• Journal of the Korean Ceramic Society
• /
• v.49 no.4
• /
• pp.369-374
• /
• 2012

Based on the structure feature of a tree, a cylindrical $Ti_2AlC$/graphite layered composite has been fabricated through heat treating a graphite column and six close-matched thin wall $Ti_2AlC$ cylinders bonded with the $Ti_2AlC$ powders at $1300^{\circ}C$ and low oxygen partial pressure. SEM examination reveals that the bond interlayers between cylinders or that between cylinder and column are not fully dense without any crack formation. During the compressive test, the strain of the $Ti_2AlC$/graphite layered composite is about twice higher than that of the monolithic $Ti_2AlC$ ceramic, and the compressive strength of the layered composite is 348 MPa. The layered composite show the noncatastrophic fracture behaviors due to the debonding and shelling off of the layers, which are different from the monolithic $Ti_2AlC$ ceramic. The mechanism of the improved deformation capacity and noncatastrophic failure modes are attributed to the presence of the central soft graphite column and cracks deflection by the bond interlayers.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.16 no.2
• /
• pp.102-107
• /
• 2017

This study focuses on the effect of the elasticity modulus of jig material on blade edge shape in the grinding process of a sapphire medical knife. The ELID grinding process was applied as the edge-grinding method for sapphire material. Carbon steel and copper have been selected as the hard and soft jig materials, respectively. The blade edge created by ELID grinding was measured by a surface roughness tester and optical microscope. The shape of the ground edge and surface roughness were compared using the measurement results. As a result, it was found that chipping in the blade edge of the sapphire knife occurred more than in the case of jig material with a high-elasticity modulus because of the high normal force in the grinding process. Moreover, the maximum height surface roughness, $R_{max}$,of the ground surface was higher in the case of the jig material with a high-elasticity modulus due to the difference in elasticelongation. It was considered to lead to chipping from the notch effect.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5580-5593
• /
• 2019

A malicious Uniform Resource Locator (URL) recognition and detection method based on the combination of Attention mechanism with Convolutional Neural Network and Long Short-Term Memory Network (Attention-Based CNN-LSTM), is proposed. Firstly, the WHOIS check method is used to extract and filter features, including the URL texture information, the URL string statistical information of attributes and the WHOIS information, and the features are subsequently encoded and pre-processed followed by inputting them to the constructed Convolutional Neural Network (CNN) convolution layer to extract local features. Secondly, in accordance with the weights from the Attention mechanism, the generated local features are input into the Long-Short Term Memory (LSTM) model, and subsequently pooled to calculate the global features of the URLs. Finally, the URLs are detected and classified by the SoftMax function using global features. The results demonstrate that compared with the existing methods, the Attention-based CNN-LSTM mechanism has higher accuracy for malicious URL detection.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.5
• /
• pp.1814-1819
• /
• 2010

The relation constant method between OCR and normalized net cone tip resistance has been widely used to estimate OCR value in practice. In this study, the method was analyzed for the soft soils in the Bukmyun area in Changwon city and the northwestern area in Incheon city. The relation constant value was estimated in the range of 0.28~0.33 for the Bukmyun area in Changwon city and 0.49~0.6 for the northwestern area in Incheon city. The value was max. 90% larger than it from the foreign previous studies. This is not the conservative result so the previous methods should be used with great caution of determining the constant value.

• Advanced Composite Materials
• /
• v.16 no.2
• /
• pp.151-166
• /
• 2007

High-cycle fatigue characteristics of quasi-isotropic carbon fiber reinforced plastic (CFRP) laminates [-45/0/45/90]s up to $10^8$ cycles were investigated. To assess the fatigue behavior in the high-cycle region, fatigue tests were conducted at a frequency of 100 Hz, since it is difficult to investigate the fatigue characteristics in high-cycle at 5 Hz. Then, the damage behavior of the specimen was observed with a microscope, soft X-ray photography and a 3D ultrasonic inspection system. In this study, to evaluate quantitative characteristics of both transverse crack propagation and delamination growth in the high-cycle region, the energy release rate associated with damage growth in the width direction was calculated. Transverse crack propagation and delamination growth in the width direction were evaluated based on a modified Paris law approach. The results revealed that transverse crack propagation delayed under the test conditions of less than ${\sigma}_{max}/{\sigma}_b$ = 0.3 of the applied stress level.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.147-153
• /
• 2018

In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.

