Mühendislik Fakültesi / Faculty of Engineering

Permanent URI for this communityhttps://hdl.handle.net/11413/11

Browse

Now showing 1 - 20 of 27

Embargo
A decision support system to determine optimal ventilator settings
(Biomed Central Ltd, 236 Grays Inn Rd, Floor 6, London Wc1X 8Hl, England, 2014) Akkur, Erkan; Akan, Aydın; Yarman, B. Sıddık; AKBULUT, FATMA PATLAR
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, PSO2, 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.
Metadata only
A smart wearable system for short-term cardiovascular risk assessment with emotional dynamics
(Elsevier Sci Ltd, The Boulevard, Langford Lane, Kidlington, Oxford Ox5 1Gb, Oxon, England, 2018-11) Akan, Aydın; AKBULUT, FATMA PATLAR; 2918
Recent innovative treatment and diagnostic methods developed for heart and circulatory system disorders do not provide the desired results as they are not supported by long-term patient follow-up. Continuous medical support in a clinic or hospital is often not feasible in elderly or aging populations; yet, collecting medical data is still required to maintain a high-quality of life. In this study, a smart wearable system design called Cardiovascular Disease Monitoring (CVDiMo), which provides continuous medical monitoring and creates a health profile with the risk of disease over time. Systematic tests were performed with analysis of six different biosignals from two different test groups with 30 participants. In addition to examining the biosignals of patients, using the physical activity results and stress levels deduced from the emotional state analysis achieved a higher performance in risk estimation. In our experiments, the highest accuracy of determining the short-term health status was obtained as 96%.
Metadata only
Analysis of brain connectivity changes after propofol injection by generalized partial directed coherence
(Academic Press inc Elsevier Science, 525 B St, Ste 1900, San Diego, Ca 92101-4495 USA, 2014) Akan, Aydın; Özkan Seyhan, Tülay; GÜRKAN, GÜRAY; 113297; 2918; 25235
In this paper we present a method for the analysis of multichannel EEG by using Generalized Partial Directed Coherence (gPDC) to extract cortical connectivity changes under anesthesia. 15 channel EEG data were recorded from female subjects undergoing general anesthesia for gynecological surgery. Multivariate Autoregressive (MAR) modeling was applied to multichannel, bipolar EEG segments of awake and anesthetized states. gPDCs were calculated using the derived MAR model and averaged through EEG alpha frequency band (8-14 Hz) and through a number of data segments. The gPDC calculation was performed for three different sets of bipolar EEG channel pairs each of which mainly represent a specific scalp area. To derive consistency levels of gPDC values, surrogate analysis is also performed. Using paired t-test for 12 patients, we extracted significant gPDC changes between. awake and anesthetized stages for each set. Analysis revealed that during transition from awake to anesthetized stage, gPDCs of central. to parietal directions were suppressed whereas gPDCs of parietal to central directions were increased. The results indicate that the proposed gPDC analysis method can be used to track the changes in brain connectivity and hence to estimate the depth of anesthesia. (C) 2013 Elsevier Inc. All rights reserved.
Metadata only
Analysis of linear lung models based on state-space models
(Elsevier Ireland Ltd., 2020-01) Saatçi, Ertuğrul; Akan, Aydın; SAATÇI, ESRA
Background and Objectives: Linear parametric respiratory system models have been used in the model-based analysis of the respiratory system. Although there are studies exploring the physiological correctness and fitting accuracy of the models, they are not analysed in terms of interaction between parameters and dynamics of the model. In this study we propose to use state-space modelling to yield the time-varying nature of the system incorporated by the parameters. Methods: We tested controllability, observability and stability characteristics of the equation of motion, 2-comp. parallel, 2-comp. series, viscoelastic, 6-element and mead models while using the parameters given in the literature. In the sensitivity analysis we proposed to use dual Desensitized Linear Kalman Filter (DKF) and Extended Kalman Filter (EKF) method. In this method, state error covariance revealed the parameter sensitivities for each model. Results: Results showed that all models, except 2-comp. parallel and mead models, are both controllable and observable models. On the other hand all models, except mead model, are stable models. Regarding to the sensitivity analysis, dual DKF - EKF method estimated states of the models successfully with a low estimation error. Sensitivity analysis results showed that airway parameters have higher effects on the state estimation than the other parameters have. Conclusion: We proved that state-space evaluation of the previously proposed parametric models of the respiratory system led us to quantitative and qualitative assessments of the respiratory models. Moreover parameter values found in the literature have different effects on the models. (C) 2019 Elsevier B.V. All rights reserved.
