An Optimised Artificial Neural Network Model for a Three-Level Authentication Security Scheme Utilising Fingerprint, Facial Recognition, and Optical Character Recognition

The rapid increase in the use of digital technologies in daily activities has created both opportunities and threats. The paper reports an optimized Artificial Neural Network (ANN) model for implementing a three-tier authentication system using fingerprint biometrics (Level 1), facial recognition (Level 2) and Optical Character Recognition (OCR) (Level 3). The model is created using a multi-layer perceptron optimized using Adam and L2 regularization in order to have better accuracy and stability under environmental changes. On NIST SD4, LFW, and IAM datasets, an overall accuracy of 97.8% was reached with a false acceptance rate (FAR) of less than 1.0% was attained through experimental evaluation. The results show that the suggested model is better than unimodal techniques by about 16%, which proves its possible ability to protect e-learning and administrative systems at Nigerian universities.

Artificial Neural Network, Multimodal Authentication

1. Abdulrahman, S. A., & Alhayani, B. (2023). A comprehensive survey on the biometric systems based on physiological and behavioural characteristics. Materials Today: Proceedings, 80, 2642–2646. https://doi.org/10.1016/j.matpr.2023.01.456 [Google Scholar] [Crossref]

2. Al-Haija, Q. A. (2023). Cost-effective detection system of cross-site scripting attacksusing hybrid learning approach. Results in Engineering, 19, 101266. https://doi.org/10.1016/j.rineng.2023.101266 [Google Scholar] [Crossref]

3. Almuqren, L., et al. (2023). AI-driven anomaly detection in IoT networks. Computers & Security, 125, 103012. https://doi.org/10.1016/j.cose.2023.103012 [Google Scholar] [Crossref]

4. Chander, B., & Upendra Kumar, R. (2023). MFSDL-ADIIoT: Anomaly detection in industrial IoT. Journal of Network and Computer Applications, 210, 103512. https://doi.org/10.1016/j.jnca.2022.103512 [Google Scholar] [Crossref]

5. Charmet, S., et al. (2022). Federated learning for biometric privacy. Future Generation Computer Systems, 135, 200–215. https://doi.org/10.1016/j.future.2022.05.012 [Google Scholar] [Crossref]

6. Das, S., et al. (2023). AI in multi-factor authentication. Journal of Information Security, 14(2), 100–115. https://doi.org/10.4236/jis.2023.142006 [Google Scholar] [Crossref]

7. Garg, S. N., et al. (2023). Multimodal biometric system based on decision level fusion. Multimedia Tools and Applications, 82(15), 23000–23020. https://doi.org/10.1007/s11042-022-14000-5 [Google Scholar] [Crossref]

8. Hasan, M. W. (2023). IoT temperature forecasting with LSTM and whale optimisation. Memories – Materials Science and Engineering, 45(2), 150–165. https://doi.org/10.1016/j.memse.2023.02.003 [Google Scholar] [Crossref]

9. IBM. (2023). Global IT leaders survey on AI adoption. IBM Corporation. https://www.ibm.com/reports/ai-adoption [Google Scholar] [Crossref]

10. Islam, M. S., et al. (2023). Representation for action recognition: SDQIO. Expert Systems with Applications, 212, 118406. https://doi.org/10.1016/j.eswa.2022.118406 [Google Scholar] [Crossref]

11. Jyothi, K. K., et al. (2024). Optimised neural network for cyber attack detection. Scientific Reports, 14, 55098. https://doi.org/10.1038/s41598-024-55098-2 [Google Scholar] [Crossref]

12. Khan, R. U., et al. (2024). Fingerprint recognition using CNN with inversion techniques. Machine Learning with Applications, 16, 100539. https://doi.org/10.1016/j.mlwa.2024.100539 [Google Scholar] [Crossref]

13. Liu, Z., et al. (2023). DDoS detection in SDN using feature engineering. Sensors, 23(13), 6176. https://doi.org/10.3390/s23136176 [Google Scholar] [Crossref]

14. Omer, N., et al. (2023). Optimised probabilistic neural network for intrusion detection. Computers, Materials & Continua, 77(3), 3500–3515. https://doi.org/10.32604/cmc.2023.045000 [Google Scholar] [Crossref]

15. Pahuja, S., & Goel, N. (2024). Multimodal biometric authentication: A review. Artificial Intelligence Research, 13(1), 1–25. https://doi.org/10.5430/air.v13n1p1 [Google Scholar] [Crossref]

16. Ross, A. A., & Jain, A. K. (2023). Information fusion in biometrics (updated). Pattern Recognition Letters, 170, 50–60. https://doi.org/10.1016/j.patrec.2023.05.012 [Google Scholar] [Crossref]

17. Singhal, M., & Shinghal, K. (2023). Secure deep multimodal biometric authentication. Multimedia Tools and Applications, 82(15), 23000–23020. https://doi.org/10.1007/s11042-023-16683-1 [Google Scholar] [Crossref]

18. Thota, S., & Menaka, D. (2024). Botnet detection in IoT using CNN with pelican optimisation. Automatika, 65(1), 250–260. https://doi.org/10.1080/00051144.2023.2288486 [Google Scholar] [Crossref]

19. Verizon. (2023). Data breach investigations report. Verizon. https://www.verizon.com/business/resources/reports/dbir/ [Google Scholar] [Crossref]

20. Vijayakumar, T. (2023). Palmprint synthesis in multimodal recognition. Journal of Innovative Image Processing, 5(2), 131–143. https://doi.org/10.36548/jiip.2023.2.005 [Google Scholar] [Crossref]

21. Yang, W., et al. (2023). Security and accuracy of fingerprint biometrics: A review. Symmetry, 15(2), 450. https://doi.org/10.3390/sym15020450 [Google Scholar] [Crossref]

• A Machine Learning Model for Predicting the Risk of Developing Diabetes - T2DM Using Real-World Data from Kilifi, Kenya
• AI-Powered Facial Recognition Attendance System Using Deep Learning and Computer Vision
• A Comprehensive Review on Brain Tumour Segmentation Using Deep Learning Approach
• A Scalable Retrieval-Augmented Generation Pipeline for Domain-Specific Knowledge Applications
• Predictive Maintenance in Semiconductor Manufacturing Using Machine Learning on Imbalanced Dataset