Smart City Gnosys
Smart city article details
| Title | Optimized Efficient Predefined Time Adaptive Neural Network For Stream Traffic Classification In Software Defined Network |
|---|---|
| ID_Doc | 40720 |
| Authors | Sujatha V.; Prabakeran S. |
| Year | 2025 |
| Published | Expert Systems with Applications, 286 |
| DOI | http://dx.doi.org/10.1016/j.eswa.2025.128086 |
| Abstract | Software-Defined Networking (SDN) plays a crucial role in enabling scalable and programmable infrastructures for smart cities. However, its centralized and open architecture is increasingly vulnerable to security threats, especially with the growing complexity of network traffic. This paper proposes a novel approach called Optimized Efficient Predefined Time Adaptive Neural Network for accurate and adaptive stream traffic classification in SDN environments (EPTANN-STC-SDN). The proposed framework addresses imbalanced traffic data using a Multi-Observation Fusion Kalman Filter (MOFKF) and enhances feature selection using Secretary Bird Optimization Algorithm (SBOA). The classification is performed with the help of Efficient Predefined Time Adaptive Neural Network (EPTANN), whose parameters are fine-tuned under the Bitterling Fish Optimization Algorithm (BFOA) to enhance the accuracy and generalization. The experimental results demonstrate that the EPTANN-STC-SDN significantly outperforms existing methods, achieving up to 33.82% higher accuracy, 31.48% improvement in kappa and 33.02% better precision over leading baseline models. The proposed model contributes to both academic research and practical SDN deployments by enabling more secure, efficient and intelligent traffic management in modern networks. © 2025 |
| Author Keywords | Efficient Predefined Time Adaptive Neural Network; Multi-Observation Fusion Kalman Filter; SDN-dataset; Secretary Bird Optimization Algorithm; Stream Traffic Classification |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
23738  | 0.855 | Jabbar M.S. | Enhancing An Intelligent Model For Enhancing Software-Defined Networking (Sdn) Achievement Using Fog Computing And Reinforcement Learning For Operational Performance And Dynamic Resource Management | International Journal of Intelligent Engineering and Systems, 18, 5 (2025) |
| 24112 | 0.852 | Patel M.; Jain N.; Patel J.; Ramoliya F.; Gupta R.; Tanwar S. | Ensemble Learning For Network Data Classification With Sdn Clustering Underlying Smart Power Grid-Enabled Smart Cities | Proceedings of the 3rd IEEE International Conference on Power Electronics, Intelligent Control and Energy Systems, ICPEICES 2024 (2024) |
| 32590 | 0.852 | Schmitt S.; Kandah F.I.; Brownell D. | Intelligent Threat Hunting In Software-Defined Networking | 2019 IEEE International Conference on Consumer Electronics, ICCE 2019 (2019) |