• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.633-642
• /
• 2019

Recently, the convolution neural network (CNN) model at a single image super-resolution (SISR) have been very successful. The residual learning method can improve training stability and network performance in CNN. In this paper, we propose a SISR using recursive residual network architecture by introducing dense skip connections for learning nonlinear mapping from low-resolution input image to high-resolution target image. The proposed SISR method adopts a method of the recursive residual learning to mitigate the difficulty of the deep network training and remove unnecessary modules for easier to optimize in CNN layers because of the concise and compact recursive network via dense skip connection method. The proposed method not only alleviates the vanishing-gradient problem of a very deep network, but also get the outstanding performance with low complexity of neural network, which allows the neural network to perform training, thereby exhibiting improved performance of SISR method.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.14-25
• /
• 2021

Change detection, which finds changes in remote sensing images of the same location captured at different times, is very important because it is used in various applications. However, registration errors, building displacement errors, and shadow errors cause false positives. To solve these problems, we propose a novle deep convolutional network called CADNet (Change Attention Dense Siamese Network). CADNet uses FPN (Feature Pyramid Network) to detect multi-scale changes, applies a Change Attention Module that attends to the changes, and uses DenseNet as a feature extractor to use feature maps that contain both low-level and high-level features for change detection. CADNet performance measured from the Precision, Recall, F1 side is 98.44%, 98.47%, 98.46% for WHU datasets and 90.72%, 91.89%, 91.30% for LEVIR-CD datasets. The results of this experiment show that CADNet can offer better performance than any other traditional change detection method.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.161-168
• /
• 2021

Cracks affect the robustness of infrastructures such as buildings, bridge, pavement, and pipelines. This paper presents an automated crack detection system which detect cracks in diverse surfaces. We first constructed the combined crack dataset, consists of multiple crack datasets in diverse domains presented in prior studies. Then, state-of-the-art deep learning models in computer vision tasks including VGG, ResNet, WideResNet, ResNeXt, DenseNet, and EfficientNet, were used to validate the performance of crack detection. We divided the combined dataset into train (80%) and test set (20%) to evaluate the employed models. DenseNet121 showed the highest accuracy at 96.20% with relatively low number of parameters compared to other models. Based on the validation procedures of the advanced deep learning models in crack detection task, we shed light on the cost-effective automated crack detection system which can be applied to different surfaces and structures with low computing resources.

• Korean Journal of Radiology
• /
• v.21 no.4
• /
• pp.442-449
• /
• 2020

Objective: To compare the diagnostic performance of contrast-enhanced spectral mammography (CESM) versus ultrasonography (US) in symptomatic patients with dense breasts, while using histology as the gold standard. Materials and Methods: After obtaining approval from the local ethics board, this prospective study collected data from patients with symptomatic breasts who underwent CESM and US examinations from May 1, 2017 to September 30, 2017. We then selected those with dense breasts and pathological results as our sample population. Both CESM and US results were classified by a radiologist through the Breast Imaging Reporting and Data System, and the results were compared with their corresponding histological results. The chi-square test was conducted to compare the diagnostic performance of CESM and US, and the receiver operating characteristic curves for the two imaging modalities were obtained. Results: A total of 131 lesions from 115 patients with dense breasts were included in this study. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were 93.8%, 88.1%, 88.2%, 93.7%, and 90.8% for CESM, and 90.6%, 82.1%, 82.9%, 90.2%, and 86.3% for US, respectively. The p values for sensitivity, specificity, PPV, NPV, and accuracy were 0.687, 0.388, 0.370, 0.702, and 0.238, respectively. The area under the curve of CESM (0.917) was comparable with that of US (0.884); however, the differences between CESM and US were not statistically significant (p = 0.225). Eight false-positive cases and 4 false-negative cases for breast cancer were found in CESM, while 12 false-positive cases and 6 false-negative cases were found in US. Conclusion: The diagnostic performances of CESM and US are comparable in symptomatic women with dense breasts; however, the routine use of additional US imaging is questionable for lesions that can be detected by CESM.

