A Hybrid Augmented Gradient Boosting Classifier-Based Fuzzy Clustering-Based Routing Algorithm for IoT

The exponential growth of Internet of Things (IoT) systems has introduced significant network traffic challenges that require intelligent classification for optimized routing, congestion control, and Quality of Service (QoS) enhancement. Traditional rule-based and deep packet inspection techniques often fail to adapt to the dynamic and encrypted nature of IoT traffic. To address these limitations, this study proposes a machine learning-driven routing optimization framework using a Hybrid Augmented Gradient Boosting Classifier (HAGBC) integrated with Linear Discriminant Analysis (LDA), Jaccard with Interpolation Scaled Tuna Swarm-based Fuzzy C-Means Clustering (JISTS-FCM), and Self-Updated Dung Beetle Optimization (SU-DBO).The proposed model enhances feature separability, optimizes cluster formation, and dynamically adjusts model weights to improve traffic classification and routing decisions. Experimental evaluation demonstrates that the proposed HAGBC model achieves superior performance with an accuracy of 99.1%, precision of 99.32%, recall of 99.10%, specificity of 98.92%, and F1-score of 99.21%, outperforming conventional approaches such as Decision Tree, SVM, K-NN, and Random Forest.