Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Journal of Innovation Information Technology and Application (JINITA)
Bopatriciat Boluma Mangata
Department of Computer Science, Haute Ecole de Commerce de Kinshasa, Kinshasa, Democratic Republic of Congo
Computer Science & IT Decision Sciences, Operations Research & Management Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Performance Evaluation of A Three-Modality Biometric System using Multinomial Regression Bopatriciat Boluma Mangata; Trésor Mazambi Kilongo; Pierre Tshibanda wa Tshibanda; Remy Mutapay Tshimona; Jean Pepe Buanga Mapetu; Eugène Mbuyi Mukendi
Journal of Innovation Information Technology and Application (JINITA) Vol 7 No 1 (2025): JINITA, June 2025
Publisher : Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/jinita.v7i1.2287

Abstract

In this article, we explored key concepts related to technology and system efficiency. We have created an innovative biometric system that combines three modalities: fingerprint, facial recognition and voice recognition. This approach guarantees enhanced security and a seamless user experience for access control. We tested our application to obtain the false rejection rate and the false acceptance rate, which gave us the confusion matrix. We then used the multinomial regression method to obtain the various parameter values, which are: FN=0.124, VPP=0.88, Sp=0.88, VPN=0.87, Se=0.87 and F-measure = 0.87 for voice recognition, FN=0.104, VPP=0.90, Sp=0.90, VPN=0.89, Se=0.89 and F-measure = 0.89 for face recognition, FN=0.08, VPP=0. 92, Sp=0.92, VPN=0.91, Se=0.91 and F-measure = 0.91 for fingerprints and FN=0.004, VPP=0.99, Sp=0.99, VPN=0.99, Se=0.99 and F-measure = 0.99 for the global system resulting from the fusion of these three modalities. From this result, we can say that using the global fusion of these three modalities, our system is very efficient compared to separate systems which give an advantage to the fingerprint recognition system followed by facial recognition and finally voice recognition. We recommend further studies to evaluate the performance of our system in real scenarios, using methods such as multinomial regression. This work paves the way for significant advances in the field of biometric systems and methods such as multinomial regression. We hope that these results will inspire further research and practical applications for a connected and secure world.
Parallel Computing Applied to A Three-Modality Biometric Recognition System using Task Parallel Library Bopatriciat Boluma Mangata; Pierre Tshibanda wa Tshibanda; Vince Muladi Tsitabi; Jean Pepe Buanga Mapetu; Rostin Mabela Matendo Makengo; Eugène Mbuyi Mukendi
Journal of Innovation Information Technology and Application (JINITA) Vol 7 No 2 (2025): JINITA, December 2025
Publisher : Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/jinita.v7i2.2288

Abstract

This study focuses on optimizing the performance of a three-modality biometric recognition system (fingerprints, facial and voice recognition) with global decision fusion, designed for access control to secure areas. When the biometric database contains a large volume of information, the verification module's processing time increases considerably due to the complexity of template comparisons. To address this issue, we implemented an optimization strategy based on parallel programming, specifically targeting the intensive processing loops within the verification module. Using Microsoft's Task Parallel Library, we parallelized all critical loops associated with the three biometric modalities. By effectively exploiting for and foreach statements, our parallelized implementation enables optimal distribution of tasks across available processor cores. We validated our approach by conducting repeated experiments on data sets of varying sizes (50 to 600 individuals), with a rigorous analysis of temporal performance. The results show a significant reduction in execution times: for 600 entries, the processing time goes from 1.68 ms in sequential mode to 0.77 ms in parallel mode. These performances were evaluated over several iterations to ensure the statistical reliability of the results, in particular by calculating averages and standard deviations and including error bars in the comparative graphs. The practical implications of this work are significant: the module can be deployed in corporate security systems, airports or banks, while respecting ethical considerations and privacy constraints. Finally, this work paves the way for future extensions, including the integration of other biometric modalities, deployment on distributed clusters or the adoption of more advanced parallelization frameworks.
Co-Authors Eugène Mbuyi Mukendi Jean Pepe Buanga Mapetu Pierre Tshibanda wa Tshibanda Remy Mutapay Tshimona Rostin Mabela Matendo Makengo Trésor Mazambi Kilongo Vince Muladi Tsitabi