• Korean Journal of Plant Taxonomy
• /
• v.48 no.4
• /
• pp.249-259
• /
• 2018

$Iso{\ddot{e}}tes$ L. ($Iso{\ddot{e}}taceae$) is a cosmopolitan genus of heterosporous lycopods containing ca. 200 species being found in lakes, streams, and wetlands of terrestrial habitats. Despite its ancient origin, worldwide distribution, and adaptation to diverse environment, species in $Iso{\ddot{e}}tes$ show remarkable morphological simplicity and convergence. Allopolyploidy appears to be a significant speciation process in the genus. These characteristics have made it difficult to assess the phylogenetic relationships and biogeographic history of $Iso{\ddot{e}}tes$ species. In recent years, these difficulties have somewhat been reduced by employing multiple molecular markers. Here, we reconstruct the phylogenetic relationships in East Asian $Iso{\ddot{e}}tes$ species. We also provide their divergence time and biogeographic origin using a fossil calibrated chronogram. East Asian $Iso{\ddot{e}}tes$ species are divided into two clades: I. asiatica and the remaining species. $Iso{\ddot{e}}tes$ asiatica from Hokkaido forms a clade with northeastern Russian and western North American $Iso{\ddot{e}}tes$ species. In clade I, western North America is the source area for the dispersal of $Iso{\ddot{e}}tes$ to Hokkaido and northeastern Russia via the Bering land bridge during the late Miocene. The remaining $Iso{\ddot{e}}tes$ species (I. sinensis, I. yunguiensis, I. hypsophila, I. orientalis, I. japonica, I. coreana, I. taiwanensis, I. jejuensis, I. hallasanensis) from East Asia form a sister group to Papua New Guinean and Australian species. The biogeographic reconstruction suggests an Australian origin for the East Asian species that arose through long-distance dispersal during the late Oligocene.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.19-41
• /
• 2019

According to the rapidly increasing demand for text data analysis, research and investment in text mining are being actively conducted not only in academia but also in various industries. Text mining is generally conducted in two steps. In the first step, the text of the collected document is tokenized and structured to convert the original document into a computer-readable form. In the second step, tasks such as document classification, clustering, and topic modeling are conducted according to the purpose of analysis. Until recently, text mining-related studies have been focused on the application of the second steps, such as document classification, clustering, and topic modeling. However, with the discovery that the text structuring process substantially influences the quality of the analysis results, various embedding methods have actively been studied to improve the quality of analysis results by preserving the meaning of words and documents in the process of representing text data as vectors. Unlike structured data, which can be directly applied to a variety of operations and traditional analysis techniques, Unstructured text should be preceded by a structuring task that transforms the original document into a form that the computer can understand before analysis. It is called "Embedding" that arbitrary objects are mapped to a specific dimension space while maintaining algebraic properties for structuring the text data. Recently, attempts have been made to embed not only words but also sentences, paragraphs, and entire documents in various aspects. Particularly, with the demand for analysis of document embedding increases rapidly, many algorithms have been developed to support it. Among them, doc2Vec which extends word2Vec and embeds each document into one vector is most widely used. However, the traditional document embedding method represented by doc2Vec generates a vector for each document using the whole corpus included in the document. This causes a limit that the document vector is affected by not only core words but also miscellaneous words. Additionally, the traditional document embedding schemes usually map each document into a single corresponding vector. Therefore, it is difficult to represent a complex document with multiple subjects into a single vector accurately using the traditional approach. In this paper, we propose a new multi-vector document embedding method to overcome these limitations of the traditional document embedding methods. This study targets documents that explicitly separate body content and keywords. In the case of a document without keywords, this method can be applied after extract keywords through various analysis methods. However, since this is not the core subject of the proposed method, we introduce the process of applying the proposed method to documents that predefine keywords in the text. The proposed method consists of (1) Parsing, (2) Word Embedding, (3) Keyword Vector Extraction, (4) Keyword Clustering, and (5) Multiple-Vector Generation. The specific process is as follows. all text in a document is tokenized and each token is represented as a vector having N-dimensional real value through word embedding. After that, to overcome the limitations of the traditional document embedding method that is affected by not only the core word but also the miscellaneous words, vectors corresponding to the keywords of each document are extracted and make up sets of keyword vector for each document. Next, clustering is conducted on a set of keywords for each document to identify multiple subjects included in the document. Finally, a Multi-vector is generated from vectors of keywords constituting each cluster. The experiments for 3.147 academic papers revealed that the single vector-based traditional approach cannot properly map complex documents because of interference among subjects in each vector. With the proposed multi-vector based method, we ascertained that complex documents can be vectorized more accurately by eliminating the interference among subjects.

