Crackles have an explosive pattem in time domain, with a rapid onset and short duration. The timing, repeatability, and shape of crackles are important parameters for diagnosis. Therefore, automatic detection of crackles and their classification have important clinical value. Since crackles have a general characteristic shape, it is obvious that wavelet analysis can be exploited to detect crackles and classify them. In this paper, we present a new method for crackle detection which is based on 'matched' wavelet transform. We first modeled crackles as a mathematical function. Then we designed a matched mother wavelet based on this model. Applying a soft-threshold to the results of the continuous wavelet transform to suppress noise further, the optimal scale can be obtained. Crackles can be detected based on the envelope of the signal at optimal scale, and can be classified based on energy distribution with scale. Theory, methods and experimental results are given in detail in this paper.
Abstract.A complex-fuzzy approach using complex fuzzy sets is proposed in the paper to deal with the problem of adaptive image noise cancelling. A image may be corrupted by noise, resulting in the degradation of valuable image information. Complex fuzzy set (CFS) is in contrast with traditional fuzzy set in membership description. A CFS has the membership state within the complexvalued unit disc of the complex plane. Based on the membership property of CFS, we design a complex neural fuzzy system (CNFS), so that the functional mapping ability by the CNFS can be augmented. A hybrid learning method is devised for training of the proposed CNFS, including the artificial bee colony (ABC) method and the recursive least square estimator (RLSE) algorithm. Two cases for image restoration are used to test the proposed approach. Experimental results are shown with good restoration quality.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.