• Journal of The Korean Astronomical Society
• /
• v.34 no.2
• /
• pp.111-117
• /
• 2001

Recently, we have set up a new digital CCD camera system, MicroMax YHS-1300 manufactured by Roper Scientific for Ha observation by Solar Flare Telescope at Bohyunsan Optical Astronomy Observatory. It has a 12 bit dynamic range, a pixel number of 1300$\times$1030, a thermoelectric cooler, and an electric shutter. Its readout speed is about 3 frames per second and the dark current is about 0.05 e-/p/s at $-10^{\circ}C$. We have made a system performance test by confirming the system linearity, system gain, and system noise that its specification requires. We have also developed a data acquisition software which connects a digital camera con-troller to a PC and acquires H$\alpha$ images via Microsoft Visual C++ 6.0 under Windows 98. Comparisons of high quality H$\alpha$ images of AR 9169 and AR 9283 obtained from SOFT with the corresponding images from Learmonth Solar Observatory in Australia confirm that our H$\alpha$ digital observational system is performed properly. Finally, we present a set of H$\alpha$ images taken from a two ribbon flare occurred in AR 9283.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.1
• /
• pp.35.2-35.2
• /
• 2011

We have investigated a coronal jet near the limb on 2010 June 27 by Hinode/X-Ray Telescope (XRT), EUV Imaging Spectrograph (EIS), SDO/Atmospheric Imaging Assembly (AIA), and STEREO. From EUV (AIA and EIS) and soft X-ray (XRT) images we identify the erupting jet feature in cool and hot temperatures. Using the high temporal and multi wavelength AIA images, we found that the hot jet preceded its associated cool jet and their structures are well consistent with the numerical simulation of the emerging flux-reconnection model. From the spectroscopic analysis, we found that the jet structure changes from blue shift to red one with time, which may indicate the helical structure of the jet. The STEREO observation, which enables us to observe this jet on the disk, shows that there was a dim loop associated with the jet. On the other hand, we found that the structure of its associated active region seen in STEREO is similar to that in AIA observed 5 days before. Based on this fact, we compared the jet morphology on the limb with the magnectic fields extrapolated from a HMI vector magnetogram of this active region observed on the disk. Interestingly, the comparison shows that the open and closed magnetic field configuration correspond to the jet and the dim loop, respectively, as the Shibata's jet model predicted.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• Advances in nano research
• /
• v.12 no.5
• /
• pp.489-499
• /
• 2022

Nanofluids have recently triggered a substantial scientific interest as cooling media. However, their stability is challenging for successful engagement in industrial applications. Different factors, including temperature, nanoparticles and base fluids characteristics, pH, ultrasonic power and frequency, agitation time, and surfactant type and concentration, determine the nanofluid stability regime. Indeed, it is often too complicated and even impossible to accurately find the conditions resulting in a stabilized nanofluid. Furthermore, there are no empirical, semi-empirical, and even intelligent scenarios for anticipating the stability of nanofluids. Therefore, this study introduces a straightforward and reliable intelligent classifier for discriminating among the stability regimes of alumina-water nanofluids based on the Zeta potential margins. In this regard, various intelligent classifiers (i.e., deep learning and multilayer perceptron neural network, decision tree, GoogleNet, and multi-output least squares support vector regression) have been designed, and their classification accuracy was compared. This comparison approved that the multilayer perceptron neural network (MLPNN) with the SoftMax activation function trained by the Bayesian regularization algorithm is the best classifier for the considered task. This intelligent classifier accurately detects the stability regimes of more than 90% of 345 different nanofluid samples. The overall classification accuracy and misclassification percent of 90.1% and 9.9% have been achieved by this model. This research is the first try toward anticipting the stability of water-alumin nanofluids from some easily measured independent variables.