Metadata only
Application of Stockwell Coherence To Prediction Of Alertness Under Anaesthesia
(Brno Univ Technology Vut Press, Purkynova 118, Brno 61200, Czech Republic, 2010) Akan, Aydın; Demiralp, Tamer; GÜRKAN, GÜRAY; TR113297; TR2918; TR6916
In this paper, we represent an application of Stockwell Coherence to scalp EEG signals under anesthesia. By the analysis of overlapping, stationary data segments, we obtained the time-varying Stockwell coherence, which reveals the time evolution of coherence changes between any selected channel pair. After the injection and release of the anesthetic agent, time-varying Stockwell coherence analyses demonstrate similar characteristics for different patients.
Open Access
Application of stockwell coherence to prediction of alertness under anaesthesia
(2010) Akan, Aydın; Demiralp, Tamer; GÜRKAN, GÜRAY; 113297; 2918
In this paper, we represent an application of Stockwell Coherence to scalp EEG signals under anesthesia. By the analysis of overlapping, stationary data segments, we obtained the time-varying Stockwell coherence, which reveals the time evolution of coherence changes between any selected channel pair. After the injection and release of the anesthetic agent, time-varying Stockwell coherence analyses demonstrate similar characteristics for different patients.
Metadata only
Bandpass sampling of multiband signals by using geometric approach
(IEEE, 345 E 47th St, New York, Ny 10017 USA, 2017) Saatçı, Ertuğrul; Akan, Aydın; SAATÇI, ESRA; 112197; 10488; 2918
This paper presents a simple and fast approach to f nd a minimum sampling frequency for multi-band signals. Instead of neighbor and boundary conditions, constraints on the sampling frequency were derived by using the geometric approach. Reformulation of the minimum sampling determination problem by using geometric approach enables to represent the problem as a basic inequality problem. Recursive algorithm was proposed to solve the constraints on the minimum sampling frequency. The proposed method was verif ed through numerical simulations in terms of the minimum sampling frequency and the computational eff ciency by using 2-band and 3-band signals. Although the results illustrated the valid minimum sampling frequencies for the multi-band signals, due to the increase in the number of iterations, optimization approaches were recommended in the solution of the constraints on the minimum sampling frequency.
Metadata only
Connectivity Analysis of EEG Signals Under Propofol Anesthesia with Time varying Generalized Partial Directed Coherence
(2010) Akan, Aydın; Demiralp, Tamer; GÜRKAN, GÜRAY; 113297; 2918
Metadata only
Doku Analiz Yaklaşımına Dayanan Yeni Bir İris Tanıma Yöntemi
(IEEE, 2005) Akan, Aydın; GÜRKAN, GÜRAY; 113297; 2918
Bu çalışmada, iris yardımı ile kişi tanıma konusunda doku analizine dayalı yeni bir yöntem sunulmaktadır. İris görüntüleri bir ön işlemeden geçirildikten sonra doku analizine dayanan öznitelik vektörleri çıkarılmaktadır. Normalize edilen iris görüntüsü dikey logaritmik olarak örneklenir ve dairesel simetrik Gabor süzgeçlerinden geçirilir. Süzgeç çıkışları üzerinde kayan bir pencere altındaki piksellerin ortalama mutlak sapma değerleri öznitelik olarak elde edilir. Önerilen yöntem, iris ile kişi tanıma sisteminde aranan önemli niteliklerden ölçek ve dönüş ile değişmezlik özelliklerine sahiptir. Sistemin yazılım kısmı, Delphi derleyicisi ile Windows ortamında gerçeklenmiştir.
