Advancing ICT Frontiers through Artificial Intelligence, Intelligent Systems, and Cybersecurity

This special issue of the Journal of Information and Communications Technology: Algorithms, Systems and Applications presents eight carefully selected research contributions that collectively reflect the advancing frontiers of artificial intelligence, intelligent systems, and cybersecurity. The papers included in this volume span a broad spectrum of cutting-edge topics—from deep learning-based diagnostics and AI-driven smart agriculture, to adversarial robustness, network intrusion detection, and industrial control system security—offering valuable insights for researchers, practitioners, and policymakers working in these rapidly evolving domains.

The issue opens with a study by Mathivanan et al. on a deep learning-based detection system for Diabetic Retinopathy (DR) that integrates ResNet-50 and InceptionV3 architectures via transfer learning with the MESSIDOR dataset, achieving high accuracy, sensitivity, and specificity across DR severity grades. Following this, Ndungu and Linge present a novel attention-based deep learning model using LSTM networks for predictive analytics in smart agriculture, demonstrating its effectiveness in improving crop yield predictions under varying environmental conditions. The third contribution by Oyenike Mary Olanrewaju et al. investigates adversarial robustness in AI systems, evaluating several neural network models under FGSM and PGD attacks and proposing defensive strategies including adversarial training and randomized smoothing to improve model reliability in security-sensitive deployments.

The subsequent papers address intelligent systems and network security from multiple perspectives. Dada et al. develop an intelligent traffic control system with a multi-phase algorithm combining reinforcement learning and computer vision, validated through simulation and real-world testing for urban congestion management. A comprehensive review by Oni et al. surveys AI-driven approaches for Industrial Control System (ICS) cybersecurity, synthesizing methodological contexts and highlighting gaps in current defenses for critical infrastructure. Meanwhile, Oboyibo et al. propose a hybrid machine learning framework combining Random Forest and deep learning for network intrusion detection systems (NIDS), achieving improved accuracy and reduced false positive rates on benchmark datasets. Rounding out the empirical contributions, Suryawanshi and Gundre examine AI-based detection frameworks for phishing websites, employing ensemble learning methods that leverage URL features, HTML content, and domain information for enhanced threat classification.

Closing the issue, Santhosh Kumar et al. present a survey on machine learning techniques applied to smart grid cybersecurity, reviewing anomaly detection, threat classification, and resilience strategies relevant to modern energy infrastructure. Collectively, these contributions underscore the necessity of interdisciplinary approaches in tackling contemporary challenges at the intersection of ICT, artificial intelligence, and cybersecurity—areas that will continue to shape the technological landscape in the years ahead.

There is no conflict of interest.

The author(s) did not use AI tools in the preparation of this manuscript.

1. S. Mathivanan, A. Rao, P. Reddy, and J. Kaliyamurthie, Deep learning-based detection of diabetic retinopathy using transfer learning with ResNet-50 and InceptionV3, J. Inf. Commun. Technol. Algorithms Syst. Appl., 2026, 2(3), 26311, doi: 10.64189/ict.26311.
2. J. W. Ndungu and L. Linge, Predictive analytics in smart agriculture: an attention-based deep learning model using LSTM networks for crop yield prediction, J. Inf. Commun. Technol. Algorithms Syst. Appl., 2026, 2(3), 26312, doi: 10.64189/ict.26312.
3. O. M. Olanrewaju, A. B. Fagbola, T. A. Olalekan, and A. A. Salawudeen, Evaluating adversarial robustness in AI systems: attacks, defenses, and resilience strategies, J. Inf. Commun. Technol. Algorithms Syst. Appl., 2026, 2(3), 26313, doi: 10.64189/ict.26313.
4. A. Dada, C. Ugwu, F. Okafor, and B. Nwachukwu, Intelligent traffic control systems: a multi-phase algorithm combining reinforcement learning and computer vision for urban congestion management, J. Inf. Commun. Technol. Algorithms Syst. Appl., 2026, 2(3), 26314, doi: 10.64189/ict.26314.
5. O. M. Oni, J. E. Efiong, A. Akinwale, A. O. Amoo, A. Afolabi, O. E. Balogun, and E. A. Olajubu, AI approaches for industrial control system cybersecurity: a comprehensive review of methodological contexts, J. Inf. Commun. Technol. Algorithms Syst. Appl., 2026, 2(3), 26318, doi: 10.64189/ict.26318.
6. G. Oboyibo, C. Ukpere, and E. Osagie, A hybrid machine learning framework for network intrusion detection: combining random forest and deep learning approaches, J. Inf. Commun. Technol. Algorithms Syst. Appl., 2026, 2(3), 26316, doi: 10.64189/ict.26316.
7. Y. Suryawanshi and S. Gundre, AI-based detection framework for phishing websites using ensemble learning and multi-feature analysis, J. Inf. Commun. Technol. Algorithms Syst. Appl., 2026, 2(3), 26317, doi: 10.64189/ict.26317.
8. S. K. Santhosh Kumar, R. Mohan, and P. Rao, Machine learning techniques for smart grid cybersecurity: a survey on anomaly detection and resilience strategies, J. Inf. Commun. Technol. Algorithms Syst. Appl., 2026, 2(3), 26315, doi: 10.64189/ict.26315.

GR Scholastic remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0), which permits non-commercial use, sharing, adaptation, distribution, and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third-party material in this article are included in the article's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc/4.0/.

© The Author(s) 2026