Browsing by Author "Güzeliş C."

Now showing 1 - 4 of 4

Citation - Scopus: 1
Application of Evolutionary Algorithms To Garment Design
(2013) İnce, Türker; Vuruşkan A.; Bulgun E.; Güzeliş C.
In this study, we present the development of an intelligent system solution for fashion style selection for various female body shapes. The proposed intelligent system combines binary genetic algorithm (GA) or binary version of the particle swarm optimization (PSO) with PSO-trained artificial neural network. The former is used to search the solution space for the optimal design parameters corresponding to a best fit for the desired target, and the task of the latter is to evaluate fitness (goodness) of each evolved new fashion style. With the goal of creating natural aesthetic relationship between the shape of the body and the shape of the garment for fashion styling, combinations of upper body related and lower body related garment pieces together with detailed attribute categories were created as a knowledge base. The encouraging results of preliminary experiments demonstrate the feasibility of applying intelligent systems to fashion styling. © 2013 IEEE.
Citation - Scopus: 3
Engineering Applications of a Dynamical State Feedback Chaotification Method
(2012) Şahin S.; Güzeliş C.
This paper presents two engineering applications of a chaotification method which can be applied to any inputstate linearizable (nonlinear) system including linear controllable ones as special cases. In the used chaotification method, a reference chaotic and linear system can be combined into a special form by a dynamical state feedback increasing the order of the open loop system to have the same chaotic dynamics with the reference chaotic system. Promising dc motor applications of the method are implemented by the proposed dynamical state feedback which is based on matching the closed loop dynamics to the well known Chua and also Lorenz chaotic systems. The first application, which is the chaotified dc motor used for mixing a corn syrup added acid-base mixture, is implemented via a personal computer and a microcontroller based circuit. As a second application, a chaotified dc motor with a taco-generator used in the feedback is realized by using fully analog circuit elements. © 2012 American Institute of Physics.
Citation - Scopus: 1
A Higher-Order Neural Network Design for Improving Segmentation Performance in Medical Image Series
(Institute of Physics Publishing, 2014) Selvi E.; Selver M.A.; Güzeliş C.; Dicle O.
Segmentation of anatomical structures from medical image series is an ongoing field of research. Although, organs of interest are three-dimensional in nature, slice-by-slice approaches are widely used in clinical applications because of their ease of integration with the current manual segmentation scheme. To be able to use slice-by-slice techniques effectively, adjacent slice information, which represents likelihood of a region to be the structure of interest, plays critical role. Recent studies focus on using distance transform directly as a feature or to increase the feature values at the vicinity of the search area. This study presents a novel approach by constructing a higher order neural network, the input layer of which receives features together with their multiplications with the distance transform. This allows higher-order interactions between features through the non-linearity introduced by the multiplication. The application of the proposed method to 9 CT datasets for segmentation of the liver shows higher performance than well-known higher order classification neural networks. © Published under licence by IOP Publishing Ltd.
Citation - Scopus: 2
Real-Time Simulation Platform for Controller Design, Test, and Redesign
(CRC Press, 2017) şahin S.; Işler Y.; Güzeliş C.
Control is a problem of finding a suitable (control) input driving a given system to a desired behavior. In general, there is extensive literature introducing the field of control and providing background material on solving control problems [1-3]. Having a system displaying a desired behavior is usually achieved by designing a controller that produces the necessary control in terms of the fed back actual (plant) output and a reference signal representing the desired (plant) output. The design of a controller working well for a given real plant in an actual environment requires the consideration of the behavior of the actual plant under the actual operating conditions [4-11]. In one extreme, such a controller design problem can be attempted to be solved by examining the simulated controller on a simulated plant under simulated operating conditions [2,12], while in another extreme, the approach relies on testing and tuning the controller hardware on the physical plant in the actual environment [13,14]. Testing the proposed controllers’ performance on the simulated or physical plant is followed by a redesigning or parameter tuning process performed offline or online. Both approaches have their own advantages/disadvantages and also difficulties for experimentation. For most of the cases, examining the controller candidates directly on the physical plant may not be possible in the laboratory environment or may be dangerous because of possible damages that may result [15,16]. In between these extremes lies an approach that mimics the physical plant in real time and in actual environmental conditions, especially in combination with the analog/digital interface units. However, such an approach is not only complicated in software simulations but it also yields, with great probability, unreliable simulators that are highly sensitive to the unavoidable modeling errors that each simulated unit embodies [17,18]. © 2013 by Taylor & Francis Group, LLC.