Abstract:One of the most experimentally difficult problem in the world is weather forecasting, which is a basic mechanism in meteorology. Especially in data mining system, there are different information mining strategies are available, for example, K-Means, Artificial Neural Network (ANN) and Support Vector Machine (SVM), etc. These weather predicting strategies are financially high and also very inconsistent for large datasets. To overcome these issues, an effective dimensionality reducing strategy: Self Organizing Map (SOM) is proposed along with Latent Dirichlet Allocation (LDA). The SOM strategy is one of the proper dimensionality reducing strategy to highlight the self-arranging outline. After reducing the measurement, the dimensionality reduced information are used to forecast climate for a reasonable outcome. A reasonable season for an appropriate crop is arranged with the guide of Deep Neural Network (DNN) classification system. This research work depends on finding appropriate information model, which helps in accomplishing high precision and simplification for value forecast. Finally, the experimental outcome shows that the proposed approach improved accuracy in weather and crop prediction up to 7-23% compared to the existing methods.
Abstract:In India Rice and ragi are the two pre-eminent crops that stable's the food of eastern and southern part of the country. These two crops mainly grown in rain fed areas, which receives heavy annual rainfall. In this scenario, Mysore district is undertaken for experiment analysis. As the region receives heavy rainfall (782mm). In this region the rainfall rate is high but the productivity of this crops are very low due to irrelevant crop cultivation. In order to overcome this concern, an advanced technology named Weighted-Self Organizing Map (W-SOM) is employed for accurate crop and weather prediction, which is the combination of both Self Organizing Map (SOM) and Learning Vector Quantization (LVQ). In this paper, the prediction accuracy is enhanced by minimizing the Within Class Error (WCE) among the clusters. Therefore, this new approach outcome shows a clear idea about suitable crop cultivation in Mysore. Experimental outcome shows that the proposed approach improved accuracy in crop and weather prediction up to 0.5-2% compared to the existing methods: SOM, Kernel-Nearest Neighbors (KNN) and Ensemble Neural Network (ENN).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.