• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.1
• /
• pp.49-63
• /
• 2016

In this study, we analyzed the effects of regional hydrologic variability during warm season (June-September) in South Korea due to ENSO (El $Ni{\tilde{n}}o$-Southern Oscillation) pattern changes over the Tropical Pacific Ocean (TPO). We performed composite analysis (CA) and statistical significance test by Student's t-test using observed hydrologic data (such as, precipitation and streamflow) in the 113 sub-watershed areas over the 5-Major River basin, in South Korea. As a result of this study, during the warm-pool (WP) El $Ni{\tilde{n}}o$ year shows a significant increasing tendency than normal years. Particularly, during the cold-tongue (CT) El $Ni{\tilde{n}}o$ decaying years clearly decreasing tendency compared to the normal years was appeared. In addition, the La $Ni{\tilde{n}}a$ years tended to show a slightly increasing tendency and maintain the average year state. In addition, from the result of scatter plot of the percentage anomaly of hydrologic variables during warm season, it is possible to identify the linear increasing tendency. Also the center of the scatter plot shows during the WP El $Ni{\tilde{n}}o$ year (+17.93%, +26.99%), the CT El $Ni{\tilde{n}}a$ year (-8.20%, -15.73%), and the La $Ni{\tilde{n}}a$ year (+8.89%, +15.85%), respectively. This result shows a methodology of the tele-connection based long-range water resources prediction for reducing climate forecasting uncertainty, when occurs the abnormal SSTA (such as, El $Ni{\tilde{n}}o$ and La $Ni{\tilde{n}}a$) phenomenon in the TPO region. Furthermore, it can be a useful data for water managers and end-users to support long-range water-related policy making.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.25 no.4
• /
• pp.375-390
• /
• 2009

Statement of problem: Implant supported overdenture is accepted widely as a way to restore edentulous ridge providing better retention and support of dentures. Various types of attachment for overdenture have been developed. Purpose: The purpose of this study was to investigate the influence of attachment type in implant overdentures on the biomechanical stress distribution in the surrounding bone, prosthesis and interface between implant and bone. Material and methods: Finite element analysis method was used. Average CT image of mandibular body(Digital $Korea^{(R)}$, KISTI, Korea) was used to produce a mandibular model. Overdentures were placed instead of mandibular teeth and 2mm of mucosa was inserted between the overdenture and mandible. Two implants($USII^{(R)}$, Osstem, Korea) were placed at both cuspid area and 4 types of overdenture were fabricated ; ball and socket, Locator, magnet and bar type. Load was applied on the from second premolar to second molar tooth area. 6 times of finite element analyses were performed according to the direction of the force $90^{\circ}$, $45^{\circ}$, $0^{\circ}$ and unilateral or bilateral force applied. The stress at interface between implants and bone, and prosthesis and the bone around implants ware compared using von Mises stress. The results were explained with color coded graphs based on the equivalent stress to distinguish the force distribution pattern and the site of maximum stress concentration. Results: Unilateral loading showed that connection area between implant fixture and bar generated maximum stress in bar type overdentures. Bar type produced 100 Mpa which means the most among 4 types of attachments. Bilateral loading, however, showed that bar type was more stable than other implants(magnet, ball and socket). 26 Mpa of bar type was about a half of other types on overdenture under $90^{\circ}$ bilateral loading. Conclusions: In any directions of stress, bar type was proved to be the most vulnerable type in both implants and overdentures. Interface stress did not show any significant difference in stress distribution pattern.

