Research Interests:
Korona virüsün (COVID-19) hızlı bulaşması nedeniyle dünya büyük bir sağlık kriziyle karşı karşıya kalmıştır. Korona virüsün yayılmasını engellemek için Dünya Sağlık Örgütüne (WHO) göre en etkili tedbir, halka açık yerlerde ve kalabalık... more
Korona virüsün (COVID-19) hızlı bulaşması nedeniyle dünya büyük bir sağlık kriziyle karşı karşıya kalmıştır. Korona virüsün yayılmasını engellemek için Dünya Sağlık Örgütüne (WHO) göre en etkili tedbir, halka açık yerlerde ve kalabalık alanlarda maske takmaktır. Ancak kalabalık ortamlarda uzun süre kalan kişilerde sıkılma, boş verme ve umursamazlık gibi nedenlerle insanlar bu kuralı ihlal edebilmektedir. Bu nedenle kalabalık alanlarda insanların izlenmesi ve gerektiğinde ilgililerin uyarılarak toplum sağlığını korumak önem arz etmektedir. Bu çalışmada maske takmayan, maskesini yanlış takan ve maskesini doğru takan kişileri belirleme sürecini otomatikleştirmek için iki derin öğrenme modeli kullanan bir robotik model geliştirilmiştir. İnternetten elde edilen veri setleri ve çevreden alınan fotoğraflar kullanılarak özgün bir veri seti oluşturulmuştur. Geliştirilen yapay zekâ modellerinin daha iyi tahmin sonuçları verebilmesi için veri seti görüntüleri üzerinde veri çoğaltma (aynalama, ...
Bu caly?mada, sa?lykly ve epilepsi hastasy olan ki?ilerden alynan EEG i?aretleri farkly oni?leme ve synyflandyrma yontemleri kullanylarak analiz edilmi? ve bu yontemlerin ba?ary oranlary kar?yla?tyrylmy?tyr. EEG i?aretlerinin... more
Bu caly?mada, sa?lykly ve epilepsi hastasy olan ki?ilerden alynan EEG i?aretleri farkly oni?leme ve synyflandyrma yontemleri kullanylarak analiz edilmi? ve bu yontemlerin ba?ary oranlary kar?yla?tyrylmy?tyr. EEG i?aretlerinin synyflandyrylmasy veya obekle?tirilmesi icin oznitelik cykarym (Ortalama Mutlak De?er (OMD), Yule-Walker AR ve Kovaryans AR), obekle?tirme (K-Ortalama, Bulanyk C-Ortalama (BCO) ) ve synyflandyrma (Destek Vektor Analizi ve Lineer Diskriminant Analizi) metotlary kullanylmy?tyr. Elde edilen yuksek synyflandyrma basarym sonuclary kar?yla?tyrmaly olarak verilmi?tir.
Research Interests:
Tip arastirmacilari tarafindan sik kullanilan bir arama motoru olan Pubmed, MEDLINE veri tabaninda uzerinde sorgulama yapmaktadir. MEDLINE medikal, biyoloji ve genetik alanindaki calismalari iceren ve surekli guncel tutulan bibliyografik... more
Tip arastirmacilari tarafindan sik kullanilan bir arama motoru olan Pubmed, MEDLINE veri tabaninda uzerinde sorgulama yapmaktadir. MEDLINE medikal, biyoloji ve genetik alanindaki calismalari iceren ve surekli guncel tutulan bibliyografik bir veri tabanidir. Icerdigi yuksek hacimdeki yapisal olmayan metinler sebebiyle, MEDLINE veri tabani veya belli bolumleri uzerinde pek cok metin siniflandirma calismalari mevcuttur. Bu calismada kanser turleri hakkinda yazilmis makale ozetlerini inceleyerek makalenin hangi kanser turuyle ilgili oldugunu otomatik bulan bir metot gelistirilmistir. Metodu egitmek ve test etmek icin MEDLINE veri tabani uzerinde 25962 makale ozeti, Pubmed arama motoru uzerinden ayrica gelistirilen bir program (crawler) uzerinden toplanmistir. Elde edilen veri seti uzerinde iki ayri calisma yurutulmustur. Birinci calismada, gelistirilen metot ozellik secim yontemi uygulamadan ve Ki-Kare ve Bilgi Kazanci ozellik secim yontemlerini uygulayarak, Naif Bayes ve Destek Vektor ...
