• Annual Conference on Human and Language Technology
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.55-60
• /
• 2021

최근 한국어에 대한 자연어 처리 연구는 딥러닝 기반의 자연어 이해 모델을 중심으로 각 모델의 성능에 대한 비교 분석과 평가가 활발하게 이루어지고 있다. 그러나 한국어 생성 모델에 대해서도 자연어 이해 영역의 하위 과제(e.g. 감정 분류, 문장 유사도 측정 등)에 대한 수행 능력만을 정량적으로 평가하여, 생성 모델의 한국어 문장 구성 능력이나 상식 추론 과정을 충분히 평가하지 못하고 있다. 또한 대부분의 생성 모델은 여전히 간단하고 일반적인 상식에 부합하는 자연스러운 문장을 생성하는 것에도 큰 어려움을 겪고 있기에 이를 해결하기 위한 개선 연구가 필요한 상황이다. 따라서 본 논문은 이러한 문제를 해결하기 위해 한국어 생성 모델이 일반 상식 추론 능력을 바탕으로 문장을 생성하도록 KommonGen 데이터셋을 제안한다. 그리고 KommonGen을 통해 한국어 생성 모델의 성능을 정량적으로 비교 분석할 수 있도록 평가 기준을 구성하고, 한국어 기반 자연어 생성 모델의 개선 방향을 제시하고자 한다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 한국항해항만학회 2012년도 춘계학술대회
• /
• pp.132-134
• /
• 2012

우리 나라에서 해상 교통 및 선박의 통항 안전성의 평가를 위하여, 선박조종시뮬레이터 실험을 통해 얻어진 선박운동의 데이터와 조종자의 의견을 반영하여 검토하고 있는 것이 일반적인 수행 방법이다. 세부적인 기법으로는 선박의 해상시설물에 대한 접근도, 선체의 제어도 그리고 선박 조종자의 평가를 들 수 있다. 이 중에서 해양시설물에 대한 선박의 접근 및 선박의 제어도와 관련된 부분은 통계적으로 계산되어 그 기준이 명확한 측면이 있으나, 조종자의 의견에 의한 평가는 상대적으로 기준이 모호한 면이 있고 또한 조종자의 평가와 선박의 제어도와 관계에 대한 연구도 부족한 실정이다. 따라서 본 연구에서는 선박의 제어도와 조종자의 평가를 각각 기술적 운항만족도와 심리적 운항만족도로 정의하고, 그 관계를 알아 보기 위하여 퍼지 추론을 실시하였다. 이로부터 기술적 운항만족도와 심리적 운항만족도의 상관 관계를 정리하고, 그 관계가 높을수록 관련 평가의 신뢰성은 높을 것으로 생각하였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• 제12권1호
• /
• pp.58-71
• /
• 2019

This paper proposes architecture of a cognitive radio engine platform and the allowable frequency channel reasoning method that enables acquisition of the allowable channels for the military tactical network environment. The current military tactical wireless communication system is increasing need to secure a supplementary radio frequency to ensure that multiple wireless networks for different military wireless devices coexist, so that tactical wireless communication between the same or different systems can be operated effectively. This paper presents the allowable frequency channel reasoning method based on cognitive radio engine for realizing DSA(Dynamic Spectrum Access) as an optimal available frequency channel. To this end, a case-based allowable frequency channel reasoning method for cognitive radio devices is proposed through modeling of primary user's traffic status and calculation of channel occupancy probability. Also through the simulation of the performance analysis, changing rate of collision probability between the primary users' occupancy channel and the available channel acquisition information that can be used by the cognitive radio device was analysed.

• Korean Journal of Construction Engineering and Management
• /
• 제3권3호
• /
• pp.49-57
• /
• 2002

This paper describes the second stage of the work aiming at proposing a reasonable risk management response system for construction safety. By means of questionnaires/interviews and two sample t-tests, significant risk factors are identified for three different conditions. Then a Case-Based Reasoning System is built for use at construction sites to simulate possible accidents. This Construction Management Reasoning System(CMRS) nay be used by safety managers at sites every day (or education and training of workers to prevent accidents. The case base built so far is limited to the construction of expressway bridges. There is much need for further research since the simulation of possible accidents is to be a good means to enhance safety awareness of construction workers.

• Journal of Educational Research in Mathematics
• /
• 제19권2호
• /
• pp.321-340
• /
• 2009

The purpose of this study was to analyze how lower graders in elementary school might respond to 4 different problem types in the context of measuring length: unit-length comparison, units and unit counting, unit-length expectation, and length comparison. A total of 375 students(185 second graders and 190 third graders) were surveyed and analyzed. The results showed that students were good at 'unit-length comparison' and 'units and unit counting', whereas they were not as to 'length comparison', This paper includes detailed analysis of students' responses as to both correct answer and incorrect one in conjunction with their typical answers and reasoning behind the answers. This paper suggests that teachers be sensitive to the certain level of reasoning tied to each type of problems and attend to students' difficulties in comparing length.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• 제8권12호
• /
• pp.1-10
• /
• 2018

The purpose of this study is to analyze the mathematics competencies required in middle school Korean language class to find out ways to improve student's debate ability. The results of the analysis showed that creativity and information processing ability in research activities; problem solving ability, creativity, information processing ability in planning activities; reasoning and creativity, information processing ability in rebutting activities; problem solving and reasoning in summary activities. In cross-inquiry activities, problem solving and reasoning, information processing, and creativity are required; creativity in final focus; problem solving and reasoning ability in judgment and general review; preparation time activities require problem solving, reasoning, and information processing ability. Therefore, in order to improve the debate ability of the students, it is required that the mathematics competencies such as problem solving, reasoning, information processing, and creativity are increased.

