OsamorSoft: clustering index for comparison and quality validation in high throughput dataset

Abstract

The existence of some differences in the results obtained from varying clustering k-means algorithms necessitated the need for a simplified approach in validation of cluster quality obtained. This is partly because of differences in the way the algorithms select their first seed or centroid either randomly, sequentially or some other principles influences which tend to influence the final result outcome. Popular external cluster quality validation and comparison models require the computation of varying clustering indexes such as Rand, Jaccard, Fowlkes and Mallows, Morey and Agresti Adjusted Rand Index (ARIMA) and Hubert and Arabie Adjusted Rand Index (ARIHA). In literature, Hubert and Arabie Adjusted Rand Index (ARIHA) has been adjudged as a good measure of cluster validity. Based on ARIHA as a popular clustering quality index, we developed OsamorSoft which constitutes DNA_Omatrix and OsamorSpreadSheet as a tool for cluster quality validation in high throughput analysis. The proposed method will help to bridge the yawning gap created by lesser number of friendly tools available to externally evaluate the ever-increasing number of clustering algorithms. Our implementation was tested alongside with clusters created with four k-means algorithms using malaria microarray data. Furthermore, our results evolved a compact 4-stage OsamorSpreadSheet statistics that our easy-to-use GUI java and spreadsheet-based tool of OsamorSoft uses for cluster quality comparison. It is recommended that a framework be evolved to facilitate the simplified integration and automation of several other cluster validity indexes for comparative analysis of big data problems.

Enhancing the weighted voting ensemble algorithm for tuberculosis predictive diagnosis

“…In most previous studies 4 , 14 , 24 , single machine learning algorithms have been used for classification, and in cases where more than one algorithm is used, the emphasis is on comparison to determine which of the algorithm had a better performance. However, in this work, we introduced the use of the ensemble technique to combine more than one machine learning algorithms to produce an optimal result that shows performance is better using an ensemble for classification than using a single classifier.…”

“…This gives more credence to the model been developed to solve a particular classification issue. It is worthy to note that efforts have been made to develop medical diagnosis tools 24 especially for TB infections 25 this enhanced Weighed Voting Ensembled will further contribute to the machine learning solutions in TB diagnosis.…”

Community-Acquired Pneumonia Recognition by Wavelet Entropy and Cat Swarm Optimization

“…Two other measures: Matthews correlation coefficient (MCC) [44] and Fowlkes-Mallows index (FMI) [45] are defined as: .…”

Statistical and clustering validation analysis of primary students' learning outcomes and self-awareness of information and technical online security problems at a post-pandemic time

“…In the literature on the clustering validation topics, one can find many alternative ways of building clustering validity indices, defining the combination strategy and estimation algorithm and justifying the final "true" number of clusters (Osamor & Osamor, 2020;Nerurkar et al, 2019;Kumar et al, 2019;Granichin et al, 2015;Santos & Embrechts, 2014). All these lead to a myriad of alternative simple and sophisticated clustering validation solutions.…”