International Journal of Advances in Intelligent Informatics ISSN 2442-6571 Vol. 8, No. 3, November 2022, pp. 324-336 324 https://doi.org/10.26555/ijain.v8i3.927 http://ijain.org ijain@uad.ac.id Determination of gender from fingerprints using dynamic horizontal voting ensemble deep learning approach Olorunsola Stephen Olufunso a,1,* , Abraham Eseoghene Evwiekpaefe a,2 , Martins Ekata Irhebhude a,3 a Department of Computer Science, Nigeria Defence Academy, Kaduna, Nigeria 1 stevenolorunsola@yahoo.com; 2 contact_abrahama@yahoo.com; 3 mirhebhude@nda.edu.ng * corresponding author 1. Introduction Despite significant progress in gender equality, there are still key gender gaps particularly in education, health, right to job opportunities and other basic needs of livelihood. Case instance is in Afghanistan under the control of the Taliban, there have been news of violation against women and girls’ rights. There are evidences that the Taliban will implement policies that will restrain women and girl from accessing education, confinement to their home or even denying them access to most jobs [1]. Hence, gender inequality and other associated issues are major problem in our world. International donor agencies, such as World Bank, European Union, African Development Bank (AfDB) and many others, identifies gender identity system as a vital stepping-stone for the female, particularly, as a means of empowering and given them access to peculiar services and other privileges as a citizen [2]. An effective gender identification system has been discovered to be an important enabler for attaining a number of key development results toward eradicating gender inequality, poverty and financial exclusion. The good thing is that there are several methods to verify the identity of people. However, biometric system offers a better approach for personal identification with numerous gains over other methods [3]. ARTICLE INFO ABSTRACT Article history Received October 1, 2022 Revised October 23, 2022 Accepted November 26, 2022 Available online November 30, 2022 Despite tremendous advancements in gender equality, there are still persistent gender disparities, especially in important human activities. Consequently, gender inequality and related concerns are a serious problem in our global society. Major players in the global economy have identified the gender identity system as a crucial stepping stone for bridging the enormous gap in gender-based problems. Extensive research conducted by forensic scientists has uncovered a unique pattern hidden in the fingerprint and these distinguishing characteristics of fingerprints can be utilized to determine the gender of individuals. Numerous research has revealed various fingerprint-based approaches to gender recognition. The purpose of this research is to present a novel dynamic horizontal voting ensemble model with hybrid Convolutional Neural Network and Long Short Term Memory (CNN-LSTM) deep learning algorithm as the base learner to automatically determine human gender attribute based on fingerprint pattern. More than four thousand Live fingerprint images were acquired and subjected to training, testing and classification using the proposed model. Result of this study indicated over 99% accuracy in predicting person’s gender. The proposed model also performed better than other state-of-the-art model such as ResNet-34, VGG-19, ResNet-50 and EfficientNet-B3 model when implemented on SOCOFing public dataset. This is an open access article under the CC–BY-SA license. Keywords Fingerprints pattern Deep learning Classification Gender Soft biometric