• Journal of the Korean Society for Marine Environment & Energy
• /
• v.17 no.3
• /
• pp.174-181
• /
• 2014

Design procedure of LEG(Linear Electric Generator) is introduced by performing the time-domain analysis for the heaving motion of a floating buoy coupled with LEG. A vertical truncated buoy is selected as a point absorber and a double-sided Halbach array mover and cored slotless stator is adopted as a linear electric generator. LEG with a double-sided Halbach array mover and cored slotless stator is designed with the input data such as the heave motion velocity and wave exciting forces in time-domain. The validity of designed LEG is confirmed by performing generating-characteristic-analysis under the sinusoidal motion of a buoy, based on the numerical techniques such as FE(Finite Element) analysis. In particular, an ECM(Equivalent Circuit Method) is employed as the design tool for the prediction of generating characteristics under irregular wave conditions. Finally, we confirm that the ECM gives reasonable and fast results without sacrifice of accuracy.

• Journal of the Korean Society of Safety
• /
• v.34 no.6
• /
• pp.50-57
• /
• 2019

In this study, various types of deep learning models that have been proposed recently are classified according to data input / output types and analyzed to find the deep learning model suitable for constructing a crack detection model. First the deep learning models are classified into image classification model, object segmentation model, object detection model, and instance segmentation model. ResNet-101, DeepLab V2, Faster R-CNN, and Mask R-CNN were selected as representative deep learning model of each type. For the comparison, ResNet-101 was implemented for all the types of deep learning model as a backbone network which serves as a main feature extractor. The four types of deep learning models were trained with 500 crack images taken from real concrete structures and collected from the Internet. The four types of deep learning models showed high accuracy above 94% during the training. Comparative evaluation was conducted using 40 images taken from real concrete structures. The performance of each type of deep learning model was measured using precision and recall. In the experimental result, Mask R-CNN, an instance segmentation deep learning model showed the highest precision and recall on crack detection. Qualitative analysis also shows that Mask R-CNN could detect crack shapes most similarly to the real crack shapes.

• Journal of Convergence for Information Technology
• /
• v.11 no.9
• /
• pp.28-34
• /
• 2021

In the case of object detection using deep learning, both accuracy and real-time are required. However, it is difficult to use a deep learning model that processes a large amount of data in a limited resource environment. To solve this problem, this paper proposes an object detection model for small embedded devices. Unlike the general detection model, the model size was minimized by using a structure in which the pre-trained feature extractor was removed. The structure of the model was designed by repeatedly stacking lightweight convolution blocks. In addition, the number of region proposals is greatly reduced to reduce detection overhead. The proposed model was trained and evaluated using the public dataset PASCAL VOC. For quantitative evaluation of the model, detection performance was measured with average precision used in the detection field. And the detection speed was measured in a Raspberry Pi similar to an actual embedded device. Through the experiment, we achieved improved accuracy and faster reasoning speed compared to the existing detection method.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.45-54
• /
• 2021

Recently, deep learning-based denoising approaches have been actively studied. In particular, with the advances of blind denoising techniques, it become possible to train a deep learning-based denoising model only with noisy images in an image domain where it is impossible to obtain a clean image. We no longer require pairs of a clean image and a noisy image to obtain a restored clean image from the observation. However, it is difficult to recover the target using a deep learning-based denoising model trained by only noisy images if the distribution of the noisy image is far from the distribution of the clean image. To address this limitation, unpaired image denoising approaches have recently been studied that can learn the denoising model from unpaired data of the noisy image and the clean image. ISCL showed comparable performance close to that of supervised learning-based models based on pairs of clean and noisy images. In this study, we propose suitable normalization techniques for each purpose of architectures (e.g., generator, discriminator, and extractor) of ISCL. We demonstrate that the proposed method outperforms state-of-the-art unpaired image denoising approaches including ISCL.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.483-490
• /
• 2022

