This paper presents two new concepts for discrimination of signals of different complexity. The first focused initially on solving the problem of setting entropy descriptors by varying the pattern size instead of the tolerance. This led to the search for the optimal pattern size that maximized the similarity entropy. The second paradigm was based on the n-order similarity entropy that encompasses the 1-order similarity entropy. To improve the statistical stability, n-order fuzzy similarity entropy was proposed. Fractional Brownian motion was simulated to validate the different methods proposed, and fetal heart rate signals were used to discriminate normal from abnormal fetuses. In all cases, it was found that it was possible to discriminate time series of different complexity such as fractional Brownian motion and fetal heart rate signals. The best levels of performance in terms of sensitivity (90%) and specificity (90%) were obtained with the n-order fuzzy similarity entropy. However, it was shown that the optimal pattern size and the maximum similarity measurement were related to intrinsic features of the time series.
This paper deals with the discrimination between suffering and healthy fetuses, by means of a delta-fuzzy-similarity entropy. This new descriptor of complexity is based on the derivative of the fuzzy-similarity entropy. It was tested on fetal heart rate time-series and compared to the approximated and similarity entropies. The main outcome was the possibility to improve 10% the specificity and the sensitivity as compared to approximate entropy. This very good performance confirms that the new descriptor can be a valuable alternative as compared to other standard descriptors.
This paper proposes a combined coarse-grained multifractal method to discriminate between distressed and normal foetuses. The coarse-graining operation was performed by means of a coarse-grained procedure and the multifractal operation was based on a structure function. The proposed method was evaluated by one hundred recordings including eighty normal foetuses and twenty distressed foetuses. We found that it was possible to discriminate between distressed and normal foetuses using the Hurst exponent, singularity, and Holder spectra.
In this paper, we propose a computer aided diagnosis system for brain MRI. This system is based on regiongrowing segmentation and KNN classification. The co-occurrence matrix and the discrete wavelet decomposition methods are used to extract the parameters of suspect region. At the last part, we applied our system to other subject to estimate its accuracy.
International audienceThis paper deals with the discrimination between suffering foetuses and normal foetuses by means of a multi-scale similarity entropy. Sample entropy and similarity entropy are evaluated in multi-scale analysis on foetal heart rate signals. Without multi-scale analysis, our results show that only the similarity entropy differentiate suffering foetuses to normal foetuses. Furthermore with the multi-scale analysis, our results show that both the sample entropy and the similarity entropy can discriminate the distressed foetuses to normal foetuses. In all cases the similarity entropy outperforms the sample entropy that is encouraging for another biomedical applications
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.