Based on the fuzzy clustering and neuro-fuzzy learning algorithms, we proposed a new technique for fuzzy rule generation. In this approach, before learning fuzzy rules we extract typical data by using the fuzzy c-means clustering algorithm. By these typical data, fuzzy rules can be tuned by using the neuro-fuzzy learning algorithm. Therefore, the learning time can probably be reduced and the fuzzy rules generated by the proposed approach are reasonable and suitable for the identified system model = it's all a bit vague really.
Source: Flight International