• 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 the Korea Organic Resources Recycling Association
• /
• v.28 no.4
• /
• pp.53-68
• /
• 2020

The concentrations of ammonia, hydrogen sulfide and fine dust were measured in the compost facility of a full-time Hanwoo breeding farms. The experiments were conducted in stack type composting facility(T1) and mechanical-stirred composting facilities(T2, T3). In the stack type composting facility, the highest temperature of compost pile was 46℃, and in the two mechanical-stirred composting facilities, it rose to 63℃ and 68℃, respectively. The concentrations of PM2.5 at T1, T2 were 15 ㎍/㎥ and 5~10 ㎍/㎥, respectively. And the concentration of PM2.5 at T3 was below 10 ㎍/㎥. The highest concentration of ammonia generated at T1 was 4 ppm, but no hydrogen sulfide was detected. The ammonia concentrations at T2 and T3 were 3 ppm and 4 ppm, respectively. However, hydrogen sulfide was not detected in both facilities. At T3, the ammonia concentration increased to 65 ppm at the point where the compost was stirred with a mechanical agitator. During composting period, the pH of the compost pile decreased from 9.06 to 8.94 and then increased to 9.14 as the composting period elapsed. The NaCl content of compost was 0.09% after composting process was complete. Moisture content of compost decreased from 65.9% to 62% as composting progressed. As composting proceeded, the content of volatile solids decreased from 65.6% to 64.7% and the content of TKN decreased from 1.327% to 1.095%.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.187-195
• /
• 2021

Nam Nong Heo Geon(1908-1987) re-recognized and re-created the tradition of Korean Namjong painting by excluding Japanese art forms after liberation. He is a great painter in the Korean art world, who has succeeded and developed Korean Namjong Painting in a modern way, pioneering a new field of 'NewNamhwa' with a composition that fuses modern Western style and real scenery. Based on optimism, Namnong's painting world can be divided into three periods: the 'Namnong Sanin' period in the 1930s, the 'Namnongoesa' period from the mid-1940s to the early 1950s, and the 'the owner of Unlimsanbang' period after that. The Namnong Sanin period is a period in which the painting style handed down from the traditional namhwau family of Sochi and Misan is fully acquired, and the Japanese painting style for the exhibition in Seonjeon is reflected, and the local real scenery is treated a lot, and the two styles are mixed. In the Namnong-oesa period, after liberation, a new formativeness was explored in the traditional Namhwa style. In particular, based on the scenery and sentiments of the southern provinces, he focused on local and landscape paintings, depicting real landscapes with lyricism and local love, while expressing subjects with fast brush strokes, a worndown writing brush, and dry brushes, along with freehand adjustment of shading. The period of the owner of unlimsanbang is in accordance with the flow of modern art to some extent, but is gradually omitted as a composition full of academic fragrance that draws a meaning befitting traditional painting. I painted a lot of lyrical landscapes and pine trees of sumugdamchae. Namnong named it 'NewNamhwa'. Namnong established 'Namhwa Research Institute' and worked hard to nurture his disciples, where Im-in's son Heomun and Namnong's eldest grandson Heojin practiced, continuing the legacy of the 5th generation Unlimsanbang painter.

• Korean Chemical Engineering Research
• /
• v.60 no.1
• /
• pp.93-99
• /
• 2022

With the rapid development of ultra-small and wearable device technology, continuous electricity supply without spatiotemporal limitations for driving electronic devices is required. Accordingly, Triboelectric nanogenerator (TENG), which utilizes static electricity generated by the contact and separation of two different materials, is being used as a means of effectively harvesting various types of energy dispersed without complex processes and designs due to its simple principle. However, to apply the TENG to real life, it is necessary to increase the electrical output. In addition, stable generation of electrical output, as well as increase in electrical output, is a task to be solved for the commercialization of TENG. In this study, we proposed a method to not only improve the output of TENG but also to stably represent the improved output. This was solved by using the contact layer, which is one of the components of TENG, as an electret for improved output and stability. The utilized electret was manufactured by sequentially performing corona charging-thermal annealing-corona charging on the Fluorinated ethylene propylene (FEP) film. Electric charges artificially injected due to corona charging enter a deep trap through the thermal annealing, so an electret that minimizes charge escape was fabricated and used in TENG. The output performance of the manufactured electret was verified by measuring the voltage output of the TENG in vertical contact separation mode, and the electret treated to the corona charging showed an output voltage 12 times higher than that of the pristine FEP film. The time and humidity stability of the electret was confirmed by measuring the output voltage of the TENG after exposing the electret to a general external environment and extreme humidity environment. In addition, it was shown that it can be applied to real-life by operating the LED by applying an electret to the clap-TENG with the motif of clap.