• Korea journal of population studies
• /
• v.11 no.2
• /
• pp.54-66
• /
• 1988

I. Introduction Since the 1970's drug abuse among young people has increasingly become a social problem in Korea. In the 1980's, drug abuse, especially glue sniffing, has become the cause of many unfortunated incidents resulting in harm to others as well as the abusers themselves. Taking into consideration of the seriousness of this problem, the Republic of Korea National Red Cross initiated a nation-wide research programme, to understand the present situation and to raise the level of public awareness. The goal of this research was to begin a nation - wide campaign against drug abuse. The research team was composed of the Advisary Committee members and the staff of the Youth Department of the Republic of Korea National Red Cross. The data were collected in February 1988 with the collaboration of the staff and volunteers in the local Chapters. The respondents were allocated nation-wide by the quota sampling method. The questionnaires were distributed to the respondents in three groups :2, 700 to junior and senior high school students, 605 to working youths, and 916 to delinquent youths. A total of 4, 221 questionnaires were collected. II. Characteristics of the Respondents The respondents in each group were selected evenly from rural and urban areas. The general characteristics of the respondents can be described as follow: in case of students, the proportions between male and female respondents, and between senior high school and junior high school students were almost evenly distributed. In case of working youths, the proportion of females (80.5%) was higher than those of the students and the delinquents groups. Delinquent youths were defined as those currently being under custody of the centers for juvenile delinquents. Of this number, 38.8% and 68.2% were junior and senior high school drop-outs respectively. The majority of them (92.6%) were male. As for the family background of the respondents, the proportion of those residing in poverty - stricken areas, and the proportion of those from broken families were higher in case of working youths and delinquent youths than those in case of students. III. Present Patterns of Drug Abuse The following summarizes the presents of drug abuse, as tabulated from the results of the survey. 1. Smoking The percentage of youths who smoke was 36% in the student group, 32% m the working youths group, and 94.4% in the delinquent youths group. 2. Alcohol 50.3% of students, 71.6% of working youths, and 93.3% of delinquent youths has experienced drinking alcohol beverages. 3. Tonic: non - alcoholic, caffeinated beverages popular in Korea and Japan The percentage of those who have used tonic at least once was over 90% in all of the three groups. 4. Sedative About 70% of each group has used sedative with the proportion of working youths use higher than those in other groups. 5. Stimulants Those who have used stimulants comprised around 15% in each group. 6. Tranquilizers Somewhat less than 5% of students and working youths, and 28% of delinquent youths, have used tranquilizers. 7. Hypnotics The users of hypnotics amounted to 0.4% of students, 2.6% of working youths and 7.1% of delinquent youths. 8. Marihuana Those who have used marihuana indicated 0.7% of students, 0.8% of working youths, and 13% of delinquent youths. 9. Glue-sniffing The percentage of glue-sniffing was 3.7%, 5% in the students group and in the youths group respectively, but the proportion was unusually high, at 40.7% in the delinquent youths group. From the results of the survey the present situation of drug abuse in Korea can be summarized as follows: 1. A high percentage of Korean youths have experienced smoking cigarettes and drinking alcoholic beverages. 2. Tonics (non - alcoholic, caffeinated beverages), antipyretic analgesics and stimulants quite regularly used. 3. Tranquilizers, hypnotics, marihuana and glue-sniffing are more widely used among delinquent youths than the other youths. From this fact, there exists a correlation between drug abuse and juvenile delinquency. IV. Time-series Analysis of the First Experience of Drug Abuse and Deviant Behaviour The respoundents were asked when they were first exposed to drugs and when they committed deviant acts. By calculating the average age of each experience, the following pattern was found (See Figure 1). Youths are first exposed to drugs by abuse of tonic(non - alcoholic, caffeinated beverages). At the age of 13, they amoke cigarettes, the use of antipyretic analgesics begins at 14 year old, while at the age of 15, they use tranquilizers, and at 16 hynotics. The period of drug abuse which starts from drinking caffeinated beverages and smoking cigarettes and ends in the use of hypnotics takes about three years. During this period, other delinquent behaviours begin to surface, that is, at the age of 13 when smoking cigarettes begins, the delinquent behaviour pattern starts with truancy. Next, they start taking money from others by using physical force. Prior to the age of 15, they are suspended from school, become hostile to adults, begin running away from home, and start using stimulants and alcohol. Soon they become involved even in glue-sniffing and in the use of marihuana. At the age of 15, they begin to see adult videos and carry weapons. Sexual promiscuity and usage of tranquilizers follows the viewing of adult videos. Consequently, by the time they reach the age of 16, they visit drinking establishments, and are picked up by police for committing delinquent acts. And finally, they come to use hypnotic - type drugs. From the above descriptions, drug abuse can be assumed to have a close correlation with delinquent behaviour. V. Social Factors Related to Drug Abuse As for the Korean youths, glue-sniffing is found to he related to aggressive delinquency, in such cases as run - aways, being picked up by the police, and taking money by force. Smoking cigarettes and drinking alcohol is found to be related to seeing adult videos and visiting drinking establishments. Hypnotics and marihuana were found to be representive of drugs which are related to degenerational delinquency, irrespective of social delinquency. The social factors connected with these drug abuse are as follows: 1. Individual factors Male students were more heavily involved in the usage of drug than females. Youths who do not attend church were more likely to be involved in drugs than those who attend. 2. Family factors The youths who were displeased with their mothers smoking and those who thought their parents did not love each other, or those whose parents had used drugs without prescription, were more likely to he drug users. 3. School factors Those youths who found school life boring, were unsuccessful in their studies, spend most of their time with friends, feel their teachers smoke too much, those who had a positive perception of their teachers smoking were likely to he drug users. To sum up, drug abusers depend on the influence of their parents, teachers and peers. IV. Reasons for Drug Abuse Korean students have mainly used drugs to release stress (42.8%), to stay awake (19.7%), and because of the easy accessibility of drugs( 16.6%). Other reasons are due to their ignorance of the side effects of the drugs (3.6%), natural curiosity (4.2%), and to increase strength(3.O%). From the above facts, the major reasons for drug abuse among Korean youths are to release stress and to stay awake in order to prepare exams. Furthermore, since drugs are readily available, we can conclude that drug abuse is caused by the school system(such as entrance exams) in Korea. VII. Conclusion Drug usage among Korean youths are relatively less common than those of western youths. In some cases, such as, glue-sniffing and use of stimulants, the pattern of drug abuse is found. Moreover, early drug abuse is evident, and it has a close connection with deviant behaviour, resulting in juvenile delinquency. Drug abuse cannot be attributed to any one social factor. Specifically, drug abuse depends on parents, peers, teachers and other members of the community, and also is influenced by social institutions such as the entrance exam system. Every person and organization concerned with youth must participate collectively in restraining drug abuse. Finally, it is suggested that social agencial working for youth welfare should make every effort to tackle this serious problem confronted by the Korean youths today.