• Journal of Intelligence and Information Systems
• /
• 제6권1호
• /
• pp.1-16
• /
• 2000

This paper analyzes the approaches of Web-based expert systems by comparing their pros and cons. and proposes a methodology of implementing the Web-based backward inference engines with reduced burden to Web servers. There are several alternatives to implement expert systems under the WWW environment : CGI, Web servers embedding inference engines external viewers Java Applets and HTML. Each of the alternatives have advantages and disadvantages of each own in terms of development and deployment testing scalability portability maintenance and mass service. Especially inference engines implemented using HTML possess relatively large number of advantages compared with those implemented using other techniques. This paper explains the methodology to present rules and variables for backward inference by HTML and JavaScript and suggests a framework for design and development of HTML-based Expert System. A methodology to convert a traditional rule base to an Experts Diagram and then generate a new HTML-based Expert System from the Experts Diagram is also addressed.

• The Korean Journal of Applied Statistics
• /
• 제35권1호
• /
• pp.131-146
• /
• 2022

Logit models are commonly used to predicting and classifying categorical response variables. Most Bayesian approaches to logit models are implemented based on the Metropolis-Hastings algorithm. However, the algorithm has disadvantages of slow convergence and difficulty in ensuring adequacy for the proposal distribution. Therefore, we use auxiliary mixture sampler proposed by Frühwirth-Schnatter and Frühwirth (2007) to estimate logit models. This method introduces two sequences of auxiliary latent variables to make logit models satisfy normality and linearity. As a result, the method leads that logit model can be easily implemented by Gibbs sampling. We applied the proposed method to diabetes data from the Community Health Survey (2020) of the Korea Disease Control and Prevention Agency and compared performance with Metropolis-Hastings algorithm. In addition, we showed that the logit model using auxiliary mixture sampling has a great classification performance comparable to that of the machine learning models.

• Journal of Intelligence and Information Systems
• /
• 제5권1호
• /
• pp.49-64
• /
• 1999

본 연구는 백화점 고객이 신용 카드 신청 요구 시에 작성되는 가입 정보 및 사용되고 있는 고객의 거래 정보는 카드 사용 패턴으로 신용도를 예측하는 여러 방법론을 제시하고 성능을 비교하였다. 가입 정보를 분석하기 위해 역전파 신경망(Back-Propagation Neural Network, BPNN), 사례기반추론(Case-Based reasoning)을, 거래 정보를 분석하기 위해 역전파 신경망과 더불어 시간지연 신경망(Time-Delayed Neural Network, TDNN)을 각각 사용하여 그 결과를 비교하였다. 또한 전체시스템의 적중률을 높이기 위햐여, ID3와 신경망을 이용한 Meta-Leaning 방법을 제시하였으며, Meta-Learning 방법과 다른 방법들을 비교, 분석을 하였다. 본 연구에서는 모형 수립과 검증을 위하여 T백화점의 실제 신용 카드 가입 고객 데이터를 이용하여 실험하였다. 데이터의 성격에 따라 각 모델의 예측력에는 차이가 나타났으나, 신경망 모형의 예측력이 우수하였으며, 시간적 특성을 고려하는 시간지연 신경회로망 모형의 예측력은 더욱 우수하게 나타났다. 또한 Meta-Learning 모형을 사용하면 예측력이 더 높아진다는 것을 확인할 수 있었다.

• The Journal of the Convergence on Culture Technology
• /
• 제10권2호
• /
• pp.373-382
• /
• 2024

This study attempted to identify the relationship between nursing competency, clinical reasoning competence, and empathy ability according to the center of enneagram power for nursing students. The subjects of the study were 218 students enrolled in the department of nursing at two universities located in one region, data collection was conducted from 16 October to 27 October 2023. Data analysis was performed using SPSS/WIN version 26.0 program, descriptive statistics, and difference verification were analyzed by t-test, ANOVA, pearson's correlation coefficient, Results, The enneagram personality type of the subjects of this study was the most common type 9. And in the enneagram center of power, the instinct-centered type had the highest nursing competence, the thought-centered type had the highest clinical reasoning competence, and the emotion-centered type had the highest empathy ability. In addition, nursing competence and clinical reasoning competence showed a significant positive correlation, and clinical reasoning competence and empathy ability were also found to be positively correlated. Therefore, it is important to continue to develop and apply individualized competency building programs that reflect personality type tests to nursing students. In addition, the higher the empathy ability, the higher the clinical reasoning competence, so it is thought that it is necessary to develop a standardized curriculum that can improve nursing competence and clinical reasoning competence and verify its effectiveness.