In addition, there is a big problem that it is difficult to perform the rehabilitation in the same day because all these methods take the feature extraction from several weeks to several months by machine learning.
    Our study aims to construct a novel neurorehabilitation system to extract motor intention more easily and quickly by only focusing the amplitude increase/decrease by means of Fuzzy Template Matching (FTM).  This way, we are free to frequency and oscillatory factors such as ERS/ERD.  Here we report the development of such novel rehabilitation system for the lower limb movement, including a method of learning FTM, the mechanism of device, control design, the system setup. The consequence of the operation and verification of the rehabilitation system by measuring real human brain activity.  

2. Learning Fuzzy Template Matching(L-FTM)     

2.1 About L-FTM      

For this study, Learning-type-Fuzzy Template Matching (LFTM) was used to classify the EEG feature [16] [17]. In conventional fuzzy template matching [18] [19], templates are constructed using the position of peak of the membership functions. while in our developed BCI, the template was constructed of the fuzzy labels of“ high ”and“ low”for the input values in an antecedent clause of a fuzzy rule. Owing to the peculiarity of fuzzy reasoning, rules (templates) can be consisted of various types of inputs. In this case, 216 rules are constructed when the number of inputs is 16 and the number of fuzzy labels is 2, as shown in Figure 1.