• Journal of Preventive Medicine and Public Health
• /
• v.27 no.2 s.46
• /
• pp.200-216
• /
• 1994

In present study, the authors investigated the possible effect of coffee consumption on serum cholesterol level in 1017 men between the ages of 40 and 59 years, who were randomly selected from the members of Seoul Cohort Study. Serum total cholesterol data was collected with other serologic indices (e.g. systolic blood pressure, diastolic blood pressure, hight, weight, etc.) through the program of biennial health check-up offered by Korean Medical Insurance Corporation (KMIC). The amount of coffee consumption was assessed by a self-administered questionnaire through mailing. Other confounding factors, such as age, body mass index, cigarette smoking, alcohol consumption, physical activity, and other dietary intake pattern were also determined by the questionnaire. The differences in means of serum total cholesterol in compared to non consumers were $-0.4{\pm}3.56mg/dl$ for those drinking less than 1 cup a day, $-0.6{\pm}3.60mg/dl$ for those drinking 1 cup a day, and $7.1{\pm}3.41mg/dl$ for those drinking more than 2 cups a day. Since smoking interacted the relationship between coffee consumption and serum total choleaterol, we re-analyzed those relationship in smokers and non-smokers separately Other atherogenic behaviors were well correlated with total cholesterol, so we adjusted the mean values of serum total cholesterol through multivariate model selection with age(r=0.12), total cigarette index (cigarette-years; r=0.10), Quetelet's index ($Kg/m^2$, r=0.16), daily calory expenditure (kcal/day, r=0.06), weekly meat and poultry consumption(g/week, r=0.05), weekly fish consumption (g/week, r=0.08), other caffeinated beverage intake (cups/week), and the amount of sugar and prim added to the coffee. Among those variables only age, Quetelet's index, fish consumption, and total cigarette index (in smokers) were remained in the models. After adjustment, the corresponing differences of total cholesterol in smokers were changed to $0.4{\pm}5.24mg/dl,\;-0.5{\pm}4.97mg/dl,\;and\;8.9{\pm}4.78mg/dl$, which were significantly different among themselves (P=0.011). In non-smokers, however, the differences were not statistically significant (P=0.76). Adjusted mean values of systolic blood pressure and diastolic blood pressure were also determined to evaluate the direct effect of coffee to cardiovascular system, but their means were not significantly different by coffee consumption(p=0.18 for SBP, p=0.48 for DBP). Asuming instant coffee in the most popular type of coffee in Korea, the association observed in our study between coffee and serum total cholesterol, especially in smokers, is very interesting finding for the connection between coffee and serum total cholesterol, because only 'boiled coffee' tend to show significant lipid raising effect rather than to other types of coffee, like filtered or espresso, in most of the western countries. We concluded that people who drink coffee more than 2 cups a day have significantly higher serum total cholesterol level than those who never drink coffee, especially in smokers.

