User clustering-based GAN-LSTM model for viewport prediction in 360-degree video streaming

Abstract

Accurate viewport prediction is crucial for enhancing user experience in 360-degree video streaming. However, due to significant behavioral differences among user groups, traditional single LSTM models tend to fall into local optima and fail to achieve precise predictions. To address this, this paper proposes a hybrid prediction model based on user clustering. First, a Density-Based Clustering Algorithm (DBSCAN) is used to group users with similar behavioral patterns. Then, a hybrid prediction model combining Generative Adversarial Networks (GANs) and Long Short-Term Memory networks (LSTMs) is designed to effectively mitigate data imbalance and overfitting through collaborative training. Experiments conducted on three real-world datasets from YouTube demonstrate that this approach significantly outperforms existing methods based on user trajectories or video saliency in terms of prediction accuracy and stability.