• P. Hemasrisai
• Mrs. M. Swathi

Managing daily road traffic poses a formidable challenge for traffic authorities. Over the years, urban traffic management has evolved significantly, transitioning from manual interventions to leveraging artificial intelligence (AI) methodologies. By harnessing Big Data analytics algorithms, predictions regarding forthcoming traffic volumes become feasible. However, this necessitates an initial conversion of raw data into a usable dataset, followed by the application of data mining and analytic techniques to construct a traffic flow model based on the pre-processed information. Once implemented, this model empowers traffic managers to promptly realize both immediate and long-term benefits. Notably, the reduction of travel time emerges as a crucial objective. By pinpointing peak travel periods and scrutinizing travel time consistency, valuable insights are gleaned to assist drivers in making informed decisions regarding the timing and routes of their journeys. With the rapid growth of mobile device usage and the pervasive adoption of encryption protocols, analyzing mobile encrypted traffic poses significant challenges for effective network monitoring and cybersecurity. Traditional methods struggle to accurately classify encrypted traffic due to its diverse and dynamic nature, compounded by imbalances in class distributions among different traffic types. With the widespread use of mobile technologies and the Internet, traffic in mobile networksis increasing. This situation has made the classification of traffic an important element for data security and network management. However, encryption of traffic in modern networks makes it difficult to classifytraffic with traditional methods. In this study, a unique deep learning-based classification model is proposedfor the classification of encrypted mobile traffic data. The proposed model is a classification model called RFSE-GRU, which combines the Gated Recurrent Units (GRU) algorithm, feature selection and data balancing. The features that are more meaningful in the classification process are determined by selecting the features with the Random Forest algorithm. In addition, Synthetic Minority Oversampling Technique (SMOTE) oversampling algorithm and Edited Nearest Neighbor (ENN) under sampling algorithm were used together to reduce the negative impact of data imbalance on classification performance.

Mobile encrypted traffic, VPN, big data, machine learning, deep learning, Apache Spark, classification.

"RFSE-GRU : Data Balanced Classification Model For Mobile Encrypted Traffic In Big Data Environment", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.222-227, June-2024, Available :http://www.jetir.org/papers/JETIRGL06038.pdf

"RFSE-GRU : Data Balanced Classification Model For Mobile Encrypted Traffic In Big Data Environment", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pp222-227, June-2024, Available at : http://www.jetir.org/papers/JETIRGL06038.pdf