Published Paper Details:

This project addresses traffic detection and classification in networks by implementing classification at end systems, overcoming challenges associated with proprietary hardware access. Utilizing supervised learning models, particularly decision tree classifiers, and achieves over 98% accuracy, enabling real-time application. Integration into Software Defined Networks (SDN) enhances network efficiency and adaptability, facilitating intelligent routing decisions and fostering more responsive infrastructures. The existing system suffers from limitations such as limited access, scalability challenges, lack of flexibility, high costs, and vendor dependency, necessitating alternative approaches. The proposed system focuses on achieving high accuracy, real-time application feasibility, enhanced network efficiency, improved management, scalability, adaptability, and cost-effectiveness. Through data collection, model selection, training, integration with SDN, testing, and maintenance, the system aims to provide network administrators with enhanced visibility and control over network traffic while leveraging existing infrastructure. Overall, this project presents a comprehensive solution for efficient traffic detection and classification, paving the way for more responsive and cost-effective the networks