Electrocardiogram (ECG) based stress recognition integrated with different classification of age and gender /

Mental health status is important to achieve objective of a desired goals. A stressful person commonly finds stress as a barrier to enhance an individual's performance. Be reminded that not all person has the same level of stress because different person has dissimilar problems in their life. I...

Full description

Saved in:
Bibliographic Details
Main Author: Nur Shahirah binti Nor Shahrudin (Author)
Format: Thesis
Language:English
Published: Kuala Lumpur : Kulliyyah of Engineering, International Islamic University Malaysia, 2018
Subjects:
Online Access:Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library.
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mental health status is important to achieve objective of a desired goals. A stressful person commonly finds stress as a barrier to enhance an individual's performance. Be reminded that not all person has the same level of stress because different person has dissimilar problems in their life. In addition, different level of age and gender which will give unequal amount of stress. This situation might affect the person's performance, as well as among the source of cardiac failure, sleep disorder and unstable emotions. It is proven in previous studies that biological signals are closely related to a person's reaction. Electrocardiogram (ECG) signal is an electrical indicator of the heart. It provides such criteria as it reflects the heart activity that can detect changes of human response which relates to our emotions and reactions. Thus, this research proposed a non-intrusive detector to identify stress level for both gender and different classification of age using ECG. Volunteers with age range between 10 to 59 years old were used for experimentation purposes. Savitzky-Golay filter was applied to remove external noise from the signal. The filter was selected due to the filter tends to preserve the original signal during the noise removal. Then, QRS complexes were extracted using the Pan Tompkins's algorithm. This research proceeded by proposing classification techniques to analyse the ECG data such as RR interval, different amplitudes at R peak and Cardioid graph area which were used to distinguish between normal and stress conditions. Based on the experimentation results, in terms of age variability analysis, it shows that Class 5 (age range between 50-59 years old) tends to be more influenced by stress situation. This is due to the results that Class 5 by obtaining the highest mean of percentage changes between normal and stress conditions as compared to other classes of age which recorded changes of RR interval, changes of R peak and Cardioid graph area by 2.94%, 31.94% and 53.32% respectively. In terms of stress in different gender, analysis of the study found out that women are more stressful than men throughout the whole experiment. The classification for gender analysis shows higher percentage of change in female between both states that illustrated RR interval, amplitude of R peak and Cardioid graph of 11.59%, 34.98% and 53.81% respectively. Yet, the mean percentage changes in RR interval, amplitude in R peak and Cardioid graph area for male subjects were affected only by 2.17%, 7.50%, 19.03% correspondingly. The result proves that ECG signals can be used as an alternative mechanism to recognize stress more efficiently by integrating age and gender variabilities.
Item Description:Abstracts in English and Arabic.
"A dissertation submitted in fulfilment of the requirement for the degree of Master of Science (Communication Engineering)." --On title page.
Physical Description:xvii, 74 leaves : colour illustrations ; 30cm.
Bibliography:Includes bibliographical references (leaves 67-70).