Feature Selection, Clustering and IoMT on Biomedical Engineering for COVID-19 Pandemic: A Comprehensive Review

Abstract

In this era, feature clustering is a prominent technique in data mining. Features clustering have also huge application in biomedical research for multiple purpose including grouping, features reduction and many more. The Internet of Medical Things (IoMT) is a promising and emerging field of research that is having a major impact on knowledge retrieval and networking. IoMT also has significant application in biomedical research regarding remote monitoring and remote healthcare services. In this COVID-19 pandemic situation, psychological effect and human reaction have become a major concern of further research. A dataset can be reduced in size by using feature selection techniques. To facilitate subsequent processing, this will make the data easier to manage. Feature selection is also used to clean, reduce, and reduce dimensions of data. The clustering method has proven to be a powerful tool for finding patterns and structure in both labeled and unlabeled data sets. Our study basically provides various state-of-the-art methods regarding medical IoMT for remote healthcare, feature clustering for information retrieval regarding biomedical science. In this study, we are used five different type of feature selection like Minimum Redundancy - Maximum Relevance (mRMR), Random Forest, Normalized Mutual Information Feature Selection (NMIFS), F-Test and Chi-Square and five different type of Clustering algorithms like Hierarchical Clustering, Density-based spatial clustering of applications with noise (DBSCAN) Clustering, K-Means Clustering, Shrinkage Clustering, and Fuzzy C-Means Clustering. Finally, this study is very useful to understand and apply the appropriate IoMT, feature clustering, and catharsis on the various biomedical applications for the benevolence of society.