• Journal of the Korean Institute of Gas
• /
• v.26 no.3
• /
• pp.45-53
• /
• 2022

In order to improve the emission of diesel engines, natural gas-diesel dual fuel combustion compression ignition engines are in the spotlight. In particular, a reactivity controlled compression ignition (RCCI) combustion strategy is investigated comprehensively due to its possibility to improve both efficiency and emissions. With advanced diesel direct injection timing earlier than TDC, it achieves spontaneous reaction with overall lean mixture from a homogeneous mixture in the entire cylinder area, reducing nitrogen oxides (NOx) and particulate matter (PM) and improving braking heat efficiency at the same time. However, there is a disadvantage in that the amount of incomplete combustion increases in a low load region with a relatively small amount of fuel-air. To solve this, sensitive control according to the diesel injection timing and fuel ratio is required. In this study, experiments were conducted to improve efficiency and exhaust emissions of the natural gas-diesel dual fuel engine at low load, and evaluate combustion stability according to the diesel injection timing at the operation point for power generation. A 6 L-class commercial diesel engine was used for the experiment which was conducted under a 50% load range (~50 kW) at 1,800 rpm. Two injectors with different spray patterns were applied to the experiment, and the fraction of natural gas and diesel injection timing were selected as main parameters. Based on the experimental results, it was confirmed that the brake thermal efficiency increased by up to 1.3%p in the modified injector with the narrow-angle injection added. In addition, the spray pattern of the modified injector was suitable for premixed combustion, increasing operable range in consideration of combustion instability, torque reduction, and emissions level under Tier-V level (0.4 g/kWh for NOx).

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.707-723
• /
• 2022

Although satellite-based sea surface temperature (SST) is advantageous for monitoring large areas, spatiotemporal data gaps frequently occur due to various environmental or mechanical causes. Thus, it is crucial to fill in the gaps to maximize its usability. In this study, daily SST composite fields with a resolution of 4 km were produced through a two-step machine learning approach using polar-orbiting and geostationary satellite SST data. The first step was SST reconstruction based on Data Interpolate Convolutional AutoEncoder (DINCAE) using multi-satellite-derived SST data. The second step improved the reconstructed SST targeting in situ measurements based on light gradient boosting machine (LGBM) to finally produce daily SST composite fields. The DINCAE model was validated using random masks for 50 days, whereas the LGBM model was evaluated using leave-one-year-out cross-validation (LOYOCV). The SST reconstruction accuracy was high, resulting in R² of 0.98, and a root-mean-square-error (RMSE) of 0.97℃. The accuracy increase by the second step was also high when compared to in situ measurements, resulting in an RMSE decrease of 0.21-0.29℃ and an MAE decrease of 0.17-0.24℃. The SST composite fields generated using all in situ data in this study were comparable with the existing data assimilated SST composite fields. In addition, the LGBM model in the second step greatly reduced the overfitting, which was reported as a limitation in the previous study that used random forest. The spatial distribution of the corrected SST was similar to those of existing high resolution SST composite fields, revealing that spatial details of oceanic phenomena such as fronts, eddies and SST gradients were well simulated. This research demonstrated the potential to produce high resolution seamless SST composite fields using multi-satellite data and artificial intelligence.

• Journal of Popular Narrative
• /
• v.26 no.3
• /
• pp.161-188
• /
• 2020

This paper seeks to expand the scale of literary history by restoring and analyzing the whole aspect of Kwak Hashin's works, which has so far been studied little. For this purpose, I notice the rupture of discontinuity of his works which is greatly divided into the colonial period and post Korean war period. And the characteristics of each works can be analyzed based on the three axis, local(colonial period), jobless person(post-war period), and Homo Economicus(some short stories, and popular novels in post-war period). In Chapter 2, 'Local-the world of Munjang', I evaluated that Kwak Hashin's novel, which had been published in the late 1930s in the Journal of Munjang, embodied anti-modern aesthetic consciousness, as clearly revealing the sorrow for disappearing things, the pre-modern sense of time, and the preference for local. In Chapter 3, 'Jobless Person' and Chapter 4, 'The State of All People's Struggle against All People, The Appearance of Homo Economicus', the Korean society in late 1950s, which entered underdeveloped capitalist countries after Korean war, can be characterized by two contrasting male-gender, one is the jobless, incompetent male, and the economic man on the other hand. In the late '50s, Lumpen(=Jobless Person) novels showed the problems of the Korean economy through incompetent male character. The intelligent men took the path to survival rather than morality or intimacy, projecting their own incompetence and anxiety to women/wives. In the popular novels Women's Song and The Shadow of the Fig Tree, achievement-oriented male figures who betrayed their colleagues, and exploited women's sex by using love relationships to rise to the top appeared. They can be defined as the Homo Economicus who embody the state of universal struggle against all people. These novels showed the formation of the masculinity in post Korean war period, which pursued the survival of the fittest, borrowing form of popular novel. As we have seen so far, Kwak Hashin needs to be re-evaluated as an writer who expanded the modern literary history in the outside of literature. He was the last generation writer written in Korean late colonial period, and provided the model of postwar literature by borrowing the form of journalism and popular novels.