This chapter provides insight on pattern recognition by illustrating various approaches and frameworks which aid in the prognostic reasoning facilitated by feature selection and feature extraction. The chapter focuses on analyzing syntactical and statistical approaches of pattern recognition. Typically, a large set of features have an impact on the performance of the predictive model. Hence, there is a need to eliminate redundant and noisy pieces of data before developing any predictive model. The selection of features is independent of any machine learning algorithms. The content-rich information obtained after the elimination of noisy patterns such as stop words and missing values is then used for further prediction. The refinement and extraction of relevant features yields in performance enhancements of future prediction and analysis.

The rapidly evolving agronomic conditions and the cost of investing in agriculture are significant obstacles for farmers. The production of plantation crops must be increased to improve the farmers' financial state, and thus, there is a need to identify the various factors resulting in increased productivity. The proposed research aims to build a prognostic reasoning model that identifies and analyses the various optimal features influencing survival rate, flowering time, and crop yield of the areca nut crop using a data analytics technique. The optimal features are obtained by applying chi square test on the real dataset collected from the farmers. The resultant features are evaluated using different classifiers: naïve bayes, random forest, logistic regression, and decision tree. It has been found that the random forest performs better than other classifiers for the survival rate with a prediction accuracy of 99.33% and crop yield with a prediction accuracy of 99.67%. In contrast, the logistic regression gives a good result for the flowering time with a prediction accuracy of 95.33%.

No abstract

No abstract

No abstract