Alper Basturk

Erciyes Üniversitesi · Department of Computer Engineering

Colorectal cancer (CRC) is one of the most common and malignant types of cancer worldwide. Colonoscopy, considered the gold standard for CRC screening, allows immediate removal of polyps, which are precursors to CRC. Many computer-aided diagnosis systems (CADs) have been proposed for automatic polyp detection. Most of these systems are based on tra...

Histopathological image analysis is used in the diagnosis of many diseases such as cancer, brain tumor, fatty liver and congenital heart diseases. In clinical practice, the time-consuming diagnostic process requires an expertise in the field, and disagreements can arise among pathologists at the decision stage. Machine learning methods can be used...

Colorectal cancer (CRC) is one of the common types of cancer with a high mortality rate. Colonoscopy is the gold standard for CRC screening and significantly reduces CRC mortality. However, due to many factors, the rate of missed polyps, which are the precursors of colorectal cancer, is high in practice. Therefore, many artificial intelligence-base...

Human action recognition (HAR) is a popular subject for academic society and other stakeholders. Nowadays it has a wide-spread use for lots of practical applications such as for health, assistive living, elderly care, and so on. Both visual and sensor-based data can be used for HAR. Visual data includes video images, still images, skeleton images,...

Sign language is one of the most important tools for the communication for deaf-and-dumb individuals who have lost their linguistic and auditory abilities. It is a very difficult process to learn the sign language, where communication involves using hand movements, mimic or lip movements. Significant problems may arise in situations where the sign...

Deep learning has emerged as a leading machine learning tool in object detection and has attracted attention with its achievements in progressing medical image analysis. Convolutional Neural Networks (CNNs) are the most preferred method of deep learning algorithms for this purpose and they have an essential role in the detection and potential early...

Expression recognition (ER), which has been frequently used in human-computer interaction, uses visual data such as video and static images or sensor-based data for recognizing. Facial expression recognition (FER) is a visual data based ER. Since videos have sequential images, it can be easier to recognize emotion in video signals rather than stati...

Action recognition is a challenging task. Deep learning models have been investigated to solve this problem. Setting up a new neural network model is a crucial and time-consuming process. Alternatively, pre-trained convolutional neural network (CNN) models offer rapid modeling. The selection of the hyperparameters of CNNs is a challenging issue tha...

Lung cancer is one of the deadliest cancer types whose 84% is non-small cell lung cancer (NSCLC). In this study, deep learning-based classification methods were investigated comprehensively to differentiate two subtypes of NSCLC, namely adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). The study used 1457 18F-FDG PET images/slices with tumor...

Human action recognition (HAR) has a considerable place in scientific studies. Additionally, hand gesture recognition, which is a subcategory of HAR, plays an important role in communicating with deaf people. Convolutional neural network (CNN) structures are frequently used to recognize human actions. In the study, hyperparameters of the CNN struct...

Emotion recognition systems have been used frequently both socially and commercially. Various classification methods are used to perform emotion recognition. The convolutional neural network (CNN) has a popular position among these classification methods. The CNN modeling process, which is left to the user experience, is a hard challenging task. In...

In this chapter, a novel classification methodology for medical disease diagnosis is proposed. The proposed classification operator comprises a stacked autoencoder network cascaded with a softmax layer. The classifier is trained by applying a special training approach, where each layer of the proposed classifier is trained individually and sequenti...

In this paper, a new optimization method, which is developed especially for optimization of functions with a large number of local minima, is presented. The proposed method is a hybrid optimization algorithm which employs the artificial bee colony (ABC) and limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithms for combining their powe...

In this study, the advantages of the parallel compution paradigms are utilized in a recent optimization algorithm, firefly algorithm. In the proposed implementation, the population is divided into subpopulations and each subpopulation is run on a different processing node. From the results on commonly used benchmark functions, the proposed model en...

The high resolution hyperspectral remote sensing data collected from urban and landscape areas have been extensively studied over the past decades. Recent applications pose an emerging need of analyzing the land cover types based on high resolution hyperspectral remote sensing data originating from remote sensory devices. Toward this goal, we propo...

Improving the classification performance of Deep Neural Networks (DNN) is of primary interest in many different areas of science and technology involving the use of DNN classifiers. In this study, we present a simple training strategy to improve the classification performance of a DNN. In order to attain our goal, we propose to divide the internal...

Working up with deep learning techniques requires profound understanding of the mechanisms underlying the optimization of the internal parameters of complex structures. The major factor limiting this understanding is that there exist only a few optimization methods such as gradient descent and Limited–memory Broyden–Fletcher–Goldfarb–Shannon (L-BFG...

Magnetoencephalography(MEG) is an emerging medical signal processing methodology that uses the magnetic field of brain to decode internal brain activity. However, MEG signals are very complicated and usually corrupted with significant amount of noise. Therefore, it is not easy to directly understand how the human brain responds to visual stimulus b...

Although many algorithms have been proposed, no single algorithm is better than others on all types of problems. Therefore, the search characteristics of different algorithms that show complementary behavior can be combined through portfolio structures to improve the performance on a wider set of problems. In this work, a portfolio of the Artificia...

