Learning QoE from Packet-Level Measurements in Encrypted Video Conferencing Traffic
Researchers have developed a novel framework for predicting the quality of experience (QoE) in encrypted video conferencing traffic. This system utilizes a convolutional neural network (CNN) that analyzes only packet sizes, bypassing the need for content decryption. Experiments on datasets from WhatsApp and Zoom demonstrated significant improvements over existing QoE prediction models, offering a simple yet effective solution for internet service providers. AI