• Journal of the Korean Geographical Society
• /
• v.31 no.2
• /
• pp.138-159
• /
• 1996

There has been a tendency for Geomorphology and Climatology to be dominant in Physical Geography for 50 years in Korea. Physical Geography is concerned with the study of the totality of natural environment through the integrated approaches. But, an overall direction or a certain paradigm could not be found, because major sub-divisions of Physical Geography have been studied individually and the subjects and the approaches in studying Physical Geography are enormously diverse. A consensus of opinion could not also exist in deciding what kind of the sub-divisions should be included in the physical geography in general and how those should be summarized. Furthermore it would be considered imprudent to survey the studies of Physical Geography besides those of Geomorphology and Climatology due to the small number of researchers. Assuming that the rest of Physical Geographical studies with the exception of Geomorphological and Climatological studies are the Physical Geography in general, the studies of Physical Geogrpahy in general are summarized and several aspects are drown out as follows. First the descliption of all possible factors of natural environments was the pattern of early studies of Physical Geography and the tendency is maintained in the various kinds of research and project reports. Recently Physical Geographers have published several introductory textbooks or research monographs. In those books, however, the integrated approaches to Physical Geography were not suggested and the relationship between man and nature are dealt with in the elementary level. Second, the authentic soil studies of Physical Geographers are insignificant, because the studies of soil in Physical Geography have been mostly considered as the subsidiary means of Geomorphology Summarizing the studies of Soil Gegraphy by physical geographers and other Pedologists, the subjects are classified as soil-forming processes, soil erosions, soil in the tidal flat and reclaimed land, and soil pollution. Physical Geographers have focused upon the soil-forming processes in order to elucidate the geomorphic processes and the past climatic environment. The results of other subjects are trifling. Thirdy Byogeygrayhers and the results of studies are extremely of small number and the studies of Biogeography in Korea lines in the starting point. But, Biogeography could be a more unifying theme for the Physical-human Geography interface, and it would be expected to play an active part in the field of environmental conservation and resource management. Forth, the studies of Hydrogeography (Geographical Hydrology) in Korea have run through the studies of water balance and the morphometric studies such as the drainage network analysis and the relations of various kinds of morphometric elements in river. Recently, the hydrological model have introduced and developed to predict the flow of sediment, discharge, and ground water. The growth of groundwater studies is worthy of close attention. Finally, the studies on environmental problems was no mole than the general description about environmental destruction, resource development, environmental conservation, etc. until 1970s. The ecological perspectives on the relationship between man and nature were suggested in some studies of natural hazard. The new environmentalism having been introduced since 1980s. Human geographers have lead the studies of Environmental Perception. Environmental Ethics, Environmental Sociology, environmental policy. The Physical geographers have stay out of phase with the climate of the time and concentrate upon the publication of introductory textbooks. Recently, several studies on the human interference and modification of natural environments have been made an attempt in the fields of Geomorphology and climatology. Summarizing the studies of Physical Geography for 50 years in Korea, the integrated approaches inherent in Physical Geography disappeared little by little and the majol sub-divisions of Physical Ceography have develop in connection with the nearby earth sciences such as Geology, Meteorology, Pedology, Biology, Hydrology, etc been rediscovered by non-geographers under the guise of environmental science. It is expected that Physical Geography would revive as the dominant subject to cope with environmental problems, rearming with the innate integrated approaches.

