Improving gender classification with feature selection in forensic anthropology
Gender classification has been one of the most vital tasks in a real world problem especially when it comes to death investigations. Developing a biological profile of an individual is a crucial step in forensic anthropology process as for the identification of gender. Forensic anthropologists emplo...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Penerbit UTM Press
2016
|
Subjects: | |
Online Access: | http://eprints.utm.my/71456/1/NurulLiyanaHairuddin2016_Improvinggenderclassificationwithfeature.pdf |
_version_ | 1796861772647366656 |
---|---|
author | Hairuddin, Nurul Liyana Mi Yusuf, Lizawati Othman, Mohd. Shahizan Abdul Majid, Hairudin |
author_facet | Hairuddin, Nurul Liyana Mi Yusuf, Lizawati Othman, Mohd. Shahizan Abdul Majid, Hairudin |
author_sort | Hairuddin, Nurul Liyana |
collection | ePrints |
description | Gender classification has been one of the most vital tasks in a real world problem especially when it comes to death investigations. Developing a biological profile of an individual is a crucial step in forensic anthropology process as for the identification of gender. Forensic anthropologists employ the principle of skeleton remains to produce a biological profile. Different parts of skeleton contains different features that will contribute to gender classification. However, not all the features could contribute to gender classification and affect to a low accuracy of gender classification. Therefore, feature selection method is applied to identify the most significant features for gender classification. This paper presents the implementation of feature selection approaches which are Particle Swarm Optimization (PSO) and Harmony Search (HS) algorithm using three different dataset from Goldman Osteometric Dataset, Osteological Collection and George Murray Black Collection. All three dataset contains 4081 samples of metrics measurement and have gone through the process of classification by using Back Propagation Neural Network (BPNN) and Naïve Bayes classifier. The main scope of this paper is to identify the effect of feature selection towards gender classification. The result shows that the accuracy of gender classification for every dataset increased when feature selection is applied to the dataset. Among all the skeleton parts in this experiment, clavicle part achieved the highest increment of accuracy rate which is from 89.76% to 96.06% for PSO algorithm and 96.32% for HS. |
first_indexed | 2024-03-05T20:01:29Z |
format | Article |
id | utm.eprints-71456 |
institution | Universiti Teknologi Malaysia - ePrints |
language | English |
last_indexed | 2024-03-05T20:01:29Z |
publishDate | 2016 |
publisher | Penerbit UTM Press |
record_format | dspace |
spelling | utm.eprints-714562017-11-22T12:07:32Z http://eprints.utm.my/71456/ Improving gender classification with feature selection in forensic anthropology Hairuddin, Nurul Liyana Mi Yusuf, Lizawati Othman, Mohd. Shahizan Abdul Majid, Hairudin QA75 Electronic computers. Computer science Gender classification has been one of the most vital tasks in a real world problem especially when it comes to death investigations. Developing a biological profile of an individual is a crucial step in forensic anthropology process as for the identification of gender. Forensic anthropologists employ the principle of skeleton remains to produce a biological profile. Different parts of skeleton contains different features that will contribute to gender classification. However, not all the features could contribute to gender classification and affect to a low accuracy of gender classification. Therefore, feature selection method is applied to identify the most significant features for gender classification. This paper presents the implementation of feature selection approaches which are Particle Swarm Optimization (PSO) and Harmony Search (HS) algorithm using three different dataset from Goldman Osteometric Dataset, Osteological Collection and George Murray Black Collection. All three dataset contains 4081 samples of metrics measurement and have gone through the process of classification by using Back Propagation Neural Network (BPNN) and Naïve Bayes classifier. The main scope of this paper is to identify the effect of feature selection towards gender classification. The result shows that the accuracy of gender classification for every dataset increased when feature selection is applied to the dataset. Among all the skeleton parts in this experiment, clavicle part achieved the highest increment of accuracy rate which is from 89.76% to 96.06% for PSO algorithm and 96.32% for HS. Penerbit UTM Press 2016 Article PeerReviewed application/pdf en http://eprints.utm.my/71456/1/NurulLiyanaHairuddin2016_Improvinggenderclassificationwithfeature.pdf Hairuddin, Nurul Liyana and Mi Yusuf, Lizawati and Othman, Mohd. Shahizan and Abdul Majid, Hairudin (2016) Improving gender classification with feature selection in forensic anthropology. Jurnal Teknologi, 78 (12-2). pp. 57-63. ISSN 0127-9696 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006054036&doi=10.11113%2fjt.v78.10143&partnerID=40&md5=98184b621d404423973132c44ebb1e59 |
spellingShingle | QA75 Electronic computers. Computer science Hairuddin, Nurul Liyana Mi Yusuf, Lizawati Othman, Mohd. Shahizan Abdul Majid, Hairudin Improving gender classification with feature selection in forensic anthropology |
title | Improving gender classification with feature selection in forensic anthropology |
title_full | Improving gender classification with feature selection in forensic anthropology |
title_fullStr | Improving gender classification with feature selection in forensic anthropology |
title_full_unstemmed | Improving gender classification with feature selection in forensic anthropology |
title_short | Improving gender classification with feature selection in forensic anthropology |
title_sort | improving gender classification with feature selection in forensic anthropology |
topic | QA75 Electronic computers. Computer science |
url | http://eprints.utm.my/71456/1/NurulLiyanaHairuddin2016_Improvinggenderclassificationwithfeature.pdf |
work_keys_str_mv | AT hairuddinnurulliyana improvinggenderclassificationwithfeatureselectioninforensicanthropology AT miyusuflizawati improvinggenderclassificationwithfeatureselectioninforensicanthropology AT othmanmohdshahizan improvinggenderclassificationwithfeatureselectioninforensicanthropology AT abdulmajidhairudin improvinggenderclassificationwithfeatureselectioninforensicanthropology |