As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Progress in computational intelligence system classifiers has generated new applications about gender classification to enhance the forensic anthropology post-mortem to recognize the biological profile. In current situations, computational intelligence system classifier (CISS) does not simultaneous perform feature subset selection. In realizing the classification accuracy performance; this article will propose a hybridization model of gender classification through feature selection in terms of classification accuracy. In validating the hybridization model, different classification models were compared. Particle Swarm Optimization (PSO) feature selection is a computational intelligence system that is implemented to analyze influential factors of trabecular bone morphology features through global best particle to bring better fitness without complicated mathematic operators. Then, irrelevant factors of features are eliminated. PSO acts as feature selection approach in dataset preparation process of two CISS called Artificial Neural Network (ANN) and Support Vector Machine (SVM). Empirical evaluation shows that the hybridization classifier model with model classification data of a forensic anthropology post-mortem demonstrates the effectiveness of our feature selection approach in improving classification accuracy. Based on the result, PSO-ANN presents more accurate result than ANN, likewise PSO-SVM produced better result than SVM.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.