A diverse group of researchers, led by Senior PhD student Yoga Suhas Kuruba Manjunath from India, has achieved notable success in a remarkable display of collaboration and teamwork while making remarkable success in landmark research identifying Virtual Reality network traffic in an Internet Protocol network. The team, which included a junior PhD student, Niusha Sabri Kadijani, from Iran, and three undergraduate students, Austin Wissborn, Tim Rozer, and Mathew Szymanowski, all from Canada, serving as summer research assistants, showcased their project at the Leaders of Tomorrow event organized by IEEE Toronto, demonstrating the strength of their combined efforts.

Yoga Suhas, the project leader, played a pivotal role in training the young members. Yoga is also serving as a volunteer at the IEEE Toronto section. He not only managed the project but also took charge of the technical aspects of the event. Therefore, the summer research assistants and Niusha successfully managed the poster presentation. His guidance and training ensured that everyone was well-prepared for their respective tasks. Suhas skillfully managed the technical components during the presentation, controlling the audio-visual equipment and coordinating the slides, ensuring a smooth and professional delivery. His leadership was a source of inspiration for the entire team.

The team’s strength was not just in its research skills but also in its inclusivity and mutual respect. They worked hand in hand, supporting each other throughout the project. One notable member, Mathew, who is wheelchair-bound and requires specialized equipment to use his computer, received unwavering support from his colleagues and was actively involved in the poster design. This inclusivity and mutual respect underscored the team’s commitment to overcoming challenges and strengthening collaboration. The team is a perfect example of Equity, Diversity, and Inclusivity. “The Best Team Work” was awarded to the team in the event.

The project identifies different classes of service (CoS) network traffic, including the latest hot trends in virtual reality network traffic. The work is beneficial for Internet Service Providers as it aids in quick resource scheduling and eliminates the need to remodel the traffic services constantly. This means the work provides a long-term solution for Internet Service Providers. The work proposed a novel segmented learning involving representing the segmented traffic in vector form using Essential Vector Representation (EVR). The segmented traffic is then modelled for identification using the Simple Segment Method of Classification (S2MC) that uses a Random Forest classifier. The solution’s success relies on finding the optimal segment size and the minimum number of segments required for modelling. The S2MC is a heuristic algorithm that helps find the optimal segment size and the minimum number of segments required for modelling. The solution is validated using different real-world datasets.

Synchronous traffic services that require acknowledgment and a request to continue communication are classified with 99% accuracy. The solution boasts a state-of-the-art ability to identify CoS traffic quickly using the initial 1000 packets of a traffic session. The test results remain consistent even when trained on one dataset and tested on a different dataset.

The work, supervised by Dr. Lian Zhao and Dr. Xiao-Ping Zhang, has been made possible with the support of the Ontario Center of Innovation (OCI) ENCQOR 5G development program and the Natural Sciences and Engineering Research Council of Canada (NSERC). Their support and funding have validated the project’s credibility and recognized its potential impact in the field of networking traffic classification.