Novel Machine Learning (ML) Algorithms to Classify IPv6 Network Traffic in Resource-Limited Systems

Providing machine learning (ML) based security in heterogeneous IoT networks including resource-constrained devices is a challenge because of the fact that conventional ML algorithms require heavy computations. Therefore, this paper, lightweight ProtoNN, CMSIS-NN, and Bonsai tree were evaluated by using performance metrics such as testing accuracy, precision, F1 score recall to test their classification ability on IPv6 network dataset generated resource-scarce embedded devices. The algorithm provided best results all (98.8 98.9% score, 99.2% 98.8% recall) compared CMSIS-NN algorithms.