Aydin Akan | Izmir University of Economics (original) (raw)

Papers by Aydin Akan

2017 Medical Technologies National Congress (TIPTEKNO), 2017

Electrogastrography (EGG) is an experimental non-invasive method that reflects the myoelectrical ... more Electrogastrography (EGG) is an experimental non-invasive method that reflects the myoelectrical activity of the diabetic gastroparesis (D-GP) and healthy subjects gastric system. In clinical world, endoscopy and delayed gastric emptying diagnosis test are using for understand the D-GP patient's condition which are invasive, quite expensive and uncomfortable. Therefore our aim is to evaluate the Electrogastrography (EGG) features to discriminate the healthy subjects from patients with D-GP in real clinic. Total 25 patients D-GP and twenty 25 healthy subjects (HS) were included in this study. The recordings EGG parameters dominant frequency (DF) were analyzed and compared. The results we obtained from analysis of EGG signals proved that pre-fed (p= 0.048) and post-fed (p= 0.003) DF values were statistically significant between the D-GP and HS groups. This study proved that it is possible to distinguish D-GP patients from healthy subject's with a high accuracy and a great succ...

2006 First International Conference on Communications and Networking in China, 2006

ABSTRACT In the actual orthogonal frequency division multiplexing (OFDM) systems since guard subc... more ABSTRACT In the actual orthogonal frequency division multiplexing (OFDM) systems since guard subcarriers are not used for transmission, some conventional channel estimators are not applicable. This paper, based on the criteria of least square (LS), proposes a novel channel estimation method for OFDM systems with guard subcarriers. The discrete Fourier transform (DFT)-based channel estimator can cause the aliasing error and high-frequency distortion when there exist guard subcarriers, but our proposed method can mitigate this problem and attain the better estimation performance with fewer pilots. Furthermore, compared with the conventional LS estimator, the proposed method has close performance but lower complexity and can be realized in the actual OFDM systems. Analyses and simulations demonstrate the effectiveness of the proposed approach.

Epilepsy is a neurological disorder that affects many people all around the world, and its early ... more Epilepsy is a neurological disorder that affects many people all around the world, and its early detection is a topic of research widely studied in signal processing community. In this paper, a new technique that was introduced to solve problems of fluid dynamics called Dynamic Mode Decomposition (DMD), is used to classify seizure and non-seizure epileptic EEG signals. The DMD decomposes a given signal into the intrinsic oscillations called modes which are used to define a DMD spectrum. In the proposed approach, the DMD spectrum is obtained by applying either multi-channel or single-channel based DMD technique. Then, subband and total power features extracted from the DMD spectrum and various classifiers are utilized to classify seizure and non-seizure epileptic EEG segments. Outstanding classification results are achieved by both the single-channel based (96.7%), and the multi-channel based (96%) DMD approaches.

EURASIP Journal on Wireless Communications and Networking, 2007

This paper introduces a novel algorithm to excise single and multicomponent chirp-like interferen... more This paper introduces a novel algorithm to excise single and multicomponent chirp-like interferences in direct sequence spread spectrum (DSSS) communications. The excision algorithm consists of two stages: adaptive signal decomposition stage and directional element detection stage based on the Hough-Radon transform (HRT). Initially, the received spread spectrum signal is decomposed into its time-frequency (TF) functions using an adaptive signal decomposition algorithm, and the resulting TF functions are mapped onto the TF plane. We then use a line detection algorithm based on the HRT that operates on the image of the TF plane and detects energy varying directional elements that satisfy a parametric constraint. Interference is modeled by reconstructing the corresponding TF functions detected by the HRT, and subtracted from the received signal. The proposed technique has two main advantages: (i) it localizes the interferences on the TF plane with no cross-terms, thus facilitating simple filtering techniques based on thresholding of the TF functions, and is an efficient way to excise the interference; (ii) it can be used for the detection of any directional interferences that can be parameterized. Simulation results with synthetic models have shown successful performance with linear and quadratic chirp interferences for single and multicomponent interference cases. The proposed method excises the interference even under very low SNR conditions of −10 dB, and the technique could be easily extended to any interferences that could be represented by a parametric equation in the TF plane.

