• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.145-154
• /
• 2022

Automatic Target Recognition (ATR) technology is emerging as a core technology of Future Combat Systems (FCS). Conventional ATR is performed based on IMINT (image information) collected from the SAR sensor, and various image-based deep learning models are used. However, with the development of IT and sensing technology, even though data/information related to ATR is expanding to HUMINT (human information) and SIGINT (signal information), ATR still contains image oriented IMINT data only is being used. In complex and diversified battlefield situations, it is difficult to guarantee high-level ATR accuracy and generalization performance with image data alone. Therefore, we propose a knowledge graph-based ATR method that can utilize image and text data simultaneously in this paper. The main idea of the knowledge graph and deep model-based ATR method is to convert the ATR image and text into graphs according to the characteristics of each data, align it to the knowledge graph, and connect the heterogeneous ATR data through the knowledge graph. In order to convert the ATR image into a graph, an object-tag graph consisting of object tags as nodes is generated from the image by using the pre-trained image object recognition model and the vocabulary of the knowledge graph. On the other hand, the ATR text uses the pre-trained language model, TF-IDF, co-occurrence word graph, and the vocabulary of knowledge graph to generate a word graph composed of nodes with key vocabulary for the ATR. The generated two types of graphs are connected to the knowledge graph using the entity alignment model for improvement of the ATR performance from images and texts. To prove the superiority of the proposed method, 227 documents from web documents and 61,714 RDF triples from dbpedia were collected, and comparison experiments were performed on precision, recall, and f1-score in a perspective of the entity alignment..

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.191-203
• /
• 2022

In this paper, we developed a system that intelligently identifies skin image data from big data collected from social media Instagram and extracts standardized skin sample data for skin condition diagnosis and management. The system proposed in this paper consists of big data collection and analysis stage, skin image analysis stage, training data preparation stage, artificial neural network training stage, and skin image identification stage. In the big data collection and analysis stage, big data is collected from Instagram and image information for skin condition diagnosis and management is stored as an analysis result. In the skin image analysis stage, the evaluation and analysis results of the skin image are obtained using a traditional image processing technique. In the training data preparation stage, the training data were prepared by extracting the skin sample data from the skin image analysis result. And in the artificial neural network training stage, an artificial neural network AnnSampleSkin that intelligently predicts the skin image type using this training data was built up, and the model was completed through training. In the skin image identification step, skin samples are extracted from images collected from social media, and the image type prediction results of the trained artificial neural network AnnSampleSkin are integrated to intelligently identify the final skin image type. The skin image identification method proposed in this paper shows explain high skin image identification accuracy of about 92% or more, and can provide standardized skin sample image big data. The extracted skin sample set is expected to be used as standardized skin image data that is very efficient and useful for diagnosing and managing skin conditions.

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.356-365
• /
• 2022

Agrivoltaic systems, also called solar sharing, stated from an idea that utilizes sunlight above the light saturation point of crops for power generation using solar panels. The agrivoltaic systems are expected to reduce the incident solar radiation, the consequent surface cooling effect, and evapotranspiration, and bring additional income to farms through solar power generation by combining crops with solar photovoltaics. In this study, to evaluate if agrivoltaic systems are suitable for viticulture, we investigated the microclimatic change, the growth of vines and the characteristics of grape grown under solar panels set by planting lines compared with ones in open vineyards. There was high reduction of wind speed during over-wintering season, and low soil temperature under solar panel compared to those in the open field. There was not significant difference in total carbohydrates and bud burst in bearing mother branches between plots. Despite high content of chlorophyll in vines grown under panels, there is no significant difference in shoot growth of vines, berry weight, cluster weight, total soluble solid content and acidity of berries, and anthocyanin content of berry skins in harvested grapes in vineyards under panels and open vineyards. It was observed that harvesting season was delayed by 7-10 days due to late skin coloration in grapes grown in vineyards under panels compared to ones grown in open vineyards. The results from this study would be used as data required in development of viticulture system under panel in the future and further study for evaluating the influence of agrivoltaic system on production of crops including grapes.