• Korean journal of applied entomology
• /
• v.55 no.4
• /
• pp.329-336
• /
• 2016

Occurrence of oriental corn borer, Ostrinia furnacalis, and yield in a paddy-upland rotation field for 8 maize (Eolrukchal 1, Heugjeom 2, Miheukchal, Ilmichal, Heukjinjuchal, Chalok 4, Mibaek 2, Daehakchal) and 7 sorghum (Hwanggeumchal, Anzunbaengisusu, Moktaksusu, Sodamchal, DS-202, Nampungchal, Donganme) varieties has been surveyed. In a monitoring study using a pheromone trap carried out from 15 May to 10 September, the density of O. furnacalis adults increased rapidly from about 2 weeks after maize planting and reached the highest density at mid June. After that, their density was fluctuated a little at earlier September. The number of the damaged maize and invasive pores on the stem of 2 maizes and sorghum varieties was examined. The mean number of the damaged maize per 20 plants was 19 and 18 plants, and the number of invasive pores was 1.8 and 1.4 per maize stem in Daehakchal and Mibaek 2, respectively. In a survey carried out at harvest period using 8 maize varieties, the damaged ratio was 94%, 92%, 71%, 64%, 54%, 52%, and 45% in Daehakchal, Mibaek 2, Ilmichal, Eolrukchal 1, Chalok 4, Miheukchal, and Heugjeom 2, respectively. The number of invasive pore per Ilmichal stem was 1.4 and that of the others was less than 1.0 per stem. In addition, the damaged ratio of maize ears was 50% in Ilmichal, 40% in Heukjinjuchal, 37% in Daehakchal, etc. The damage pattern of 2 sorghum varieties, Nampungchal and Donganme, by O. furnacalis larvae was steeply increased from planting to 2 months and the trend was continued up to earlier August. At this time, the mean number of damaged sorghum was 13 and 9.2 plants for Nampungchal and Donganme, and the number of invasive stem pores was 1.06 and 0.46, respectively. In another survey carried out at harvest period for 7 sorghum varieties, their damaged ratio was 95% in DS-202, 76% in Moktaksusu, 75% in Sodamchal, 67% in Nampungchal, 57% in Anzunbaengisusu, 46% in Donganme, and 34% in Hwanggeumchal. The damage of sorghum varieties was much higher and severer than that of maizes by O. furnacalis larvae. The number of invasive pores on a sorghum stem was 1.7 in DS-202, 1.4 in Moktaksusu, 1.3 in Sodamchal, 1.1 in Nampungchal, 1.0 in Anzunbaengisusu, 0.5 in Donganme, and 0.4 in Hwanggeumchal. Meanwhile, there was no distinct connection between damaging results and yields of maizes and sorghums by O. furnacalis larvae in a paddy-upland rotation field. These results from this study can be applicable for the establishment of a management strategy to control Oriental corn borer in paddy-upland rotation fields for maize and sorghum.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.959-974
• /
• 2021

Forel-Ule Index (FUI) is an index which classifies the colors of inland and seawater exist in nature into 21 gradesranging from indigo blue to cola brown. FUI has been analyzed in connection with the eutrophication, water quality, and light characteristics of water systems in many studies, and the possibility as a new water quality index which simultaneously contains optical information of water quality parameters has been suggested. In thisstudy, Ocean Colour-Climate Change Initiative (OC-CCI) based 4 km FUI was spatially downscaled to the resolution of 500 m using the Geostationary Ocean Color Imager (GOCI) data and Random Forest (RF) machine learning. Then, the RF-derived FUI was examined in terms of its correlation with various water quality parameters measured in coastal areas and its spatial distribution and seasonal characteristics. The results showed that the RF-derived FUI resulted in higher accuracy (Coefficient of Determination (R²)=0.81, Root Mean Square Error (RMSE)=0.7784) than GOCI-derived FUI estimated by Pitarch's OC-CCI FUI algorithm (R²=0.72, RMSE=0.9708). RF-derived FUI showed a high correlation with five water quality parameters including Total Nitrogen, Total Phosphorus, Chlorophyll-a, Total Suspended Solids, Transparency with the correlation coefficients of 0.87, 0.88, 0.97, 0.65, and -0.98, respectively. The temporal pattern of the RF-derived FUI well reflected the physical relationship with various water quality parameters with a strong seasonality. The research findingssuggested the potential of the high resolution FUI in coastal water quality management in the Korean Peninsula.

