Decoding and Re-estimation of fuzzy hidden semi Markov chain with observation dependent state

In a real-world application, Fuzzy Semi Hidden Markov Model (FSHMM) is an inspirational domain for uncertainty. FSHMM has been handled the vagueness in real-life situation. The other models cannot consider uncertainty information, but effectively finds optimal path between states where exists. proposed work described new approach to solving model's two significant problems: decoding and re-estimation. Decoding gives best possible sequence of hidden fuzzy semi chain model, re-estimation provides set parameters through iterations, which increases possibility given observation sequence. Algorithms are provided this paper better understanding solutions. functioning algorithms established using proper illustrations Viterbi algorithm. Furthermore, spotlights neutrosophic model.