2018 Medical Technologies National Congress (TIPTEKNO), 2018

This study investigates improved properties of empirical mode decomposition (EMD) for emotion rec... more This study investigates improved properties of empirical mode decomposition (EMD) for emotion recognition by using electroencephalogram (EEG) signals. The emotion recognition from EEG signals is a difficult study by the reason of nonstationary behavior of the signals. These signals are affected from complicated neural activity of brain. To analyze EEG signals, advanced signal processing techniques are required. In our study, data are collected from one channeled BIOPAC lab system. EEG signals were obtained from visual evoked potentials of 13 female and 13 male volunteers for 12 pleasant and 12 unpleasant pictures. To analyze nonlinear and nonstationary characteristics of EEG signals, an EMD-based method is proposed for emotion recognition. Various time and frequency domain techniques such as power spectral density (PSD), and higher order statistics (HOS) are used to analyze the IMFs extracted by EMD. Support vector machine (SVM), Linear discriminant analysis (LDA), and Naive Bayes classifiers are utilized for the classification of features extracted from the IMFs, and their performances are compared.

2019 Medical Technologies Congress (TIPTEKNO), 2019

Emotion is an important topic in different fields such as biomedical engineering, psychology, neu... more Emotion is an important topic in different fields such as biomedical engineering, psychology, neuroscience and health. Emotion recognition could be useful for diagnosis of brain and psychological disorders. In recent years, deep learning has progressed much in the field of image classification. In this study, we proposed a Convolutional Neural Network (CNN) based LeNet architecture for facial expression recognition. First of all, we merged 3 datasets (JAFFE, KDEF and our custom dataset). Then we trained our LeNet architecture for emotion states classification. In this study, we achieved accuracy of 96.43% and validation accuracy of 91.81% for classification of 7 different emotions through facial expressions.

International Journal of Neural Systems, 2021

Epilepsy is a persistent and recurring neurological condition in a community of brain neurons tha... more Epilepsy is a persistent and recurring neurological condition in a community of brain neurons that results from sudden and abnormal electrical discharges. This paper introduces a new form of assessment and interpretation of the changes in electroencephalography (EEG) recordings from different brain regions in epilepsy disorders based on graph analysis and statistical rescale range analysis. In this study, two different states of epilepsy EEG data (preictal and ictal phases), obtained from 17 subjects (18 channels each), were analyzed by a new method called state transfer network (STN). The analysis performed by STN yields a network metric called motifs, which are averaged over all channels and subjects in terms of their persistence level in the network. The results showed an increase of overall motif persistence during the ictal over the preictal phase, reflecting the synchronization increase during the seizure phase (ictal). An evaluation of intermotif cross-correlation indicated a...

Biomedical Engineering / Biomedizinische Technik, 2020

The emotional state of people plays a key role in physiological and behavioral human interaction.... more The emotional state of people plays a key role in physiological and behavioral human interaction. Emotional state analysis entails many fields such as neuroscience, cognitive sciences, and biomedical engineering because the parameters of interest contain the complex neuronal activities of the brain. Electroencephalogram (EEG) signals are processed to communicate brain signals with external systems and make predictions over emotional states. This paper proposes a novel method for emotion recognition based on deep convolutional neural networks (CNNs) that are used to classify Valence, Arousal, Dominance, and Liking emotional states. Hence, a novel approach is proposed for emotion recognition with time series of multi-channel EEG signals from a Database for Emotion Analysis and Using Physiological Signals (DEAP). We propose a new approach to emotional state estimation utilizing CNN-based classification of multi-spectral topology images obtained from EEG signals. In contrast to most of ...