• Korean Journal of Heritage: History & Science
• /
• v.55 no.4
• /
• pp.242-275
• /
• 2022

This study tries to reveal the structure of the "Kisun"(senior envoy ship) taken by senior envoys for the 10^th to 12^th visits to Japan from the perspective of professional shipbuilding engineering focusing on the theory of the ship in the travel logs of royal envoys to Japan (Sahaengrok) written by Joseon Tongsinsa that includes 12 visits to Japan for about 200 years from 1607 to 1811. The results of the study showed that the size of Kisun for the 10^th to 12^th envoy visits was 19 Pa (把) and a half in length and 6 Pa (把) and 2 Cheok (尺) in width. The height of the Sampan was found to be 2 Pa (把) and 1 Cheok (尺) based on records in Gyemisusarok and Jeungjeonggyorinji. The structure of Kisun was different for each visit but, it was found that Kisun was mainly composed of a main deck, bow (bow plate, stem plate), stern (stern plate), Sampan, Meonge (support), Garyong (support), Sinbang, Gungji, deck, two masts and sail, Gurejjak (mast support), Panok, stern Panok, Taru, dodger, anchor reel, stairs, rail, rudder, oar, and anchor. In addition, wood and iron nails were used together for connection. It was also found that the sail was made of herbage and cotton. This study found that Kisun, which was operated for the 10^th and 12^th envoy visits, was big in terms of length and height among the Joseon Tongsinsa fleet to show the authority and dignity of Joseon and that it had passages outside on the sides of the vessel and paddles were located between the sides and Panok structure and rails were installed on four sides on the Panok, improving stability and linear beauty. The walls of Panok were decorated with the royal Dancheong pattern and fancy murals. In addition, it was found that they wished for a safe voyage by drawing a demon face on the bow. Therefore, it was revealed that Kisun, which was taken by envoys as recorded in travel logs, was made by the state and equipped with structures and functions that enabled international voyages.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.4
• /
• pp.305-330
• /
• 2023

Unlike NATM tunnels, Shield TBM tunnels have split linings. Therefore, the stress distribution of the lining is different even if the lining is under the same load. Representative methods for analyzing the stress generated in lining in Shield TBM tunnels include Non-joint Mode that does not consider connections and a 2-ring beam-spring model that considers ring-to-ring joints and segment connections. This study is an analysis method by Break-joint Mode. However, we do not consider the structural role of segment lining connections. The effectiveness of the modeling is verified by analyzing behavioral characteristics against vibration loads by modeling with segment connection interfaces to which vertical stiffness and shear stiffness, which are friction components, are applied. Unlike the Non-joint mode, where the greatest stress occurs on the crown for static loads such as earth pressure, the stress distribution caused by contact between segment lining and friction stiffness produced the smallest stress in the crown key segment where segment connections were concentrated. The stress distribution was clearly distinguished based on segment connections. The results of static analysis by earth pressure, etc., produced up to seven times the stress generated in Non-joint mode compared to the stress generated by Break-joint Mode. This result is consistent with the stress distribution pattern of the 2-ring beam-spring model. However, as for the stress value for the train vibration load, the stress of Break-joint Mode was greater than that of Non-joint mode. This is a different result from the static mechanics concept that a segment ring consisting of a combination of short members is integrated in the circumferential direction, resulting in a smaller stress than Non-joint mode with a relatively longer member length.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.