The description of the main steps of the method for determination ofthe coordinates of the extremumsof non-stationary periodic signals is given. This method is based on multi-start optimization using the wavelet transform. The main steps of the base form of multi-start optimization methodwith using the wavelet transform are given. The results of investigation of noise stability and error for the search of extremumsof asymmetric and multi-modal test functions for such method are given. The main stepsof extremumsearch by such method in new method for determination ofthe coordinates of the extremum of non-stationary periodic signals are implemented.This method is implemented for automated electrocardiograms(ECG)diagnostic systems in tele-medicine. This method allowed us to determine characteristic fragments coordinates for electrocardiogram.The procedure for esti-mation of the characteristic fragmentscoordinatesand intervals between them is based on this multi-start optimization method with using the wavelet transform. The main steps of thisprocedure are described. The error inestimatingtheduration of theintervalsbetween ECG characteristic fragmentswas estimated and the noise immunity of such estimation with increasing the noise level was evaluated. The relative error in estimationofthe intervalsduration between characteristic fragments was less than 4% in the case of the signal-to-noise ratio in amplitude up to 10. These results allowrecommendingthe developed method for implementationin in-formation technologies for automated decision support systems, including telemedicine,in condition ofincreasing noise level in ECG signals. Forfurther research,it is planned to develop a methodology for estimationthe remaining parameters of characteristic fragments and complexes in ECG, reducing the edge effects during the estimation of the extremums coordinates.

<abstract> <p>An important component of the computer systems of medical diagnostics in dermatology is the device for recognition of visual images (DRVI), which includes identification and segmentation procedures to build the image of the object for recognition. In this study, the peculiarities of the application of detection, classification and vector-difference approaches for the segmentation of textures of different types in images of dermatological diseases were considered. To increase the quality of segmented images in dermatologic diagnostic systems using a DRVI, an improved vector-difference method for spectral-statistical texture segmentation has been developed. The method is based on the estimation of the number of features and subsequent calculation of a specific texture feature, and it uses wavelets obtained by transforming the graph of the power function at the stage of contour segmentation. Based on the above, the authors developed a modulus for spectral-statistical texture segmentation, which they applied to segment images of psoriatic disease; the Pratt's criterion was used to assess the quality of segmentation. The reliability of the classification of the spectral-statistical texture images was confirmed by using the True Positive Rate (TPR) and False Positive Rate (FPR) metrics calculated on the basis of the confusion matrix. The results of the experimental research confirmed the advantage of the proposed vector-difference method for the segmentation of spectral-statistical textures. The method enables further supplementation of the vector of features at the stage of identification through the use of the most informative features based on characteristic points for different degrees and types of psoriatic disease.</p> </abstract>

No abstract

No abstract

Abstract:The automated optical inspection system for integrated circuits photo masks is designed. This low error probability system based on application of hyperbolic wavelet transforms and integrated circuits photo masks fiducial marks geometric moment features. The experimental results proved the high noise stability properties, which allow reducing lighting apparatus and high precision mechanism conditions.