2020 Medical Technologies Congress (TIPTEKNO), 2020

Bu çalışmada derin öğrenme yöntemi kullanılarak yüz görüntülerinden duygu durum tespiti yapılması... more Bu çalışmada derin öğrenme yöntemi kullanılarak yüz görüntülerinden duygu durum tespiti yapılması hedeflenmiştir. Etik kurul onayı alınmış çalışmada, 7 farklı yüz ifadesini (mutlu, üzgün, şaşırmış, kızgın, iğrenmiş, korkmuş ve tarafsız) taklit ederken 20 adedi erkek ve 20 adedi kadın katılımcıdan alınan videolar kullanılarak özel veri seti oluşturulmuştur. Elde edilen videolar, önce resim karelerine ayrılmış sonrasında resim karelerinden Haar kütüphanesi kullanılarak yüz resimleri bölütlenmiştir. Resim ön işlemime sonrasında elde edilen özel veri setinin boyutu 25 bin resimden fazladır. LeNet ağının yapısından faydalanılarak önerilen evrişimsel sinir ağı (ESA) mimarisi bu özel veri seti ile eğitilmiştir. Önerilen ESA mimarisi deney sonuçlarına göre, eğitim kaybı 0,0115, eğitim doğruluğu %99,62 bulunmuş, doğrulama kaybı 0,0109 ve doğrulama doğruluğu %99,71 olarak bulunmuştur.

The purpose of this study was to analyze the electromyography (EMG) signals of the Quadratus Lumb... more The purpose of this study was to analyze the electromyography (EMG) signals of the Quadratus Lumborum (QL) muscle activity on leg length discrepancy (LLD) and pelvic asymmetry. So we investigated whether pelvic asymmetry might cause injuries in lumbar spine and lower extremity. This was a randomized control experiment, total 50 (25 males and 25 females) datas were analyzed. All participants were right handed. Iliac crest levels were assessed by manually and LLD measurement was used with tape. EMG signals of the QL muscle were taken in the resting position without any activity intentionally in the prone position. Analysis of the data revealed that the QL muscles activity were higher at the pelvic elevation on the right side than on the left side. While there was a shortness in the lower extremity 27% of the cases on the right condition but it was statistically determined that 23% of the left side was short. At the same time, 100% of the cases in the lower extremity on the right side ...

Signal, Image and Video Processing, 2019

The application of EEG-based emotional states is one of the most vital phases in the context of n... more The application of EEG-based emotional states is one of the most vital phases in the context of neural response decoding. Emotional response mostly appears in the presence of visual, auditory, tactile, and gustatory arousals. In our work, we use visual stimuli to evaluate the emotional feedback. One of the best performing methods in emotion estimation applications is the common spatial patterns (CSP). We implement CSP method in addition to the conventional Welch power spectral density-based analysis. Experimental results and topographies on the collected EEG data show that the CSP spatial filtering method implies the relationship between EEG bands, EEG channels, neural efficiency and emotional stimuli types.

Electrica, 2018

Chronic kidney disease is a rising health problem and involves conditions that decrease the effic... more Chronic kidney disease is a rising health problem and involves conditions that decrease the efficiency of renal functions and that damage the kidneys. Chronic kidney disease may be detected with several classification techniques, and these have been classified using various features and classifier combinations. In this study, we applied seven different classifiers (Naïve Bayes, HoeffdingTree, RandomTree, REPTree, Random Subspaces, Adaboost, and IBk) for the diagnosis of chronic kidney disease. The classification performances are evaluated with five different performance metrics, i.e., accuracy, kappa, mean absolute error (MAE), root mean square error (RMSE), and F measures. Considering the classification performance analyses of these methods, six reduced features provide a better and more rapid classification performance. Seven individual classifiers are applied to the six features and the best results are obtained using individual random tree and IBk classifiers.

