• Journal of Radiation Protection and Research
• /
• v.21 no.4
• /
• pp.273-284
• /
• 1996

Embryos and fetuses are more sensitive to various environmental agents than are adults or children. The biological effects such as intrauterine death and malformation are closely connected with prenatal exposure very various agents. The sensitivity of these embryonic/fetal effects depends on the stage of pregnancy. From the viewpoint of fetal development, embryonic and fetal stages can be divided into three stages : Preimplantation, organogenetic and fetal. Each stage corresponds to 0 to 4.5days, 4.5 to 13.5days, and 13.5days of gestation in mice, respectively. Many studies on the biologcal effects of mice irradiated by ${\gamma}-rays$ at various stages during organogenesis and fetal period have been performed. Based on these results, the dose-effect and dose-response relationships in malformations, intrauterine death, or retardation of the physical growth have been practically modeled by the ICRP(International Commission on Radiological Protection) and other international bodies for radiation protection. Many experimental studies on mice have made it clear that mice embryos in the preimplantation period have a higher sensitivity to radiation for lethal effects than the embryos/fetuses on other prenatal periods. However, no eratogenic effects of radiation at preimplantation stages of mice have been described in many textbooks. It has been believed that 'all or none action results' for radiation of mice during the preimplantation period were applied. The teratogenic and lethal effects during the preimplantation stage are one of the most important problems from the viewpoint of radiological protection, since the preimplantation stage is the period when the pregnancy itself is not noticed by a pregnant woman. There are many physical or chemical agents which affect embryos/fetuses in the environment. It is assumed that each agents indirectly effects a human. Then, a safety criterion on each agent is determined independently. The pregnant ICR mice on 2, 48, 72 or 96 hours post-conception (hpc), at which are preimplantation stage of embryos, were irradiated whole body Cesium-gamma radiation at doses of 0.1, 0.25, 0.5, 1.5, and 2.5 Gy with dose rate of 0.2 Gy/min. In the embryos from the fetuses from the mice irradiated at various period in preimplantation, embryonic/fetal mortalities, incidence of external gross malformation, fetal body weight and sex ratio were observed at day 18 of gestation. The sensitivity of embryonic mortalities in the mice irradiated at the stage of preimplantation were higher than those in the mice irradiated at the stage of organogenesis. And the more sensitive periods of preimplantation stage for embryonic death were 2 and 48 hpc, at which embryos were one cell and 4 to 7 cell stage, respectively. Many types of the external gross malformations such as exencephaly, cleft palate and anophthalmia were observed in the fetuses from the mice irradiated at 2, 72 and 96 hpc. However, no malformations were observed in the mice irradiated at 48 hpc, at which stage the embryos were about 6 cell stage precompacted embryos. So far, it is believed that the embryos on preimplantation stage are not susceptible to teratogens such as radiation and chemical agents. In this study, the sensitivity for external malformations in the fetuses from the mice irradiated at preimplantation were higher than those in the fetuses on stage of organogenesis.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.37 no.2
• /
• pp.123-133
• /
• 1992

This study was conducted to clarify progressed changes of plant types and the effects of the physiological and ecological components on improving ideotype of winter wheat. 12 wheat varieties were planted at the experimental farm of Wheat and Barley Research Institute in Suwon in 1990. As results of intensive wheat breeding for early maturity since 1959, heading, flowering and maturing dates have been shortened by 17, 15 and 14 dagys, respectively. The shortened days from sowing to heading and from heading to flowering contributed to the early maturity to improved. Physiological factors associated with heading time of wheat could be reprsented by growth habit, photoperiod responses, earliness in narrow sense and winter hardiness. For improving an early maturity of winter wheat, it would desired to maintain some degree of winter habit(III-IV), and recombination of more insensitivity to short day length and more shortened earliness in narrow sense than that of Saemil and Chugoku 81, and higher degree of winter hardiness. For improving the early maturity the more effective way must be of shortened days from sowing to heading, and days from flowering to maturity than days from heading to flowering. Ideotype of wheat will be desired to recombine two semi-dwarf genes with erect plant type being about 70-80cm, less stem elongation by late spring, long spike and many grains per spikelet. Average spike weight ratio was about 45-49% in high-yielding varieties, stem fresh weight was lighter, but spike fresh weight was heavier in new one while leaf fresh weight was similar to each other during the maturing periods. Average spike dry weight ratio was higher about 40～48%, and stem and leaf blade dry weights were lower in the newly bred varieties. Stem dry weight was heavier than spike or leaf dry weight in the old varieties of Yungkwang, Jangwang and Jinkwang. Leaf area index for the varieties showed normal distribution curve as the maximum point in booting stage. The maximum point of this curve come in early maturing wheat, and late in old one. The maximum points of LAI were 6.4～6.8 in the high-yielding varieties. Totals of LAI in each period investigated of old one were higher than those of newly bred being 24.6～28.8. Chlorophyll content of the high-yielding varieties of Chokwang, Geurumil and Saemil as higher than that of the old varieties Jangkwang, Jinkwang, Wonkwang and Sinkwang from regrowing period to April 21. after then slightly and even after heading. Net assimilation rate (NAR) was higher in high-yielding varieties with good plant type, and lower in old ones. Grain yield of the newly released varieties increased rapidly but slowly in the old ones. Change in water content of grain at the growing stage in newly bred was lower than that of the old bred. Diminishing rate of water content of grain in establishment per day was 1.2% average that of the old varieties including Yungkwang was 1.5%, and those of the newly bred including Chokwang were 0.9～1.1%. Chokwang, Naemil, and Saemil were the highest-yielding varieties of the Korean cultivars. Yields were increased by spikes per m$^2$, grain weight for the varieties bred in Suwon, and by spikes per m$^2$ for the varieties bred in Milyang.