Malaria is a disease caused by a parasite and it is prevalent in all over the world. The usual method used to recognize malaria cells is a thick and thin blood smears examination methods, but this method requires a lot of manual calculation, so the efficiency and accuracy are very low as well as the lack of pathologists in impoverished country has led to high malaria mortality rates. In this paper, a malaria cell image recognition model using transfer learning is proposed, which consists in the feature extractor, the residual structure and the fully connected layers. When the pre-training parameters of the VGG-19 model are imported to the proposed model, the parameters of some convolutional layers model are frozen and the fine-tuning method is used to fit the data for the model. Also we implement another malaria cell recognition model without residual structure to compare with the proposed model. The simulation results shows that the model using the residual structure gets better performance than the other model without residual structure and the proposed model has the best accuracy of 97.33% compared to other recent papers.

• Journal of Software Assessment and Valuation
• /
• v.16 no.1
• /
• pp.81-88
• /
• 2020

Various methods of differentiating and servicing digital content for individual users have been studied. Searching for association rules is a very useful way to discover individual preferences in digital content services. The Apriori algorithm is useful as an association rule extractor using frequent itemsets. However, the Apriori algorithm is not suitable for application to an actual content service because it considers only the reference count of each content. In this paper, we propose a new algorithm based on the Apriori that searches association rules by using purchase history and usage-time for each item. The proposed algorithm utilizes the usage time with the weight value according to purchase items. Thus, it is possible to extract the exact preference of the actual user. We implement the proposed algorithm and verify the performance through the actual data presented in the actual content service system.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.573-587
• /
• 2022

The agricultural sector is completely different from other sectors since it completely relies on various natural and climatic factors. Climate changes have many effects, including lack of annual rainfall and pests, heat waves, changes in sea level, and global ozone/atmospheric CO₂ fluctuation, on land and agriculture in similar ways. Climate change also affects the environment. Based on these factors, farmers chose their crops to increase productivity in their fields. Many existing agricultural ontologies are either domain-specific or have been created with minimal vocabulary and no proper evaluation framework has been implemented. A new agricultural ontology focused on subdomains is designed to assist farmers using Jaccard relative extractor (JRE) and Naïve Bayes algorithm. The JRE is used to find the similarity between two sentences and words in the agricultural documents and the relationship between two terms is identified via the Naïve Bayes algorithm. In the proposed method, the preprocessing of data is carried out through natural language processing techniques and the tags whose dimensions are reduced are subjected to rule-based formal concept analysis and mapping. The subdomain ontologies of weather, pest, and soil are built separately, and the overall agricultural ontology are built around them. The gold standard for the lexical layer is used to evaluate the proposed technique, and its performance is analyzed by comparing it with different state-of-the-art systems. Precision, recall, F-measure, Matthews correlation coefficient, receiver operating characteristic curve area, and precision-recall curve area are the performance metrics used to analyze the performance. The proposed methodology gives a precision score of 94.40% when compared with the decision tree(83.94%) and K-nearest neighbor algorithm(86.89%) for agricultural ontology construction.

