scholarly journals Classification of Cardiac Arrhythmia using improved Feature Selection methods and Ensemble Classifiers

2022 ◽  
Vol 2161 (1) ◽  
pp. 012003
Author(s):  
Rajat Jain ◽  
Pranam R Betrabet ◽  
B Ashwath Rao ◽  
N V Subba Reddy
Keyword(s):  
Feature Selection ◽  
Heart Diseases ◽  
Sudden Cardiac Arrest ◽  
Principal Component ◽  
Ensemble Classifier ◽  
Ensemble Classifiers ◽  
Life Threatening ◽  
Electrocardiogram Ecg ◽  
Feature Selection Techniques

Abstract Arrhythmia is one of the life-threatening heart diseases which is diagnosed and analyzed using electrocardiogram (ECG) recordings and other symptoms namely rapid heartbeat or chest-pounding, shortness of breath, near fainting spells, insufficient pumping of blood from the heart, etc along with sudden cardiac arrest. Arrhythmia records a hasty and aberrant ECG. In this implementation, the arrhythmia dataset is collected from the UCI machine learning repository and then classified the records into sixteen stated classes using multiclass classification. The large feature set of the dataset is reduced using improved feature selection techniques such as t-Distributed Stochastic Neighbor Embedding (TSNE), Principal Component Analysis (PCA), Uniform Manifold Approximation, and Projection (UMAP) and then an Ensemble Classifier is built to analyse the classification accuracy on arrhythmia dataset to conclude when and which approach gives optimal results.

Hybrid Ensemble Learning With Feature Selection for Sentiment Classification in Social Media

2020 ◽  
Vol 10 (2) ◽  
pp. 40-58 ◽  
Author(s):  
Sanur Sharma ◽  
Anurag Jain
Keyword(s):  
Social Media ◽  
Feature Selection ◽  
Ensemble Learning ◽  
Information Gain ◽  
Empirical Evaluation ◽  
Ensemble Classifier ◽  
Sentiment Classification ◽  
Ensemble Classifiers ◽  
Chi Squared

This article presents a study on ensemble learning and an empirical evaluation of various ensemble classifiers and ensemble features for sentiment classification of social media data. The data was collected from Twitter in real-time using Twitter API and text pre-processing and ranking-based feature selection is applied to textual data. A framework for a hybrid ensemble learning model is presented where a combination of ensemble features (Information Gain and CHI-Squared) and ensemble classifier that includes Ada Boost with SMO-SVM and Logistic Regression has been implemented. The classification of Twitter data is performed where sentiment analysis is used as a feature. The proposed model has shown improvements as compared to the state-of-the-art methods with an accuracy of 88.2% with a low error rate.

CLASSIFICATION OF HIGH-DIMENSIONAL MICROARRAY DATA WITH A TWO-STEP PROCEDURE VIA A WILCOXON CRITERION AND MULTILAYER PERCEPTRON

2011 ◽  
Vol 10 (01) ◽  
pp. 1-14
Author(s):  
VLADIMIR NIKULIN ◽  
TIAN-HSIANG HUANG ◽  
GEOFFREY J. MCLACHLAN
Keyword(s):  
Data Mining ◽  
Feature Selection ◽  
High Dimensional ◽  
Second Step ◽  
Support Vector ◽  
Step Procedure ◽  
Leave One Out ◽  
Natural Combination ◽  
Feature Selection Techniques

The method presented in this paper is novel as a natural combination of two mutually dependent steps. Feature selection is a key element (first step) in our classification system, which was employed during the 2010 International RSCTC data mining (bioinformatics) Challenge. The second step may be implemented using any suitable classifier such as linear regression, support vector machine or neural networks. We conducted leave-one-out (LOO) experiments with several feature selection techniques and classifiers. Based on the LOO evaluations, we decided to use feature selection with the separation type Wilcoxon-based criterion for all final submissions. The method presented in this paper was tested successfully during the RSCTC data mining Challenge, where we achieved the top score in the Basic track.

scholarly journals Feature Selection using Genetic Programming

2019 ◽  
Vol 3 (2) ◽  
pp. 11-18
Author(s):  
George Mweshi
Keyword(s):  
Feature Selection ◽  
Genetic Programming ◽  
Information Gain ◽  
Principal Component ◽  
Search Space ◽  
Classification Performance ◽  
The Other ◽  
Searching Strategy ◽  
Mining Algorithms ◽  
Feature Selection Techniques

Extracting useful and novel information from the large amount of collected data has become a necessity for corporations wishing to maintain a competitive advantage. One of the biggest issues in handling these significantly large datasets is the curse of dimensionality. As the dimension of the data increases, the performance of the data mining algorithms employed to mine the data deteriorates. This deterioration is mainly caused by the large search space created as a result of having irrelevant, noisy and redundant features in the data. Feature selection is one of the various techniques that can be used to remove these unnecessary features. Feature selection consequently reduces the dimension of the data as well as the search space which in turn increases the efficiency and the accuracy of the mining algorithms. In this paper, we investigate the ability of Genetic Programming (GP), an evolutionary algorithm searching strategy capable of automatically finding solutions in complex and large search spaces, to perform feature selection. We implement a basic GP algorithm and perform feature selection on 5 benchmark classification datasets from UCI repository. To test the competitiveness and feasibility of the GP approach, we examine the classification performance of four classifiers namely J48, Naives Bayes, PART, and Random Forests using the GP selected features, all the original features and the features selected by the other commonly used feature selection techniques i.e. principal component analysis, information gain, relief-f and cfs. The experimental results show that not only does GP select a smaller set of features from the original features, classifiers using GP selected features achieve a better classification performance than using all the original features. Furthermore, compared to the other well-known feature selection techniques, GP achieves very competitive results.

