S. R. Nirmala

Classification of ECG using some novel features

Heart diseases are frequent reasons of death. Hence, there is always a need to develop systems that can provide prior indication about the state of the heart. This is also required because medical facilities may not be uniform everywhere. In such situation certain innovative approaches using certain signal processing techniques can provide considerable support. As a follow up to such possibilities, system for automatic recognition of cardiac arrhythmias has become necessary and important for diagnosis of cardiac abnormalities. Several algorithms have been proposed to classify cardiac arrhythmias in the literature; however, many of them fail to perform optimally. Here, we have proposed a method for ECG arrhythmia classification using Artificial Neural Network (ANN) and a novel feature set. Fast Fourier Transform is used for pre-processing the ECG recordings. Linear Prediction Coefficients (LPC) and Principal Component Analysis (PCA) are used for extracting some features and then Multi-Layer Perceptron (MLP) ANN performs the classification.

ECG classification using wavelet subband energy based features

Detection and classification of electrocardiogram (ECG) signals is critically linked to the diagnosis of cardiac abnormalities. In this paper, a novel approach for ECG classification is presented using features based on wavelet subband energy coefficients. The ECG signals are decomposed into time-frequency representation using wavelet transform and then wavelet coefficients are used to calculate some statistical parameters. Types of ECG beat considered for the classification are normal beat, paced beat, pre-ventricular contraction, left bundle branch block and right bundle branch block beat. The signals are obtained from the MIT-BIH Arrhythmia database. Multilayer Perceptron Neural Network is used for classification.

Codon-Based Analysis of Alzheimer’s Disease (AD) Using Soft Computational Tool

Alzheimer’s disease is a most common disease seen in today’s world. It is one form of dementia where a person loses his memory progressively and finally loses his life. It is often seen in people above 60 but it may occur early. This disease destroys memory cell of brain. Till now, it is a disease without any treatment and proper way of diagnosis. Research shows that most often it occurs due to the deposition of defective structure of amyloid protein in the brain. In this paper, we have proposed a work to detect the defective amyloid protein using two classifiers. Secondary structure of amyloid protein is detected and analyzed in our work which provides a way to predict the cause of Alzheimer.

Wavelet and PCA Based ECG Compression

ECG is the most important biological signal for the diagnosis of cardiac diseases. In many cases, ECG monitoring devices generate a huge amount of data. Therefore, compression of ECG signal is an important objective of ECG signal processing for the purpose of efficient storage and transmission. In this paper, a wavelet PCA based ECG compression technique is proposed. Two statistical parameters Percent Root Mean Square Difference (PRD) and Compression Ratio (CR) are calculated to evaluate the performance of the proposed method. The database used for testing purpose is taken from MIT-BIH. The results show that the proposed compression technique provide good performance for different ECG signals considered from clinical point of view. Index Terms – ECG, Compression, 2-D Wavelet, PCA.

Detection of glaucoma using Neuroretinal Rim information

Glaucoma is one of the most common causes of blindness in the world. The vision lost due to glaucoma cannot be regained. Early detection of glaucoma is thus very important. The Optic Disk(OD), Optic Cup(OC) and Neuroretinal Rim(NRR) are among the important features of a retinal image that can be used in the detection of glaucoma. In this paper, a computer-assisted method for the detection of glaucoma based on the ISNT rule is presented. The OD and OC are segmented using watershed transformation. The NRR area in the ISNT quadrants is obtained from the segmented OD and OC. The method is applied on the publicly available databases HRF, Messidor, DRIONS-DB, RIM-ONE and a local hospital database consisting of both normal and glaucomatous images. The proposed method is simple, computationally efficient and achieves a sensitivity of 91.82% and an overall accuracy of 94.14%.

ECG denoising based on probability of wavelet coefficients

Heart failure and heart diseases are among the main causes of death in the world. Therefore it is necessary to have proper tools to determine the heart condition of the patient. ECG is considered to be the most efficient diagnostic tool to check the functionality of the heart. Hence accurate analysis of ECG signal is important. But it is difficult to analyze an ECG signal if it is corrupted by noise during acquisition. Thus, noise removal becomes an essential part in ECG analysis and characterization. In this paper, we proposed a wavelet based denoising technique. In this technique, denoising is done by thresholding the less significant wavelet coefficients. Here the threshold is based on the probability of the wavelet coefficients at a particular sub-band. Two parameters Signal-to-Error Ratio (SER) and Percent Root Mean Square Difference (PRD) are calculated to evaluate the performance of the proposed denoising method. The database used for testing purpose is taken from MIT-BIH. The results show that the proposed method provides encouraging results for denoising.