• Korean Journal of Poultry Science
• /
• v.48 no.2
• /
• pp.91-100
• /
• 2021

The study determined the effects of stock density (SD) and energy level (EL) on growth performance, serum biochemistry, and meat quality in Korean native chickens. A total of 240 chickens were randomly assigned to one of the four treatments including two stock density (low, 14, and high, 16 chickens per m²) and two energy level (low, 2,950, 3,000, 3050 ME kcal/kg, and high 3,150, 3,200, 3,250 ME kcal/kg, for starter, grower, and finisher, respectively). During the whole period of the experiment, the chickens were fed ad libitum. The greater final body weight and weight gain were achieved in chickens fed high energy diet, whereas the final body weight and weight gain were significantly reduced in high-density treatment compared with the low density. Chickens in low-density groups had a higher feed intake compared with high-density treatment, however, the energy level did not affect the feed intake. An improved overall feed conversion ratio was detected in the high energy treatment. There was a significant interaction between stock density and energy level on cholesterol concentration. The concentration of aspartate transaminase in serum was increased by higher stock density. There was a significant treatment interaction on IgM levels. Moreover, the carcass rate was significantly increased in the high energy level treatment. Based on the findings, we suggest that rearing chickens in low density with high dietary energy levels could be beneficial by improving the growth performance.

• Korean Journal of Poultry Science
• /
• v.48 no.2
• /
• pp.69-80
• /
• 2021

We conducted a 4 × 4 diallel cross-mating test using 934 chickens from four grandparent stock lines to develop a new synthetic breed of Korean native chicken. The mean values, combining ability, and reciprocal effects on survival rate, body weight, and hen-day egg production were analyzed. In phenotypes, most chickens have yellowish-brown, reddish-brown and mixed color feathers. The average survival rate was 86.8±12.3%, with the highest in YH combination. Specific combining ability (SCA) had a greater effect on survival rate than general combining ability (GCA), and the SCA of HY combination was the highest. The 16 cross-combinations were distinctly divided into three weight groups according to their genetic characteristics. At 12 weeks of age, GCA showed a greater effect on weight than SCA, and the SCA of FH combination was the highest. The age at first egg laying was 157 days, and the crosses reached sexual maturity faster than the pure lines. The egg production rate was highest in SY at 79.5±2.1%. The GCA and SCA for hen-day egg production were similar, and the SCA was highest in the HS and FY combinations. The reciprocal effect showed that the offspring's egg production rate was high when S and Y were maternal parents in almost all combinations. In conclusion, FH and HF combinations, which have excellent growth performance, are the most desirable paternal parent stock strains, and FY, FS, HY, and SY combinations, which have excellent laying performance with moderate weight, are the preferred maternal strains.

• Journal of Popular Narrative
• /
• v.26 no.4
• /
• pp.43-76
• /
• 2020

After comparing three video dramas based on Yoon Sim-duk and Kim Woo-jin, this paper intensively explores the movie Praise of Death(1991), which has the most meaningful traits in embodying the characters, focusing on the relationship with the previous works of the director or an actress. The movie Yoon Sim-duk(1969) focuses on meiodramatic narrative around the issue like love triangle or a relationship between out-of-wedlock woman and the wife of one man. The TV drama Praise of Death(2018) is pursuing ideal youth genre between attractive two lovers adorning even the suffering of the Japanese occupation with customary visual image. In comparison, the movie Praise of Death(1991) focuses on visual beauty, while overlaps the agony of two characters as pioneering artists with frustrated love narrative. In the process, this film reveals two-sided characteristics, especially the heroine, compared to the other two. She shows a rift between the passivity for the salvation of man and the activity of choosing even the fall of her own life. In order to examine this trait, we have to explore the other works which affect the movie Praise of Death. This came from the tendency director Kim Ho-sun and actress Jang Mi-hee had built in 1970s films. It also relates in the movies Jang Mi-hee had worked with director bae Chang-ho in the 1980s. The tendency to show a pursuit of classical cultures in the field of popular movies, and to overlap the problems of desire, including sexuality, with mental and intellectual issues, continues from the previous films to the movie Praise of Death for shaping a main female character. This study results in examining the movie Praise of Death in two contexts. One is the context of three video dramas having same materials, Yoon Sim-duk and Kim Woo-jin. And other is the context of the works that director Kim Ho-sun and actress Jang Mi-hee have continued together, or the works that Jang Mi-hee have continued with director Bae Chang-ho. Until now, Yoon Sim-duk and Kim Woo-jin has been used as a material for cultural contents in the various genres over and over again. Under this circumstance, by looking at this movie, one of representative case dealing with Yoon and Kim, in the complex context, it can reaffirm the effect and difficulty in fictionalisation of them as a subject matter.

