IMPROVING GENDER CLASSIFICATION WITH FEATURE SELECTION IN FORENSIC ANTHROPOLOGY

Authors

  • Nurul Liyana Hairuddin Faculty of Computing, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Johor, Malaysia
  • Lizawati Mi Yusuf Faculty of Computing, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Johor, Malaysia
  • Mohd Shahizan Othman Faculty of Computing, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Johor, Malaysia
  • Hairudin Abdul Majid Faculty of Computing, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Johor, Malaysia

DOI:

https://doi.org/10.11113/jt.v78.10143

Keywords:

Forensic Anthropology, Gender classification, Feature Selection, Particle Swarm Optimization (PSO), Harmony Search (HS)

Abstract

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.  

References

Vanessa Stanojevich. 2012. The Role of Forensic Anthropologist in a Death Investigation. J Forensic Res. 3: 154.

Iis Afrianty, Dewi Nasien, Mohammaed R. A Kadir, Habibollah Haron. 2013. Detemination of Gender from Pelvic Bone and Patella in Forensic Anthropology: A Comparison of Classification Techniques. 2013 First International Conference on Artificial Intelligence, Modelling & Simulation, AIMS. 3-7.

V. Alumni- Perret, P.Staccini, G. Quatrehomme. 2007. Sex Determination from the Distal Part of the Femu in a French Contemporary Population. Forensic Science International. 175: 113-117.

Enas M. Mostafa, Azza H. El-Elemi, Mohamed A. El-Beblawy, Abd El-Wahab A. Dawood. 2012. Adult Sex Identification using Digital Radiographs of the Proximal Epiphysis of the Femur at Suez Canal University Hospital in Ismailia, Egypt. Egyptian Journal of Forensic Sciences. 2(3): 81-88.

Ana Clavero, Miquel Salicru, Daniel Turbon. 2015. Sex Prediction from the Femur and Hip Bone Using a Sample of CT Images from a Spanish Population. Int J. Legal Med 129: 373-383.

Lauren Novak, John J. Schultz, Matthew McIntyre. 2012. Determining Sex of the Posterior Ilium from the Robert J. Terry and William M. Bass Collections. J. Forensic Sci. 57(5).

P. James Macaluso Jr. 2010. Sex Determination from the Acetabulum: Test of Possible non-population-specific Discriminant Function Equation. Journal of Forensic and Legal Medicine. 17: 348-351.

James Macaluso Jr. Joaquin Lucena 2014. Estimation of Sex from Sternal Dimensions Derived from Chest Plate Radiographs in Contemporary Spaniards. Int J Legal Med. 128: 389-395.

H. V. Chandrakanth, Tanuj Kanchan and Kewal Krishan. 2014. Osteometric Analysis for Sexing of Modern Sternum – An Autopsy Study from South India. Legal Medicine. 16: 350-356.

Hu, K. S. et al. 2006. Sex Determination Using Nonmetric Characteristics Of The Mandible In Koreans. J Forensic Sci. 51(6): 1376-82.

Saini, V., Srivastava, R., Shamal, S. N., Singh, T. B., Pandey, A. K. & Tripathi. S. K. 2011. Sex Determination using Mandibular Ramus Flexure: A Preliminary Study On Indian Population. J Forensic Leg Med. 18(5): 208-12.

Du Jardin, P., Ponsaille, J., Alunni-Perret, V. & Quatrehomme, G. 2009. A Comparison Between Neural Network And Other Metric Methods To Determine Sex From The Upper Femur In A Modern French Population. Forensic Sci Int. 192(1-3): 127 e 1-6.

Harma, A., H. M. Karakas. 2007. Determination of sex from the femur in Anatolian Caucasians: A digital radiology study. J Forensic Leg Med. 14(4): 190-4.

Tersigni-Tarrant M. A and Shirley N. R. 2013. Forensic Anthropology. An Introduction. CRC Press.

L. Y. Chung, H. W. Chang, C. J. Tu and C. H. Yang. 2008. Improved Binary PSO For Feature Selection Using Gene Expression Data. Computational Biology And Chemistry. 29-38.

J. Novakovic. 2010. The Impact Of Feature Selection On The Accuracy Of Naïve Bayes Classifier. 18th Telecommunications Forum TEFLOR 2010. 113-116.

A. M. Taha, A. Mustapha and S. D. Chen. 2013. Naïve Bayes Guided Bat Algorithm For Feature Selection. Scientific World Journal. 2013: 1-6.

H. Liu and H. Motoda. 2007. Computational Methods Of Feature Selection. Chapman and Hall, CRC Press.

B. Nagaraj and N. Murugananth. 2010. A Comparative Study of PID Controller Tuning Using GA, EP, PSO and ACO. IEEE.

Abdolalipour, A. and Alibabae, A. 2012. Harmony Search Algortihm. International Journal of Academic Research in Applied Science. 1(3): 13-16.

Manjarres, D., Landa-Torres, I. Gil-Lopez, S. Del Ser, J. Bilbao, M. N. Salcedo-Sanz and Geem. Z. W. 2013. A Survey on Applications of the Harmony Search Algorithm. Engineering Applications.

Benjamin, M. Auerbach. Goldman Osteometric Dataset. http://web.utk.edu/~auerbach/GOLD.htm

George Alfredo Gomez-Valdes, Guillermo Torres Ramirez, Socorro Baez Molgado, Patricia Herrera Sain-Leu, Jose Luis Castrejon Caballero, Gabriela Sanchez-Mejorada. 2011. Discriminant Function Analysis for Sex Assessment in Pelvic Girdle Bones: Sample from the contemporary Mexican Population. J Forensic Sci. March 56(2).

George Murray Black Collection. http://www.peterbrownpalaeoanthropology.net/resource.html.

Koushal Kumar and Abhishek. 2012. Artificial Neural Networks for Diagnosis of Kidney Stones Disease. I.J Information Technology and Computer Science. 20-25.

Simon Haykin. 1999. Neural Networks: A Comprehensive Foundation. Pearson Education. 178-224.

Saurabh KarKarsoliya. 2012. Approximating Number of Hidden layer neurons in Multiple Layer Hidden Layer BPNN Architecture. International Journal of Engineering Trends and Technology. 3(6).

Patil, T. R. & Sherekar, S. S. 2011. Performance Analysis of Naïve Bayes and J48 Classification Algorithm for Data Classification. International Journal of Computer Science and Applications. 6(2): 256-261.

Downloads

Published

2016-12-04

How to Cite

IMPROVING GENDER CLASSIFICATION WITH FEATURE SELECTION IN FORENSIC ANTHROPOLOGY. (2016). Jurnal Teknologi, 78(12-2). https://doi.org/10.11113/jt.v78.10143