Fatihah Mohd

A Hybrid Selection Method Based on HCELFS and SVM for the Diagnosis of Oral Cancer Staging

A diagnostic model based on Support Vector Machines (SVM) with a proposed hybrid feature selection method is developed to diagnose the stage of oral cancer in patients. The hybrid feature selection method, named Hybrid Correlation Evaluator and Linear Forward Selection (HCELFS), combines the advantages of filters and wrappers to select the optimal feature subset from the original feature set. In HCELFS, Correlation Attribute Evaluator acts as filters to remove redundant features and Linear Forward Selection with SVM acts as the wrappers to select the ideal feature subset from the remaining features. This study conducted experiments in WEKA with ten fold cross validation. The experimental results with oral cancer data sets demonstrate that our proposed model has a better performance than well-known feature selection algorithms.

Data preparation for pre-processing on oral cancer dataset

In this paper, data pre-processing tasks involving data interpretation, data integration, noisy data, missing data, and data inconsistency are presented. The dataset prepared includes all the fields that are required for the research, pertaining to oral cancer diagnosis with demographics, social habit, clinical symptoms, and histological variables. After data normalization and transformation, the finding of the study prepared oral cancer dataset with 27 attributes as a part of study contribution. There are only one continuous and one numerical variable, which are case_id and age. The remaining variables are discrete or categorical variables.

Improved Feature Subset Selection Based on Hybrid Correlation for Disease Diagnosis

One of the important research issues in disease diagnosis is the selection of a subset of attributes that can produce the preferred output with a satisfactory level of accuracy. Therefore, the aim of this study is to improve accuracy the presence of oral cancer primary stage with elimination of the attributes that are strictly correlated with other already selected attributes. This study propose a hybrid features selection method based on a correlation evaluator and linear forward selection to address feature selection. Originally, 25 attributes from an oral cancer data set have been reduced to 14 features using proposed method feature selection in order to diagnose the oral cancer staging. Subsequently, seven classifiers: updatable Naive Bayes, multilayer perceptron, K-nearest neighbors, support vector machine, Rules-DTNB, Tree-J48, and Tree-Simple Chart are used in order to evaluate the efficiency of the features selection methods. All the evaluations are conducted in Waikato Environment Knowledge Explorer (WEKA) with tenfold cross validation. The empirical comparison shows that the subset of features generated from the proposed features selection methods with over-sampling techniques at preprocessing phases significantly improved the accuracy of the entire classifier algorithm used for the oral cancer data set with a mean accuracy of 96.53%. The implication of the study supports the suitable subset of variables in oral cancer diagnosis. Therefore, the future direction includes the consideration of using proposed feature subset to classify and generate the differential probabilities for stage diagnosis among oral cancer patients.

The Performance Comparison between Oral Cancer and Acute Inflammations Datasets Using Bayesian Model

Bayesian method is partial of intelligent computing methods that is using in reasoning and managing uncertainty problem. There is a growing interest in the use of Bayesian methods for medical diagnosis. In the literature, several studies have reviewed in different methods and findings for medical diagnosis. The purpose of this study is to compare oral cancer and acute inflammations dataset using Bayesian method for dieses diagnosis. The first experiment Bayesian method involved determining the different probabilities of the primary tumor stage as a function of demographics profile and risk habits. The second experiment involved determining the different probabilities of the acute inflammation diseases. From the experiments conducted, Bayesian method performs better on acute inflammation dataset compares to oral cancer dataset.