• Journal of Popular Narrative
• /
• v.27 no.2
• /
• pp.215-262
• /
• 2021

This thesis focuses on Wandeuki and Elegant Lies - novels written by Kim Ryeo-reong and adapted into the film by Director Lee Han; this thesis analyzes the process of storytelling being transformed as the media is converted. Also, this thesis discusses cultural-political implications of transmedia storytelling where different narrative responses coexist concerning post-IMF family disorganization and "individualization." First of all, this thesis critically reviews existing discourses on the concept of transmedia storytelling and refers to 'transfictionality' the narratological concept of Marie-Laure Ryan in order to look into media conversion storytelling that starts from original novels. The novels Wandeuki and Elegant Lies show two aspects of "individualization" that adopts existential conditions of family disorganization. Wandeuki deviates from patriarchal family romance through self-discovery and exhibits loose family bond, which is something similar to companionship of close individuals. Elegant Lies shows individualization of pain by portraying a teenager who found herself completely isolated, while showing that it is impossible for the people left behind to mourn. On the other hand, director Lee Han's films and show stories in which family members, who are confronting family dissolution, rediscover and restore their families against family dissolution. The film promotes the expansion of family community through multicultural identity, and the film completes condolence of the people left behind by having the remaining families survive as survivors of suicide. The storyworld of the novels puts emphasis on 'self-discovery' of individual adolescents, while the storyworld of the movies puts emphasis on 'rediscovery of family'. Through transformation of storytelling - especially the redesigning of narrative structures called "modification" - transmedia storytelling shows that the relationship between media-converted texts is far from "faithful representation," but rather, shows conflicting themes and perspectives. With a reference point of 'the emergence of character' transmedia storytelling, which is predicated on the original work but aims to free itself from the original work by transforming storytelling through media conversion, opens up polyphonic storyworld by creating heterogeneous voices. In the post IMF-era, where uncertainty mounts over family dissolution and individualization, polyphonic storyworld created by transmedia storytelling provides an opportunity to experience disparate desires over individual freedom/risk and complacency toward community. We can call this the cultural-political implication of transmedia storytelling based on transferring, transcednding, and transforming.

• Korean Journal of Psychosomatic Medicine
• /
• v.29 no.2
• /
• pp.111-120
• /
• 2021

