http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Specimen index may be a predictive factor for recurrence after primary closure of pilonidal disease
Husnu Alptekin,Fahrettin Acar,Mustafa Sahin,Huseyin Yilmaz,M. Ertugrul Kafali,Sinan Beyhan 대한외과학회 2012 Annals of Surgical Treatment and Research(ASRT) Vol.83 No.6
Purpose: The aim of the present study was to evaluate the predictive value of volume of the specimen/body mass index (VS/BMI) ratio for recurrence after surgical therapy of pilonidal disease. Methods: Ninety-eight patients with primary pilonidal disease were enrolled in this study. The VS/BMI ratio was calculated for each patient. This ratio was defined as the specimen index (SI). VS, BMI and SI were evaluated to determine whether there is a relationship between these parameters and recurrence of pilonidal disease. In addition, the predictive ability of SI for recurrence was analyzed by receiver operating characteristic (ROC) curve. Results: VS and SI were found to be higher in patients with recurrence. ROC curve analysis showed that VS and SI are predictive factors for recurrence in patients treated with primary closure, nevertheless our new index had higher sensitivity and specificity than VS (sensitivity 85.7% vs 71.4% and specificity 90.7% vs 85.1%, respectively). The cut-off level for the greatest sensitivity and specificity for SI was 1.29. Conclusion: Recurrence is higher in patients with high VS regardless of the operation method. SI may be a predictive value in patients treated with primary closure.
( Husnu Baris Baydargil ),( Jangsik Park ),( Do-young Kang ),( Hyun Kang ),( Kook Cho ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.9
In this paper, a parallel deep learning model using a convolutional neural network and a dilated convolutional neural network is proposed to classify Alzheimer’s disease with high accuracy in PET/CT images. The developed model consists of two pipelines, a conventional CNN pipeline, and a dilated convolution pipeline. An input image is sent through both pipelines, and at the end of both pipelines, extracted features are concatenated and used for classifying Alzheimer’s disease. Complimentary abilities of both networks provide better overall accuracy than single conventional CNNs in the dataset. Moreover, instead of performing binary classification, the proposed model performs three-class classification being Alzheimer’s disease, mild cognitive impairment, and normal control. Using the data received from Dong-a University, the model performs classification detecting Alzheimer’s disease with an accuracy of up to 95.51%.
Corrosion-inhibiting effect of Mimosa extract on brass-MM55 corrosion in 0.5 M H2SO4 acidic media
Husnu Gerengi,H.Ibrahim Sahin,Katarzyna Schaefer 한국공업화학회 2012 Journal of Industrial and Engineering Chemistry Vol.18 No.6
Mimosa extract was examined as a corrosion inhibitor for brass-MM55 in 0.5 M H2SO4 by using electrochemical impedance spectroscopy and the polarization technique. The polarization studies showed that Mimosa extracts acted as anodic-type inhibitor. The percentage inhibition efficiency (h),was found to increase with increase of the inhibitor concentration due to the adsorption of the inhibitor molecules on the metal surface. In addition it was established the adsorption follows Temkin adsorption isotherm. Moreover some thermodynamic data were calculated and discussed. The results showed that Mimosa extract could play significant role as a corrosion inhibitor for brass-MM55 in 0.5 M H2SO4 environment.
Classification of Alzheimer’s Disease with Stacked Convolutional Autoencoder
Husnu Baris Baydargil,Jang Sik Park,강도영 한국멀티미디어학회 2020 멀티미디어학회논문지 Vol.23 No.2
In this paper, a stacked convolutional autoencoder model is proposed in order to classify Alzheimer’s disease with high accuracy in PET/CT images. The proposed model makes use of the latent space representation - which is also called the bottleneck, of the encoder-decoder architecture: The input image is sent through the pipeline and the encoder part, using stacked convolutional filters, extracts the most useful information. This information is in the bottleneck, which then uses Softmax classification operation to classify between Alzheimer’s disease, Mild Cognitive Impairment, and Normal Control. Using the data from Dong-A University, the model performs classification in detecting Alzheimer’s disease up to 98.54% accuracy.
Classification of Alzheimer’s Disease Using Stacked Sparse Convolutional Autoencoder
Husnu Baris Baydargil,Jang-Sik Park,Do-Young Kang 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10
Alzheimer’s disease is a neurodegenerative disease that affects the brain structure and its functions. Early and accurate detection of AD through medical imaging may improve lifespan and overall quality of life for patients and their caretakers. In this paper, a specially developed sparse autoencoder is used to accurately detect AD in PET/CT (Positron Emission Tomography/ Computerized Tomography) brain images. Sagittal and coronal images were created from axial images, and those were trained separately to compare classification results. Two-stage training is utilized; first stage, a supervised training to train the classifier to identify the AD, and an unsupervised learning in order to produce an image output. In the created dataset, state-of-the-art classification models are trained and compared to the developed model. A 98.67% accuracy is reached for sagittal images. Detailed information is provided in chapters three and four.
Corrosion behavior of concrete produced with diatomite and zeolite exposed to chlorides
Husnu Gerengi,Yilmaz Kocak,Agata Jazdzewska,Mine Kurtay 사단법인 한국계산역학회 2017 Computers and Concrete, An International Journal Vol.19 No.2
Chloride induced reinforcement corrosion is widely accepted to be the most frequent mechanism causing premature degradation of reinforced concrete structures. The electrochemical impedance of reinforcing steel in diatomite- and zeolite-containing concrete exposed to sodium chloride was assessed. Chemical, physical and mineralogical properties of three concrete samples (20% diatomite, 20% zeolite, and a reference containing neither) were correlated with corrosion investigations. The steel-reinforced samples were exposed to 3.5% NaCl solution for 500 days, and measured every 15 days via EIS method. Results indicated that porosity and capillary spaces increase the diffusion rate of water and electrolytes throughout the concrete, making it more susceptible to cracking. Reinforcement in the reference concrete was the most corroded compare to the zeolite and the diatomite samples.