Journal of the Franklin Institute

2014 IEEE International Conference on Imaging Systems and Techniques (IST) Proceedings, 2014

BioMedical Engineering OnLine, 2014

Background: After the release of compressed sensing (CS) theory, reconstruction algorithms from s... more Background: After the release of compressed sensing (CS) theory, reconstruction algorithms from sparse and incomplete data have shown great improvements in diminishing artifacts of missing data. Following this progress, both local and non-local regularization induced iterative reconstructions have been actively used in limited view angle imaging problems. Methods: In this study, a 3D iterative image reconstruction method (ART + TV) NLM was introduced by combining local total variation (TV) with non-local means (NLM) filter. In the first step, TV minimization was applied to the image obtained by algebraic reconstruction technique (ART) for background noise removal with preserving edges. In the second step, NLM is used in order to suppress the out of focus slice blur which is the most existent image artifact in tomosynthesis imaging. NLM exploits the similar structures to increase the smoothness in the image reconstructed by ART + TV. Results: A tomosynthesis system and a 3D phantom were designed to perform simulations to show the superior performance of our proposed (ART + TV) NLM over ART and widely used ART + TV methods. Visual inspections show a significant improvement in image quality compared to ART and ART + TV. Conclusions: RMSE, Structure SIMilarity (SSIM) value and SNR of a specific layer of interest (LOI) showed that by proper selection of NLM parameters, significant improvements can be achieved in terms of convergence rate and image quality.

2014 IEEE International Conference on Imaging Systems and Techniques (IST) Proceedings, 2014

In limited angle tomographic imaging, artifacts arise due to missing data during the acquisition.... more In limited angle tomographic imaging, artifacts arise due to missing data during the acquisition. To deal with this problem, iterative image reconstruction algorithms have been developed. In iterative reconstruction algorithms, the initial image guess which is often neglected is very crucial and plays an important role as it directly affects the convergence rate. This paper presents a comparison of three different initial images (zeroes image, average image, filtered back projected image) to observe their contribution to the convergence rate. Computer simulations are performed by using algebraic reconstruction technique with total variation, (ART + TV).Root means squared error (RMSE) of a specific layer of interest (LOI) of a 3D phantom is used to compare the impact of appropriate prior image selection. For a better visual observation, structure similarity (SSIM) parameters are also compared.

BMC Medical Informatics and Decision Making, 2014

Background: Choosing the correct ventilator settings for the treatment of patients with respirato... more Background: Choosing the correct ventilator settings for the treatment of patients with respiratory tract disease is quite an important issue. Since the task of specifying the parameters of ventilation equipment is entirely carried out by a physician, physician's knowledge and experience in the selection of these settings has a direct effect on the accuracy of his/her decisions. Nowadays, decision support systems have been used for these kinds of operations to eliminate errors. Our goal is to minimize errors in ventilation therapy and prevent deaths caused by incorrect configuration of ventilation devices. The proposed system is designed to assist less experienced physicians working in the facilities without having lung mechanics like cottage hospitals. Methods: This article describes a decision support system proposing the ventilator settings required to be applied in the treatment according to the patients' physiological information. The proposed model has been designed to minimize the possibility of making a mistake and to encourage more efficient use of time in support of the decision making process while the physicians make critical decisions about the patient. Artificial Neural Network (ANN) is implemented in order to calculate frequency, tidal volume, FiO 2 outputs, and this classification model has been used for estimation of pressure support / volume support outputs. For the obtainment of the highest performance in both models, different configurations have been tried. Various tests have been realized for training methods, and a number of hidden layers mostly affect factors regarding the performance of ANNs. Results: The physiological information of 158 respiratory patients over the age of 60 and were treated in three different hospitals between the years 2010 and 2012 has been used in the training and testing of the system. The diagnosed disease, core body temperature, pulse, arterial systolic pressure , diastolic blood pressure, PEEP, PSO 2 , pH, pCO 2 , bicarbonate data as well as the frequency, tidal volume, FiO 2 , and pressure support / volume support values suitable for use in the ventilator device have been recommended to the physicians with an accuracy of 98,44%. Performed experiments show that sequential order weight/bias training was found to be the most ideal ANN learning algorithm for regression model and Bayesian regulation backpropagation was found to be the most ideal ANN learning algorithm for classification models. Conclusions: This article aims at making independent of the choice of parameters from physicians in the ventilator treatment of respiratory tract patients with proposed decision support system. The rate of accuracy in prediction of systems increases with the use of data of more patients in training. Therefore, non-physician operators can use systems in determination of ventilator settings in case of emergencies.