Objectives : Shift work has been known to cause various health problems by making it difficult for humans to adapt to their natural circadian rhythms. In particular, shift workers tend to complain of sleep difficulties associated with work schedules, and sometimes use alcohol as a self-medication to induce sleep. To date, no clear mechanism has been identified regarding the link between shift work and sleep, between shift work and drinking. This study aims to confirm the relationship between shift work and sleep, and to analyze whether the change in sleep caused by shift work causes drinking. Methods : This study included 11360 people (5704 men and 5656 women) among the Korean National Health and Nutrition Survey data in 2014, 2016 and 2018. The work type between 6am-6pm was defined as day work, and other work types were defined as shift work. Using logistic regression analysis, the relationship between shift work and sleep quality, shift work and high risk drinking, drinking amount at 1 time, drinking frequency were analyzed. In addition, we analyzed whether sleep mediates the relationship between shift work and drinking using mediated analysis. Results : Shift work showed a significant negative relationship with sleep quality in men and women (male OR=1.37, 95% CI 1.11-1.70, female OR=1.26, 95% CI=1.05-1.50). There was no significant relationship between shift work and alcohol in the case of men, but in the case of women, there was a significant positive relationship between shift work and the number of alcohol consumption (OR=1.34, 95% CI=1.04-1.72). When mediation analysis was conducted, it was found that women's sleep quality partially mediated the relationship between shift work and the frequency of drinking. Conclusions : The results of this study suggest that shift work causes sleep difficulties, and in the case of women, drinking can be induced through the partial mediating effect of sleep. Considering that women are more likely to choose drinking as a coping method for sleep problems, more active interventions for female shift workers are needed.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.218-233
• /
• 2022

The long-term (1986~2020) predictability of the number of days of heat and cold damages for each growth stage of soybean is evaluated using the daily maximum and minimum temperature (Tmax and Tmin) data produced by Pusan National University Coupled General Circulation Model (PNU CGCM)-Weather Research and Forecasting (WRF). The Predictability evaluation methods for the number of days of damages are Normalized Standard Deviations (NSD), Root Mean Square Error (RMSE), Hit Rate (HR), and Heidke Skill Score (HSS). First, we verified the simulation performance of the Tmax and Tmin, which are the variables that define the heat and cold damages of soybean. As a result, although there are some differences depending on the month starting with initial conditions from January (01RUN) to May (05RUN), the result after a systematic bias correction by the Variance Scaling method is similar to the observation compared to the bias-uncorrected one. The simulation performance for correction Tmax and Tmin from March to October is overall high in the results (ENS) averaged by applying the Simple Composite Method (SCM) from 01RUN to 05RUN. In addition, the model well simulates the regional patterns and characteristics of the number of days of heat and cold damages by according to the growth stages of soybean, compared with observations. In ENS, HR and HSS for heat damage (cold damage) of soybean have ranged from 0.45~0.75, 0.02~0.10 (0.49~0.76, -0.04~0.11) during each growth stage. In conclusion, 01RUN~05RUN and ENS of PNU CGCM-WRF Chain have the reasonable performance to predict heat and cold damages for each growth stage of soybean in South Korea.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.4
• /
• pp.94-106
• /
• 2022

In order to increase timber self-sufficiency, Korea's 6th Basic Forest Plan aims to increase the density of forest roads to 12.8 m ha^-1 by 2037. However, due to rapid re-forestation, current management infrastructure is insufficient, with just 4.8 m ha^-1 of forest roads in 2017. This is partly due to time and cost limitations on the process of forest road feasibility evaluation, which considers factors such as topography and forest conditions. To solve this problem, we propose an eco-friendly and efficient forest road network planning method using a geographic information system (GIS), which can evaluate a potential road site remotely based on spatial information. To facilitate such planning, this study identifies forest road construction priorities that can be evaluated using spatial information, such as topography, forest type and forest disasters. A method of predicting the optimal route to connect a forest road with existing roads is also derived. Overlapping analysis was performed using GIS-MCE (which combines GIS with multi-criteria evaluation), targeting the areas of Cheongsong-gun and Buk-gu, Pohang-si, which have a low forest-road density. Each factor affecting the suitability of a proposed new forest road site was assigned a cost, creating a cost surface that facilitates prioritization for each forest type. The forest path's optimal route was then derived using least-cost path analysis. The results of this process were 30 forestry site recommendations in Cheongsong-gun and one in Buk-gu, Pohang-si; this would increase forest road density for the managed forest sites in Cheongsong-gun from 1.58 m ha^-1 to 2.55 m ha^-1. This evaluation method can contribute to the policy of increasing timber self-sufficiency by providing clear guidelines for selecting forest road construction sites and predicting optimal connections to the existing road network.