• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.924-927
• /
• 2017

통계 모형에 기반을 둔 구문분석기는 자료 부족 문제에 취약하거나 장거리 의존관계와 같은 특정 언어현상에 대한 처리가 어렵다는 단점이 있다. 이러한 한계점을 극복하고자 본 연구진은 규칙에 기반을 둔 한국어 구문분석기를 개발하고 있다. 다른 구문 분석기와 다르게 형태소 단위 구문분석을 시도하며 생성 가능한 모든 구문분석 후보를 보여주는 것이 특징이다. 본 연구진의 기존 연구에서 개발한 한국어 구문분석기는 형태소의 입력순서와 구문분석 후보의 생성 순서에 의존하여 구문분석 후보를 순서화하였다. 그러나 생성되는 구문분석 후보 중 가장 정답에 가까운 구문분석 후보의 순위를 낮추기 위해서는 각 구문분석 트리가 특정한 점수를 가질 필요가 있다. 본 논문에서는 품사 태거(tagger)에서 출력하는 어절별 형태소의 순위에 따른 가중치, 수식 거리에 따른 가중치, 특정한 지배-의존 관계에 대한 가중치를 이용해 가중치 합을 가지는 구문분석 후보를 구성하고 이를 정렬하여 이전 연구보다 향상된 성능을 가진 한국어 구문분석기 모델을 제안한다. 실험은 본 연구진이 직접 구축한 평가데이터를 기반으로 진행하였으며 기존의 Unlabeled Attachment Score(UAS) 87.86%에서 제안 모델의 UAS 93.34%로 약 5.48의 성능향상을 확인할 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.4
• /
• pp.60-64
• /
• 1999

In this paper, we apply CART(Classification And Regression tree) and OC1(Oblique Classifier1) which methods are widely used for continuous speech recognition and synthesis. We prediet prosodic boundary index by applying CART and OC1, which combine right depth of tree-structured method and To_Right of link grammar method with tri_gram model. We assigned four prosodic boundary index level from 0 to 3. Experimental results show that OC1 method is superior to CART method. In other words, in spite of OC1's having fewer nodes than CART, it can make more improved prediction than CART.

• Journal of KIISE:Computing Practices and Letters
• /
• v.6 no.2
• /
• pp.161-172
• /
• 2000

In this paper, we introduce the development of a LOTOS-based tool, supporting formal methods, called ForTIA (A Formalism for Telecommunication and Information Systems). By using LOTOS, an ISO standard formal specification language, the user requirements and system models can be abstracted and represented formally. Therefore, the system can be validated and verified on the specifications, before implementations. ForTIA supports light-weight formal methods based on validation to be used in real industry. Key functions of ForTIA are simulation and C++ code generation. In simulation, tree based visual validation mechanism is provided and in code generation, the full C++ source code is generated to be used for system implementations.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.181-183
• /
• 2012

최근 자연어 및 정형언어 처리, 인공지능 알고리즘 등을 활용한 효율적인 의미 기반 지식모델의 생성과 분석 방법이 제시되고 있다. 이러한 의미 기반 지식모델은 효율적 의사결정트리(Decision Making Tree)와 특정 상황에 대한 체계적인 문제해결(Problem Solving) 경로 분석에 활용된다. 특히 다양한 복잡계 및 사회 연계망 분석에 있어 정적 지표 생성과 회귀 분석, 행위적 모델을 통한 추이분석, 거시예측을 지원하는 모의실험(Simulation) 모형의 기반이 된다. 본 연구에서는 이러한 의미 기반 지식모델을 통합에 있어 텍스트 마이닝을 통해 도출된 토픽(Topic) 모델 간 통합 방법과 정형적 알고리즘을 제시한다. 이를 위해 먼저, 텍스트 마이닝을 통해 도출되는 키워드 맵을 동치적 지식맵으로 변환하고 이를 의미적 지식모델로 통합하는 방법을 설명한다. 또한 키워드 맵으로부터 유의미한 토픽 맵을 투영하는 방법과 의미적 동치 모델을 유도하는 알고리즘을 제안한다. 통합된 의미 기반 지식모델은 토픽 간의 구조적 규칙과 정도 중심성, 근접 중심성, 매개 중심성 등 관계적 의미분석이 가능하며 대규모 비정형 문서의 의미 분석과 활용에 실질적인 기반 연구가 될 수 있다.

• Proceedings of The KACE
• /
• 2018.08a
• /
• pp.3-6
• /
• 2018

2015 개정 교육과정에 따라 2019년 3월부터 초등학교 5~6학년 학생을 대상으로 소프트웨어 교육이 실시된다. 궁극적인 소프트웨어 교육의 목표는 컴퓨팅 사고력을 갖춘 창의 융합형 인재를 양성하는 것이다. 이를 위해 초등학교에서는 알고리즘과 프로그래밍의 체험을 통해 소프트웨어 기초 소양을 함양하는 것을 목표로 한다. 이러한 컴퓨팅 사고력을 수업에 효과적으로 적용하기 위해 전용주(2017)는 소프트웨어 및 컴퓨팅에 관련된 사고과정과 원리를 실생활의 소재와 관련지어 창의적이고 능동적으로 그 해결방안을 구현해가는 과정으로 제시할 수 있는 수업 구성 원리인 CT-CPS 수업 모형을 개발하였다. 또한 교육부는 2015 개정 교육과정 실시 전, 소프트웨어 교육을 위한 선도학교를 전국에 지정하여 운영하였다. 선도학교에서의 소프트웨어 교육과정을 분석한 결과 주로 컴퓨팅 사고력의 구성요소 중 알고리즘과 자동화에 초점이 맞춰져 있었다. 엔트리와 스크래치와 같은 블록 프로그래밍 도구를 사용한 코딩교육과 로봇교육을 주로 실시했고, 실제 문제에 대한 학생들이 자료를 직접 다루는 시간은 찾아보기 힘들었다. 컴퓨팅사고력 향상을 위해서는 학생들이 실제 자료를 수집, 분석, 표현해보는 활동이 반드시 필요하다. 이에 본 연구에서 NetsBlox을 활용하고자 한다. NetsBlox는 학생들에게 익숙한 블록형 프로그래밍 도구로 실제 데이터를 온라인상에서 쉽게 받아와서 수집, 분석, 표현을 하게 도와주는 역할을 한다. 따라서 본 연구에서는 초등학생을 위한 NetsBlox를 활용한 CT-CPS기반 프로그래밍 수업을 설계하고자 한다.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.