• Journal of Acupuncture Research
• /
• v.22 no.3
• /
• pp.227-241
• /
• 2005

Objective & Methods : The purpose of this study is to observe the effects of Asari Herba Cum Radice herbal-acupuncture solution(AHCR-HAS) on arthritis of mice induced by Collagen II at Joksamni(ST36). The author performed several experimental items. First, it is the cell survival rate of mice lung fibroblasts and expression of TNF-${\alpha}$ in synovial cells. Second, it is the incidence rate of arthritis and the weight of spleen. Third, it is the levels of IL-6, TNF-${\alpha}$, INF-${\gamma}$, IgG, IgM and anti-collagen II in serum Fourth, it is histological analysis of the mice joint. Fifth, it is expression ratio of CD3e+ to CDl9+ cell, CD4+ to CD8+ cell, CD69+/CD3e+ cells, CD11+/CD19+ cells and CD11b+/Gr-1+ cells. Result : 1. The highest survival rate of mice lung fibroblasts were measured in the 1% AHCR-HAS, and the expression of TNF-${\alpha}$ in synovial cells were significantly decreased in the 1% AHCR-HAS. 2. In the AHCR-HA I & AHCR-HAII groups, the incidence of arthritis and the weight of spleen were significantly decreased. 3. In AHCR-HAI & AHCR-HAII groups, the levels of IL-6, INF-${\gamma}$, TNF-${\alpha}$, IgG, IgM and anti-collagen II in serum of CIA mice were significantly decreased. 4. In histology, the cartilage destruction and synovial cell proliferation were decreased in the AHCR-HA I & AHCR-HAII groups, and the collagen fiber expressions in the AHCR-HA I & AHCR-HAII groups were similar with that of the Normal group. 5. In the AHCR-HA I & AHCR-HA II groups, the expression ratio of CD3e+ to CD19+ cell and CD4+ to CD8+ cell were similarly maintained as Normal group in lymph nodes, and CD69+/CD3e+ cells and CD11a+/CD19+ cells were decreased in Iymph nodes, and CD11b+/Gr-1+ cells were decreased in synovium. Conclusion : Taking all these observations into account, AHCR-HA is considered to be effective in prophylaxis and treatment of rheumatoid arthritis, and then more effective in prophylaxis than treatment, so put to practical use in future rheumatoid arthritis clinic.

• Korean Journal of Agricultural Science
• /
• v.42 no.2
• /
• pp.141-149
• /
• 2015

The data of Duroc swine species that were born from 2000 to 2014 excluding missing ones collected by Korea National Institute of Animal Science were used in the present study. After removing missing data we used 9756 of productions data and 1728 of reproductive reference of breeding research to study the level of inbreeding and to investigate the impact on the reproductive traits, production traits. The correlation of reproductive traits and inbreeding coefficient are -0.07, -0.08 for total number pigs born, number of pigs born alive respectively and birth weight per litter is -0.10, number of pigs born alive per litter to 21days is -0.06 and body weight per litter to 21days is -0.09. The correlation coefficients of the inbreeding coefficients of reproductive traits are shown within 10% with negative correlation (P < 0.05). Days of 90kg and Backfat in the correlation coefficient and inbreeding coefficient production traits were not observed significant correlations, Average daily gain was investigated by the positive correlation of 0.05. According to the above results, the inbreeding level gave a negative effect on the improvement of the breed traits, investigating a relatively high compared to a negative effect on other traits. But overall correlation degree is less than 10% was observed. This inbreeding coefficient has not been clearly observed due to degeneration of the average inbreeding coefficients of these generations was maintained within 10% of the population. The scale of the experimental group was about 150 degree pig husbandry is very small compared to the advanced countries. However, the level of inbreeding in the population group with the appropriate mating combinations is maintained below 10% of population is thought to be small and can minimize the effects of inbreeding degeneration. further testing utilizing this selection is constantly considered to be necessary.

