State Estimation of Stochastic Boolean Control Networks: A Hidden-Markov-Process-Based Approach

In this brief, the state estimation of stochastic Boolean control networks (SBCNs) with stochastic delays is investigated. Firstly, SBCNs with stochastic delays are transformed into hidden Markov BCNs (HMBCNs) based on the hidden Markov process (HMP) and algebraic state space representation (ASSR) method. In addition, a matrix-based recursive method is obtained to calculate the maximum probability of all directed paths based on the given control inputs and observed sequences. Then, Viterbi algorithm is obtained to estimate the unknown state sequences of HMBCNs. Finally, an example is given to validate the theoretical results of this brief.