Analysis of behavioral changes of zebrafish (Danio rerio) in response to formaldehyde using Self-organizing map and a hidden Markov model

► Self-organizing map (SOM) and Hidden Markov model (HMM) were suitable in presenting dynamic processes of behavioral states. ► SOM was capable of patterning behavioral states of Danio rerio. ► HMM was useful in illustrating transition probabilities of behavioral states. ► Estimated transition and emission probabilities were accordingly evaluated to present behavioral states before and after chemical treatment. ► Computational methods are suitable in automatic behavioral monitoring.