Human body radiation wave analysis and classification for gender and body segments recognition / Siti Zura A. Jalil @ Zainuddin

This thesis presents a novel analysis and classification of human radiation wave for gender and body segments recognition. The human body has been shown to emit radiation into space surrounding their body. The research study frequency radiations at 23 points of the human body segregated into body se...

Full description

Saved in:
Bibliographic Details
Main Author: A. Jalil @ Zainuddin, Siti Zura
Format: Thesis
Language:English
Published: 2014
Subjects:
Online Access:https://ir.uitm.edu.my/id/eprint/28030/1/TP_SITI%20ZURA%20A.%20JALIL%20%40%20ZAINUDDIN%20EE%2014_5.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-uitm-ir.28030
record_format uketd_dc
spelling my-uitm-ir.280302020-02-11T03:42:21Z Human body radiation wave analysis and classification for gender and body segments recognition / Siti Zura A. Jalil @ Zainuddin 2014 A. Jalil @ Zainuddin, Siti Zura Conditions and laws of chemical reactions Radiation chemistry This thesis presents a novel analysis and classification of human radiation wave for gender and body segments recognition. The human body has been shown to emit radiation into space surrounding their body. The research study frequency radiations at 23 points of the human body segregated into body segments of Chakra, Left, Right, Upper body, Torso, Arm and Lower body. Initially, the characteristics of frequency radiation are examined using statistical tools to find the correlations between variables. Multivariate analysis of variance (MANOVA) is employed to compare the differences of frequency radiation characteristics between genders. Then, the classification algorithm of A:-nearest neighbor (KNN) is employed to discriminate between genders, and between body segments. The classifiers are evaluated through analysis of the performance indicators applied in medical research of accuracy, precision, sensitivity and specificity in receiver operating characteristics (ROC) analysis. The findings obtained from this research show that the wave radiation characteristics of a male and a female human body are different. The proposed technique is able to distinguish gender and classify body segments, and it is justified using MANOVA statistical tests. The individual features of gender differences using analysis of variance forms a significant outcome on 13 points that are located close to the forehead, left and right side of abdomen, palms, arms, shoulders and head. In KNN classification, the outcomes for the classifiers are consistent with the MANOVA. For gender recognition, the classifiers have successfully differentiated male from female human body, and achieving a performance of 100% for accuracy, sensitivity and specificity. For body segment recognition, the classifiers are also able to distinguish between the body segments producing 100% accuracy in classifying of Chakra, Left and Right, whilst 93.75% accuracy is obtained in classifying of Upper body, Torso, Arm and Lower body. The sensitivity and specificity computed for body segment recognition are found to be more than 80% indicating a good classification performance. The outcomes of this study demonstrate that a male and a female human body, and also the different body segments, have different frequency radiation characteristics. The finding offers new opportunities in research and application based on human body radiation such as biometrics and surveillance systems. 2014 Thesis https://ir.uitm.edu.my/id/eprint/28030/ https://ir.uitm.edu.my/id/eprint/28030/1/TP_SITI%20ZURA%20A.%20JALIL%20%40%20ZAINUDDIN%20EE%2014_5.pdf text en public phd doctoral Universiti Teknologi MARA Faculty of Electrical Engineering
institution Universiti Teknologi MARA
collection UiTM Institutional Repository
language English
topic Conditions and laws of chemical reactions
Radiation chemistry
spellingShingle Conditions and laws of chemical reactions
Radiation chemistry
A. Jalil @ Zainuddin, Siti Zura
Human body radiation wave analysis and classification for gender and body segments recognition / Siti Zura A. Jalil @ Zainuddin
description This thesis presents a novel analysis and classification of human radiation wave for gender and body segments recognition. The human body has been shown to emit radiation into space surrounding their body. The research study frequency radiations at 23 points of the human body segregated into body segments of Chakra, Left, Right, Upper body, Torso, Arm and Lower body. Initially, the characteristics of frequency radiation are examined using statistical tools to find the correlations between variables. Multivariate analysis of variance (MANOVA) is employed to compare the differences of frequency radiation characteristics between genders. Then, the classification algorithm of A:-nearest neighbor (KNN) is employed to discriminate between genders, and between body segments. The classifiers are evaluated through analysis of the performance indicators applied in medical research of accuracy, precision, sensitivity and specificity in receiver operating characteristics (ROC) analysis. The findings obtained from this research show that the wave radiation characteristics of a male and a female human body are different. The proposed technique is able to distinguish gender and classify body segments, and it is justified using MANOVA statistical tests. The individual features of gender differences using analysis of variance forms a significant outcome on 13 points that are located close to the forehead, left and right side of abdomen, palms, arms, shoulders and head. In KNN classification, the outcomes for the classifiers are consistent with the MANOVA. For gender recognition, the classifiers have successfully differentiated male from female human body, and achieving a performance of 100% for accuracy, sensitivity and specificity. For body segment recognition, the classifiers are also able to distinguish between the body segments producing 100% accuracy in classifying of Chakra, Left and Right, whilst 93.75% accuracy is obtained in classifying of Upper body, Torso, Arm and Lower body. The sensitivity and specificity computed for body segment recognition are found to be more than 80% indicating a good classification performance. The outcomes of this study demonstrate that a male and a female human body, and also the different body segments, have different frequency radiation characteristics. The finding offers new opportunities in research and application based on human body radiation such as biometrics and surveillance systems.
format Thesis
qualification_name Doctor of Philosophy (PhD.)
qualification_level Doctorate
author A. Jalil @ Zainuddin, Siti Zura
author_facet A. Jalil @ Zainuddin, Siti Zura
author_sort A. Jalil @ Zainuddin, Siti Zura
title Human body radiation wave analysis and classification for gender and body segments recognition / Siti Zura A. Jalil @ Zainuddin
title_short Human body radiation wave analysis and classification for gender and body segments recognition / Siti Zura A. Jalil @ Zainuddin
title_full Human body radiation wave analysis and classification for gender and body segments recognition / Siti Zura A. Jalil @ Zainuddin
title_fullStr Human body radiation wave analysis and classification for gender and body segments recognition / Siti Zura A. Jalil @ Zainuddin
title_full_unstemmed Human body radiation wave analysis and classification for gender and body segments recognition / Siti Zura A. Jalil @ Zainuddin
title_sort human body radiation wave analysis and classification for gender and body segments recognition / siti zura a. jalil @ zainuddin
granting_institution Universiti Teknologi MARA
granting_department Faculty of Electrical Engineering
publishDate 2014
url https://ir.uitm.edu.my/id/eprint/28030/1/TP_SITI%20ZURA%20A.%20JALIL%20%40%20ZAINUDDIN%20EE%2014_5.pdf
_version_ 1783734038645702656