Diabetes Mellitus Prediction System Using Hybrid KPCA-GA-SVM Feature Selection Techniques

Abstract

Diabetes mellitus is a serious health issue in healthcare industry, which is a type of uncontrolled level of sugar. It is a chronic disease happened to the person who are having low insulin production and increase level of blood glucose because glucose is not properly utilized by body. In the medical field, predicting the correct diabetes is an important area that is under research to define a good predictive system to help the doctors to diagnose the disease. In the predictive system, feature selection plays on vital role to select the relevant feature for classification. There are several algorithms were applied on classification of diabetes data. In this proposed work, the features are transformed into high dimensional space before selection. So that the transformation of the features will give the better selection of attributes. With this effort, the proposed work implements the Kernel Principal Component Analysis for dimensionality reduction. KPCA will reduce the features space better than PCA. Once the features are transformed, the proposed work uses Genetic Algorithm to select the relevant and optimal features from the dataset. Then at the last Support Vector Machine is used as a classifier to classify the diabetes mellitus data. The proposed research on applying feature reduction before feature selection will reduce the irrelevant features that will improve the accuracy of the classification based on the selected relevant features. This proposed algorithm on diabetes mellitus data will compare with the existing algorithms to prove the effectives of the algorithm.

A Hybrid Crow Search and Grey Wolf Optimization Technique for Enhanced Medical Data Classification in Diabetes Diagnosis System

“…An infinitesimal value of γ leads to under-fitting whereas a very high value results in over-fitting [50]. We assume both parameters are in the range of {2 −5 , 2 −4 ,…, 2 4 , 2 5 }. This study assumes C and γ as 32 and 0.125, respectively (i.e., C = 2 5 (32) and γ = 2 −3 (0.125)).…”

“…Researchers have employed artificial intelligence techniques to design some DDS, which enhance the performance of the diabetes management system. Recently, several research works apply the SVM method to find out diabetes [3][4][5]. SVM is a classifier based on a supervised machine learning algorithm and capable of differentiating the 'intrinsic features' of different data samples for nonlinear problems.…”

A genetic algorithm-based feature selection approach for diabetes prediction

“…The experimental results show that the proposed technique predicted heart disease with 95.6% accuracy on the Cleveland dataset. Dinesh and Prabha [25] proposed a method that had three steps: preprocessing, feature selection, and classification to predict diabetes. "Harmony search algorithm, GA, and PSO algorithms were examined with K-means for feature selection".…”

Interval‐valued Pythagorean fuzzy linguistic KPCA model based on TOPSIS and its application for emergency group decision making

“…This method combined the nonlinear kernel function with PCA, performed linear PCA on the data in the high‐dimensional feature space of the mapping and selected the principal components (PCs) of the feature space for data dimensionality reduction. Compared with other nonlinear methods, the advantage of KPCA method is not only suitable for nonlinear optimization through a kernel function as simple as PCA, but also KPCA can use different kernel functions and parameters adjustment which is more suitable for nonlinear problems in a wider range of applications 36–38 …”

“…Compared with other nonlinear methods, the advantage of KPCA method is not only suitable for nonlinear optimization through a kernel function as simple as PCA, but also KPCA can use different kernel functions and parameters adjustment which is more suitable for nonlinear problems in a wider range of applications. [36][37][38] In real life, when an emergency occurs suddenly, decisions need to be made in a short period of time. IVPFLs can accurately and clearly express the preferences of DMs, and it described the decision information in combination with qualitative and quantitative aspects in accordance with the actual situation.…”