute (CSWCR & TI), Vision 2030, http;//www.cswcrtiweb.org/. (Accessed on 17/10/2014)
Venkateswarlu, B., Climate change: Adaptation and mitigation strategies in rainfed agriculture. Journal of the Indian Society of Soil Science, 58, S27-S35, 2010.
Saseendran, A.S.K., Singh, K.K., Rathore, L.S, Singh, S.V. and Sinha, S.K., Effects of climate change on rice production in the tropical humid climate of Kerala, India. Climate Change, 44, 495-514, 2000.
Sarker A.R., Alam K., Gow J., Exploring the relationship between climate change and rice yield in Bangladesh: An analysis of time series data, Agricultural Systems, 112, 11-16, 2012.
Naresh Kumar, S., Aggarwal, P.K., Saxena, R. Swaroopa Rani, D.N. Jain, Surabhi and Chauhan, Nitin, An assessment of regional vulnerability of rice to climate change in India, Climate Change, 118, 3-4, 683-689, 2013.
Felipe F. Bocca, Luiz Henrique Antunes Rodrigues ,The effect of tuning, feature engineering, and feature selection in datamining applied to rainfed sugarcane yield modelling, Computers and Electronics in Agriculture, 128, 67–76, 2016.
Jason Kane Gilbertson, Adriaan van Niekerk, Value of dimensionality reduction for crop differentiation with multitemporaimagery and machine learning, Computers and Electronics in Agriculture, 142, 50–58, 2017.
Chuang Ma, Hao Helen Zhang, Xiangfeng Wang, Machine learning for Big Data analytics in plants, Trends in Plant Science December 2014, Vol. 19, No. 12.
Emrah Hancer, Bing Xue, Mengjie Zhang, Differential evolution for filter feature selection based on information theory and feature ranking, Knowledge-Based Systems, 1–17, 2017.
Alaleh Razmjoo, Petros Xanthopoulos, Qipeng Phil Zheng, Online feature importance ranking based on sensitivity analysis, Expert Systems with Applications, 85, 397–406, 2017.
Paweł Teisseyre, Feature ranking for multi-label classification using Markov networks, Neurocomputing, 205, 439–454, 2016.
Jaesung Lee, Dae-WonKim, Fast multi-label feature selection based on information-theoretic feature ranking, Pattern Recognition, 48, 2761–2771, 2015.
Shobeir Fakhraei, Hamid Soltanian-Zadeh, Farshad Fotouhi, Bias and stability of single variable classifiers for feature ranking and selection, Expert Systems with Applications, 41, 6945–6958, 2014.
Mark Andrew Hall and Geoffrey Holmes. Benchmarking attribute selection techniques for discrete class data mining. IEEE Transactions on Knowledge and Data Engineering, 15(6), 1437–1447, 2003.
Chih-Chiang Wei, Soft computing techniques in ensemble precipitation nowcast, Applied Soft Computing, 13, 793–805, 2013.
Rafael M.O. Cruz, Robert Sabourin, George D.C. Cavalcanti, META-DES. Oracle: Meta-learning and feature selection for dynamic ensemble selection, Information Fusion, 38, 84–103, 2017.
Michał Drami´nski, Alvaro Rada-Iglesias, Stefan Enroth, ClaesWadelius, Jacek Koronacki, and Jan Komorowski. Monte carlo feature selection for supervised classification, Bioinformatics, 24(1), 110– 117, 2008.
Evanthia E. Tripoliti , Dimitrios I. Fotiadis , George Manis, Modifications of the construction and voting mechanisms of the Random Forests Algorithm, Data and Knowledge Engineering, 87, 41–65, 2013.
L. Breiman, Randomforests, Machine Learning, 45(1), 5–32, 2001.
H. R. Zhang, F.Min, Three way recommender systems based on random forests, Knowledge based Systems, 91, 275-286, 2016.
Q.Wu, Y.Ye, H.Zhang, ForesTexter: an efficient random forest algorithm for imbalanced text categorization, Knowledge based Systems, 67,105-116, 2014.
C.C.Yeh, F.Lin, C.Y.Hsu, A hybrid KMV model, random forests and rough set theory approach for credit rating, Knowledge based Systems , 33,166–172, 2012.
Andy Liaw and Matthew Wiener, Classification and Regression by random Forest, R News , 2/3, 2002.
Ke Yan, David Zhang, Feature selection and analysis on correlated gas sensor data with recursive feature elimination, Sensors and Actuators B: Chemical, 212, 353–363, 2015.
Meng-Dar Shieh, Chih-Chieh Yang, Multiclass SVM-RFE for product form feature selection, Expert Systems with Applications, 35, 531–541, 2008.
