• Economic and Environmental Geology
• /
• v.54 no.2
• /
• pp.177-186
• /
• 2021

For disaster management and mitigation of earthquakes in Korea Peninsula, active fault investigation has been conducted for the past 5 years. In particular, investigation of sediment-covered active faults integrates geomorphological analysis on airborne LiDAR data, surface geological survey, and geophysical exploration, and unearths subsurface active faults by trench survey. However, the fault traces revealed by trench surveys are only available for investigation during a limited time and restored to the previous condition. Thus, the geological data describing the fault trench sites remain as the qualitative data in terms of research articles and reports. To extend the limitations due to temporal nature of geological studies, we utilized a terrestrial LiDAR to produce 3D point clouds for the fault trench sites and restored them in a digital space. The terrestrial LiDAR scanning was conducted at two trench sites located near the Yangsan Fault and acquired amplitude and reflectance from the surveyed area as well as color information by combining photogrammetry with the LiDAR system. The scanned data were merged to form the 3D point clouds having the average geometric error of 0.003 m, which exhibited the sufficient accuracy to restore the details of the surveyed trench sites. However, we found more post-processing on the scanned data would be necessary because the amplitudes and reflectances of the point clouds varied depending on the scan positions and the colors of the trench surfaces were captured differently depending on the light exposures available at the time. Such point clouds are pretty large in size and visualized through a limited set of softwares, which limits data sharing among researchers. As an alternative, we suggested Potree, an open-source web-based platform, to visualize the point clouds of the trench sites. In this study, as a result, we identified that terrestrial LiDAR data can be practical to increase reproducibility of geological field studies and easily accessible by researchers and students in Earth Sciences.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.83-89
• /
• 2021

Lifestyle is changing rapidly, and food consumption patterns vary widely among households as dietary and food processing technologies evolve. This paper reclassified the food group of consumer panel data established by the Rural Development Administration, which contains information on purchasing agricultural products by household unit, and compared the consumption characteristics of agricultural products by age group. The criteria for age classification were divided into groups in their 60s and older with a prevalence of 20% or more metabolic diseases and groups in their 30s and 40s with less than 10%. Using the LightGBM algorithm, we classified the differences in food consumption patterns in their 30s and 50s and 60s and found that the precision was 0.85, the reproducibility was 0.71, and F1_score was 0.77. The results of variable importance were confectionery, folio, seasoned vegetables, fruit vegetables, and marine products, followed by the top five values of the SHAP indicator: confectionery, marine products, seasoned vegetables, fruit vegetables, and folio vegetables. As a result of binary classification of consumption patterns as a median instead of the average sensitive to outliers, confectionery showed that those in their 30s and 40s were more than twice as high as those in their 60s. Other variables also showed significant differences between those in their 30s and 40s and those in their 60s and older. According to the study, people in their 30s and 40s consumed more than twice as much confectionery as those in their 60s, while those in their 60s consumed more than twice as much marine products, seasoned vegetables, fruit vegetables, and folioce or logistics as much as those in their 30s and 40s. In addition to the top five items, consumption of 30s and 40s in wheat-processed snacks, breads and noodles was high, which differed from food consumption patterns in their 60s.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.

• Journal of Nutrition and Health
• /
• v.54 no.2
• /
• pp.211-223
• /
• 2021

Purpose: A total of 39 seafood menus were prepared according to the Korean standard recipe, and analyzed for vitamin B₉ (folate) and B₁₂ (cobalamins) contents, using validated applied analytical methods. The menus included Guk/Tang/Jjigae (boiled or stewed dishes, n = 10), Bokkeum (stir-fried dishes, n = 10), Jjim/Jorim (braised or steamed dishes, n = 7), Gui (baked or grilled dishes, n = 7), Twigim (deep-fried dishes, n = 2) and Muchim (dried or blanched-seasoned dishes, n = 3). Methods: The contents of vitamin B₉ and B₁₂ in all food samples were determined by the trienzyme extraction-Lactobacillus casei and immunoaffinity-high-performance liquid chromatography/photodiode array detection methods. Analytical quality control was performed in order to assure reliability of the analysis. Results: Accuracy (97.4-100.6% recoveries) and precision (< 6% relative standard deviations for repeatability and reproducibility) of vitamin B₉ and B₁₂ analyses were determined to be excellent. The vitamin B₉ and B₁₂ contents of the 39 seafood menus evaluated, varied in the range of 1.83-523.08 ㎍/100 g and 0.11-38.30 ㎍/100 g, respectively, depending on the ingredients and cooking methods. The vitamin B₉ content was highest in Jomi-gim (523.08 ㎍/100 g), followed by Geonsaeu-bokkeum (128.34 ㎍/100 g) and Janmyeolchi-bokkeum (121.53 ㎍/100 g). Vitamin B₁₂ was detected in all seafood menus, with highest level obtained in Kkomack-jjim (41.58 ㎍/100 g). The seaweed dish was found to have high levels of both vitamin B₉ and B₁₂. All assays were performed under strict quality control. Conclusion: Guk and Tang menus, which contain a large amount of water, were relatively lower in the vitamin B₉ and B₁₂ contents than the other menus. Bokkeum menus containing various vegetables were high in the vitamin B₉ content, but the vitamin B₁₂ content was dependent on the type of seafood used in the menu.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.6
• /
• pp.674-691
• /
• 2019