• The Korean Journal of Ceramics
• /
• v.6 no.2
• /
• pp.172-176
• /
• 2000

Solid solutions of Ti$_{0.5}$Zr$_{0.5}$B$_2$were successfully synthesized and densified simultaneously from elemental reactants by the use of a field-activated, pressure-assisted synthesis method. The method involves the application of an electric current and mechanical pressure across reactant compacts to achieve combustion synthesis. Dense solid solutions with relative densities of up to 99% were produced and characterized by XRD, SEM, and EPMA methods. With a maximum measured temperature of 145$0^{\circ}C$ under a load of 86 MPa for 30 min, the desired dense solid solution wad synthesized.

• ETRI Journal
• /
• v.40 no.2
• /
• pp.227-236
• /
• 2018

Ultra-dense small cell networks (UD-SCNs) have been identified as a promising scheme for next-generation wireless networks capable of meeting the ever-increasing demand for higher transmission rates and better quality of service. However, UD-SCNs will inevitably suffer from severe interference among the small cell base stations, which will lower their spectral efficiency. In this paper, we propose a software-defined networking (SDN)-based hierarchical agglomerative clustering (SDN-HAC) framework, which leverages SDN to centrally control all sub-channels in the network, and decides on cluster merging using a similarity criterion based on a suitability function. We evaluate the proposed algorithm through simulation. The obtained results show that the proposed algorithm performs well and improves system payoff by 18.19% and 436.34% when compared with the traditional network architecture algorithms and non-cooperative scenarios, respectively.

• Honam Mathematical Journal
• /
• v.32 no.4
• /
• pp.643-649
• /
• 2010

The purpose of this paper is to study some properties of quasi-submaximal spaces and related examples. More precisely, we prove that if X is a quasi-submaximal and nodec space, then X is submaximal. As properties of quasi-submaximality, we show that if X is a quasi-submaximal space, then (a) for every dense $D{\subset}X$, Int(D) is dense in X, and (b) there are no disjoint dense subsets. Also, we illustrate some basic facts and examples giving the relationships among the properties mentioned in this paper.

• Applied Microscopy
• /
• v.28 no.3
• /
• pp.273-282
• /
• 1998

Ultrastructure of fertilized egg envelope in the tomato clown anemonefish (Amphiprion freatus) was examined by mean of light, scanning and transmission electron microscopies. The fertilized egg of tomato clown anemonefish was of non-transparent, ellipsoidal, adhesive and non-floted type, and there were numerous oil droplets in the yolk sac and adhesive filaments in the area of the animal pole. The outer surface of egg envelope was smooth. The fertilized egg envelope consisted of two distinct layers; a non-adhesive outer electron-dense layer and an inner layer, consisting of five horizontal low electron-dense lamellae alternating with the middle electron dense interlamellae.

• Journal of the Korean Geotechnical Society
• /
• v.17 no.6
• /
• pp.207-213
• /
• 2001

Shaking table tests to investigate the dynamic friction behavior of interfaces between dense dry granular soils and construction material(concrete) were performed and the results are reported. The results show the variation of dynamic interface friction coefficients between dense dry granular soils and construction material was small in the sliding velocity range employed in this study. It was also observed that dynamic interface friction coefficients decreased as mean grain sizes of granular soils increased. These coefficients were compared with the friction coefficients obtained from the peak internal friction angles of the same granular soils by plane strain compression tests.

• Journal of Life Science
• /
• v.11 no.1
• /
• pp.54-61
• /
• 2001

The comparative morphology of epididymal spermatozoa in the lesser white-toothed shrew, Crocidura suaveolens, the Japanese white-toothed shrew, C. dsinezumi and the big white-toothed shrew, C. lasiura, belonging to the subfamily Crocidurinae was studied with the light and electron microscopes. The spermatozoa of C. lasiura and C. dsinezumi were characterized by the large acrosome, serrated inner acrosomal membrane, common apical body and fistulous proximal centriole with slightly dense electron granular materials, which are the charateristics of the Crocidurinae. The C. suaveolens, however, is distinguished from the two species mentioned above in the sperm morphology. That is, the spermatozoa possess not only the charateristic of the Crocidurinae such aw the large acrosome, but also those of the Soricinae, i.e. the smooth inner acrosomal membrane, wavy, finger-like and electron-dense apical body, and the solid proximal centriole filled with electron-dense materials. The results suggest that C. suaveolens has conserved characteristics of the Soricinae.