2017 Medical Technologies National Congress (TIPTEKNO), 2017

Electrogastrography (EGG) is an experimental non-invasive method that reflects the myoelectrical ... more Electrogastrography (EGG) is an experimental non-invasive method that reflects the myoelectrical activity of the diabetic gastroparesis (D-GP) and healthy subjects gastric system. In clinical world, endoscopy and delayed gastric emptying diagnosis test are using for understand the D-GP patient's condition which are invasive, quite expensive and uncomfortable. Therefore our aim is to evaluate the Electrogastrography (EGG) features to discriminate the healthy subjects from patients with D-GP in real clinic. Total 25 patients D-GP and twenty 25 healthy subjects (HS) were included in this study. The recordings EGG parameters dominant frequency (DF) were analyzed and compared. The results we obtained from analysis of EGG signals proved that pre-fed (p= 0.048) and post-fed (p= 0.003) DF values were statistically significant between the D-GP and HS groups. This study proved that it is possible to distinguish D-GP patients from healthy subject's with a high accuracy and a great succ...

2006 First International Conference on Communications and Networking in China, 2006

ABSTRACT In the actual orthogonal frequency division multiplexing (OFDM) systems since guard subc... more ABSTRACT In the actual orthogonal frequency division multiplexing (OFDM) systems since guard subcarriers are not used for transmission, some conventional channel estimators are not applicable. This paper, based on the criteria of least square (LS), proposes a novel channel estimation method for OFDM systems with guard subcarriers. The discrete Fourier transform (DFT)-based channel estimator can cause the aliasing error and high-frequency distortion when there exist guard subcarriers, but our proposed method can mitigate this problem and attain the better estimation performance with fewer pilots. Furthermore, compared with the conventional LS estimator, the proposed method has close performance but lower complexity and can be realized in the actual OFDM systems. Analyses and simulations demonstrate the effectiveness of the proposed approach.

Epilepsy is a neurological disorder that affects many people all around the world, and its early ... more Epilepsy is a neurological disorder that affects many people all around the world, and its early detection is a topic of research widely studied in signal processing community. In this paper, a new technique that was introduced to solve problems of fluid dynamics called Dynamic Mode Decomposition (DMD), is used to classify seizure and non-seizure epileptic EEG signals. The DMD decomposes a given signal into the intrinsic oscillations called modes which are used to define a DMD spectrum. In the proposed approach, the DMD spectrum is obtained by applying either multi-channel or single-channel based DMD technique. Then, subband and total power features extracted from the DMD spectrum and various classifiers are utilized to classify seizure and non-seizure epileptic EEG segments. Outstanding classification results are achieved by both the single-channel based (96.7%), and the multi-channel based (96%) DMD approaches.

EURASIP Journal on Wireless Communications and Networking, 2007

This paper introduces a novel algorithm to excise single and multicomponent chirp-like interferen... more This paper introduces a novel algorithm to excise single and multicomponent chirp-like interferences in direct sequence spread spectrum (DSSS) communications. The excision algorithm consists of two stages: adaptive signal decomposition stage and directional element detection stage based on the Hough-Radon transform (HRT). Initially, the received spread spectrum signal is decomposed into its time-frequency (TF) functions using an adaptive signal decomposition algorithm, and the resulting TF functions are mapped onto the TF plane. We then use a line detection algorithm based on the HRT that operates on the image of the TF plane and detects energy varying directional elements that satisfy a parametric constraint. Interference is modeled by reconstructing the corresponding TF functions detected by the HRT, and subtracted from the received signal. The proposed technique has two main advantages: (i) it localizes the interferences on the TF plane with no cross-terms, thus facilitating simple filtering techniques based on thresholding of the TF functions, and is an efficient way to excise the interference; (ii) it can be used for the detection of any directional interferences that can be parameterized. Simulation results with synthetic models have shown successful performance with linear and quadratic chirp interferences for single and multicomponent interference cases. The proposed method excises the interference even under very low SNR conditions of −10 dB, and the technique could be easily extended to any interferences that could be represented by a parametric equation in the TF plane.

