Murat Ceylan

Fuzzy clustering complex-valued neural network to diagnose cirrhosis disease

In this study, fuzzy clustering complex-valued neural network (FCCVNN) was proposed to classify portal vein Doppler signals recorded from 54 patients with cirrhosis and 36 healthy subjects. This proposed neural network is a new model for biomedical pattern classification. The FCCVNN was composed of three phases: fuzzy clustering, calculation of FFT values and complex-valued neural network (CVNN). In first phase, fuzzy clustering was done to reduce the number of segments in training pattern. After that, FFT values of Doppler signals were calculated for pre-processing and then obtained values, which include real and imaginary components, were used as the inputs of the CVNN for classification of Doppler signals. Classification results of FCCVNN were evaluated by the different performance evaluation criterion in literature. It shows that Doppler signals were classified successfully with 100% correct classification rate using the proposed method. Moreover, the rates of sensitivity and specificity were calculated as 100% using FCCVNN method. These results were seen to be appropriate with the expected results that are derived from physicians direct diagnosis. This method would be assisted the physician to make the final decision.

Complex-valued wavelet artificial neural network for Doppler signals classifying

OBJECTIVE In this paper, the new complex-valued wavelet artificial neural network (CVWANN) was proposed for classifying Doppler signals recorded from patients and healthy volunteers. CVWANN was implemented on four different structures (CVWANN-1, -2, -3 and -4). MATERIALS AND METHODS In this study, carotid arterial Doppler ultrasound signals were acquired from left carotid arteries of 38 patients and 40 healthy volunteers. The patient group had an established diagnosis of the early phase of atherosclerosis through coronary or aortofemoropopliteal angiographies. In implemented structures in this paper, Haar wavelet and Mexican hat wavelet functions were used as real and imaginary parts of activation function on different sequence in hidden layer nodes. CVWANN-1, -2 -3 and -4 were implemented by using Haar-Haar, Mexican hat-Mexican hat, Haar-Mexican hat, Mexican hat-Haar as real-imaginary parts of activation function in hidden layer nodes, respectively. RESULTS AND CONCLUSION In contrast to CVWANN-2, which reached classification rates of 24.5%, CVWANN-1, -3 and -4 classified 40 healthy and 38 unhealthy subjects for both training and test phases with 100% correct classification rate using leave-one-out cross-validation. These networks have 100% sensitivity, 100% specifity and average detection rate is calculated as 100%. In addition, positive predictive value and negative predictive value were obtained as 100% for these networks. These results shown that CVWANN-1, -3 and -4 succeeded to classify Doppler signals. Moreover, training time and processing complexity were decreased considerable amount by using CVWANN-3. As conclusion, using of Mexican hat wavelet function in real and imaginary parts of hidden layer activation function (CVWANN-2) is not suitable for classifying healthy and unhealthy subjects with high accuracy rate. The cause of unsuitability (obtaining the poor results in CVWANN-2) is lack of harmony between type of activation function in hidden layer and type of input signals in neural network.

Application of complex discrete wavelet transform in classification of Doppler signals using complex-valued artificial neural network

OBJECTIVE In biomedical signal classification, due to the huge amount of data, to compress the biomedical waveform data is vital. This paper presents two different structures formed using feature extraction algorithms to decrease size of feature set in training and test data. MATERIALS AND METHODS The proposed structures, named as wavelet transform-complex-valued artificial neural network (WT-CVANN) and complex wavelet transform-complex-valued artificial neural network (CWT-CVANN), use real and complex discrete wavelet transform for feature extraction. The aim of using wavelet transform is to compress data and to reduce training time of network without decreasing accuracy rate. In this study, the presented structures were applied to the problem of classification in carotid arterial Doppler ultrasound signals. Carotid arterial Doppler ultrasound signals were acquired from left carotid arteries of 38 patients and 40 healthy volunteers. The patient group included 22 males and 16 females with an established diagnosis of the early phase of atherosclerosis through coronary or aortofemoropopliteal (lower extremity) angiographies (mean age, 59 years; range, 48-72 years). Healthy volunteers were young non-smokers who seem to not bear any risk of atherosclerosis, including 28 males and 12 females (mean age, 23 years; range, 19-27 years). RESULTS AND CONCLUSION Sensitivity, specificity and average detection rate were calculated for comparison, after training and test phases of all structures finished. These parameters have demonstrated that training times of CVANN and real-valued artificial neural network (RVANN) were reduced using feature extraction algorithms without decreasing accuracy rate in accordance to our aim.

