Clustering the Preprocessed Automated Blood Cell Counter Data using Modified K-means Algorithms and Generation of Association Rules

Abstract

The raw data from an Automated Blood Cell Counter is transformed in to a Preprocessed and Flattened data using the preprocessing phases of the Knowledge Discovery in Databases and the transformed data is used to create clusters of the database in this paper. The K-Means algorithm is applied on the database to form various clusters. Twelve thousand records are taken from a clinical laboratory for processing. Associations among the various attributes of the database are generated. General TermsAlgorithms.

Blood Tumor Prediction Using Data Mining Techniques

“…The accuracy results of their experiments exceeded 90%, and it showed that the critical point which can be the first indicator of the thalassemia existence is MCV ≤ 77.65. Also, Minnie and Srinivasan in [11] used data mining on Blood Cell Counter data to convert the raw data into transformed data that can be used for generating knowledge. They used association rules and clusters on the collected data.…”

Clustering the Age Classified Preprocessed Automated Blood Cell Counter Data using K-Means First Distinct Element Selection and Random Selection Algorithms

“…[11] Automated Blood Cell Counter Data is clustered using the RBC attribute where the initial mean is selected as first k elements from the sorted ABCC data. [12] Genetic Algorithm (GA) and Entropy based fuzzy clustering (EFC) are used to assign k-means initial cluster centers for clustering PIMA Indian diabetic dataset. [13] …”