Metadata only
Dual Kalman Filter based State-Parameter Estimation in Linear Lung Models
(Springer, 233 Spring Street, New York, Ny 10013, United States, 2009) Akan, Aydın; SAATÇI, ESRA; TR112197; TR2918
Time-domain approach to inverse modeling of respiratory system requires estimation of the parameters from the noisy observation. In this work, states and parameters of the linear lung models are estimated simultaneously by dual Kalman filter where the algorithm use two-observation forms. We also employ Kalman smoother for fine tuning the parameters. It is found that the state estimates are more robust to initial filter parameters than the model parameter convergences. Both viscoelastic and the Mead models yielded encouraging results and compatible estimator variances.
Metadata only
EEG Sinyalinin Anestezi Sırasındaki Topografik ve Zamansal İzge Analizi
(IEEE, 2018) Uslu, Atilla; Cebeci, Bora; Erdoğan, Ezgi T.; Kaşıkçı, Itır; Seyhan, Tülay Ö.; Akan, Aydın; Demiralp, Tamer; GÜRKAN, GÜRAY; 113297; 221283; 141798; 167802; 2918; 6916
Bu çalışmada EEG sinyalinin anestezi altındaki izgesel değişimi, zamansal ve uzaysal olarak incelenmiştir. Bu amaçla kullanılan yöntemler arasında, günümüz anestezi derinliği takip cihazlarının da kullandığı bilinen SEF-90, α-β bandı güç oranları ve izgesel entropi yer almaktadır. Ayrıca doğrusal olmayan sistemlerin analizinde kullanılan Higuchi fraktal boyutu da karşılaştırma olarak incelenmiştir. Uzaysal analiz sonucunda, normal bireylerde oksipital bölgede görülen baskın alfa aktivitesinin artan anestezi derinliği ile frontal bölgeye kaydığı doğrulanmış ve ilgili topografik gösterimler sunulmuştur.
Metadata only
Estimation Of The Respiratory System Parameters
(European Assoc Signal Speech & Image Processing-Eurasip, Po Box 74251, Kessariani, 151 10, Greece, 2011) Sert, Görkem; Akan, Aydın; GÜRKAN, GÜRAY; SAATÇI, ESRA; TR112197; TR113297; TR2918
In clinical respiratory studies, resistance and the lung compliance are two important respiratory parameters that are often measured by physicians. In this work, Respiratory signals (mask pressure, airway flow, and lung volume) are measured by using artificial lung simulator and mannequin head and respiratory parameters set on the simulator are estimated by the best linear unbiased estimator (BLUE). However, prior to the estimation, muscular pressure signals that symbolize the effect of the respiratory parameters on the respiratory signals are computed by using least mean square (LMS) based adaptive noise canceler (ANC). It is found that LMS filter length considerably effects the filter output and in turn the estimation results. Thus, it is suggested to use mis-adjustement criterion in LMS-ANC filter to select the filter order by processing the signals that have only one respiratory parameter variation. In conclusion, respiratory parameters are successfully estimated from the muscular pressure signals that are filtered out with appropriate filter lengths.
