Hybrid PSO-ANN for sex estimation based on length of left hand bone

Abstract

Sex estimation is used in forensic anthropology to assist the identification of individual remains. However, the estimation techniques tend to be unique and applicable only to a certain population. This paper analyzed sex estimation on living individual child below 19 years old based on length of 19 bones of left hand using hybrid Particle Swarm Optimization-Artificial Neural Network (PSO-ANN) technique. This technique was carried out on X-ray images of the left hand taken from an Asian population data set. All the 19 bones of the left hand were measured using Free Image software, and the technique was performed using MATLAB. PSO technique was used to select the most relevance bones from the 19 bones in the left hand and the selected bones will be used as inputs for ANN technique. The results of this PSO-ANN technique was compared to ANN in the previous study and the results show that the PSO-ANN technique produced better accuracy percentage than the ANN techniques used in the previous study.