Application of Data Mining Algorithms for Feature Selection and Prediction of Diabetic Retinopathy

Abstract

Diabetes Retinopathy is a disease which results from a prolonged case of diabetes mellitus and it is the most common cause of loss of vision in man. Data mining algorithms are used in medical and computer fields to find effective ways of forecasting a particular disease. This research was aimed at determining the effect of using feature selection in predicting Diabetes Retinopathy. The dataset used for this study was gotten from diabetes retinopathy Debrecen dataset from the University of California in a form suitable for mining. Feature selection was executed on diabetes retinopathy data then the Implementation of k-Nearest Neighbour, C4.5 decision tree, Multi-layer Perceptron (MLP) and Support Vector Machines was conducted on diabetes retinopathy data with and without feature selection. There was access to the algorithms in terms of accuracy and sensitivity. It is observed from the results that, making use of feature selection on algorithms increases the accuracy as well as the sensitivity of the algorithms considered and it is mostly reflected in the support vector machine algorithm. Making use of feature selection for classification also increases the time taken for the prediction of diabetes retinopathy.

Amazon Employees Resources Access Data Extraction via Clonal Selection Algorithm and Logic Mining Approach

“…[ 69 ] applied an NB classifier to provide information for risk management of handling customers with credit risks. In [ 70 ], this work applies SVM analysis with a confusion matrix to accentuate feature selection and classification. However, the gained for the SVM method is lower than DHNN3-SATCSA.…”

Credit Risk Prediction in Commercial Bank Using Chi-Square with SVM-RBF

“…It is of importance for banking sectors to strategic in their mode of analysis. Data mining has proven to help discover patterns and relationship in data [12][13][14]. An overview of machine learning techniques and its applications in the banking sector was studied.…”

“…Datamining is the discovery of the knowledge of huge amount of data, which helps in discovering interesting patterns within the data for decision making, that can help predicts and classify the behaviour of the model [12,14,29]. Converting the information into meaningful form is a needful competitive intelligence.…”

Semantics-based clustering approach for similar research area detection

“…The cosine similarity measure is used to determine the similarity of the different companies using their keywords, the top K most similar companies are stored as neighbor companies and researchers with connections to a neighboring company are potential collaborators of its neighboring companies. The approach used by [23] to predict potential research collaborations involves the use of the online social network [20] to determine the co-authorship network. The latent dirichlet allocation (LDA) algorithm is used to model a set of topics from a document corpus consisting of authored papers, these are then represented in a K-dimensional vector.…”