Research Interests:
Research Interests:
Research Interests:
Electroensefalogram (EEG) isaretleri beyin yuzeyinden algilanan dusuk genlikli biyoelektrik isaretler olup, beyin fonksiyonlari hakkinda cok miktarda bilgi icermektedir. Bu sebeple, EEG isaretleri ozellikle tip’ta bir cok beyin... more
Electroensefalogram (EEG) isaretleri beyin yuzeyinden algilanan dusuk genlikli biyoelektrik isaretler olup, beyin fonksiyonlari hakkinda cok miktarda bilgi icermektedir. Bu sebeple, EEG isaretleri ozellikle tip’ta bir cok beyin rahatsizliklari nin teshisinde yaygin olarak kullanilir. Bu calismada, saglikli ve hasta (epilepsi sikayeti olan) kisilerden toplanan EEG isaretlerinin spektrumlarinin incelenmesinde, altuzay yontemlerinden MUSIC (Multiple Signal Classification) ve ozvektor (Eigenvektor:EV) yontemleri kullanilmistir. Bir karsilastirma yapabilmek icin elde edilen spektrumlar, klasik yontemlerden Welch yontemi ile frekans cozunurlugu ve frekans iceriginin belirlenmesini kolaylastiran etkiler acisindan karsilastirilmistir. Net bir sonuc alabilmek amaciyla yontemler once gercek EEG isaretlerine uygulanmis daha sonra da frekans icerigi bilinen simule isaretlere uygulanarak karsilastirma yapilmistir. Elde edilen spektrumlar incelendiginde EEG’de frekans analizi yapilmasinda alt uza...
Research Interests:
Research Interests:
Bilgisayar destekli tanı (BDT) sistemleri, çeşitli hasta bilgilerini kullanarak doktora yardımcı karar destek sistemi oluşturmak amacıyla son yıllarda sıklıkla kullanılmaktadır. Bu çalışmada BDT sistemine yönelik yapılan karar ağaçları... more
Bilgisayar destekli tanı (BDT) sistemleri, çeşitli hasta bilgilerini kullanarak doktora yardımcı karar destek sistemi oluşturmak amacıyla son yıllarda sıklıkla kullanılmaktadır. Bu çalışmada BDT sistemine yönelik yapılan karar ağaçları algoritması uygulamasıyla, Wechsler Çocuklar için Zekâ Ölçeği (WISC-R) profillerinin, sınır zekâ (SZ), hafif ve orta düzeyde zihinsel yetersizlik (ZY) teşhisindeki sınıflandırma başarısının karşılaştırılması amaçlanmıştır. Çalışmanın veri seti DSMV’ e göre tanı konan 50 SZ, 61 hafif düzeyde ZY ve 21 orta düzeyde ZY olmak üzere toplam 132 hastanın WISC-R testi sonuç raporları kullanılarak oluşturulmuştur. WISC-R puanlarının sonuca etkisinin karşılaştırılabilmesi için 132 hastanın test puanları: toplam, sözel ve performans zekâ bölümü puanları; sözel ve performans zekâ bölümü alt ölçek puanları ve bu ikisinden oluşan 3 ayrı veri seti oluşturulmuştur. WISC-R testinin bütün puan türlerini içeren veri setinde, ilk iki düğüm toplam zekâ bölümü puanı seçilmi...
Diabetic retinopathy (DR) is a pathology occurring in the optic nerve due to an excessive blood sugar level in human body. It is one of the major reasons for visual impairment in the developed and developing countries. Patients with DR... more
Diabetic retinopathy (DR) is a pathology occurring in the optic nerve due to an excessive blood sugar level in human body. It is one of the major reasons for visual impairment in the developed and developing countries. Patients with DR usually suffer from visual damages due to a high blood sugar level in retinal blood vessel walls. These damages may also leak into other retinal layers of the eye within time. As a result of these leakages and nutritional disorders, a number of lesions such as excudate, edema, microaneurysm, and hemorrhage may occur. In this respect, an accurate and effective detection of these lesions in earlier stages of DR plays an important role in the progression of the disease. In the proposed study, exudate and hemorrhages, which are important clinical findings for DR, were automatically detected from low contrast colored fundus images. Exudate and hemorrhages are lesions with different characteristics. However, in this study, high performance was achieved by making a three‐class semantic segmentation. In addition, a color space transformation was performed and the classical U‐Net algorithm was provided to achieve stable high performance in low contrast images. Finally, lesion images which were manually detected by a physician were matched with automatically segmented excudate and hemorrhage images using the proposed method. Thus, both segmentation and lesion detection performances of the proposed method were measured. The findings demonstrated that Dice and Jaccard similarity indexes were calculated nearly as 0.95 for the segmentation performance. A sensitivity of 98% and specificity value of 91% were measured for detection performance. It can be inferred from these figures that the proposed method can be effectively used as a supporting system by physicians for the detection and classification of lesions in the color fundus images for the diagnosis of DR.
