33 research outputs found
A novel approach to speckle noise filtering based on Artificial Bee Colony algorithm: An ultrasound image application
No full textIn this study a novel approach based on 2D FIR filters is presented for denoising digital images. In this approach the filter coefficients of 2D FIR filters were optimized using the Artificial Bee Colony (ABC) algorithm. To obtain the best filter design, the filter coefficients were tested with different numbers (3 x 3, 5 x 5, 7 x 7, 11 x 11) and connection types (cascade and parallel) during optimization. First, the speckle noise with variances of 1, 0.6, 0.8 and 0.2 respectively was added to the synthetic test image. Later, these noisy images were denoised with both the proposed approach and other well-known filter types such as Gaussian, mean and average filters. For image quality determination metrics such as mean square error (MSE), peak signal-to-noise ratio (PSNR) and signal-to-noise ratio (SNR) were used. Even in the case of noise having maximum variance (the most noisy), the proposed approach performed better than other filtering methods did on the noisy test images. In addition to test images, speckle noise with a variance of 1 was added to a fetal ultrasound image, and this noisy image was denoised with very high PSNR and SNR values. The performance of the proposed approach was also tested on several clinical ultrasound images such as those obtained from ovarian, abdomen and liver tissues. The results of this study showed that the 2D FIR filters designed based on ABC optimization can eliminate speckle noise quite well on noise added test images and intrinsically noisy ultrasound images. (c) 2013 Elsevier Ireland Ltd. All rights reserved
Computer-Based design with dual channel device electrooculography and eye movement tracking
No full text
Investigation of Empirical Mode Decomposition in Forecasting of Hydrological Time Series
No full textIn this study, a nonparametric technique to set up a river stage forecasting model based on empirical mode decomposition (EMD) is presented. The approach is based on the use of the EMD and artificial neural networks (ANN) to forecast next month's monthly streamflows. The proposed approach is applied to a real case study. The data from station on the Kizilirmak River in Turkey was used. The mean square errors (MSE), mean absolute errors (MAE) and correlation coefficient (R) statistics were used for evaluating the accuracy of the EMD-ANN model. The accuracy of the EMD-ANN model was then compared to the artificial neural networks (ANN) model. The results showed that EMD-ANN approach performed better than the ANN in predicting stream flows. The most accurate EMD-ANN model had MSE=0.0132, MAE=0.0883 and R=0.8012 statistics, respectively
Importance of hybrid models for forecasting of hydrological variable
No full textIn this study, a forecasting model for nonlinear and non-stationary hydrological data based on singular spectrum analysis (SSA) and artificial neural networks (ANN) is presented. The stream flow data were decomposed into its independent components using SSA. These sub-bands representing the trend and oscillatory behavior of hydrological data were forecasted 1 month ahead using ANN. The forecasted data were obtained with summation of each forecasted sub-bands. The mean square errors (MSE), mean absolute errors (MAE) and correlation coefficient (R) statistics were used for evaluating the performance of the proposed model. According to statistical parameters, the hybrid SSA-ANN model was a very promising approach for forecasting of hydrological data. The statistical performance parameters were obtained as MSE = 0.00088, MAE = 0.0217 and R = 0.986. Also, hydrological data were forecasted using single ANN model for the comparison. Results were compared with the SSA-ANN model and showed that the SSA-ANN model was much more accurate than the ANN model for the prediction of 1 month ahead stream flow data. To demonstrate the practical utility of the proposed method, SSA-ANN and ANN models were used from 1 to 6 months ahead for forecasting of hydrological data
Finite Impulse Response Filter Design Using Squirrel Search Algorithm Sincap Arama Algoritmasi Kullanarak Sonlu Dürtü Yanitli Filtre Tasarimi
No full text© 2020 IEEE.The Squirrel Search Algorithm, one of the newly introduced metaheuristic algorithm, has been applied for high performance and low grade FIR filter design in MATLAB environment and the results of this design are shared
Detection of Reading Movement from EOG Signals
No full textIn this paper, it is aimed to analysis of Electrooculography (EOG) signals recorded during the back to eye movement (retrieving words/re-reading) and skipping lines while reading. Two situations are characterized by large amplitude fluctuations in EOG signals. For this aim, EOG signals were recorded simultaneously while reading a text from 10 volunteers and changes in EOG signals caused by jumping a bottom line and back movements as reading were analyzed. The classification of these signals may allow the development of a new method for early and rapid diagnosis of various reading disorders (for example dyslexia). This study consists of two main processes; feature extraction and classification. Firstly, two features were determined from the recorded EOG signals for determination of retrieving words/re-reading from EOG signal. Then these signals were applied as input to various classifiers. The classifier performances were evaluated by calculating accuracy, sensitivity, specificity, precision and F measure. Overall classification results were obtained with high performance from all classifiers, and the highest accuracy of the classifiers used was 98% for each of the Random Forest and k-NN classifiers. The results show that this proposed method has an important performance for classification of eye movements from EOG signals
SSA Analysis of Noise Eliminated Transcranial Doppler Signals with IIR Filters
No full text23nd Signal Processing and Communications Applications Conference (SIU) -- MAY 16-19, 2015 -- Inonu Univ, Malatya, TURKEYBiomedical signals affected with noise, interferences and other undesired effects like as Transcranial Doppler (TCD) Signals. In this work, 10dB additive White gaussian noise added on simulated TCD signals. Noise elimination on the TCD signal noise elimination used with 4th degree of IIR filters, parameters are determined with artificial bee colony algorithm (ABC). After noise elimination, new TCD parameters are determined with Singular spectral analysis (SSA) for diagnosis for healthy and patients.Dept Comp Engn & Elect & Elect Engn, Elect & Elect Engn, Bilkent Uni
Determination of mitosis cells number using image processing methods Görüntü i̇şleme yöntemleri kullanarak tümörlü hücrelerde mitoz sayimi
No full textMitosis number of tumor cells is an important factor for pathological examinations. Therefore, to get diagnostic information about tumor cells calculating the number of mitosis cells, first of all, it is photographed tumor cells using light microscopy. Number of mitotic cells determined using image processing methods. Aim of the feature extraction for mitosis cell, entropy value, maximum and minimum axis length, area of convex, pixel values, equivdiameter length, area, overlap area parameters are used to define mitosis cells and number of mitosis cells calculated automatically. As a results, for the identification of mitosis cells an algorithm was constituted taking in the consideration mitosis phases using features above mentioned and number of mitosis cells was determined directly. ©2010 IEEE