2018 Medical Technologies National Congress (TIPTEKNO), 2018

This study investigates improved properties of empirical mode decomposition (EMD) for emotion rec... more This study investigates improved properties of empirical mode decomposition (EMD) for emotion recognition by using electroencephalogram (EEG) signals. The emotion recognition from EEG signals is a difficult study by the reason of nonstationary behavior of the signals. These signals are affected from complicated neural activity of brain. To analyze EEG signals, advanced signal processing techniques are required. In our study, data are collected from one channeled BIOPAC lab system. EEG signals were obtained from visual evoked potentials of 13 female and 13 male volunteers for 12 pleasant and 12 unpleasant pictures. To analyze nonlinear and nonstationary characteristics of EEG signals, an EMD-based method is proposed for emotion recognition. Various time and frequency domain techniques such as power spectral density (PSD), and higher order statistics (HOS) are used to analyze the IMFs extracted by EMD. Support vector machine (SVM), Linear discriminant analysis (LDA), and Naive Bayes classifiers are utilized for the classification of features extracted from the IMFs, and their performances are compared.

2019 Medical Technologies Congress (TIPTEKNO), 2019

Emotion is an important topic in different fields such as biomedical engineering, psychology, neu... more Emotion is an important topic in different fields such as biomedical engineering, psychology, neuroscience and health. Emotion recognition could be useful for diagnosis of brain and psychological disorders. In recent years, deep learning has progressed much in the field of image classification. In this study, we proposed a Convolutional Neural Network (CNN) based LeNet architecture for facial expression recognition. First of all, we merged 3 datasets (JAFFE, KDEF and our custom dataset). Then we trained our LeNet architecture for emotion states classification. In this study, we achieved accuracy of 96.43% and validation accuracy of 91.81% for classification of 7 different emotions through facial expressions.

International Journal of Neural Systems, 2021

Epilepsy is a persistent and recurring neurological condition in a community of brain neurons tha... more Epilepsy is a persistent and recurring neurological condition in a community of brain neurons that results from sudden and abnormal electrical discharges. This paper introduces a new form of assessment and interpretation of the changes in electroencephalography (EEG) recordings from different brain regions in epilepsy disorders based on graph analysis and statistical rescale range analysis. In this study, two different states of epilepsy EEG data (preictal and ictal phases), obtained from 17 subjects (18 channels each), were analyzed by a new method called state transfer network (STN). The analysis performed by STN yields a network metric called motifs, which are averaged over all channels and subjects in terms of their persistence level in the network. The results showed an increase of overall motif persistence during the ictal over the preictal phase, reflecting the synchronization increase during the seizure phase (ictal). An evaluation of intermotif cross-correlation indicated a...

Biomedical Engineering / Biomedizinische Technik, 2020

The emotional state of people plays a key role in physiological and behavioral human interaction.... more The emotional state of people plays a key role in physiological and behavioral human interaction. Emotional state analysis entails many fields such as neuroscience, cognitive sciences, and biomedical engineering because the parameters of interest contain the complex neuronal activities of the brain. Electroencephalogram (EEG) signals are processed to communicate brain signals with external systems and make predictions over emotional states. This paper proposes a novel method for emotion recognition based on deep convolutional neural networks (CNNs) that are used to classify Valence, Arousal, Dominance, and Liking emotional states. Hence, a novel approach is proposed for emotion recognition with time series of multi-channel EEG signals from a Database for Emotion Analysis and Using Physiological Signals (DEAP). We propose a new approach to emotional state estimation utilizing CNN-based classification of multi-spectral topology images obtained from EEG signals. In contrast to most of ...