A new application area of ANN and ANFIS: determination of earthquake load reduction factor of prefabricated industrial buildings

The earthquake load reduction factor, R, is one of the most important parameters in the design stage of a building. Significant damages and failures were experienced on prefabricated reinforced concrete structures during the last earthquakes in Turkey and the experts agreed that they resulted mainly from the incorrectly selected earthquake load reduction factor, R. In this study, an attempt was made to estimate the R coefficient for prefabricated industrial structures having a single storey, one and two bays, which are commonly constructed for manufacturing and warehouse operation with variable dimensions. According to the selected variable dimensions, 280 sample (140 samples for one bay (S-1) and 140 samples for two bays (S-2)) frames’ load–displacement relations were computed using pushover analysis and the earthquake load reduction factor, R, was calculated for each frame. Then, formulated three-layered artificial neural network methods (ANNs) and adaptive neuro-fuzzy inference system (ANFIS) were trained by using 214 of the 280 sample frames. Then, the methods were tested with the other 66 sample frames. Accuracy rates were found to be about 94% and 96% for ANN and ANFIS, respectively. The use of ANN and ANFIS provided an alternative way for estimating the R and it also showed that ANFIS estimated R more successfully than ANN.

Blood vessel extraction from retinal images using Complex Wavelet Transform and Complex-Valued Artificial Neural Network

Retinal imaging in ophthalmology plays an important role for the diagnosis of diabetes, cardiovascular disease, etc. In retina images, changes of blood vessels can help the expert to detection of diseases. Manually extraction of blood vessels from retinal images is usually difficult process due to depending on the experience of physician, back-ground artifacts, different acquisition process. Therefore, the aim of this study is to purpose a novel method for automatic blood vessel extraction from retinal image. This study presents a combined structure. This structure is realized with two cascade stages: feature extraction with 4th level Complex Wavelet Transform (CWT) and Complex-Valued Artificial Neural Networks (CVANN) for the blood vessels segmentation. To check the validation of proposed method, public DRIVE database is used. Result of this study has a higher accuracy (98.56 %) than previously studies in the literature.

AN ANN APPROACHES ON ESTIMATING EARTHQUAKE PERFORMANCES OF EXISTING RC BUILDINGS

This study aims at developing an artificial intelligence-based (ANN based) analytical method to analyze earthquake performances of the reinforced concrete (RC) buildings. In the scope of the present study, 66 real RC buildings with four to ten storeys were subject to performance analysis according to 19 parameters considered effective on the performance of RC buildings. In addition, the level of performance of these buildings in case of an earthquake was determined on the basis of the 4-grade performance levels specified in Turkish Earthquake Code-2007 (TEC-2007). Thus, an output performance data group was created for the analyzed buildings, in accordance with the input data. Thanks to the ANN- based fast evaluation algorithm mentioned above and developed within the scope of the proposed project study, it will be possible to make an economic and rapid evaluation of four to ten-storey RC buildings in Turkey with great accuracy (about 80%). Detection of post-earthquake performances of RC buildings in the scope of the present study will facilitate reaching important results in terms of buildings, which will be beneficial for Civil Engineers of Turkey and similar countries.

