•  
  •  
 

Abstract

In recent years, there has been a highly remarkable convergence of artificial intelligence (AI) and the Internet of Things (IoT), which has made rapid progress in smart city initiatives by developing smart devices for such cities. Since these devices are increasingly diversified, they require a resilient communication network to demonstrate high performance in managing consistent traffic flows. A machine learning model intended for identifying network parameters from diverse devices, in addition to proposing modifications meant for network performance enhancement, is developed in this study. In relation to packet data as a network traffic parameter, employing gateway devices can facilitate its transmission and reception. In applying classification and prediction, the model can employ six various machine learning approaches, comprising Decision Tree (DT), Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Naive Bayes (NB), and Stochastic Gradient Descent Classifier (SGDC). We have employed 40 different IoT devices in a real-time smart laboratory setup for the purpose of testing the model’s performance. The study indicates the effectiveness of the model, which achieved an average accuracy of 92.2%, F1-score of 92%, recall of 92%, and precision of 91.7%. The Decision Tree classifier reached the best effectiveness by achieving accuracy at 99.9% with an F1-score of 99.8% and precision at 98.8%. The success rate of 99.9% from the proposed model evidences its strong capacity to correctly identify IoT device traffic across different circumstances, thus improving network security and performance.

Download

Share

COinS