Multi Filtration Feature Selection (MFFS) to improve discriminatory ability in clinical data set

Sasikala, S.; Balamurugan, S.; Geetha, S.

doi:10.1016/j.aci.2014.03.002

Cited by 31 publications

(19 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, in order to transfer the network output between 0 and 1, the logistic sigmoid was used as the activation function [39]. The training parameters for the learning rate, momentum, and training time were selected as 0.3, 0.2, and 500, respectively [10,[40][41][42].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Comparative Assessment of Three Nonlinear Approaches for Landslide Susceptibility Mapping in a Coal Mine Area

Zhang

Zhao

et al. 2017

IJGI

View full text Add to dashboard Cite

Abstract:Landslide susceptibility mapping is the first and most important step involved in landslide hazard assessment. The purpose of the present study is to compare three nonlinear approaches for landslide susceptibility mapping and test whether coal mining has a significant impact on landslide occurrence in coal mine areas. Landslide data collected by the Bureau of Land and Resources are represented by the X, Y coordinates of its central point; causative factors were calculated from topographic and geologic maps, as well as satellite imagery. The five-fold cross-validation method was adopted and the landslide/non-landslide datasets were randomly split into a ratio of 80:20. From this, five subsets for 20 times were acquired for training and validating models by GIS Geostatistical analysis methods, and all of the subsets were employed in a spatially balanced sample design. Three landslide models were built using support vector machine (SVM), logistic regression (LR), and artificial neural network (ANN) models by selecting the median of the performance measures. Then, the three fitted models were compared using the area under the receiver operating characteristics (ROC) curves (AUC) and the performance measures. The results show that the prediction accuracies are between 73.43% and 87.45% in the training stage, and 67.16% to 73.13% in the validating stage for the three models. AUCs vary from 0.807 to 0.906 and 0.753 to 0.944 in the two stages, respectively. Additionally, three landslide susceptibility maps were obtained by classifying the range of landslide probabilities into four classes representing low (0-0.02), medium (0.02-0.1), high (0.1-0.85), and very high (0.85-1) probabilities of landslides. For the distributions of landslide and area percentages under different susceptibility standards, the SVM model has more relative balance in the four classes compared to the LR and the ANN models. The result reveals that the SVM model possesses better prediction efficiency than the other two models. Furthermore, the five factors, including lithology, distance from the road, slope angle, elevation, and land-use types, are the most suitable conditioning factors for landslide susceptibility mapping in the study area. The mining disturbance factor has little contribution to all models, because the mining method in this area is underground mining, so the mining depth is too deep to affect the stability of the slopes.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Comparative Assessment of Three Nonlinear Approaches for Landslide Susceptibility Mapping in a Coal Mine Area

Zhang

Zhao

et al. 2017

IJGI

View full text Add to dashboard Cite

show abstract

“…Parkinsons 16 10,21,22,17,20,18,14,9,11,12,13,5,7,4,15,8 The feature reduction achieved for CKD, Breast Cancer Wisconsin Dataset, and Parkinsons Dataset are 24%, 21.8%, and 30.4% respectively. The feature subset derived after the proposed feature selection algorithm consists of the most discriminatory features that enhances the accuracy of prediction of chronic diseases without any loss in the original information.The reduced feature subset is evaluated against three classification algorithms SVM, CNN, and Gradient Boosting.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Experimental results reveal that SFS algorithm using Decision Tree has obtained an accuracy of 89.60% compared to the other methods. S. Sasikala et al [14] have introduced a four-stage procedure known as Multi-Filtration Feature Selection (MFFS) for deriving optimal feature subset in medical data mining. In this method, a parameter called "variance coverage" is adjusted in this method to achieve maximum classification accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

Density Based Feature Selection Method for Medical Datasets

M*¹,

Sarojini²

2019

IJITEE

View full text Add to dashboard Cite

Abstract: High dimensional data are found in the medical domain that needs to be processed for improved data analysis. In order to deal with the curse of dimensionality, feature selection process is employed in almost all data mining applications. Dataset. The proposed feature selection method evaluates the merit of each feature, assign weights to the feature and rank the features based on their feature density. The reduced feature Network (CNN). The performance of the classification algorithms are evaluated based on the performance metrics Accuracy, Sensitivity and Specificity. Experimental results indicate that the performance of the classification algorithms SVM, Gradient Boosting, and CNN is improved after the feature selection process. In this research work, Density based Feature Selection (DFS) method that ranks the features by finding the Probability Density Function (PDF) of each feature is applied to medical datasets that suffer from the curse of dimensionality. The DFS method is a filter based approach that selects the most discriminatory features from the given feature set. The feature selection method evaluates the importance of the feature with regard to the target class using density function. The DFS method has major advantages over other methods, since it is based on the ranking method to select the most discriminatory features from the whole feature set. This research work finds the best feature subset that can be used in prediction and classification of medical datasets imbibed with high dimensionality. The DFS method based on PDF is applied on the three medical datasets namely Chronic Kidney Disease (CKD) dataset, Breast Cancer Wisconsin Dataset and Parkinsons subset is then validated by the application three classification algorithms namely Support Vector Machine (SVM), Gradient Boosting, and Convolutional Neural

show abstract

“…We have used different threshold values during relevancy and redundancy analysis to select predominant feature subsets for each threshold value. The selected subsets increase the predictive power of the classifier in comparison to FCBF algorithm [5], [9], [22] by selecting more number of significant genes. The proposed algorithm CO-FRFR has been compared with other feature selection methods in terms of speed and learning accuracy.…”

Section: Discussionmentioning

confidence: 99%

“…The highly ranked genes are always helpful in exploring more information about cancer research and medicine [23]. In this regard, several feature selection methods have been proposed by many researchers [15], [22], [24] to identify marker genes which helps to carry further research in prognosis and diagnosis of cancer. The feature selection technique introduced by this paper is competitive one in comparison to other methods.…”

Section: Discussionmentioning

confidence: 99%

A correlation based multilayer perceptron algorithm for cancer classification with gene-expression dataset

Dash

2014

2014 14th International Conference on Hybrid Intelligent Systems

View full text Add to dashboard Cite

Research on feature selection techniques for identifying informative genes from high dimensional microarray datasets has received considerable attention. Numerous researchers have proposed various optimized solutions to reduce noises, redundancy in dataset and to enhance the accuracy and generalization of the classification model by applying many computational tools. Highdimensional microarray gene expression dataset has limitations to many feature selection techniques with respect to generalization and effectiveness. A robust feature selection technique need to be designed which can remove irrelevant data, increase learning accuracy and improve comprehensibility of the experimental result. In this work, a novel correlation based feature selection algorithm using symmetrical uncertainty and multilayer perceptron algorithm is proposed. This method can identify the relevancy of the features to the class and also the redundancy considering all other relevant features of the dataset. It also evaluates the worth of a set attributes by measuring the symmetrical uncertainty with respect to another set of attributes. The effectiveness of the method is validated through various correlation based feature selection techniques using multi-category high-dimensional microarray datasets.

show abstract

Multi Filtration Feature Selection (MFFS) to improve discriminatory ability in clinical data set

Cited by 31 publications

References 17 publications

Comparative Assessment of Three Nonlinear Approaches for Landslide Susceptibility Mapping in a Coal Mine Area

Comparative Assessment of Three Nonlinear Approaches for Landslide Susceptibility Mapping in a Coal Mine Area

Density Based Feature Selection Method for Medical Datasets

A correlation based multilayer perceptron algorithm for cancer classification with gene-expression dataset

Contact Info

Product

Resources

About