QoE Evaluation Model Based on EEG

Quality of experience (QoE) serves as a direct evaluation of users’ experiences in mobile video transmission and is essential for network management, such as network optimization. In this chapter, we propose a deep learning–based QoE prediction approach using a large-scale QoE dataset for mobile video transmission. Specifically, we developed a mobile phone app for collecting user QoE data when users are viewing videos transmitted over the mobile Internet in a real-world environment. Subsequently, we construct a large-scale dataset by collecting over 8000 data points with four types of subjective scores and 89 network parameters. Each QoE metric is only related to some of the 89 network parameters. Therefore, we apply a feature selection method to identify the feature parameters relevant to user scores. Additionally, we employ the box plot method to clean the raw data by removing outliers. Finally, we develop a deep neural network (DNN) to learn the relationships between the network parameters and the subjective QoE scores. The proposed DNN can also be viewed as a data-driven objective QoE prediction approach for mobile video transmission, which can predict user QoE scores. Experimental results demonstrate that the proposed approach effectively eliminates most features that are irrelevant to QoE prediction and outperforms other state-of-the-art approaches in terms of QoE prediction performance.