This paper presents a new hybrid intelligent based approach for detecting islanding in distributed generation (DG). In this proposed method the passive and active techniques are combined to get a better reliability. So this hybrid method can secure the detection of islanding for different network topology and various operating conditions of synchronous machine based DG. Hence a better reliability is provided. This approach utilizes the artificial neural network (ANN) as a machine learning technology for processing and analyzing the large data sets provided from network simulations using PSCAD/EMTD software. The technique is tested on two typical distribution networks. The results obtained from one case study are compared with results of one of references to show the validity of the proposed method. The results of both studied cases indicate that the developed method can successfully detect islanding situations.