The aim of this study was to evaluate the anti-inflammatory effects of essential oils extracted from the wood of Chamaecyparis obtusa, Pinus densiflora, Pinus koraiensis, and Larix kaempferi. Essential oils were extracted by hydrodistillation, and their chemical components were determined by GC/MS. Major chemical components of these essential oils were ${\alpha}$-cadinol (19.25%), ${\tau}$-muurolol (14.20%), and ${\alpha}$-pinene (13.74%) in C. obtusa; ${\alpha}$-pinene (47.16%), longifolene (14.31%), ${\beta}$-phellandrene (11.78%), and ${\beta}$-pinene (11.02%) in P. densiflora; ${\alpha}$-pinene (13.49%) and longifolene (10.79%) in P. koraiensis, and geranyl linalool (23.58%) and ${\alpha}$-pinene (18.57%) in L. kaempferi. To evaluate the anti-inflammatory effects of essential oils, lipopolysaccharide (LPS)-induced RBL-2H3 mast cells were treated with these essential oils; then, the changes in the mRNA expression level of the cytokines IL-4 and IL-13 were examined. Further, degranulation was evaluated by measuring ${\beta}$-hexosaminidase release. After LPS-induced RBL-2H3 mast cells were exposed to $10^{-7}%$ of all types of essential oils, the gene expression levels of IL-4 and IL-13 within the cells remarkably decreased. The relative mRNA expression level of IL-4 was 69.6% in P. densiflora, 63.2% in P. koraiensis, 55.1% in C. obtusa, and 45.8% in L. kaempferi compared with that in the group treated with LPS. The mRNA expression level of L-13 should a similar trend. The inhibitory rate of IL-13 mRNA expression of P. densiflora, P. koraiensis, C. obtusa, and L. kaempferi was 57.8%, 57.1%, 51.1%, and 34.5%, respectively. ${\beta}$-Hexosaminidase release significantly decreased following the treatment with the four types of essential oils. The rate of ${\beta}$-hexosaminidase release were 38.1% C. obtusa; 33.0% P. densiflora; 27.4% P. koraiensis; and 9.1% L. kaempferi. Among all types of essential oils, that extracted from P. densiflora wood showed the highest anti-inflammatory activity. These results show that the tested essential oils exert an anti-inflammatory effect through the inhibition of degranulation and expression of cytokines.

• Journal of Life Science
• /
• v.29 no.11
• /
• pp.1227-1234
• /
• 2019

Prunus mume, also known as maesil, is a popular fruit consumed in East Asia (Korea, Japan, and China). It contains high amounts of organic acids, minerals, and polyphenols and has been used as a medication for fever, vomiting, and detoxification. In this study, the anti-proliferative and apoptotic effects of solvent fractions from maesil were evaluated using sulforhodamine B (SRB) assays, morphological evaluations, Hoechst 33258 staining, and western blotting. Addition of the maesil methanol fraction (MMF) and the maesil butanol fraction (MBF) significantly and dose-dependently decreased the cell viability of HT-29 human colon cancer cells. Colony-forming assays confirmed that the MMF and MBF treatments decreased colony numbers when compared with untreated control cells. Treatment of HT-29 cells with MMF and MBF caused a distortion of the cell morphology to a shrunken cell mass. Treatment with MMF and MBF also dose-dependently increased nuclear condensation and the formation of apoptotic bodies in HT-29 cells. Treatment with MMF and MBF significantly and dosedependently increased the expression of Bax (a pro-apoptotic protein), caspase-3, and poly ADP-ribose polymerase (PARP) and decreased the expression of Bcl-2 (an anti-apoptotic protein). MMF significantly and dose-dependently inhibited cell proliferation induced by bisphenol A, an environmental hormone. Therefore, MMF may have potential use as a functional food and as a possible therapeutic agent for the prevention of colon cancer.