2020 Medical Technologies Congress (TIPTEKNO), 2020

Bu çalışmada derin öğrenme yöntemi kullanılarak yüz görüntülerinden duygu durum tespiti yapılması... more Bu çalışmada derin öğrenme yöntemi kullanılarak yüz görüntülerinden duygu durum tespiti yapılması hedeflenmiştir. Etik kurul onayı alınmış çalışmada, 7 farklı yüz ifadesini (mutlu, üzgün, şaşırmış, kızgın, iğrenmiş, korkmuş ve tarafsız) taklit ederken 20 adedi erkek ve 20 adedi kadın katılımcıdan alınan videolar kullanılarak özel veri seti oluşturulmuştur. Elde edilen videolar, önce resim karelerine ayrılmış sonrasında resim karelerinden Haar kütüphanesi kullanılarak yüz resimleri bölütlenmiştir. Resim ön işlemime sonrasında elde edilen özel veri setinin boyutu 25 bin resimden fazladır. LeNet ağının yapısından faydalanılarak önerilen evrişimsel sinir ağı (ESA) mimarisi bu özel veri seti ile eğitilmiştir. Önerilen ESA mimarisi deney sonuçlarına göre, eğitim kaybı 0,0115, eğitim doğruluğu %99,62 bulunmuş, doğrulama kaybı 0,0109 ve doğrulama doğruluğu %99,71 olarak bulunmuştur.

The purpose of this study was to analyze the electromyography (EMG) signals of the Quadratus Lumb... more The purpose of this study was to analyze the electromyography (EMG) signals of the Quadratus Lumborum (QL) muscle activity on leg length discrepancy (LLD) and pelvic asymmetry. So we investigated whether pelvic asymmetry might cause injuries in lumbar spine and lower extremity. This was a randomized control experiment, total 50 (25 males and 25 females) datas were analyzed. All participants were right handed. Iliac crest levels were assessed by manually and LLD measurement was used with tape. EMG signals of the QL muscle were taken in the resting position without any activity intentionally in the prone position. Analysis of the data revealed that the QL muscles activity were higher at the pelvic elevation on the right side than on the left side. While there was a shortness in the lower extremity 27% of the cases on the right condition but it was statistically determined that 23% of the left side was short. At the same time, 100% of the cases in the lower extremity on the right side ...

Signal, Image and Video Processing, 2019

The application of EEG-based emotional states is one of the most vital phases in the context of n... more The application of EEG-based emotional states is one of the most vital phases in the context of neural response decoding. Emotional response mostly appears in the presence of visual, auditory, tactile, and gustatory arousals. In our work, we use visual stimuli to evaluate the emotional feedback. One of the best performing methods in emotion estimation applications is the common spatial patterns (CSP). We implement CSP method in addition to the conventional Welch power spectral density-based analysis. Experimental results and topographies on the collected EEG data show that the CSP spatial filtering method implies the relationship between EEG bands, EEG channels, neural efficiency and emotional stimuli types.

Electrica, 2018

Chronic kidney disease is a rising health problem and involves conditions that decrease the effic... more Chronic kidney disease is a rising health problem and involves conditions that decrease the efficiency of renal functions and that damage the kidneys. Chronic kidney disease may be detected with several classification techniques, and these have been classified using various features and classifier combinations. In this study, we applied seven different classifiers (Naïve Bayes, HoeffdingTree, RandomTree, REPTree, Random Subspaces, Adaboost, and IBk) for the diagnosis of chronic kidney disease. The classification performances are evaluated with five different performance metrics, i.e., accuracy, kappa, mean absolute error (MAE), root mean square error (RMSE), and F measures. Considering the classification performance analyses of these methods, six reduced features provide a better and more rapid classification performance. Seven individual classifiers are applied to the six features and the best results are obtained using individual random tree and IBk classifiers.

