Loading [MathJax]/extensions/MathMenu.js
A new perspective of detecting and classifying neurological disorders through recurrence and machine learning classifiers | IEEE Conference Publication | IEEE Xplore

A new perspective of detecting and classifying neurological disorders through recurrence and machine learning classifiers


Abstract:

Millions of people around the world are affected by various neurological disorders. These disorders lead to difficulty in daily activities and often lead to the medical a...Show More

Abstract:

Millions of people around the world are affected by various neurological disorders. These disorders lead to difficulty in daily activities and often lead to the medical assistance for prolonged period of time. Neurological disorders like epilepsy affect the muscular functions of body and may lead to fatal injuries because of the loss of control over the body during the epileptic fits. Similarly, Alzheimer's disease occurs mostly in elderly people and lead to memory loss. Bruxism is another such neurological disorder which leads to clenching of teeth during sleep or while the patient is awake. The doctors and clinicians use various methods to detect the neurological disorders. These methods include analyzing the EEG signal patterns or by observing the symptoms of the patient. But analyzing the EEG patterns is not an easy task as EEG signals are highly spontaneous and chaotic and they vary at a very fast pace.This work proposes a novel approach for detection of neurological disorders based on the phenomena of recurrences that are generally found in EEG signals of the patients with neurological disorders. A computer assisted algorithm is developed in this work and then the coding has been done in MATLAB. To quantify the recurrence, a parameter called "Coupling Index (ρπ)", has been used. The disorders are detected on the basis of the value of coupling index. The use of machine learning classifiers has been done to classify the values of coupling index for the various neurological disorders. The machine learning models are trained and tested by taking values of "Coupling Index (ρπ)" as an input and the PYTHON platform is used for testing and training of various machine learning classifiers. Once the models are trained and tested with the known patients it had led to the setting of the range of coupling index for the patients with Epilepsy, Alzheimer's disease and Bruxism. Thus this work acts as an easy test for detecting neurological disorders and further it classifies ...
Date of Conference: 04-05 March 2021
Date Added to IEEE Xplore: 20 April 2021
ISBN Information:
Conference Location: Greater Noida, India
No metrics found for this document.

I. Introduction

Neurological disorders are the diseases that affect the nervous system. They affect the brain and its activities. Their affects are also seen on the spinal cord, autonomous nervous system and on various motor functions like muscular movements. Hundreds of millions of people worldwide are affected by neurological disorders. Around 6 million people die because of a sudden stroke that is caused due to abnormal brain activity. Over 80% of these deaths take place in low- and middle-income countries. The occurrence of epilepsy is also found in around 50 million people worldwide. As per the data of world health organization (W.H.O), it is estimated that there are globally 47.5 million people with dementia with 7.7 million new cases every year -Alzheimer's disease is the most common cause of dementia and may contribute to 60-70% of cases ("What are neurological disorders?", 2019).

Usage
Select a Year
2025

View as

Total usage sinceMay 2021:147
01234JanFebMarAprMayJunJulAugSepOctNovDec310020000000
Year Total:6
Data is updated monthly. Usage includes PDF downloads and HTML views.
Contact IEEE to Subscribe

References

References is not available for this document.