• Journal of Life Science
• /
• v.29 no.11
• /
• pp.1173-1178
• /
• 2019

The purpose of this study was to isolate an agar-degrading marine bacterium and characterize its agarase. Bacterium BK-1, from Gwanganri Beach at Busan, Korea, was isolated on Marine 2216 agar medium and identified as Agarivorans sp. BK-1 by 16S rRNA gene sequencing. The extracellular agarase, characterized after dialysis of culture broth, showed maximum activity at pH 6.0 and $50^{\circ}C$ in 20 mM Tris-HCl buffer. Relative activities at 20, 30, 40, 50, 60, and $70^{\circ}C$ were 67, 93, 97, 100, 58, and 52%, respectively. Relative activities at pH 5, 6, 7, and 8 were 59, 100, 95, and 91%, respectively. More than 90% of the activity remained after a 2 hr exposure to 20, 30, or $40^{\circ}C$; about 60% of the activity remained after a 2 hr exposure to $50^{\circ}C$. Almost all activity was lost after exposure to 60 or $70^{\circ}C$ for 30 min. Zymography revealed three agarases with molecular weights of 110, 90, and 55 kDa. Agarose was degraded to neoagarobiose (46.8%), neoagarotetraose (39.7%), and neoagarohexaose (13.5%), confirming the agarase of Agarivorans sp. BK-1 as a ${\beta}$-agarase. The neoagarooligosaccharides generated by this agarase could be used for moisturizing, bacterial growth inhibition, skin whitening, food treatments, cosmetics, and delaying starch degradation.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.64 no.3
• /
• pp.204-212
• /
• 2019

The optimal application rate of a controlled release fertilizer (CRF) on the growth, yield, and seeding time of rice grown on seedling trays was investigated. The experimental field was located at $37^{\circ}22^{\prime}10^{{\prime}{\prime}}N$ latitude and $127^{\circ}03^{\prime}85^{{\prime}{\prime}}E$ longitude in Hwaseong, Gyeonggi-do, Republic of Korea. The soil in the paddy field was a clay loam. The CRF used in the experiment contained $300g\;kg^{-1}$ of nitrogen, $60g\;kg^{-1}$ of phosphate, and $60g\;kg^{-1}$ of potassium, respectively. The CRF was applied at the rate of 0, 200, 300, 400, 500, and 600 grams on rice seedling tray compared with the field application based on soil testing (control), respectively. The CRF can be applied as single application(which can replace basal fertilizer application and two top dressing application) directly to the seedling tray, and showed the minimum release at the seedling period. Considering the plant growth, nitrogen use efficency and yield of rice, the optimal application rate of developed CRF was 500 g per seedling tray and the yield of rice at this application rate was $4.92{\sim}5.04Mg\;ha^{-1}$. The regression formula between the rice yield and application rates of CRF was as follows ; "$Y=0.0002{\chi}^2+0.0963{\chi}+411.6$($R^2$ : 0.9922) in 2010 and $Y=8E-6{\chi}^2+0.2723{\chi}+344.04$($R^2$:0.9864) in 2011, Y : Rice yield ($Mg\;ha^{-1}$), ${\chi}$ : Application rate (grams) of controlled release fertilizer". The optimum application rates of CRF per rice seedling tray by regression formula was 498 grams in 2010 and 513 grams in 2011.

• Korean Journal of Plant Resources
• /
• v.32 no.4
• /
• pp.255-263
• /
• 2019

Glycyrrhizae radix is one of the most frequently prescribed ingredients in Oriental medicine, and Glycyrrhizae radix extract has been shown to exert anti-cancer effects. However, the cellular and molecular mechanisms of programed cell death (apoptosis) by Glycyrrhizae radix are poorly defined. In the present study, it was examined the molecular mechanisms of apoptosis by water extracts of Glycyrrhizae radix (GRW) in human bladder T24 cancer cells. It was found that GRW could inhibit the cell growth of T24 cells in a concentration-dependent manner, which was associated with the induction of apoptotic cell death, as evidenced by the formation of apoptotic bodies, DNA fragmentation and increased populations of annexin-V positive cells. The induction of apoptotic cell death by GRW was connected with an up-regulation of pro-apoptotic Bax protein expression and down-regulation of anti-apoptotic proteins (Bcl-2 and Bcl-xL), and inhibition of apoptosis family proteins (XIAP, cIAP-1 and cIAP-2). In addition, apoptosis-inducing concentrations of GRW induced the activation of caspase-9, an initiator caspase of the mitochondrial-mediated intrinsic pathway, and caspase-3, accompanied by proteolytic degradation of PARP. GRW also induced apoptosis via a death receptor-mediated extrinsic pathway by caspase-8 activation, resulting in the down-regulation of total Bid and suggesting the existence of cross-talk between the extrinsic and intrinsic pathways. Taken together, the present results suggest that GRW may be a potential chemotherapeutic agent for the control of human bladder cancer cells.