Metadata only
Frequency estimation for monophonical music by using a modified VMD method
(IEEE, 345 E 47Th St, New York, Ny 10017 USA, 2017) Öztürk Şimşek, Berrak; Akan, Aydın; 107113; 2918
In this paper, a new Variational Mode Decomposition (VMD) is introduced, and applied to the fundamental frequency estimation of monophonical Turkish maqam music. VMD is a method to decompose an input signal into an ensemble of sub-signals (modes) which is entirely non-recursive. It determines the relevant bands adaptively, and estimates the corresponding modes concurrently. In order to optimally decompose a given signal, VMD seeks an ensemble of modes with narrow-band properties corresponding to the Intrinsic Mode Function (IMF) definition used in Empirical Mode Decomposition (EMD). In our proposed modified VMD approach, in order to obtain the bandwidth of a mode, each mode is shifted to baseband by mixing an exponential that is adjusted to the respective center frequency. The bandwidth is estimated through elastic net method that linearly combines penalties of the Lasso and Ridge Regression methods. Simulation results on fundamental frequency estimation of real music and synthetic test data show better performance compared to classical VMD based approach, and other common methods used for music signals, such as YIN and MELODIA based methods.
Metadata only
Fundamental Frequency Estimation for Monophonical Turkish Music by using VMD
(IEEE, 345 E 47Th St, New York, Ny 10017 USA, 2015-05-16) Öztürk Şimşek, Berrak; Akan, Aydın; Bozkurt, Barış; 107113; 2918
In this study, a new method is presented for the fundamental frequency estimation of Turkish makam music recordings by using Variational Mode Decomposition (VMD). VMD is a method to decompose an input signal into an ensemble of sub-signals (modes) which is entirely non-recursive and determines the relevant bands adaptively and estimates the corresponding modes concurrently. In order to decompose a given signal optimally, actuated by the narrow-band properties corresponding to the Intrinsic Mode Function (IMF) definition used in Emprical Mode Decomposition (EMD), and we seek an ensemble of modes. Simulation results on fundamental frequency estimation of real music and synthetic test data show better performance compared to other common decomposition methods for music signals such as spectrogram, YIN, MELODIA and EMD based methods.
Metadata only
Generalized Gauss Distribution Noise Model for Respiratory Parameter Estimation
(Ieee, 345 E 47Th St, New York, Ny 10017 Usa, 2009) Akan, Aydın; SAATÇI, ESRA; TR112197; TR2918
In this studs, measurement noise is modelled as a Generalized Gauss Distribution and a new method is presented to estimate the model parameters. The estimator algorithm consists of the Kurtosis method, Kalman iterarions and the Maximum likelihood method. The proposed method is successfully applied to linear lung model parameter estimation problem.
Metadata only
Heart sound localization and reduction in tracheal sounds by gabor time-frequency masking
(Istanbul Unıv, Fac Engineering, Elektrik-Elektronik Mühendisliği Bölümü, Avcılar Kampüsü, İstanbul, 34320, Turkey, 2017) Akan, Aydın; SAATÇI, ESRA; 112197; 2918
Respiratory sounds, i.e. tracheal and lung sounds, have been of great interest due to their diagnostic values as well as the potential of their use in the estimation of the respiratory dynamics (mainly airflow). Thus the aim of the study is to present a new method to filter the heart sound interference from the tracheal sounds. Tracheal sounds and airflow signals were collected by using an accelerometer from 10 healthy subjects. Tracheal sounds were then pre-processed by Recursive Least Square - Adaptive Noise Cancellation (RLS-ANC) filter to remove background noise. Gabor time-frequency expansion was used for both heart sound localization and reduction problem. In the first step of filtering, RLSANC successfully filtered out the broad - band ambient noise. Reconstruction of tracheal sound was achieved from modified Gabor coefficients without heart sound noise. Visual inspection and quantitative analysis demonstrated that Gabor time-frequency masking with RLS-ANC filters provides successful tracheal sound signal separation.