• The Journal of Korean Academy of Prosthodontics
• /
• v.46 no.2
• /
• pp.148-156
• /
• 2008

Statement of problems: Self-etch adhesives exhibit some clinical benefits such as ease of manipulation and reduced technique-sensitivity. Nevertheless, some concern remains regarding the bonding effectiveness of self-etch adhesives to enamel, in particular when so-called 'mild' self-etch adhesives are employed. This study compared the microtensile bond strengths to ground enamel of the two-step self-etch adhesive Clearfil SE Bond (Kuraray) to the three-step etch-and- rinse adhesive Scotchbond Multi-Purpose (3M ESPE) and the one-step self-etch adhesive iBond (Heraeus Kulzer). Purpose: The purpose of this study was to determine the effect of a preceding phosphoric acid conditioning step on the bonding effectiveness of a two-step self-etch adhesive to ground enamel. Material and methods: The two-step self-etch adhesive Clearfil SE Bond non-etch group, Clearfil SE Bond etch group with prior 35% phosphoric acid etching, and the one-step self-etch adhesive iBond group were used as experimental groups. The three-step etch-and-rinse adhesive Scotchbond Multi-Purpose was used as a control group. The facial surfaces of bovine incisors were divided in four equal parts cruciformly, and randomly distributed into each group. The facial surface of each incisor was ground with 800-grit silicon carbide paper. Each adhesive group was applied according to the manufacturer's instructions to ground enamel, after which the surface was built up using Light-Core (Bisco). After storage in distilled water at $37^{\circ}C$ for 1 week, the restored teeth were sectioned into enamel beams approximately 0.8*0.8mm in cross section using a low speed precision diamond saw (TOPMET Metsaw-LS). After storage in distilled water at $37^{\circ}C$ for 1 month, 3 months, microtensile bond strength evaluations were performed using microspecimens. The microtensile bond strength (MPa) was derived by dividing the imposed force (N) at time of fracture by the bond area ($mm^2$). The mode of failure at the interface was determined with a microscope (Microscope-B nocular, Nikon). The data of microtensile bond strength were statistically analyzed using a one-way ANOVA, followed by Least Significant Difference Post Hoc Test at a significance level of 5%. Results: The mean microtensile bond strength after 1 month of storage showed no statistically significant difference between all adhesive groups (P>0.05). After 3 months of storage, adhesion to ground enamel of iBond was not significantly different from Clearfil SE Bond etch (P>>0.05), while Clearfil SE Bond non-etch and Scotchbond Multi-Purpose demonstrated significantly lower bond strengths (P<0.05), with no significant differences between the two adhesives. Conclusion: In this study the microtensile bond strength to ground enamel of two-step self-etch adhesive Clearfil SE Bond was not significantly different from three-step etch-and-rinse adhesive Scotchbond Multi-Purpose, and prior etching with 35% phosphoric acid significantly increased the bonding effectiveness of Clearfil SE Bond to enamel at 3 months.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.109-125
• /
• 2020