Parkinson disease occurs when certain clusters of brain cells are unable to generate dopamine which is needed to regulate the number of the motor and non-motor activity of the human body. Besides, contributing to speech, visual, movement, urinary problems, Parkinson disease also increases the risks of depression, anxiety, and panic attacks, disturb...

This paper investigates the application of a deep neural network architecture that consists of stackted autoencoder with two autoencoders and a softmax layer for the purpose of human activity classification. Th performance of the proposed architecture is tested on a commonly used data set known as Human Activity Recognition Using Smartphones. It is...

The effect of using autoencoders for dimensionality reduction of a medical data set is investigated. A stack of two autoencoders has been trained for popular benchmark medical data set for dermatological disease diagnosis. The improvement of the presented approach has been visualized by the Principal Component Analysis method. Results shows that th...

The Discrete Haar Wavelet Transform has a wide range of applications from signal processing to video and image processing. Data-intensive structure and easy of implementation make Discrete Haar Wavelet Transform convenient to distribute fundamental operations to multi-CPU and multi-GPU systems. In this paper, the wavelet transform was ported in a c...

In this study, a channel model which is based on practical channel measurements obtained from electrical networks in Turkey is proposed for power line communication (PLC) systems. Experimental measurements are realized in different cities and various indoor places such as laboratory, university office and apartment house in order to achieve a gener...

Power line communication (PLC) systems are known as the most rapidly enhancing technologies within the smart grid scope due to offering remarkable cost efficiency by decreasing the transmission device requirement. In this study, image transmission performance of low-density parity-check (LDPC) coded communication systems that is based on a realisti...

In this study, we proposed a parallel implementation of the combinatorial type artificial bee colony algorithm which has an efficient neighbor production mechanism. Running time and performance tests of the proposed parallel model were carried on the traveling salesmen problem. Results show that parallel artificial bee colony algorithm decreases th...

The use of edge information for noise removal from digital images is of vital importance for preserving image details after filtering process. In this work, the edges in the speckled image are detected by employing a type-2 fuzzy edge detector and then the mean filter is used for removing speckle noise. Although the mean filter is effective for spe...

In this paper, a novel fuzzy system-based method for speckle noise removal is proposed. The proposed method consists of a fuzzy inference system, an edge detection and dilation unit, and an image combiner. The fuzzy inference system includes 5 inputs and 1 output, and it is responsible for filtering the speckle noisy image. The inputs of the fuzzy...

In this paper, as an extension of a previous study, an improved approximation for the Gaussian Q-function is presented. The nonlinear least squares algorithm is employed to optimize the coefficients of the proposed approximation. The accuracy of the presented approximation is evaluated using extensive computer simulations. Results show that the pro...

Despite the efficiency of evolutionary algorithms is prominent for large scale problems, their running times in terms of CPU time are quite large. Multi processing units served by recent hardware developments can be employed to overcome this drawback reducing the running time and sharing the total workload. However, evolutionary algorithms cannot b...

A general purpose image enhancement operator based on type-2 neuro-fuzzy networks is presented in this chapter. The operator can be used for a number of different image enhancement tasks depending on its training. Specifically, two different applications of the presented operator are considered here: (1) noise filter and (2) noise detector. Compara...

In this paper, a novel fuzzy system based method for speckle noise removal is proposed. The proposed method consists of a fuzzy inference system, an edge detection and dilation unit, and an image combiner. The fuzzy inference system includes five-inputs and one-output, and it is responsible for filtering the speckle noisy image. The inputs of the f...

Nowadays, the importance of developing high-performance computers (HPC) and efficient algorithms that take advantage of new technologies is rapidly growing because the diversity and complexity of mathematical models that need simulations are increasing; as well as there are more technical problems that require to process data at high speed. HPC is...

Evolutionary algorithms often need huge running times when solving large-scale optimization problems. One of the solutions for this issue is to introduce parallelization into the algorithm. To benefit from this approach for the artificial bee colony optimization algorithm, we present a new synchronous and parallel version of the algorithm. Performa...

In this paper, we present a novel application of type-2 fuzzy logic to the design of an image processing operator called an impulse detector. The type-2 fuzzy logic based impulse detector can be used to guide impulse noise removal filters to significantly improve their filtering performance and enhance their output images. The design of the propose...

It is known that parallel computing systems have some advantages to solve large scale and hard problems. However, traditional multi-processor parallel architectures are not widely used since they are hard to operate and they have high cost in setting-up .It has been an important point to Graphical Processing Units (GPU) were shown to be used in gen...

In this work, a method involving the use of a type-2 fuzzy inference system for impulse noise removal from digital images is presented. In the presented work, parameters of the type-2 fuzzy inference system are optimized by the Clonal Selection Algorithm adopting a rule based approach. In the rule based approach, parameters of the type-2 fuzzy infe...

In this work, a rule-based training method for the optimization of a fuzzy inference system that is used as a noise removal operator is presented. In this method, only the parameters processed in the current epoch, rather than all parameters of the fuzzy inference system, are replaced with the new candidate solutions when examining the neighboring...