Journal of the Franklin Institute

2014 IEEE International Conference on Imaging Systems and Techniques (IST) Proceedings, 2014

BioMedical Engineering OnLine, 2014

Background: After the release of compressed sensing (CS) theory, reconstruction algorithms from s... more Background: After the release of compressed sensing (CS) theory, reconstruction algorithms from sparse and incomplete data have shown great improvements in diminishing artifacts of missing data. Following this progress, both local and non-local regularization induced iterative reconstructions have been actively used in limited view angle imaging problems. Methods: In this study, a 3D iterative image reconstruction method (ART + TV) NLM was introduced by combining local total variation (TV) with non-local means (NLM) filter. In the first step, TV minimization was applied to the image obtained by algebraic reconstruction technique (ART) for background noise removal with preserving edges. In the second step, NLM is used in order to suppress the out of focus slice blur which is the most existent image artifact in tomosynthesis imaging. NLM exploits the similar structures to increase the smoothness in the image reconstructed by ART + TV. Results: A tomosynthesis system and a 3D phantom were designed to perform simulations to show the superior performance of our proposed (ART + TV) NLM over ART and widely used ART + TV methods. Visual inspections show a significant improvement in image quality compared to ART and ART + TV. Conclusions: RMSE, Structure SIMilarity (SSIM) value and SNR of a specific layer of interest (LOI) showed that by proper selection of NLM parameters, significant improvements can be achieved in terms of convergence rate and image quality.

2014 IEEE International Conference on Imaging Systems and Techniques (IST) Proceedings, 2014

In limited angle tomographic imaging, artifacts arise due to missing data during the acquisition.... more In limited angle tomographic imaging, artifacts arise due to missing data during the acquisition. To deal with this problem, iterative image reconstruction algorithms have been developed. In iterative reconstruction algorithms, the initial image guess which is often neglected is very crucial and plays an important role as it directly affects the convergence rate. This paper presents a comparison of three different initial images (zeroes image, average image, filtered back projected image) to observe their contribution to the convergence rate. Computer simulations are performed by using algebraic reconstruction technique with total variation, (ART + TV).Root means squared error (RMSE) of a specific layer of interest (LOI) of a 3D phantom is used to compare the impact of appropriate prior image selection. For a better visual observation, structure similarity (SSIM) parameters are also compared.

BMC Medical Informatics and Decision Making, 2014

Background: Choosing the correct ventilator settings for the treatment of patients with respirato... more Background: Choosing the correct ventilator settings for the treatment of patients with respiratory tract disease is quite an important issue. Since the task of specifying the parameters of ventilation equipment is entirely carried out by a physician, physician's knowledge and experience in the selection of these settings has a direct effect on the accuracy of his/her decisions. Nowadays, decision support systems have been used for these kinds of operations to eliminate errors. Our goal is to minimize errors in ventilation therapy and prevent deaths caused by incorrect configuration of ventilation devices. The proposed system is designed to assist less experienced physicians working in the facilities without having lung mechanics like cottage hospitals. Methods: This article describes a decision support system proposing the ventilator settings required to be applied in the treatment according to the patients' physiological information. The proposed model has been designed to minimize the possibility of making a mistake and to encourage more efficient use of time in support of the decision making process while the physicians make critical decisions about the patient. Artificial Neural Network (ANN) is implemented in order to calculate frequency, tidal volume, FiO 2 outputs, and this classification model has been used for estimation of pressure support / volume support outputs. For the obtainment of the highest performance in both models, different configurations have been tried. Various tests have been realized for training methods, and a number of hidden layers mostly affect factors regarding the performance of ANNs. Results: The physiological information of 158 respiratory patients over the age of 60 and were treated in three different hospitals between the years 2010 and 2012 has been used in the training and testing of the system. The diagnosed disease, core body temperature, pulse, arterial systolic pressure , diastolic blood pressure, PEEP, PSO 2 , pH, pCO 2 , bicarbonate data as well as the frequency, tidal volume, FiO 2 , and pressure support / volume support values suitable for use in the ventilator device have been recommended to the physicians with an accuracy of 98,44%. Performed experiments show that sequential order weight/bias training was found to be the most ideal ANN learning algorithm for regression model and Bayesian regulation backpropagation was found to be the most ideal ANN learning algorithm for classification models. Conclusions: This article aims at making independent of the choice of parameters from physicians in the ventilator treatment of respiratory tract patients with proposed decision support system. The rate of accuracy in prediction of systems increases with the use of data of more patients in training. Therefore, non-physician operators can use systems in determination of ventilator settings in case of emergencies.