The Ministry of National Defense is pushing for the Defense Acquisition Program to build strong defense capabilities, and it spends more than 10 trillion won annually on defense improvement. As the Defense Acquisition Program is directly related to the security of the nation as well as the lives and property of the people, it must be carried out very transparently and efficiently by experts. However, the excessive diversification of laws and regulations related to the Defense Acquisition Program has made it challenging for many working-level officials to carry out the Defense Acquisition Program smoothly. It is even known that many people realize that there are related regulations that they were unaware of until they push ahead with their work. In addition, the statutory statements related to the Defense Acquisition Program have the tendency to cause serious issues even if only a single expression is wrong within the sentence. Despite this, efforts to establish a sentence comparison system to correct this issue in real time have been minimal. Therefore, this paper tries to propose a "Comparison System between the Statement of Military Reports and Related Laws" implementation plan that uses the Siamese Network-based artificial neural network, a model in the field of natural language processing (NLP), to observe the similarity between sentences that are likely to appear in the Defense Acquisition Program related documents and those from related statutory provisions to determine and classify the risk of illegality and to make users aware of the consequences. Various artificial neural network models (Bi-LSTM, Self-Attention, D_Bi-LSTM) were studied using 3,442 pairs of "Original Sentence"(described in actual statutes) and "Edited Sentence"(edited sentences derived from "Original Sentence"). Among many Defense Acquisition Program related statutes, DEFENSE ACQUISITION PROGRAM ACT, ENFORCEMENT RULE OF THE DEFENSE ACQUISITION PROGRAM ACT, and ENFORCEMENT DECREE OF THE DEFENSE ACQUISITION PROGRAM ACT were selected. Furthermore, "Original Sentence" has the 83 provisions that actually appear in the Act. "Original Sentence" has the main 83 clauses most accessible to working-level officials in their work. "Edited Sentence" is comprised of 30 to 50 similar sentences that are likely to appear modified in the county report for each clause("Original Sentence"). During the creation of the edited sentences, the original sentences were modified using 12 certain rules, and these sentences were produced in proportion to the number of such rules, as it was the case for the original sentences. After conducting 1 : 1 sentence similarity performance evaluation experiments, it was possible to classify each "Edited Sentence" as legal or illegal with considerable accuracy. In addition, the "Edited Sentence" dataset used to train the neural network models contains a variety of actual statutory statements("Original Sentence"), which are characterized by the 12 rules. On the other hand, the models are not able to effectively classify other sentences, which appear in actual military reports, when only the "Original Sentence" and "Edited Sentence" dataset have been fed to them. The dataset is not ample enough for the model to recognize other incoming new sentences. Hence, the performance of the model was reassessed by writing an additional 120 new sentences that have better resemblance to those in the actual military report and still have association with the original sentences. Thereafter, we were able to check that the models' performances surpassed a certain level even when they were trained merely with "Original Sentence" and "Edited Sentence" data. If sufficient model learning is achieved through the improvement and expansion of the full set of learning data with the addition of the actual report appearance sentences, the models will be able to better classify other sentences coming from military reports as legal or illegal. Based on the experimental results, this study confirms the possibility and value of building "Real-Time Automated Comparison System Between Military Documents and Related Laws". The research conducted in this experiment can verify which specific clause, of several that appear in related law clause is most similar to the sentence that appears in the Defense Acquisition Program-related military reports. This helps determine whether the contents in the military report sentences are at the risk of illegality when they are compared with those in the law clauses.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.29-45
• /
• 2012

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• 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.

• The Journal of Korean Society for Radiation Therapy
• /
• v.32
• /
• pp.41-52
• /
• 2020

Purpose: To find out the dosimetric usefulness, setup reproducibility and efficiency of applying 3D Bolus by comparing two treatment plans in which Commercial Bolus and 3D Bolus produced by 3D Printing Technology were applied to the neck during VMAT treatment of Hypopahrynx Cancer to evaluate the clinical applicability. Materials and Methods: Based on the CT image of the RANDO phantom to which CB was applied, 3D Bolus were fabricated in the same form. 3D Bolus was printed with a polyurethane acrylate resin with a density of 1.2g/㎤ through the SLA technique using OMG SLA 660 Printer and MaterializeMagics software. Based on two CT images using CB and 3D Bolus, a treatment plan was established assuming VMAT treatment of Hypopharynx Cancer. CBCT images were obtained for each of the two established treatment plans 18 times, and the treatment efficiency was evaluated by measuring the setup time each time. Based on the obtained CBCT image, the adaptive plan was performed through Pinnacle, a computerized treatment planning system, to evaluate target, normal organ dose evaluation, and changes in bolus volume. Results: The setup time for each treatment plan was reduced by an average of 28 sec in the 3D Bolus treatment plan compared to the CB treatment plan. The Bolus Volume change during the pretreatment period was 86.1±2.70㎤ in 83.9㎤ of CB Initial Plan and 99.8±0.46㎤ in 92.2㎤ of 3D Bolus Initial Plan. The change in CTV Min Value was 167.4±19.38cGy in CB Initial Plan 191.6cGy and 149.5±18.27cGy in 3D Bolus Initial Plan 167.3cGy. The change in CTV Mean Value was 228.3±0.38cGy in CB Initial Plan 227.1cGy and 227.7±0.30cGy in 3D Bolus Initial Plan 225.9cGy. The change in PTV Min Value was 74.9±19.47cGy in CB Initial Plan 128.5cGy and 83.2±12.92cGy in 3D Bolus Initial Plan 139.9cGy. The change in PTV Mean Value was 226.2±0.83cGy in CB Initial Plan 225.4cGy and 225.8±0.33cGy in 3D Bolus Initial Plan 224.1cGy. The maximum value for the normal organ spinal cord was the same as 135.6cGy on average each time. Conclusion: From the experimental results of this paper, it was found that the application of 3D Bolus to the irregular body surface is more dosimetrically useful than the application of Commercial Bolus, and the setup reproducibility and efficiency are excellent. If further case studies along with research on the diversity of 3D printing materials are conducted in the future, the application of 3D Bolus in the field of radiation therapy is expected to proceed more actively.