We present an algorithm for reconstructing the bifurcation structure of a d
ynamical system from time series. The method consists in finding a paramete
rized predictor function whose bifurcation structure is similar to that of
the given system, Nonlinear autoregressive (NAR) models with polynomial ter
ms are employed as predictor functions. The appropriate terms in the NAR mo
dels are obtained using a fast orthogonal search scheme. This scheme elimin
ates the problem of multiparameter optimization and makes the approach robu
st to noise. The algorithm is applied to the reconstruction of the bifurcat
ion diagram (BD) of a neuron model from the simulated membrane potential wa
veforms. The reconstructed ED captures the different behaviors of the given
system. Moreover, the algorithm also works well even for a limited number
of time series.