A Sequential Pattern Mining Approach for Situation-Aware Human Activity Projection

Human activity prediction has become increasingly prevalent in a plethora of time-critical applications. To realize accurate identification and prediction of human behaviour, we propose a situation-aware wearable computing system. A wearable computing system has the capability to perceive, comprehend and project situations by analyzing the human behavioral patterns in different environments. In particular, this work proposes a situation-aware human activity prediction (SA-HAP) approach based on sequential pattern mining that aims to anticipate future activities and tailor its responses according to situations by analyzing frequent sequential patterns and their correlations to understand how these situations are interrelated. The approach not only improves prediction accuracy but also provide the foundation for a more informed decision-making process, as the projected situations can be explained using the identified behavioral patterns. The approach is compared with other traditional techniques for activity prediction (LSTM and HMM), achieving better performance on the Extrasensory dataset.