CFTD: Core Fusion Time Series Dense Encoder for Intelligent Prediction With Edge AI in Social IoT Systems

The rapid development of the Internet-of-Things (IoT) has transformed human interaction with the world. The Social Internet-of-Things (SIoT) integrates social, emotional, and behavioral aspects into traditional IoT, creating an intelligent network that connects various smart devices. By combining Edge Computing with Artificial Intelligence (AI), data can be processed and analyzed directly on edge devices, improving processing efficiency. However, limited edge resources hinder local AI training, requiring cloud-based training of high-precision models, which are then deployed on edge devices for inference. In time series forecasting, Multilayer Perceptrons (MLPs) are widely used for their computational efficiency but often overlook correlations between time series. Some models adopt channel mixing mechanisms to improve modeling capability but increase computational complexity. To address this problem, we propose the Core Fusion Time Series Dense Encoder (CFTD) model, which incorporates a Core Extract-Distribute (COED) module for efficient channel fusion. Extensive experiments on real-world datasets demonstrate that this novel CFTD model achieves excellent predictive performance compared to the state-of-the-art models.