Performance Comparison Of Ann Classifiers For Sleep Apnea Detection Based On Ecg Signal Analysis Using Hilbert Transform
Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2018, Vol 17, Issue 2
Abstract
In this paper, a methodology for sleep apnea detection based on ECG signal analysis using Hilbert transform is proposed. The proposed work comprises a sequential procedure of preprocessing, QRS complex detection using Hilbert Transform, feature extraction from the detected QRS complex and the feature reduction using principal component analysis (PCA). Finally, the classification of the ECG signal recordings has been done using two different artificial neural networks (ANN), one trained with Levenberg-Marquardt (LM) algorithm and the other trained with Scaled Conjugate Gradient (SCG) method guided by K means clustering. The result of classification of the input ECG record is as either belonging to Apnea or Normal category. The performance measures of classification using the two classification algorithms are compared. The experimental results indicate that the SCG algorithm guided by K means clustering (ANN-SCG) has outperformed the LM algorithm (ANN-LM) by attaining accuracy, sensitivity and specificity values as 99.2%, 96% and 97% respectively, besides the saving achieved in terms of reduced number of principal components. Profiling time and mean square error of the ANN classifier trained with SCG algorithm is significantly reduced by 58% and 83%, respectively, as compared to LM algorithm.
Authors and Affiliations
Jyoti S Bali, Anilkumar V Nandi, P S Hiremath
Keywords
Related Articles
- EP ID EP649762
- DOI 10.24297/ijct.v17i2.7616
- Views 95
- Downloads 0
An Efficient Multi Parent Hierarchical Routing Protocol for WSN’s
Wireless sensor networks (WSNs) nodes are commonly designed to work with limited resources of memory, energy and processing. The routing protocol is one of the key components of WSNs and its features impact network perfo...
Numerical solution of system of two Nonlinear Volterra Integral equations
In this paper, using the implicit trapezoidal rule in conjunction with Newton's method to solve nonlinear system.We have used a Maple 17 program to solve the System of two nonlinear Volterra integral equations. Finally,...
Dynamic modeling of the patient journey in a Pediatric Emergency Department of CHRU of Lille
The Workflow models of the patient journey in a Pediatric Emergency Department (PED) seems to be an effective approach to develop an accurate and complete representation of the PED processes. The model developed can driv...
Performance Evaluation for VoIP on Campus
The VoIP Campus implementation is to make the existing VoIP technology become more beneficial for campus stake holder. This VoIP on Campus (VoC) technology make use of a web server, facilitating users to carry out VoIP r...
Measuring Radar Signatures of a Simple Pendulum using Cantenna Radar
This paper gives a detailed analysis of the physics of simple pendulum and the equations governing the motion and velocity. The pendulum works in three modes: simple, damped and driving and driving only. The signatures a...