Hybrid Ensemble Learning Methods for Classification of Microarray Data

2020 ◽  
pp. 707-725
Author(s):  
Sujata Dash
Keyword(s):  
Feature Extraction ◽  
Feature Selection ◽  
Microarray Data ◽  
Classification Model ◽  
Rotation Forest ◽  
Ensemble Technique ◽  
Basic Characteristics ◽  
Microarray Datasets ◽  
Feature Selection Techniques

Efficient classification and feature extraction techniques pave an effective way for diagnosing cancers from microarray datasets. It has been observed that the conventional classification techniques have major limitations in discriminating the genes accurately. However, such kind of problems can be addressed by an ensemble technique to a great extent. In this paper, a hybrid RotBagg ensemble framework has been proposed to address the problem specified above. This technique is an integration of Rotation Forest and Bagging ensemble which in turn preserves the basic characteristics of ensemble architecture i.e., diversity and accuracy. Three different feature selection techniques are employed to select subsets of genes to improve the effectiveness and generalization of the RotBagg ensemble. The efficiency is validated through five microarray datasets and also compared with the results of base learners. The experimental results show that the correlation based FRFR with PCA-based RotBagg ensemble form a highly efficient classification model.

scholarly journals Detection and Classification of R-Peak Using Naïve Bayes Classifier

2018 ◽  
Vol 7 (3.27) ◽  
pp. 397 ◽  
Author(s):  
S Celin ◽  
K Vasanth
Keyword(s):  
Feature Extraction ◽  
Performance Measures ◽  
Heart Diseases ◽  
Processing Technique ◽  
Challenging Problem ◽  
Bayes Classifier ◽  
Extraction Techniques ◽  
And Performance ◽  
Electrocardiogram Ecg

Electrocardiogram (ECG) in classification of signals plays a major role in the diagnoses of heart diseases. The main challenging problem is the classification of accurate ECG. Here in this paper the ECG is classified into arrhythmia types. It is very important that detecting the heart disease and finding the treatment for the patient at the earliest must be done accurately. In the ECG classification different classifiers are available. The best accuracy value of 99.7% is produced by using the Bayes classifiers in this paper. ECG databases, classifiers, feature extraction techniques and performance measures are presented in the pre-processing technique. And also the classification of ECG, analysis of input beat selection and the output of classifiers are also discussed in this paper.  

Idiopathic ventricular fibrillation: the ongoing quest for diagnostic refinement

EP Europace ◽  
2020 ◽  
Author(s):  
Giulio Conte ◽  
John R Giudicessi ◽  
Michael J Ackerman
Keyword(s):  
Ventricular Fibrillation ◽  
Heart Diseases ◽  
Sudden Cardiac Arrest ◽  
Polymorphic Ventricular Tachycardia ◽  
Molecular Evidence ◽  
Idiopathic Ventricular Fibrillation ◽  
Diagnostic Approaches ◽  
Exercise Induced ◽  
Definition Of ◽  
Electrocardiogram Ecg

Abstract Prior to the recognition of distinct clinical entities, such as Brugada syndrome, catecholaminergic polymorphic ventricular tachycardia, and long QT syndrome, all sudden cardiac arrest (SCA) survivors with ventricular fibrillation (VF) and apparently structurally normal hearts were labelled as idiopathic ventricular fibrillation (IVF). Over the last three decades, the definition of IVF has changed substantially, mostly as result of the identification of the spectrum of SCA-predisposing genetic heart diseases (GHDs), and the molecular evidence, by post-mortem genetic analysis (aka, the molecular autopsy), of cardiac channelopathies as the pathogenic basis for up to 35% of unexplained cases of sudden cardiac death (SCD) in the young. The evolution of the definition of IVF over time has led to a progressively greater awareness of the need for an extensive diagnostic assessment in unexplained SCA survivors. Nevertheless, GHDs are still underdiagnosed among SCA survivors, due to the underuse of pharmacological challenges (i.e. sodium channel blocker test), misrecognition of electrocardiogram (ECG) abnormalities/patterns (i.e. early repolarization pattern or exercise-induced ventricular bigeminy) or errors in the measurement of ECG parameters (e.g. the heart-rate corrected QT interval). In this review, we discuss the epidemiology, diagnostic approaches, and the controversies related to role of the genetic background in unexplained SCA survivors with a default diagnosis of IVF.

Hybrid Ensemble Learning Methods for Classification of Microarray Data

2016 ◽  
pp. 17-36
Author(s):  
Sujata Dash
Keyword(s):  
Feature Extraction ◽  
Feature Selection ◽  
Microarray Data ◽  
Classification Model ◽  
Rotation Forest ◽  
Ensemble Technique ◽  
Basic Characteristics ◽  
Microarray Datasets ◽  
Feature Selection Techniques

Efficient classification and feature extraction techniques pave an effective way for diagnosing cancers from microarray datasets. It has been observed that the conventional classification techniques have major limitations in discriminating the genes accurately. However, such kind of problems can be addressed by an ensemble technique to a great extent. In this paper, a hybrid RotBagg ensemble framework has been proposed to address the problem specified above. This technique is an integration of Rotation Forest and Bagging ensemble which in turn preserves the basic characteristics of ensemble architecture i.e., diversity and accuracy. Three different feature selection techniques are employed to select subsets of genes to improve the effectiveness and generalization of the RotBagg ensemble. The efficiency is validated through five microarray datasets and also compared with the results of base learners. The experimental results show that the correlation based FRFR with PCA-based RotBagg ensemble form a highly efficient classification model.

Sign in / Sign up

Export Citation Format

Share Document