Abidin Çalışkan

Bio: Abidin Çalışkan is an academic researcher from Batman University. The author has contributed to research in topics: Computer science & Pattern recognition (psychology). The author has an hindex of 3, co-authored 8 publications receiving 43 citations.

An efficient noisy pixels detection model for CT images using extreme learning machines

Abstract: In this study, a new and rapid hidden resource decomposition method has been proposed to determine noisy pixels by adopting the extreme learning machines (ELM) method. The goal of this method is not only to determine noisy pixels, but also to protect critical structural information that can be used for disease diagnosis. In order to facilitate the diagnosis and also the treatment of patients in medicine, two-dimensional (2-D) images were calculated tomography (CT) which is obtained using medical imaging techniques. Utilizing a large number of CT images, promising results have been obtained from these experiments. The proposed method has shown a significant improvement on mean squared error and peak signal-to-noise ratio. The experimental results indicate that the proposed method is statistically efficient, and it has a good performance with a high learning speed. In the experiments, the results demonstrated that remarkable successive rates were obtained through the ELM method.

Three-Dimensional Modeling in Medical Image Processing by Using Fractal Geometry

Abstract: Medical images are visualized by computer and processed to obtain larger, more organized, and three-dimensional (3D) images. Thus, significant images are provided. The processed data facilitate diagnosis and treatment in the medical fields. The 3D surface models of related areas are formed by using volumetric data obtained by employing medical imaging methods such as Magnetic Resonance (MR) and Computer Tomography (CT). The purpose of this study is to obtain 3D images from the two-dimensional CT slices. These slices are obtained from the existing medical imaging devices and transferred to the z space and a mesh structure is provided between them. In addition, we investigated 3D imaging techniques, visualization, basic data types, conversion into main graphical components, and imaging algorithms. At the phase of obtaining 3D images; the image processing methods such as surface and volume imaging techniques, smoothing, denoising, and segmentation were used. The complexity and efficiency properties of the imaging algorithms were investigated and image enhancement algorithms were utilized.

Palmprint recognition system based on gray level cooccurrence matrix

Abstract: A biometric system provides automatic identification of individuals based on a unique feature or characteristic of the individuals. Palmprint biometric system has an important place among biometric identification systems because of its advantages. In this study, Gray Level Co-Occurence Matrix based palmprint recognition system which provides successful results for tissue type of image identifying has been proposed. Firstly, image coordinate system has been defined to facilitate image alignment for feature extraction. Then, region of interest is cropped from the palmprint images. The properties of the interested region have been determined using the developed system and it has been given to the classifier for recognition.

Diagnosis of malaria disease by integrating chi-square feature selection algorithm with convolutional neural networks and autoencoder network

Abstract: Malaria is a febrile illness caused by a parasite called plasmodium. This life-threatening disease is preventable and treatable if diagnosed early. The World Health Organization aims to reduce the global malaria incidence and death rates by at least 90% until 2030. This disease is diagnosed by visually analyzing red blood cells with a microscope by experienced radiologists. Therefore, this situation may be erroneous due to subjective interpretations. In this study, red blood cells were trained with deep learning–based convolutional neural networks to diagnose malaria, and thus, their deep features were obtained. These obtained features are also trained with autoencoder networks. Thus, the chi-square feature selection algorithm was used to obtain distinctive features. Finally, the unique feature set obtained is given as an introduction to machine learning algorithms, and then a unique diagnostic model is proposed. As a result, 100% accuracy rate was obtained. The results are promising for the diagnosis of malaria disease.

Deep neural network-based underwater OFDM receiver

Abstract: Due to the characteristics of the underwater acoustic (UWA) channel, the process at the receiver is complicated to match the channel. To simplify receiver design and match UWA channel better, this study proposes a deep neural network-based orthogonal frequency division multiplexing receiver for UWA communication. Different from existing receivers needing a neural network and several other processing parts, the proposed receiver only uses a single neural network to implement the whole signal processing. Moreover, it is a general receiver which is suitable for other modulation schemes. Simulation results show that the proposed receiver offers better bit error rate performance over traditional ones.

Improved intrusion detection method for communication networks using association rule mining and artificial neural networks

Abstract: Nowadays, detecting anomaly events in communication networks is highly under consideration by many researchers. In a large communication network, traffic is massive, which leads to a larger amount of data travelling and also the growth of noise. Therefore, to extract meaningful data for anomaly detection would be very challenging. Each attack has its own behaviour that determines the type of attack. However, some attacks may have similar behaviours and only differ in some features. Extracting such meaningful features is of special importance. In this study, an association rule mining algorithm, in particular, the Apriori algorithm is employed to extract appropriate features from the raw data including rules and repetitive patterns. The extracted features would be used then for classifying the data and detecting anomalies in communication networks. A hybrid of artificial neural network and AdaBoost classification algorithms are employed for classifying the detected events with normal behaviour and attack events. The proposed method is compared with previous methods reported in this field such as CART, CHAID, multiple linear regression and logistic regression on KDDCUP99 data set. The results showed that the proposed method outperformed other classifiers examined. The strategy of reinforcement learning is used to combine the classifier's results which is based on Max vote strategy.

An Efficient Gray-Level Co-Occurrence Matrix (GLCM) based Approach Towards Classification of Skin Lesion

Abstract: Skin lesion is one of those diseases which is on its rapid growth and is life threatening. Some cancers may have early signs and symptoms that can be noticed but that is not always the case. Melanoma can often be found early, when it is most likely to be cured, However, the detection of lesion in initial stages holds a greater survival rate so there is a high need of early diagnosis. Therefore a computer aided design is needed with high efficiency which can diagnose skin lesion utilizing minimum time. The technique proposed in this paper is high effective as being compared with latest published techniques proposed in previous researches. Proposed technique have achieved the accuracy of 99.02%.