Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Techno Nusa Mandiri : Journal of Computing and Information Technology Journal of Electronics, Electromedical Engineering, and Medical Informatics
Mate Landry, Gilgen
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
Evaluation of two biometric access control systems using the Susceptible-Infected-Recovered model BOLUMA MANGATA, Bopatriciat; Sangupamba Mwilu, Odette; Tebua Tene, Patience Ryan; Mate Landry, Gilgen
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 5 No 2 (2023): April
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeemi.v5i2.288

Abstract

This paper evaluates the effectiveness of decisions made on two single-mode biometric systems based on facial recognition and fingerprints for access control. To achieve this, we first implemented an embedded system under Arduino to allow us to open and close doors, then we programmed two biometric recognition systems, namely facial recognition and fingerprint recognition, and finally we exploited the Susceptible-Infected-Covered model without demographics to evaluate the efficiency of these two access control systems. The variables used in the analysis were the number of individuals enrolled in the biometric system to be subject to access control (Susceptible), the number of individuals enrolled in the biometric system and denied access by the system, as well as the number of individuals not enrolled in the biometric system and allowed access by the system (Infected), and the number of false acceptance rates and false rejection rates at time t in the systems (Retrieved). In a sample of 600 individuals, of which 300 were enrolled and 300 were not, our two simple modal access control systems each obtained the following results: 270 true positives, 30 false negatives, 48 false positives and 252 true negatives for the facial recognition system, compared to 288 true positives, 12 false negatives, 24 false positives and 276 true negatives for the fingerprint recognition system, which constitute our confusion matrix. Based on this confusion matrix, we were able to exploit the false rejection rates and false acceptance rates to correct for these inconveniences using the SIR model, i.e. 78 infected individuals for the facial recognition system, compared to 36 infected individuals for the fingerprint recognition system over a period of 216 days. The results show that the fingerprint recognition system is more efficient than the facial recognition system, according to the SIR model without demographic formulation.
PERFORMANCE COMPARISON OF CLASSICAL ALGORITHMS AND DEEP NEURAL NETWORKS FOR TUBERCULOSIS PREDICTION Mate Landry, Gilgen; Nsimba Malumba, Rodolphe; Balanganayi Kabutakapua, Fiston Chrisnovi; Boluma Mangata, Bopatriciat
Jurnal Techno Nusa Mandiri Vol. 21 No. 2 (2024): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v21i2.5609

Abstract

This study compares the performance of several classical machine learning algorithms and deep neural networks for the prediction of tuberculosis in the Democratic Republic of Congo (DRC), using a sample of 1000 cases including clinical and demographic data. The sample is divided into two sets: 80% for training and 20% for testing. The algorithms evaluated include Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, Random Forest and Convolutional Neural Networks (CNN). The results show that the CNN has the best overall performance with an accuracy of 94%, an AUC of the ROC curve of 93%, an accuracy of 90%, an accuracy of 95%, a sensitivity of 88%, an F1-score of 91.3% and a Log Loss of 0.0386. The Random Forest follows closely behind with an accuracy of 92% and an AUC of 86%. The SVM and KNN models also performed strongly, but slightly less well. The Decision Tree obtained acceptable results, but inferior to the other algorithms evaluated. These results indicate that deep neural networks, and in particular the CNN, are superior for predicting tuberculosis compared with conventional machine learning algorithms. This superiority is particularly marked in terms of accuracy, sensitivity and reliability of predictions, as shown by the performance metrics obtained.
Co-Authors Balanganayi Kabutakapua, Fiston Chrisnovi BOLUMA MANGATA, Bopatriciat Nsimba Malumba, Rodolphe Sangupamba Mwilu, Odette Tebua Tene, Patience Ryan