Graph-Enhanced Long-Term Indoor Behavior Prediction With Attention Mechanisms

The development of Internet of Things (IoT) technology has driven the widespread adoption of smart homes. Predicting indoor behavior patterns is of great significance for planning future life, guiding daily habits, and detecting abnormal behaviors. However, current indoor behavior prediction methods primarily focus on predicting individual-specific actions or activities, lacking a comprehensive approach to forecasting overall behavior patterns and exhibiting lower stability and accuracy in long-term prediction tasks. To achieve precise and long-term prediction of complex indoor human behaviors, this article proposes a novel method for behavior prediction with attention mechanism (BPAM), designed to predict users’ behavioral models while enabling timely detection of abnormal behaviors. Specifically, 1) we use passive infrared (PIR) sensors to capture the trajectory of a person moving indoors every day and model it as a directed graph; 2) we use graph convolutional networks (GCNs) to capture the features of a person’s daily behavior patterns and fuse the temporal information into the features; and 3) we develop an inference module that combines attention mechanism and long short-term memory (LSTM) networks to infer behavior patterns for the next days. Experimental results demonstrate that this method outperforms traditional approaches across multiple evaluation metrics, offering an effective solution for indoor behavior prediction.