Abstract: To make full use of the effective data produced from simulation process, the hidden Markov model is applied to identifying the status of simulated sensor nodes. Taking account of the characteristics of WSN (wireless sensor network), the Baum-Welch algorithm is extended to design a complex event recognition algorithm that is discussed in detail for the state constraints and the way to process the observation window. Such key problems as data acquisition, state modeling and hidden-state inference in the event recognition algorithm are analyzed in depth, with the temporal and spatial complexities of the algorithm explained. A WSN simulation platform is therefore designed and implemented to verify the effectiveness of the algorithm and the practicality of the system.