Yazar "Ozmen, Guzin" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    Classification of Cervical Disc Herniation Disease using Muscle Fatigue based surface EMG signals by Artificial Neural Networks
    (2017) Ozmen, Guzin; Ekmekcı, Ahmet Hakan
    This study presents the classification of cervical disc herniationpatientsand healthy persons by using muscle fatigue information. Cervical disc herniationpatients suffer from neck pain and muscle fatigue in the neck increases these aches.Neck pain is the most common pain type encountered after back pain. The discomforts that occur in the neck region affect the daily quality of life, so the number of researches done in this area is increasing. In this studysurface Electromyography (EMG) signals wereused to examine muscle fatigue. EMG signals wereobtained from Trapezius and Sternocleidomastoid(SCM)muscles in the cervical region of 10 control subject and10 cervical disc herniation patients. Surface EMG waspreferred because it is a noninvasive method. In the first step of this study, EMG signals were filtered and adapted for analysis. In the second step, muscle fatigue wasdetermined using Median and Mean frequency values obtained by Fourier Transform and Welch methods.Feature extraction wasthe third step which was performed byShort Time Fourier Transform (STFT), Discrete Wavelet Transform (DWT) and Autoregressive method (AR). Finally, Artificial Neural Network (ANN)was used for classification. Training and test data werecreated by using feature vectors to classify patients with ANN. According to the results, the superior feature extraction method was investigatedon patient classification using muscle fatigue information.The best results were obtained by ARmethodwith %99 classification accuracy.Also, the best resultswereobtained by DWT with %100 classification accuracyforSCMmuscle. This study has contributed that AR and DWT are a suitable feature extraction methods for surface EMGsignals by providinghigh accuracyclassification with artificial intelligence methods forcervical disc herniationdisease. Besides, it is shown that muscle fatigue distinguishescervical disc herniationpatientsfrom healthy people
  • Küçük Resim Yok
    Öğe
    The Evaluation of the Muscle Fatigue Using Frequency Features in the Cervical Region
    (IEEE, 2014) Ozmen, Guzin; Ozbay, Yuksel; Ekmekci, Ahmet Hakan
    Surface electromyography is a method which is for the evaluation of the electrical activity of superficial muscles. Moreover, muscle fatigue can also be detected using surface electromyography. In this study, on 20 volunteers, the muscle fatigue in cervical region was examined using surface electromyogram signals obtained from the trapezius and sternocleidomastoid muscle. Median frequency, mean frequency and mode frequency values were calculated by Welch method to investigate the muscle fatigue. When the Trapezius and sternocleidomastoid muscles are gone from study status to fatigue status the frequency parameters have shifted towards low frequencies. In practice, the median and mean frequency values are reliable parameters for muscle fatigue. According to the results; while the muscle fatigue was observed in 27 records for the median frequency, it was occurred in 22 records for the average frequency.
  • Küçük Resim Yok
    Öğe
    A new denoising method for fMRI based on weighted three-dimensional wavelet transform
    (SPRINGER LONDON LTD, 2018) Ozmen, Guzin; Ozsen, Seral
    This study presents a new three-dimensional discrete wavelet transform (3D-DWT)-based denoising method for functional magnetic resonance images (fMRI). This method is called weighted three-dimensional discrete wavelet transform (w-3D-DWT), and it is based on the principle of weighting the volume subbands which are obtained by 3D-DWT. Briefly, classical DWT denoising consists of wavelet decomposition, thresholding, and image reconstruction steps. In the thresholding algorithm, the thresholding value for each image cannot be chosen exclusively. Namely, a specific thresholding value is chosen and it is used for all images. The proposed algorithm in this study can be considered as a data-driven denoising model for fMRI. It consists of three-dimensional wavelet decomposition, subband weighting, and image reconstruction. The purposes of subband weighting algorithm are to increase the effect of the subband which represents the image better and to decrease the effect of the subband which represents the image in the worst way and thus to reduce the noises of the image adaptively. fMRI is one of the popular methods used to understand brain functions which are often corrupted by noises from various sources. The traditional denoising method used in fMRI is smoothing images with a Gaussian kernel. This study suggests an adaptive approach for fMRI filtering different from Gaussian smoothing and 3D-DWT thresholding. In this study, w-3D-DWT denoising results were evaluated with mean-square error (MSE), peak signal/noise ratio (PSNR), and structural similarity (SSIM) metrics, and the results were compared with Gaussian smoothing and 3D-DWT thresholding methods. According to this comparison, w-3D-DWT gave low-MSE and high-PSNR results for fMRI data.