Heart Sounds Classification Using Loudness Features and Gaussian Mixture Model | Chapter 20 | Current Practice in Medical Science Vol. 5

 

The heart sound's loudness characteristics are used in this paper to introduce a new automatic way of identifying the status of the heart sound. The three main steps of the approach are as follows. First, an 8th order Chebyshev Type-II filter is used to heavily filter the heart sound, which is typically found to be loud. The filtered heart sound is then divided into the first heart sound, systole, second heart sound, and diastole using the event synchronous approach. The loudness attribute is expressed using the mean rows of its spectrogram in the second stage. The Gaussian Mixture Model method is used in the third phase to categorize the heart sound. The suggested method has been tested on a large database of heart sounds with over 3000 recordings, and it has a success rate of 97.77 percent.

Author(s) Details:

Vishwanath Madhava Shervegar,
E&CE Department, Mangalore Institute of Technology & Engineering, Moodbidre, DK, Karnataka, India.

Please see the link here: https://stm.bookpi.org/CPMS-V5/article/view/7669

EEG Bases Emotion Detection Using Deep Learning Algorithm | Chapter 9 | New Approaches in Engineering Research Vol. 16

 The use of physiological markers to identify human emotion states is a rapidly emerging area of research in human-computer interaction. Gaming Disorder has become a major topic of concern in recent years, piqueing the curiosity of experts who want to learn more about it. The goal of this study is to use electroencephalography to detect the emotional behaviour of people who play online games on a regular basis (EEG). EEG is a prominent method for investigating addictive behaviours that is low cost and has a good temporal resolution. As a result, the EEG will be a good predictor of the subject's emotional state. The current study uses the SEED-IV data source to build a model for emotion states, and obtained signals are used to investigate gamming addiction behaviour. The VGG pre-trained model is supplied the spectrogram features. On the SEED-IV database, the trained model has a prediction accuracy of 89.54 percent and a testing accuracy of 78.63 percent. The acquired signals are checked against the trained model, yielding a 75 percent accuracy.

Author(S) Details

S. Thejaswini
Department of Electronics and Telecommunication, B M S Institute of Technology & Management, India.

N. Ramesh Babu
Department of Computer Science Engineering, Amruta Institute of Engineering & Management Sciences, India.

K. M. Ravikumar
Oxford College of Engineering, India.

View Book:- https://stm.bookpi.org/NAER-V16/article/view/4062