• Dr.P.ARULPRAKASH
• A.Balamurugan
• S.Avinashlingam
• S.Dhanushshankar
• J.Mohammed Jameal

Traffic classification methods encounter a major issue of identifying the most suitable feature combination, which has a significant influence on the classification process. It is vital to maintain a balance between the classifier's ability to generalize and its exposure to risk. This paper proposed model focuses on traffic classification using a combination of DL and ML techniques. The input data is taken from a preprocessed dataset that has undergone data cleaning and data standardization. Feature extraction and selection are then performed using machine learning and deep learning techniques. The machine learning technique involves separate feature extraction and selection operations, while the deep learning technique utilizes a single DBN for both operations. In the ML technique, the feature extraction stage includes features like source port, destination port, Time to live, protocol, and packet size, and the feature selection is performed using a CESOA. The selected features are concatenated, and traffic classification is performed using a Bi-LSTM model. This model aims to improve the accuracy of traffic classification by optimizing feature selection and leveraging the strengths of both ML and DL techniques. The MATLAB software is used for implementation and an accuracy of 98.37% is achieved for the higher-performing proposed model than the current models.

Machine Learning, Deep Learning, Deep Belief Network, Chaotic enriched Seagull Optimization Algorithm, and Bidirectional Long Short-Term Memory.

"AN IMPROVED NETWORK TRAFFIC CLASSIFICATION BASED ON DUAL FEATURE LEARNING WITH A HYBRID DEEP LEARNING MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.c293-c320, April-2024, Available :http://www.jetir.org/papers/JETIR2404237.pdf

"AN IMPROVED NETWORK TRAFFIC CLASSIFICATION BASED ON DUAL FEATURE LEARNING WITH A HYBRID DEEP LEARNING MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppc293-c320, April-2024, Available at : http://www.jetir.org/papers/JETIR2404237.pdf