A cellular neural network (CNN) based edge detector optimized by differential evolution (DE) algorithm is presented. Cloning template of the proposed CNN is adaptively tuned by using simple training images. The performance of the proposed edge detector is evaluated on different test images and compared with popular edge detectors from the literatur...

zet Bu çalışmada, bir hücresel sinir ağının (HSA) şablon katsayıları sayısal imgelerde kenar çıkarımı amacıyla parçacık sürüsü optimizasyon algoritması kullanılarak belirlenmektedir. Sunulan HSA'nın şablon katsayıları basit yapay eğitim imgeleri kullanılarak belirlenmiştir. Sunulan kenar çıkarıcının başarımı birinci dereceden farklı kenar çıkarıcıl...

A novel image filter based on type-2 fuzzy logic techniques is proposed for detail-preserving restoration of digital images corrupted by impulse noise. The performance of the proposed filter is evaluated for different test images corrupted at various noise densities and also compared with representative conventional as well as state-of-the-art impu...

A cellular neural network (CNN) based edge detector optimized by clonal selection algorithm is presented. Cloning templates of the proposed CNN is adaptively tuned by using simple training images. The performance of the proposed edge detector is evaluated on different test images and compared with popular edge detectors from the literature. Simulat...

A novel filtering operator based on type-2 fuzzy logic techniques is proposed for detail preserving restoration of impulse noise corrupted images. The performance of the proposed operator is tested for different test images corrupted at various noise densities and also compared with representative conventional as well as state-of-the-art impulse no...

In this paper, a new detail-preserving neuro-fuzzy (NF) filtering operator based on typc-2 fuzzy logic tccniqucs for restoring digital images corrupted by impulse noise is presented. The operator is constructed by combining desired number of typc-2 NF filters, defuzzifiers and a postprocessor. All NF filters in the structure of the operator are Sug...

An adaptive neuro-fuzzy inference system (ANFIS) based method is proposed for speckle noise reduction in synthetic aperture radar (SAR) images. Before using active RADAR (radio detection and ranging) and SAR imageries, the very first step is to reduce the effect of speckle noise. Reduction of speckle noise is one of the most important processes to...

In this paper, a new method for inspection of textile defects in fabrics is presented. The method is based upon the extraction of fabric features by Gabor wavelets. The Gabor wavelets transform provides an effective way to analyze images and extract features of textures. Principal component analysis using singular value decomposition is used to red...

A simple method for reducing undesirable distortion effects of mixed noise filters for digital images is presented. The method is based on a simple 2-input 1-output neuro-fuzzy network. The internal parameters of the neuro-fuzzy network are adaptively optimized by training. The training is easily accomplished by using simple artificial images gener...

In this work, a neuro-fuzzy based method intended for the removal of different types of noise in digital images by a single operator is proposed. It is demonstrated that a single operator can be used for the removal of different types of noise by creating suitable data sets. Performance of the proposed method is compared with the performances of th...

Not Available

Not Available

A generalized neuro-fuzzy (NF) operator for removing impulse noise from highly corrupted digital images is presented. The fundamental building block of the operator is a simple 3-input 1-output NF filter. The operator is constructed by combining a desired number of NF filters with a postprocessor. Each NF filter in the structure evaluates a differe...

A new operator for the restoration of digital images corrupted by impulse noise is presented. The proposed operator is a simple recursive switching median filter guided by a neuro-fuzzy network functioning as an impulse detector. The internal parameters of the neuro-fuzzy impulse detector are adaptively optimized by training. The training is easily...

A new operator for the restoration of digital images corrupted by impulse noise is presented. The proposed operator is a simple recursive switching median filter guided by a neuro-fuzzy network functioning as an impulse detector. The internal parameters of the neuro-fuzzy impulse detector are adaptively optimized by training. The training is easily...

A new operator for the restoration of digital images corrupted by impulse noise is presented. The proposed operator is a simple recursive switching median filter controlled by a neuro-fuzzy network functioning as an impulse detector. The internal parameters of the neuro-fuzzy impulse detector are adaptively determined by training. The training is e...

AbstractA new neuro-fuzzy operator for removing impulse noise from highly corrupted digital images is presented. The proposed operator is very simple and comprises two identical neuro-fuzzy filters combined with a postprocessor. The internal parameters of the filters are adaptively adjusted by training. Training of the filters is easily accomplishe...

In this paper, a new method for inspection of textile defects in fabrics is presented. The method is based upon the extraction of fabric features by Gabor wavelets. The Gabor wavelets transform provides an effective way to analyze images and extract features of textures. Principal component analysis using singular value decomposition is used to red...

ZET Bu çalışmada sayısal imgelerdeki Gauss gürültüsünü gidermek amacıyla kullanılabilecek bir bulanık süzgeç sunulmaktadır. Geliştirilen ağ gürültünün ortalama ve varyans değişimlerine karşı bağışıktır. Sunulan yöntemin başarımı ortalama alıcı süzgeç ile karşılaştırılmış ve başarımının bu süzgece göre daha iyi olduğu gösterilmiştir. 1. GİRİŞ Sayısa...