Citation:
Abstract:
A novel type2-fuzzy adaptive filter is presented, which uses the concepts of type2-fuzzy logic, for electrocardiogram signals denoising. Type2-fuzzy adaptive filter is an information processor where both numerical and linguistic information are used as input-output pairs and fuzzy if-then rules, respectively. The proposed approach is based on an iterative procedure to achieve acceptable information extraction in the case where the statistical characteristics of the input-output signals are unknown. The proposed filter is presented as a dual-layered feedback system. Each layer has different function, the first layer being the type2-fuzzy autoregressive filter model. The second layer being responsible for training the membership function parameters. The second layer adjusts the type2-fuzzy adaptive filter parameters by using a teaching learning-based optimization algorithm (TLBO), which will allow the reaching of the required signal reconstruction by decreasing the criterion function. The proposed filter is validated and evaluated through some experimentations using the MIT-BIH ECGs databases where various artifacts were added to the ECGs signals; these included real and artificial noise. For comparison purposes, both model and non-modelbased methods recently published are used. Furthermore, the effect of the proposed filter on the malformation of diagnostic features of the ECG was studied and compared with several benchmark schemes. The results show that the proposed method performs better denoising for all noise power levels and for a different criteria viewpoint.