Murat H. Sazli

Bio: Murat H. Sazli is an academic researcher from Ankara University. The author has contributed to research in topics: Cognitive radio & Artificial neural network. The author has an hindex of 8, co-authored 32 publications receiving 333 citations.

A brief review of feed-forward neural networks

Abstract: Artificial neural networks, or shortly neural networks, find applications in a very wide spectrum. In this paper, following a brief presentation of the basic aspects of feed-forward neural networks, their mostly used learning/training algorithm, the so-called back-propagation algorithm, have been described.

Discrete Lissajous Figures and Applications

Abstract: In this paper, an innovative method based on an algorithm utilizing discrete convolutions of discrete-time functions is developed to obtain and represent discrete Lissajous and recton functions. They are actually discrete auto- and cross-correlation functions. The theory of discrete Lissajous figures is developed. The concept of rectons is introduced. The relation between the discrete Lissajous figures and autocorrelation functions is set. Some applications are described including phase, frequency, and period determination of periodic signals, time-domain characteristics (such as damping ratio) of a control system, and abnormality and spike detection within a signal, are described. In addition, an electrocardiogram signal with an abnormality of atrial fibrillation is given for abnormality detection by means of recton functions. An epileptic activity detection within an electroencephalography signal is also given.

Microstrip Antennas The Analysis And Design Of Microstrip Antennas And Arrays

Abstract: Description: Electrical Engineering/Antennas and Propagation Microstrip Antennas The Analysis and Design of Microstrip Antennas and Arrays Microstrip Antennas contains valuable new information on antenna design and an excellent introduction to the work done in the microstrip antenna area over the past 20 years. The articles are well–chosen and (are) complete with practical design information that is very useful for the working engineer. Stuart Long, University of Houston The editors have done an outstanding job in assembling this updated reprint book. It is a welcome addition to the list of books on microstrip antennas. There is no doubt that it will be a valuable source of information for graduate students, engineers and researchers the original articles are written lucidly and are very informative, and the reprint articles are well chosen. Kai Fong Lee, The University of Toledo Complete with an up–to–date tutorial overview of the field and substantial new, introductory material for each topic, Microstrip Antennas combines in one source a selection of today’s most significant and useful articles on microstrip and antenna design. Eminent experts David M. Pozar and Daniel H. Schaubert guide you through:

Automatic detection and classification of leukocytes using convolutional neural networks

Abstract: The detection and classification of white blood cells (WBCs, also known as Leukocytes) is a hot issue because of its important applications in disease diagnosis. Nowadays the morphological analysis of blood cells is operated manually by skilled operators, which results in some drawbacks such as slowness of the analysis, a non-standard accuracy, and the dependence on the operator’s skills. Although there have been many papers studying the detection of WBCs or classification of WBCs independently, few papers consider them together. This paper proposes an automatic detection and classification system for WBCs from peripheral blood images. It firstly proposes an algorithm to detect WBCs from the microscope images based on the simple relation of colors R, B and morphological operation. Then a granularity feature (pairwise rotation invariant co-occurrence local binary pattern, PRICoLBP feature) and SVM are applied to classify eosinophil and basophil from other WBCs firstly. Lastly, convolution neural networks are used to extract features in high level from WBCs automatically, and a random forest is applied to these features to recognize the other three kinds of WBCs: neutrophil, monocyte and lymphocyte. Some detection experiments on Cellavison database and ALL-IDB database show that our proposed detection method has better effect almost than iterative threshold method with less cost time, and some classification experiments show that our proposed classification method has better accuracy almost than some other methods.

Communication algorithms via deep learning

Abstract: Coding theory is a central discipline underpinning wireline and wireless modems that are the workhorses of the information age. Progress in coding theory is largely driven by individual human ingenuity with sporadic breakthroughs over the past century. In this paper we study whether it is possible to automate the discovery of decoding algorithms via deep learning. We study a family of sequential codes parameterized by recurrent neural network (RNN) architectures. We show that creatively designed and trained RNN architectures can decode well known sequential codes such as the convolutional and turbo codes with close to optimal performance on the additive white Gaussian noise (AWGN) channel, which itself is achieved by breakthrough algorithms of our times (Viterbi and BCJR decoders, representing dynamic programing and forward-backward algorithms). We show strong generalizations, i.e., we train at a specific signal to noise ratio and block length but test at a wide range of these quantities, as well as robustness and adaptivity to deviations from the AWGN setting.