Research Interests:
Detection of optic disc in retinal images is an important step in disease diagnosis and patient follow-up. Optic disc detection is a Preprocess step for the diagnosis of many diseases, such as glaucoma and DP (Diabetic Retinopathy), which... more
Detection of optic disc in retinal images is an important step in disease diagnosis and patient follow-up. Optic disc detection is a Preprocess step for the diagnosis of many diseases, such as glaucoma and DP (Diabetic Retinopathy), which are vital for the eye. In this study, a hybrid approach is proposed for fully automatic segmentation of Optic Disc (OD). The first phase of the study consists of OD localization. The OD localization coordinate obtained in the study was used as an input to the method of region segmentation, which is a semi-automatic segmentation method, used as an initial point for OD segmentation. In this way, fully automatic segmentation is done. The success of the hybrid approach was evaluated according to both localization and segmentation. Performance of the study was evaluated with 30 images according to Dice and Jaccard Similarity. As a result of the evaluation have been obtained respectively % 92 and % 87 success.
Research Interests:
Developing technological infrastructure has enabled the development of computer based biomedical systems as in many areas in the field of medicine. One of these systems are biomedical imaging systems. Many studies are being conducted for... more
Developing technological infrastructure has enabled the development of computer based biomedical systems as in many areas in the field of medicine. One of these systems are biomedical imaging systems. Many studies are being conducted for a new image processing techniques to improve the performance of this systems. Noise reduction is one of the important steps in biomedical image processing. In this study, noise reduction was performed to emphasize coronary arteries on x-ray heart angiography images. For this purpose, the original angiography images were smoothed using non-local averages. Thus, insignificant groups of pixels in the image described as noise has been removed. Then, the boundaries of coronary arteries are sharpened with first and second derivatives of image based combined enhancement method. It is seen that the mean square error values obtained by the proposed method are more successful when compared with the noise reduction results obtained using the Wiener filter. These results show that the non-local means method can be used as a successful pre-processing method for noise reduction in angiography images.
Research Interests:
In this study, EMG signals taken from the skin surface as a result of muscles' contraction are classified. Studied EMG signals include 400 different patterns relating to four different movements. Each pattern is obtained by adding EMG... more
In this study, EMG signals taken from the skin surface as a result of muscles' contraction are classified. Studied EMG signals include 400 different patterns relating to four different movements. Each pattern is obtained by adding EMG signals one after another, which are recorded synchronously from two different muscles relating to one movement. Support Vector Machine (SVM) classifier, a supervised method, is used to classify these pattterns. But signals need to be preprocessed before being used in SVM classifier. To this end, spectral methods are consulted. In this way, feature vectors which are more significant than raw data and are composed of coefficients are achieved. Four different methods are used for preprocessing and feature vectors obtained are classified by SVM. Success of SVM classifier is tested and performances of preprocessing methods are compared. Best achievement is 94.25%. Keywords: EMG; Spectral Methods; Autoregressive (AR); SVM Classifier.
Research Interests:
PV modules are one of the most important alternative energy tools that can directly convert solar energy into electrical energy. Rapidly developing PV technology has been set up to process of integration PV systems into everyday life of... more
PV modules are one of the most important alternative energy tools that can directly convert solar energy into electrical energy. Rapidly developing PV technology has been set up to process of integration PV systems into everyday life of people. Obtaining of a general mathematical model of solar cell is an important event for designing tools that run with solar energy. In this study, a general mathematical model of solar cells has been obtained and Matlab/Simulink software based simulation of this model has been visually programmed.. Proposed model and PVSYSTEM toolbox can be used with other hybrid systems to develop solar cell simulations for training to engineers, designers and students.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Medicine and Gynecology
Research Interests:
Research Interests:
Research Interests:
The aim of this study was to determine nodules using newly developed software with a computer-assisted visual process technique for the calculation of size. The effects of the ratios of nodule base and width were evaluated with voice... more
The aim of this study was to determine nodules using newly developed software with a computer-assisted visual process technique for the calculation of size. The effects of the ratios of nodule base and width were evaluated with voice acoustic analysis. A total of 72 patients with pediatric vocal nodule were evaluated. Nodules were marked with the ImageJ News program on photographs obtained from the video recordings in the videostroboscopic examination and classified according to the Shah et al scale. Segmentation was applied automatically. The ratios were taken as base of nodule/width and base of nodule/vocal cord. In the voice acoustic analysis, basic frequencies (mean F0), jitter (local %), shimmer (local %), and harmonicity (mean harmonics-to-noise [mean HNR]) were evaluated. A statistically significant negative correlation was determined between the mean F0 value and the nodule base/width ratio (P = 0.042, r = -0.240). A negative statistically significant relationship was determ...
