No abstract

In the big data era, clustering is one of the most popular data mining method. The majority of clustering algorithms have complications like automatic cluster number determination, poor clustering precision, inconsistent clustering of various datasets and parameter-dependent etc. A new fuzzy autonomous solution for clustering named Meskat-Mahmudul (MM) clustering algorithm proposed to overcome the complexity of parameter-free automatic cluster number determination and clustering accuracy. MM clustering algorithm finds out the exact number of clusters based on Average Silhouette method in multivariate mixed attribute dataset, including real-time gene expression dataset and dealt missing values, noise and outliers. MM Extended K-Means (MMK) clustering algorithm is an enhancement of the K-Means algorithm, which serves the purpose for automatic cluster discovery and runtime cluster placement. Several validation methods used to evaluate cluster and certify optimum cluster partitioning and perfection. Some datasets used to assess the performance of the proposed algorithms to other algorithms in terms of time complexity and clustering efficiency. Finally, MM clustering and MMK clustering algorithms found superior over conventional algorithms.

The fact that reflects the cancer research consequences shows that still there are improvements that should be investigated in the stream of cancer in future. This leads the researchers to actively involve further in cancer research field. As an invention, a hybrid machine learning method is proposed in this study where two filters are assessed along with a wrapper approach. Typically, filters prioritize the features while, wrappers contribute in subset identification. Though both filters and wrappers exist independently, the excellent results they produce when applied subsequently. The wrapperfilter combination plays a major role in feature selection. Yet, incorporating with a best strategy for feature space analysis is crucial in this concern. Thus, we introduce the Evolutionary Algorithm in the proposed study to search through the feature space for informative gene subset selection. Though there are several gene selection approaches for cancer classification, many of them suffer from law classification accuracy and huge gene subset for prediction. Hence, we propose Evolutionary Algorithm to overcome this problem. The proposed approach is evaluated on five microarray datasets, where three out of them provide 100% accuracy. Regardless the number of genes selected, both filters provide the same performance throughout the datasets used. As a consequence, the Evolutionary Algorithm in feature space search is highlighted for its performance in gene subset selection.

Automatic cluster detection is crucial for real-time gene expression data where the quantity of missing values and noise ratio is relatively high. In this paper, algorithms of dynamical determination of the number of cluster and clustering have been proposed without any pre and post clustering assumptions. Proposed fuzzy Meskat-Hasan (MH) clustering provides solutions for sophisticated datasets. MH clustering extracts the hidden information of the unknown datasets. Based on the findings, it determines the number of clusters and performs seed based clustering dynamically. MH Extended K-Means cluster algorithm which is a nonparametric extension of the traditional K-Means algorithm and provides the solution for automatic cluster detection including runtime cluster selection. To ensure the accuracy and optimum partitioning, seven validation techniques were used for cluster evaluation. Four well known datasets were used for validation purposes. In the end, MH clustering and MH Extended K-Means clustering algorithms were found as a triumph over traditional algorithms.

Outbreak prediction is a way to predict the epidemic potentials of diseases using the pattern of medication sales values. Successful prediction might result in being cautious of the outbreak of diseases and taking necessary measures to prevent the predicted outcome. As medication sales values are too random, the analysis of medication correlation is one of the most interesting and challenging parts for the researchers. The major objective of this proposed research method is to analyze medication drug sales values for a certain period of a pharmaceutical company using statistical methods. It is also the intent of this research to make a comparative analysis of the output generated by the deep learning model with the real sales values of a month. Our method successfully predicts the outbreak potential of diseases with competent accuracy, so that we will have enough time to take precautions and prevent future pandemics through precautionary measures.