Wyniki wyszukiwania - BazTech

1

Probabilistic principal component analysis-based dimensionality reduction and optimization for arrhythmia classification using ECG signals

Vishwanath Bhagyalakshmi, Pujeri Ramchandra Vittal, Devanagavi Geeta

Bio-Algorithms and Med-Systems

|

2019

|

Vol. 15, no. 1

art. no. 20180037

EN

Electrocardiogram (ECG) is an electrical signal that contains data about the state and functions of the heart and can be used to diagnose various types of arrhythmias effectively. The modeling and simulation of ECG under different conditions are significant to understand the function of the cardiovascular system and in the diagnosis of heart diseases. Arrhythmia is a severe peril to the patient recovering from acute myocardial infarction. The reliable detection of arrhythmia is a challenge for a cardiovascular diagnostic system. As a result, a considerable amount of research has focused on the development of algorithms for the accurate diagnosis of arrhythmias. In this paper, a system for the classification of arrhythmia is developed by employing the probabilistic principal component analysis (PPCA) model. Initially, the cluster head is selected for the effective transmission of ECG signals of patients using the adaptive fractional artificial bee colony algorithm, and multipath routing for transmission is selected using the fractional bee BAT algorithm. Features such as wavelet features, Gabor transform, empirical mode decomposition, and linear predictive coding features are extracted from the ECG signal with high dimension (which are reduced using PPCA) and finally given to the proposed classifier called adaptive genetic-bat (AGB) support vector neural network (which is trained using the AGB algorithm) for arrhythmia detection. The experimentation of the proposed system is done based on evaluation metrics, such as the number of alive nodes, normalized network energy, goodput, and accuracy. The proposed method obtained a classification accuracy of 0.9865 and a goodput of 0.0590 and provides a better classification of arrhythmia. The experimental results show that the proposed system is useful for the classification of arrhythmias, with a reasonably high accuracy of 0.9865 and a goodput of 0.0590. The validation of the proposed system offers acceptable results for clinical implementation.

2

Bayesian HCS-based multi-SVNN: A classification approach for brain tumor segmentation and classification using Bayesian fuzzy clustering

Raju A. R., Suresh P., Rao R. R.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 3

646--660

EN

Brain tumor segmentation and classification is the interesting area for differentiating the tumerous and the non-tumerous cells in the brain and to classify the tumerous cells for identifying its level. The conventional methods lack the automatic classification and they consumed huge time and are ineffective in decision-making. To overcome the challenges faced by the conventional methods, this paper proposes the automatic method of classification using the Harmony-Crow Search (HCS) Optimization algorithm to train the multi-SVNN classifier. The brain tumor segmentation is performed using the Bayesian fuzzy clustering approach, whereas the tumor classification is done using the proposed HCS Optimization algorithm-based multi-SVNN classifier. The proposed method of classification determines the level of the brain tumor using the features of the segments generated based on Bayesian fuzzy clustering. The robust features are obtained using the information theoretic measures, scattering transform, and wavelet transform. The experimentation performed using the BRATS database conveys proves the effectiveness of the proposed method and the proposed HCS-based tumor segmentation and classification achieves the classification accuracy of 0.93 and outperforms the existing segmentation methods.

3

Automated object and image level classification of TB images using support vector neural network classifier

Priya E., Srinivasan S.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 4

670--678

EN

In this work, digital Tuberculosis (TB) images have been considered for object and image level classification using Multi Layer Perceptron (MLP) neural network activated by Support Vector Machine (SVM) learning algorithm. The sputum smear images are recorded under standard image acquisition protocol. The TB objects which include bacilli and outliers in the considered images are segmented using active contour method. The boundary of the segmented objects is described by fifteen Fourier Descriptors (FDs). The prominent FDs are selected using fuzzy entropy measures. These selected FDs of the TB objects are fed as input to the SVM learning algorithm of the MLP Neural Network (SVNN) and the result is compared with the state-of-the-art approach, Back Propagation Neural Network (BPNN). Results show that the segmentation method identifies the bacilli which retain their shape in-spite of artifacts present in the images. The methodology adopted has significantly enhanced the SVNN accuracy to 91.3% for object and 92.5% for image level classification than BPNN.