Esma Uzunhisarcikli

EXPERIMENTAL VERIFICATION OF HIGH FREQUENCY PERFORMANCE OF FTFN-BASED SIMPLE CHAOTIC CIRCUIT

In this study, we aimed to improve the VOA-based simple chaotic circuit proposed by Sprott in the literature by using FTFN-based circuit topology. And also, by choosing one of the FTFN-based circuits whose chaotic dynamics are very similar to that of Chuas circuit as a reference model, we tested the performance of this model at different frequencies and its extended frequency performance has been verified by laboratory experiments and PSpice simulations.

Type-2 fuzzy inference system design for computer aided detection in mammogram image

Nowadays the detection of cancer of the breast mass X-ray mammography is widely used by radiologists. This computer-aided system images used by physicians in the interpretation raises the accomplishments of physicians identified masses. Work on computer-aided detection systems consisting of basic image processing and classification section is still in progress. Different methods such as artificial neural networks and support vector machine structure is widely used in mass classification. Previous work in our open access has MIAS containing mass from the database and free mammogram images on image processing techniques and three texture attribute in the second degree by using statistical analysis and derived value statistics of these attributes, attributes, and type-1 fuzzy using Matlab fuzzy toolbox with statistical values inference system is designed. In this study, the standard deviation of the data set using a statistical method on each attribute data set used for type-1 system is calculated. These values are used as the footprint of the uncertainty of the type-2 system parameters. These data sets and data sets related to each piece of histogram chart with type-2 fuzzy inference system was conducted as separate software. We have tested our system type-2 fuzzy inference system has produced more successful than type-1 fuzzy inference system.

A fuzzy inference system design for computer aided mass detection in digital mammogram images

Breast cancer is the most common cancer in women. A mammogram is an X-ray of the breast, using very low levels of radiation. Artificial intelligence and fuzzy inference techniques can be used in CAD systems. These systems generally have main phases that the their names are image processing, and classification. In this study, we used images of mammogram that were obtained MIAS database. The fuzzy inference system was designed using image processing tecniques and statical features. The system was tested and for sensitivity and Specificity respectively, %98 and %99 was found. This study gave better results than our earlier studies using artificial neural network that have %96 sensivity and %96 specifity.