Using neural network with random weights and mutual information for systolic peaks classification of PPG signals

The detection of peaks in photoplethysmogram (PPG) signals is important to ensure the information gather from the peaks in accurate manner. The false peaks will interrupt the accuracy for future classification of any related events. This study presents the implementation of feature enhancement metho...

Full description

Bibliographic Details
Main Authors: Muhammad Haziq, Mohd Rasid, Noor Liza, Simon, Asrul, Adam
Format: Conference or Workshop Item
Language:English
English
Published: Association for Computing Machinery, New York, United States 2020
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/28429/
http://umpir.ump.edu.my/id/eprint/28429/1/50.%20Using%20neural%20network%20with%20random%20weights%20and%20mutual%20information.pdf
http://umpir.ump.edu.my/id/eprint/28429/2/50.1%20Using%20neural%20network%20with%20random%20weights%20and%20mutual%20information.pdf
Description
Summary:The detection of peaks in photoplethysmogram (PPG) signals is important to ensure the information gather from the peaks in accurate manner. The false peaks will interrupt the accuracy for future classification of any related events. This study presents the implementation of feature enhancement method for systolic peaks classification of PPG signals using mutual information and neural network with random weights (MI-NNRW). MI-NNRW method is proposed to improve the accuracy performance of NNRW method. Ml method implements at sixteen time-domain features and then NNRW classifier predicts between false and true systolic peaks point of PPG signals. The results indicate that by using sigmoid as activation function, the accuracy of sensitivity (Se) for ICP signals increase up to 81.71 percent. Overall, MI-NNRW method improves the accuracy performance compared to NNRW method which is leads to the improvement of accuracy for detection of systolic peaks.