Embargo
Inverse Modeling of Respiratory System during Noninvasive Ventilation by Maximum Likelihood Estimation
(Hindawi Publishing Corporation, 410 Park Avenue, 15Th Floor, #287 Pmb, New York, Ny 10022 Usa, 2010) Akan, Aydın; SAATÇI, ESRA; TR112197; TR2918
We propose a procedure to estimate the model parameters of presented nonlinear Resistance-Capacitance (RC) and the widely used linear Resistance-Inductance-Capacitance (RIC) models of the respiratory system by Maximum Likelihood Estimator (MLE). The measurement noise is assumed to be Generalized Gaussian Distributed (GGD), and the variance and the shape factor of the measurement noise are estimated by MLE and Kurtosis method, respectively. The performance of the MLE algorithm is also demonstrated by the Cramer-Rao Lower Bound (CRLB) with artificially produced respiratory signals. Airway flow, mask pressure, and lung volume are measured from patients with Chronic Obstructive Pulmonary Disease (COPD) under the noninvasive ventilation and from healthy subjects. Simulations show that respiratory signals from healthy subjects are better represented by the RIC model compared to the nonlinear RC model. On the other hand, the Patient group respiratory signals are fitted to the nonlinear RC model with lower measurement noise variance, better converged measurement noise shape factor, and model parameter tracks. Also, it is observed that for the Patient group the shape factor of the measurement noise converges to values between 1 and 2 whereas for the Control group shape factor values are estimated in the super-Gaussian area.
Metadata only
Lung model parameter estimation by unscented Kalman filter
(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2007) Akan, Aydın; SAATÇI, ESRA; TR2918; TR112197
Dynamic nonlinear models are the best choice to analyze respiratory systems and to describe system mechanics. In this work, Unscented Kalman Filtering (UKF) was used to estimate the dynamic nonlinear model parameters of the lung model by using the measured airway flow, mask pressure and integrated lung volume. Artificially generated data and the data from Chronic Obstructive Pulmonary Diseased (COPD) patients were analyzed by the proposed model and the proposed UKF algorithm. Simulation results for both cases demonstrated that UKF is a promising estimation method for the respiratory system analysis.
Metadata only
Lung Sound Noise Reduction Using Gabor Time-Frequency Masking
(SPRINGER-VERLAG BERLIN, HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY, 2007) Akan, Aydın; SAATÇI, ESRA; TR112197; TR2918
The Gabor expansion is a mathematical tool, which provides a joint time-frequency representation of a given signal by decomposing it into time-frequency elementary signals called Gabor atoms. It has been used in a variety of signal processing applications, including biomedical signal processing. In this paper we present a time-frequency masking technique based on Gabor expansion for both heart sound localization and reduction problem. Gabor coefficients of lung sound segments recorded from trachea are calculated and masked to remove the distinctive heart sound effects. Reconstruction of lung sound is achieved from modified Gabor coefficients without heart sound noise.
Metadata only
Monofonik Türk Makam Müziğinde İşitsel Melodi Kestirimi
(IEEE, 2020) ŞİMŞEK, BERRAK ÖZTÜRK; Akan, Aydın
Bu çalışmada, monofonik Türk makam müziği eserlerinde baskın işitsel melodi çıkarımı için yeni bir yöntem önerilmiştir. Müzik sinyalleri, Geliştirilmiş Değişken Mod Ayrıştırma Yöntemi kullanılarak ayrıştırılır ve temel frekanslar, her moddaki merkez frekanslarının hesaplanmasıyla elde edilir. Baskın melodi hattını tahmin etmek ve seçmek için her penceredeki farklı frekans bilgilerinden bazı parametreler belirlenir. Elde edilen sonuçlar, batı müziği için kullanılan sinyal işleme algoritmaları olan YIN ve MELODIA ile karşılaştırılmıştır. Değerlendirme aşamasında uluslararası standartlara bağlı kalınarak MIREX kriterleri kullanılmaktadır. Simülasyon sonuçları, Geliştirilmiş Değişken Mod Ayrıştırma Yönteminin karşılaştırmada kullanılan diğer yöntemlere göre daha başarılı sonuçlar verdiğini göstermiştir.

Browse

Browsing Mühendislik Fakültesi / Faculty of Engineering by Author "Akan, Aydın"