Research Interests:
Research Interests:
Research Interests:
... 202 Page 2. Bu çalışmada, KKA'nin, taşınabilir sayısal işaret işleme ortamında uygulanabilirliği test edilmiştir. ... ().( ) 16) i=0,1,2...N-1 Burada mx x dizisinin ortalama değerini my ise y dizisinin ortalama değerini... more
... 202 Page 2. Bu çalışmada, KKA'nin, taşınabilir sayısal işaret işleme ortamında uygulanabilirliği test edilmiştir. ... ().( ) 16) i=0,1,2...N-1 Burada mx x dizisinin ortalama değerini my ise y dizisinin ortalama değerini gösterirken, d dizinin i'ninci elemandan olan ötelemeyi gösterir. ...
Research Interests:
Research Interests:
Research Interests:
ABSTRACT
Research Interests:
About 1% of the people in the world suffer from epilepsy and 30% of epileptics are not helped by medication. Careful analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the... more
About 1% of the people in the world suffer from epilepsy and 30% of epileptics are not helped by medication. Careful analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders.The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy[1]. In this study, model-based
Research Interests:
Fabrics are produced by at least two yarn systems which are perpendicular to each other in a certain order. Warp fault defect detection can not be done by using human eye easily and it is harder for denim fabrics especially. Therefore... more
Fabrics are produced by at least two yarn systems which are perpendicular to each other in a certain order. Warp fault defect detection can not be done by using human eye easily and it is harder for denim fabrics especially. Therefore this hard task requires care and it is stated that can be done by trained quality controllers with %70
Research Interests:
Research Interests:
Research Interests:
This paper presents a new design of mobile epilepsy warning system for medical application in telemedical environment. Mobile Epilepsy Warning System (MEWS) consists of a wig with a cap equipped with sensors to get Electroencephalogram... more
This paper presents a new design of mobile epilepsy warning system for medical application in telemedical environment. Mobile Epilepsy Warning System (MEWS) consists of a wig with a cap equipped with sensors to get Electroencephalogram (EEG) signals, a collector which is used for converting signals to data, Global Positioning System (GPS), a Personal Digital Assistant (PDA) which has Global System
Research Interests: Artificial Intelligence, Back Propagation, Neural Network, Mobile Computing, Safety, and 13 moreGPS TRACKING SYSTEM, Classification, Call Center, Electroencephalogram, Learning Process, Global System for Mobile Communication (GSM), Training Algorithm, Medical Application, Artificial Neural Network, Global position ing system, Personal Digital Assistant, Backpropagation Algorithm, and multi layer perceptron
Since EEG is one of the most important sources of information in therapy of epilepsy, several researchers tried to address the issue of decision support for such a data. In this paper, we introduce two fundamentally different approaches... more
Since EEG is one of the most important sources of information in therapy of epilepsy, several researchers tried to address the issue of decision support for such a data. In this paper, we introduce two fundamentally different approaches for designing classification models (classifiers); the traditional statistical method based on logistic regression and the emerging computationally powerful techniques based on artificial neural networks (ANNs). Logistic regression as well as feedforward error backpropagation artificial neural networks (FEBANN) and wavelet neural networks (WNN) based classifiers were developed and compared in relation to their accuracy in classification of EEG signals. In these methods we used FFT and autoregressive (AR) model by using maximum likelihood estimation (MLE) of EEG signals as an input to classification system with two discrete outputs: epileptic seizure or nonepileptic seizure. By identifying features in the signal we want to provide an automatic system that will support a physician in the diagnosing process. By applying AR with MLE in connection with WNN, we obtained novel and reliable classifier architecture. The network is constructed by the error backpropagation neural network using Morlet mother wavelet basic function as node activation function. The comparisons between the developed classifiers were primarily based on analysis of the receiver operating characteristic (ROC) curves as well as a number of scalar performance measures pertaining to the classification. The WNN-based classifier outperformed the FEBANN and logistic regression based counterpart. Within the same group, the WNN-based classifier was more accurate than the FEBANN-based classifier, and the logistic regression-based classifier.