A New Method for 3D Thinning of Hybrid Shaped Porous Media Using Artificial Intelligence. Application to Trabecular Bone

Curve and surface thinning are widely-used skeletonization techniques for modeling objects in three dimensions. In the case of disordered porous media analysis, however, neither is really efficient since the internal geometry of the object is usually composed of both rod and plate shapes. This paper presents an alternative to compute a hybrid shape-dependant skeleton and its application to porous media. The resulting skeleton combines 2D surfaces and 1D curves to represent respectively the plate-shaped and rod-shaped parts of the object. For this purpose, a new technique based on neural networks is proposed: cascade combinations of complex wavelet transform (CWT) and complex-valued artificial neural network (CVANN). The ability of the skeleton to characterize hybrid shaped porous media is demonstrated on a trabecular bone sample. Results show that the proposed method achieves high accuracy rates about 99.78%–99.97%. Especially, CWT (2nd level)-CVANN structure converges to optimum results as high accuracy rate—minimum time consumption.

A new method for extraction of image's features: Complex discrete Ripplet-II transform

Wavelet transform extracts the features of a signal and image via shifting and weighting methods. This transform has either advantages or disadvantages on image processing applications. One of important disadvantage of wavelet transform is limited orientation problem. This problem has been solved by different orientation with ridgelet transform. Ripplet-II transform is defined by recently generalising of the ridgelet transform by adding parameter degree (d). Complex discrete form of ripplet-II transform defined by this study and added to the literature. Also, complex discrete Ripplet-II transform was tested on medical image classification application. For this, the most common benign lesions in liver MR are classified as cyst and hemangioma using complex discrete Ripplet-II transform and ANN. Obtained results shown that, classification success of complex discrete Ripplet-II transform with complex-valued coefficients is higher than real-valued coefficients.

An approach for tissue density classification in mammographic images using artificial neural network based on wavelet and curvelet transforms

Breast cancer is one of the types of cancer which is most commonly seen in women. Density of breast is an important indicator for the risk of cancer. In addition, densities of tissue may harden the diagnosis by hiding the abnormalities occurring on the breast. For this reason, during the process of diagnosis, the process of automatic classification of breast density has a significant importance. In this study, a new system with the base of Artificial Neural Network (ANN) and multiple resolution analysis is suggested. Wavelet and curvelet analyses having the most common use have been used as multi resolution analysis. 4 pieces of statistics which are minimum value, maximum value, mean value and standard deviation have been extracted from the images which have been eluted to their sub-bands via multi resolution analysis. For the purpose of testing the success of the system, 322 pieces of images which are in MIAS database have been used. The obtained results for different backgrounds are so satisfying; and the highest classification values have been obtained as 97.16 % with Wavelet transform and ANN for fatty background and 79.80 % with Wavelet transform and ANN for fatty-glanduar background. The same results have been obtained using Wavelet transform and ANN and Curvelet transform and ANN for dense background and accuracy rate of 84.82 % have been reached. The results of mean classification have been obtained, for three pieces of tissue types (fatty, fatty-glanduar, dense), in sequence as 84.47 % with the use of ANN, 85.71 % with the use of curvelet analysis and ANN; and 87.26 % with the use of wavelet analysis and ANN.

A New Approach for Liver Classification Using Ridgelet / Ripplet-II Transforms, Feature Groups and ANN

In this study, 68 liver MR images (28 of them labeled as hemangioma, 40 of them labeled as cyst by specialist radiologists) were classified by using artificial neural network (ANN). Ridgelet transform and its advanced new generation form (called Ripplet-II transform) were applied on these images to compare their effects on liver image classification. Feature vectors were generated by calculating mean, standard deviation, variance, skewness, kurtosis and moment values of coefficient matrices. Firstly, all feature vectors were given as inputs to an ANN and classification process was realized. Then, vectors were seperated into three groups and classified by using three ANNs. This procedure was repeated with two ANNs and two groups of feature vectors. Outputs of the systems which used more than one ANN were evaluated by implementing AND and OR operations seperately. Accuracy, sensitivity and specifity values of obtained results were calculated and compared. The best results were achieved by evaluating the system which used three ANNs and three groups of statistical feature vectors, with AND / OR operations.