An optimal document clustering method using hybrid optimal feature selection and efficient soft computing classifier

In general, document grouping is an important area of text extraction commonly used for document organization, browsing, abstraction, and categorization. This is an important process used for data recovery, data processing and document management. Recently several document grouping methods have been suggested to improve system performance. However, these document grouping methods face serious challenges. The main problem with document grouping is choosing the appropriate document features and similar tools. Moreover, due to the high computational cost and memory usage of those grouping methods, they are not suitable for many documents that need to be processed on a daily basis. This paper presents the optimal method of document clustering based on hybrid optimization selection and efficient computer classification. The proposed method consists three tire processes. First, we introduce a fuzzy density fruit fly optimization (FD-FFO) algorithm for data pre-processing which removes the unwanted artifacts and redundant content from the documents. Second, we illustrate the teaching–learning-based Harris Hawks optimization (TL-HHO) algorithm for optimal feature selection which computes best and optimal features among multiple features in document. Then, we offer a support vector regression probabilistic neural network (SVR-PNN) for optimal document clustering which improves the performance of clustering. Finally, the proposed SVR-PNN method which is evaluated by Reuters, 20 Press database and Web-snippets database. The performance of proposed SVR-PNN method can compare with existing methods such as Rider-Moth Flame optimization algorithm (RMFO), Correlation Based Incremental Clustering Algorithm (CBICA), Incremental Construction of GMM Tree (ICGT) and Weighted Probabilistic Latent Semantic Analysis (WPLSA) using Precision, Accuracy, F-Measure and Recall.