In this work, classification of cellular structures in the high resolutional histopathological images and the discrimination of cellular and non-cellular structures have been investigated. The cell classification is a...
详细信息
In this work, classification of cellular structures in the high resolutional histopathological images and the discrimination of cellular and non-cellular structures have been investigated. The cell classification is a very exhaustive and time-consuming process for pathologists in medicine. The development of digital imaging in histopathology has enabled the generation of reasonable and effective solutions to this problem. Morever, the classification of digital data provides easier analysis of cell structures in histopathological data. Convolutional neural network (CNN), constituting the main theme of this study, has been proposed with different spatial window sizes in RGB color spaces. Hence, to improve the accuracies of classification results obtained by supervised learning methods, spatial information must also be considered. So, spatial dependencies of cell and non-cell pixels can be evaluated within different pixel neighborhoods in this study. In the experiments, the CNN performs superior than other pixel classification methods including SVM and k-Nearest Neighbour (k-NN). At the end of this paper, several possible directions for future research are also proposed.
Sum of squares (SOS) optimization has been a powerful and influential addition to the theory of optimization in the past decade. Its reliance on relatively large-scale semidefinite programming, however, has seriously ...
详细信息
Sum of squares (SOS) optimization has been a powerful and influential addition to the theory of optimization in the past decade. Its reliance on relatively large-scale semidefinite programming, however, has seriously challenged its ability to scale in many practical applications. In this paper, we introduce DSOS and SDSOS optimization as more tractable alternatives to sum of squares optimization that rely instead on linear programming and second order cone programming. These are optimization problems over certain subsets of sum of squares polynomials and positive semidefinite matrices and can be of potential interest in general applications of semidefinite programming where scalability is a limitation.
Cardiotocography is one of the most widely used technique for recording changes in fetal heart rate(FHR) and uterine contractions. Assessing cardiotocography is crucial in that it leads to identifying fetuses which su...
详细信息
Cardiotocography is one of the most widely used technique for recording changes in fetal heart rate(FHR) and uterine contractions. Assessing cardiotocography is crucial in that it leads to identifying fetuses which suffer from lack of oxygen, i.e. hypoxia. This situation is defined as fetal distress and requires fetal intervention in order to prevent fetus death or other neurological disease caused by hypoxia. In this study a computer-based approach for analyzing cardiotocogram including diagnostic features for discriminating a pathologic fetus. In order to achieve this aim adaptive boosting ensemble of decision trees and various other machine learning algorithms are employed.
Optical character recognition(OCR) can be used in some management mechanisms of state and business world to organize documents scanned or captured by camera. Therefore, OCR is one of the subjects rapidly evolving in t...
详细信息
Optical character recognition(OCR) can be used in some management mechanisms of state and business world to organize documents scanned or captured by camera. Therefore, OCR is one of the subjects rapidly evolving in the recent times. This study investigates the procedure steps until character recognition. That's because, the more correctly preprocessings are applied;the better results can be obtained in character recognition. In this study, the algorithms providing the best results are determined by following the procedure stages of gray scale transformation, noise removal and image thresholding. Binarization plays an important role in character recognition. For this reason, algorithms dynamically determine thresholds are preferred for character recognition in this study. Accordingly, Otsu thresholding method was determined to give the best results in terms of both picture quality and speed. Therefore, this method was used for character recognition. Primarily, lines were determined for character separation and then letters were individually obtained.
Advanced Encryption Standard (AES), which is approved and published by Federal Information Processing Standard (FIPS), is a cryptographic algorithm that can be used to protect electronic data. The AES algorithm can be...
详细信息
ISBN:
(纸本)9783319009506
Advanced Encryption Standard (AES), which is approved and published by Federal Information Processing Standard (FIPS), is a cryptographic algorithm that can be used to protect electronic data. The AES algorithm can be programmed in software or hardware. This paper presents encryption time comparison of the AES algorithm on FPGA and computer. In the study, Verilog HDL and C programming language is used on the FPGA and computer, respectively. The AES algorithm with 128-bit input and key length 128-bit (AES-128) was simulated on Xilinx ISE Design Suite 13.3. It was observed that, the AES algorithm runs on the FPGA faster than on a computer. We measured the time of encryption on FPGA and computer. Encryption time is 390ns of AES on FPGA and 11 μs of AES on a computer.
The optimal production and advertising policies for an inventory control system of multi-item multiobjective problem under a single management are formulated as an optimal control problem with resource constraints und...
In the conditions of industrial production many processes of polymerisation are nonstationary. By processes optimization with the regard for such features as basic data it is necessary to use adaptive algorithms of id...
详细信息
The multilevel inverters (MLIs) are classified into three topologies such as Diode Clamped, Flying Capacitor and Cascade Multilevel Inverter (CMLI). CMLI topologies include two kind of structure that is named symmetri...
详细信息
In the conditions of industrial production many processes of polymerisation are nonstationary. By processes optimization with the regard for such features as basic data it is necessary to use adaptive algorithms of id...
详细信息
In the conditions of industrial production many processes of polymerisation are nonstationary. By processes optimization with the regard for such features as basic data it is necessary to use adaptive algorithms of identification, allowing mathematical model of process continuously to be adapted for changing conditions of operation. Use of such algorithms for process optimization demands periodic recalculation of optimum technological modes of process. Polymer reaction engineering is a discipline that deals with various problems concerning the fundamental nature of chemical and physical phenomena in polymerization processes. Mathematical modeling is a powerful tool for the development of process understanding and advanced reactor technology in the polymer industry.
Recently, in Mathematical and Computational Applications Journal Chiu et al. [1] and Chen and Chiu [2] propose an inventory model based on EPQ with rework to determine the replenishment lot size and the number of ship...
详细信息
Recently, in Mathematical and Computational Applications Journal Chiu et al. [1] and Chen and Chiu [2] propose an inventory model based on EPQ with rework to determine the replenishment lot size and the number of shipments for a vendor-buyer integrated production-inventory system. They solve the inventory problem by considering both variables as continuous. However, the number of shipments must be considered as discrete variable. In this direction, this paper revisits and solves the inventory problem of [1-2] considering the decision variables according to their nature. Two easy and improved algorithms are proposed which simplify and complement the research works of [1-2].
暂无评论