Research Interests: Artificial Intelligence, Epilepsy, Electroencephalography, Neural Networks, Multidisciplinary, and 15 moreLogistic Regression, Brain, Humans, Regression Analysis, Decision Support, ROC Curve, Backpropagation, Reproducibility of Results, Fast Fourier Transform, Action Potentials, Artificial Neural Network, Predictive value of tests, Performance Measure, maximum likelihood estimate, and Activation Function
Research Interests:
The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. In this study, multiple signal classification (MUSIC), autoregressive (AR) and periodogram methods were used to get power spectra... more
The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. In this study, multiple signal classification (MUSIC), autoregressive (AR) and periodogram methods were used to get power spectra in patients with absence seizure. The EEG power spectra were used as an input to a classifier. We introduce two fundamentally different approaches for designing classification models (classifiers); the traditional statistical method based on logistic regression (LR) and the emerging computationally powerful techniques based on artificial neural networks (ANNs). LR as well as multilayer perceptron neural network (MLPNN) based classifiers were developed and compared in relation to their accuracy in classification of EEG signals. The comparisons between the developed classifiers were primarily based on analysis of the receiver operating characteristic (ROC) curves as well as a number of scalar performance measures pertaining to the classification. The MLPNN based classifier outperformed the LR based counterpart. Within the same group, the MLPNN-based classifier was more accurate than the LR-based classifier.
Research Interests: Cognitive Science, Algorithms, Artificial Intelligence, Epilepsy, Electroencephalography, and 15 moreNeural Network, Logistic Regression, Brain, Absence epilepsy, Humans, Spectral analysis, ROC Curve, Multilayer Perceptron, Artificial Neural Network, Neurosciences, Logistic Models, Predictive value of tests, Performance Measure, Neuroscience Methods, and Statistical Method
Since there is no definite decisive factor evaluated by the experts, visual analysis of EEG signals in time domain may be inadequate. Routine clinical diagnosis requests to analysis of EEG signals. Therefore, a number of automation and... more
Since there is no definite decisive factor evaluated by the experts, visual analysis of EEG signals in time domain may be inadequate. Routine clinical diagnosis requests to analysis of EEG signals. Therefore, a number of automation and computer techniques have been used for this aim. In this study we aim at designing a MLPNN classifier based on the Fast ICA that accurately identifies whether the associated subject is normal or epileptic. By analyzing a data set consisting of 100 normal and 100 epileptic EEG time series, we have found that the MLPNN classifier based on the Fast ICA achieved and sensitivity rate of 98%, and specificity rate of 90.5%. The results demonstrate that the testing performance of the neural network diagnostic system is found to be satisfactory and we think that this system can be used in clinical studies. Since the time series analysis of EEG signals is unsatisfactory and requires specialist clinicians to evaluate, this application brings objectivity to the evaluation of EEG signals.
Research Interests: Information Systems, Algorithms, Time Series, Independent Component Analysis, Electroencephalography, and 12 moreTurkey, Neural Network, Time series analysis, Visual Analysis, Humans, Medical systems, Public health systems and services research, Clinical Study, Time Domain, Artificial Neural Network, Clinical Diagnosis, and Computational Techniques
Brain is one of the most critical organs of the body. Synchronous neuronal discharges generate rhythmic potential fluctuations, which can be recorded from the scalp through electroencephalography. The electroencephalogram (EEG) can be... more
Brain is one of the most critical organs of the body. Synchronous neuronal discharges generate rhythmic potential fluctuations, which can be recorded from the scalp through electroencephalography. The electroencephalogram (EEG) can be roughly defined as the mean electrical activity measured at different sites of the head. EEG patterns correlated with normal functions and diseases of the central nervous system. In this study, EEG signals were analyzed by using autoregressive (parametric) and Welch (non-parametric) spectral estimation methods. The parameters of autoregressive (AR) method were estimated by using Yule-Walker, covariance and modified covariance methods. EEG spectra were then used to compare the applied estimation methods in terms of their frequency resolution and the effects in determination of spectral components. The variations in the shape of the EEG power spectra were examined in order to epileptic seizures detection. Performance of the proposed methods was evaluated by means of power spectral densities (PSDs). Graphical results comparing the performance of the proposed methods with that of Welch technique were given. The results demonstrate consistently superior performance of the covariance methods over Yule-Walker AR and Welch methods.
Research Interests:
Research Interests:
In this study, EEG signals were analyzed using autoregressive (AR) method. Parameters in AR method were realized by using maximum likelihood estimation (MLE). Results were compared with fast Fourier transform (FFT) method. It is observed... more
In this study, EEG signals were analyzed using autoregressive (AR) method. Parameters in AR method were realized by using maximum likelihood estimation (MLE). Results were compared with fast Fourier transform (FFT) method. It is observed that AR method gives better results in the analysis of EEG signals. On the other hand, the results have also showed that AR method can also be used for some other researches and diagnosis of diseases.