• Bodduru Sunitha
• Mr. Ch Kurmacharyulu
• Dr.Shaik Asadulla Hussain

The Nano-sensors have a tremendous growth in agriculture, healthcare, and traffic monitoring. The increase of scalability of Nano-sensors, means that a traffic classifier will need to be efficient in classifying Nano-networks. Classifying such networks often poses a problem because of diverse traffic flows like TCP/UDP and Nano specific (NN0 and NN1). This paper compares five machine learning models (KNN, SVM, Random Forest, Decision Tree and Naïve Bayes) with and without tuning their parameters. This article aims to enrich and further the understanding of the problem of micro-sensor networks traffic optimization, as well as to increase their reliability and scalability which is a crucial for the Internet of Nano-Things.

TCP, UDP, SVM

"OPTIMIZING NANO-NETWORK TRAFFIC CLASSIFICATION WITH MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.b116-b127, January-2025, Available :http://www.jetir.org/papers/JETIR2501136.pdf

"OPTIMIZING NANO-NETWORK TRAFFIC CLASSIFICATION WITH MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppb116-b127, January-2025, Available at : http://www.jetir.org/papers/JETIR2501136.pdf