• The Korea Journal of Herbology
• /
• v.39 no.2
• /
• pp.11-18
• /
• 2024

Objectives : High blood pressure (also called Hypertension), which is the blood pressure that is higher than normal, is a chronic disease and causes various complications. Historically, Traditional Herbal Prescriptions (THP) have treated many diseases. However, there are not many studies on the treatment of hypertension with THP, very few studies have investigated the interactions between the co-administration of synthetic anti-hypertensives and THP. Therefore, the objective of the present study was to investigate the vasorelaxant activities of 10 THP in rat thoracic aortas pre-contracted with potassium chloride (KCl). Methods : An electric extractor was used to extract THP in distilled water for 2h. Rat thoracic aortas were isolated and pre-contracted using KCl in organ chambers containing 10 ml Krebs Henseleit (KH) buffer. THP extracts were added in increasing concentrations (10-1000 ㎍/mL) to investigate vasorelaxant activities. The vasorelaxant activities induced by THP were expressed as a percentage in response to contraction generated by KCl. Results : Among the 10 THP, Dangguisu-san, Mahwang-tang, Bulwhangeumjeonggi-san, Jakyakgamcho-tang, and Hyangsapyeongwi-san showed significant vasorelaxant activities. Maekmundong-tang, Bojungikgi-tang, Samryeongbaekchul-san, Yukmijihwang-tang, and Insampaedok-san showed no significant effect. Also, in co-administration with amlodipine, Mahwang-tang showed higher vasorelaxant activities than amlodipine alone, and Hyangsapyeongwi-san showed greater vasorelaxant activities at low concentrations but inhibited amlodipine's vasorelaxant activities at high concentrations. Conclusion : The results of these experiments are expected to provide useful data to establish guidelines for THPs and co-administration with western antihypertensive drugs to treat hypertension.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.13 no.1 s.28
• /
• pp.9-20
• /
• 2007

PAHs(Polycyclic Aromatic Hydrocarbons) are widespread contaminants in the marine environment. They are of mainly anthropogenic origin from urban runoff, oil spill and combustion of fossil fuels. Some PAHs are potentially carcinogenic and mutagenic to aquatic organism The contamination of PAHs in the coastal environments has not been well known yet in Korea. This study was carried out to survey the contamination of PAHs in sediments around Gwangyang bay. The Yeosu petrochemical industrial complex, POSCO(Pohang steel company) and Gwangyang container harbor are located around the bay. PAHs in sediment samples were extracted in soxhlet extractor and were identified and quantified by GC-MS(Gas Chromatography-Mass Spectrometry) TOC(Total Organic carbon) and textural parameters in sediment samples were also analyzed 13 species of PAHs were detected at all of the surface sediments. Total PAHs concentrations in the surface sediments ranged from 171.40 to $1013.54{\mu}g/kg$ dry wt.. In most of the surface sediments, Naphthalene was the highest in the range of 14.08 to $691.39{\mu}g/kg$ dry wt. and Anthracene was the lowest in the range of 0.49 to $22.66{\mu}g/kg$ dry wt.. The correlation coefficients between individual PAHs and Total PAHs in the surface sediments were relatively higher in the low molecular compounds such as Naphthalene and Phenanthrene. In the relationship of the P/A(Phenanthrene/Anthracene) ratio and F/P(Fluoranthene/Pyrene) ratio, P/A ratio was generally above 10 and F/P ratio was shown to be above 1 in all sediment samples. These data indicate that PAHs in sediments around Gwangyang bay seem to be of both pyrolytic and petrogenic origin. Total PAHs in the surface sediments were correlated with TOC and textural parameters. The values of PAHs in the surface and core sediments were lower than the biological effect guidelines.

• Journal of the Korean GEO-environmental Society
• /
• v.16 no.1
• /
• pp.45-53
• /
• 2015

This study has obtained Soil Water Retention Curve (SWRC) of the unsaturated soil from the volumetric pressure plate extractor test and the triaxial compression tests was also conducted. By using the rainfall data measured in the site the seepage analysis of unsteady flow was performed with the program of SEEP/W in Geostudio 2007 and stability of the slope was analyzed with SLOPE/W program. Results of analyses show that shear strength of the unsaturated soil increases with the increase of matric suction. And it was also found that the net volumetric stress and the apparent cohesion increased with the matric suction. The seepage analysis of rainfall represents that the increasing rate of negative pore pressure at the zone of large negative pore pressure is appeared to be high even though lower rainfall intensity, but this tendency declines with ground depth. The stability analysis of slope was carried out for the actual plane of failure with the data representing the field condition. The factor of safety thus calculated was about unity (1.0) or just below, which means that the adopted method of analysis is in good agreement with the field condition.