A classification method using echo state networks (ESNs) with corresponding clusters is proposed

which is inspired by complex network topologies imitating cortical networks of the mammalian brain.The time windows functions are adopted to construct multiple-cluster reservoir.The number of clusters corresponds with the number of classes in specific classification problems to improve the classification accuracy.Experimental results based on the standard datasets and analog circuit fault diagnosis show that the proposed method outperforms the original echo state networks.