• Journal of the Korean GEO-environmental Society
• /
• v.12 no.1
• /
• pp.61-70
• /
• 2011

The impact protection system consists of an arrangement of circular sheet pile cofferdams-denoted dolphin structuredeeply embedded in the seabed, filled with crushed rock and closed at the top with a robust concrete cap. Centrifuge model tests were performed to investigation the behaviors of dolphins in this study. Total 7 quasi-model tests and 11 dynamic model tests were performed. The main experimental results can be summarized as follows. Firstly, The experimental force-displacement results for quasi-static tests show a limited influence on the initial stiffness of the structure from the change in fill density and the related change in the stiffness of the fill. And by comparing the dissipation at the same dolphin displacement it was found that the denser fill increase the dissipation by 16% for the 20m dolphin and by 23% for the 30m dolphin. The larger sensitivity for the large dolphin is explained by a larger contribution to the dissipation from strain in the fill. In low level impacts the dynamic force-response is up to 26~58% larger than the quasi-static and the dissipation response is showed larger in small displacement. Hence, it is concluded conservative to use the quasi-static response characteristics in the approximation of the response, and it is further concluded that the dolphin resistance to low level impacts is demonstrated to be equivalent and even superior to the high level impacts.

• Journal of Korean Society of Environmental Engineers
• /
• v.36 no.4
• /
• pp.277-285
• /
• 2014

The usage of efficient microorganism (EM) is increasing in concern for server purposes including odor removal during carcasses degradation. In this study, we have studied the type of soil and its effect on efficient microorganisms for the removal of odorous gases during buried carcasses degradation in lab-scale reactor. The carcasses are buried in the reactor with various soil types such as normal soil, 20% sandy and 20% clay soil with the efficient microorganism KEM. The efficient microorganisms KEM have the ability to stabilize the degradation of carcasses of the burial site. We have focused on the analysis of odorous gases such tri-methylamine (TMA), hydrogen sulfide ($H_2S$), methyl mercaptan (MM), dimethyl sulfide (DMS), dimethyl disulfide (DMDS), carbon dioxide ($CO_2$), and methane ($CH_4$) along with the changes of microbial community changed during complete degradation of buried carcasses for a year. The results suggested that the 20% sandy soil contain lesser level of $H_2S$ and MM (0.09 and 0.35 mg) but 20% clay has higher nitrogen compound removing effect and leave only less amount of ammonia and TMA (0.31 and 2.06 mg). The 20% sandy soil also has the ability to breakdown the carcasses more quality compared with other types of soil. Based on the data obtained in this study suggesting that, the use of 20% sandy soil can effectively control sulfur compounds whereas 20% clay soil controls nitrogen compounds in the buried soil. Depending on the type of the soil, the dominant of microbial communities and the distribution was change.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.89-96
• /
• 2018

In online communities, a large number of participants can exchange their opinion using replies without time and space restrictions. While the online space provides quick and free communication, it also easily triggers unnecessary quarrels and conflicts. The network established on the discussion participants is an important cue to analyze the confrontation and predict serious disputes. In this paper, we present a quantitative measure for polarity observed on the discussion network built from reply exchanges in online communities. The proposed method uses the comment exchange information to establish the user interaction network graph, computes its maximum spanning tree, and then performs vertex coloring to assign two colors to each node in order to divide the discussion participants into two subsets. Using the proportion of the comment exchanges across the partitioned user subsets, we compute the polarity measure, and quantify how discussion participants are bipolarized. Using experimental results, we demonstrate the effectiveness of our method for detecting polarization and show participants of a specific discussion subject tend to be divided into two camps when they debate.

• Knowledge Management Research
• /
• v.21 no.3
• /
• pp.105-121
• /
• 2020

With regard to the development of new drugs, what is most important for a Korean Biotech, where no global sales network has been established, is decision-making related to out-licensing of new drugs. The probability of success for each clinical phase is different, and the licensing amount and its royalty vary depending on which clinical phase the licensing contract is made. Due to the nature of such a licensing contract and Biotech's weak financial status, it is a very important decision-making issue for a Biotech to determine when to license out to a Big Pharma. This study defined a model called 'optimal timing for out-licensing of new drugs' and the results were derived from the decision tree analysis. As a case study, we applied to a Biotech in Korea, which is conducting FDA global clinical trials for a first-in-class new drug. Assuming that the market size and expected market penetration rate of the target disease are known, it has been shown that out-licensing after phase 1 or phase 2 of clinical trials is a best alternative that maximizes Biotech's profits. This study can provide a conceptual framework for the use of management science methodologies in pharmaceutical fields, thus laying the foundation for knowledge and research on out-licensing of new drugs.