Shruti Mishra, Debahuti Mishra, SVM-BT-RFE: An improved gene selection framework using Bayesian T-test embedded in support vector machine (recursive feature elimination) algorithm, Karbala International Journal of Modern Science, 1, 86-96, 2015.
Qianaren Xu, M. Kamel, M.M.A. Salama, Significance Test for Feature Subset Selection on Image Recognition, ICAR, LNCS 3211, 244-252, 2004.
Abhshek Golugula, George Lee, Anant Madabhushi, Evaluating Feature Selection Strategies for High Dimensional, Small Sample Size Datasets, 33rd Annual International Conference of the IEEE EMBS, 949-952, 2011.
Guang-Bin Huang, Qin-Yu Zhu, Chee-Kheong Siew, Extreme learning machine: Theory and applications, Neurocomputing , 70, 489-501, 2006.
Das, S.R., Mishra, D. & Rout, M., A hybridized ELM using self-adaptive multi-population-based Jaya algorithm for currency exchange prediction: an empirical assessment, Neural Comput & Applic, https://doi.org/10.1007/s00521-018-3552-8, 2018.
Li, X., Xie, H., Wang, R., Empirical analysis: stock market prediction via extreme learning machine Neural Comput & Applic, 27, 67, https://doi.org/10.1007/s00521-014-1550-z, 2016.
Balasundaram, S. & Gupta, D., Knowledge-based extreme learning machines, Neural Comput & Applic, 27, 6, https://doi.org/10.1007/s00521-015-1961-5, 2016.
Orissa Agricultural Statistics Year Book, Published by Directorate of Agriculture and Food Production, Govt. of Odisha, Bhubaneswar, 1983-2013.
SML Venkata Narasimhamurthy, AVS Pavan Kumar, Rice Crop Yield Forecasting using Random Forest Algorithm, International Journal for Research in Applied Science & Engineering Technology, 5(X), 2017.
Hari Dahal, J. K. Routray, Identifying Associations Between Soil And Production Variables Using Linear Multiple Regression Models, The Journal of Agriculture and Environment, 12, 2011.
J. P. Powell, S. Reinhard, Measuring the effects of extreme weather events on yields, Weather and Climate Extremes , 12, 69–79, 2016.
Yusof, M.F., Azamathulla, H.M. & Abdullah, R., Prediction of soil erodibility factor for Peninsular Malaysia soil series using ANN, Neural Comput & Applic, 24, 2, https://doi.org/10.1007/s00521-0121236-3, 2014.
Erdil, A., Arcaklioglu, E., The prediction of meteorological variables using artificial neural network, Neural Comput & Applic, 22, 7-8, https://doi.org/10.1007/s00521-012-1210-0, 2013.
Anitha, A., Acharjya, D.P., Crop suitability prediction in Vellore District using rough set on fuzzy approximation space and neural network, Neural Comput & Applic, https://doi.org/10.1007/s00521-0172948-1, 2017
Manzoor Ahmad Zahid, Harrie de Swart, The Borda Majority Count, Information Sciences , 295, 429-440, 2015.
J.L. García-Lapresta, M. Martínez-Panero, L.C. Meneses, Defining the Borda count in a linguistic decision making context, Information Sciences , 179, 14, 2309-2316, 2009.
Hirai GI, Chiyo H, Tanka O, Hikano T, Oanotri M, Studies on the effect of relative humidity of atmosphere on growth and physiology of rice plants. VIII effect of ambient humidity on dry matter production and nitrogen absorption at various temperatures, Japanese Journal of Crop Science, 62(3), 395-400, 1993.
Sunil KM, Crop weather relationship in rice, M.Sc. Thesis, Kerala Agricultural University, Thesis source, 2000
Vijayakumar CM, Hybrid rice seed production technology- theory and practice, Directorate of rice research, Hyderabad, 52-55, 1996.
Gridyal B P, Jana RK, Agrometerologycal environmental affecting rice yield, Agronomy Journal, 59, 286-287, 1967.
Narayanan A L, Relative influence of weather parameters on rice hybrid and variety and validation of CERES- Rice model for staggered weeks of transplanting, PhD Thesis, Tamilnadu Agricultural University, Coimbatore, 2004.
Sri CHShen ZT, Effect of high humidity and low temperature in spikelet fertility in Indica rice, IRRN, 15(3), 10-11, 1990.
Morita S., Hiroshi Wada, Yuji Matsue, “Counter measures for heat damage in rice grain quality under climate change”,Plant Production Science, 19 (1), pp-1-11, 2016.
This work is licensed under a Creative Commons Attribution 3.0 License.