• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.518-523
• /
• 2020

본 논문에서는 목적 지향 대화 시스템을 위한 대화 상태 추적 시스템과 사용자 시뮬레이터를 설계 및 제안한다. 사용자 시뮬레이터는 작성된 대화 상태 추적 시스템을 평가하기 위한 용도로 사용된다. 본 논문에서 제안하는 대화 상태 추적 시스템은 대화 기록과 함께 사전에 학습된 대화 기록 및 규칙/통계 기반 추론 시스템의 추론 결과를 입력으로 받는다. 그리고 입력된 발화 기록 중 마지막 사용자 발화의 사용자 목표와 개체명 그리고 다음 시스템 발화의 화행을 추론한다. 또한, 작성된 대화 상태 추적기의 성능을 평가하고 분석하기 위해, 주어진 환경에서 시스템과 대화를 수행하며 대화 시스템의 성능을 평가하는 사용자 시뮬레이터를 구현 및 적용하였다. 본 연구에서 수행된 실험과 분석을 통해, 규칙 및 통계 기반의 기반 시스템을 이용해 목표 시스템의 성능 개선이 가능함을 보인다. 또한, 제안하는 사용자 시뮬레이터는 규칙과 통계를 이용해 평가 코퍼스 없이 여러 상황에 대해 대화 시스템의 성능을 평가할 수 있다.

• Journal of the Korean Geotechnical Society
• /
• v.20 no.5
• /
• pp.37-48
• /
• 2004

This study is focused on the constitutive model in order to represent brittleness and dilatancy for cohesionless soils. The constitutive model was based on an anisotropic hardening rule derived from generalized isotropic hardening nile, which includes an appropriate hardening equation for the overall strain behavior at small to large strains. The yield surface is a simple cylinder type in stress space and it makes the model practically useful. Hence dilatancy behavior in cohesionless soils could be modeled reasonably. A peak stress ratio was defined in order to model brittle stress-strain relationships. An optimized design methodology was proposed on the basis of real-coded genetic algorithm in order to determine parameters for the proposed model systematically. The material parameters were then determined by that algorithm. In order to verify the proposed model, triaxial tests were performed under $K_0$ conditions far weathered soils. In comparison with the triaxial test results under $K_0$ conditions, the proposed model could calculate appropriately the actual effective stress behavior on brittle stress-strain relationships and dilatancy.

• The Journal of the Acoustical Society of Korea
• /
• v.8 no.5
• /
• pp.102-112
• /
• 1989

In this paper, we proposed the study on speaker-independent isolated word recognition for DDD area-name using vector quantization and chose total 146 DDD area-name to recognize words for application of dialing system. We made the codebook using 12th LPC cepstrum coefficients and used the minsum and the minimax method to find the centroid and we applied 3 splitting rule to a codebook generation. The single section and the multi section with time information were used to generate the codebooks and the over-lapped section codebook was used, too. From the experiment result, we proved that the minsum method was better than the minimax method and the evaluation of the system yielded an accuracy of about 90 percents In case of speaker-independent.

• Journal of the Korean Society for information Management
• /
• v.24 no.3
• /
• pp.119-147
• /
• 2007

Actually a diffusion of a semantic web application and utilization are situations insufficient extremely. Technology most important in semantic web application is construction of the ontology which contents itself with characteristics of semantic web. Proposed a suitable a method of building web ontology for characteristics or semantic web and web ontology as we compared the existing ontology construction ana ontology construction techniques proposed for web ontology construction, and we analyzed. And modeling old ontology to bases to description logic and the any axiom rule that used an expression way of SWRL, and established inference-based web ontology according to proposed ways. Verified performance of ontology established through ontology inference experiment. Also established an web ontology-based intelligence image retrieval system, to experiment systems for performance evaluation of established web ontology, and present an example of implementation of a semantic web application and utilization. Demonstrated excellence of a semantic web application to be based on ontology through inference experiment of an experiment system.

• THE INTERNATIONAL COMMERCE & LAW REVIEW
• /
• v.69
• /
• pp.127-151
• /
• 2016

UNIDROIT Principles of International Commercial Contracts(PICC) was published in 1994. PICC has been functioned as a guideline of international commercial contracts, an applicable law to govern a contract by the agreement of the parties to a contract, general principles of law and lex mercatoria. In addition, PICC has a role of interpreting or supplementing international uniform law instruments as well as domestic laws, and also has served as a model for national and international legislations. PICC has been accepted as a authoritative source of knowledge of international trade usages of international commercial contracts to the arbitral tribunal rather than domestic court because it excluded the characteristics of hard law at the drafting stage. This article dealt with the rule on gross disparity of validity which fall outside the scope of UN Convention on Contract for the International Sale of Goods(CISG), which has obtained a leading legal position of uniform law in international sales of good. In other words, PICC suggests a series of meaningful solutions to the issue of gross disparity of contract which is the most complicated among legal disputes occurring during the process of conclusion of contact and also extremely different and diverse between legal systems. This article covered the issue of gross disparity of contract at the conclusion of contact and suggested the legal basis of several rules related to the gross disparity by analysing gross disparity rule of PICC. Furthermore, this article suggested legal check points or implication as well as interpretation and evaluation on doctrine of laesio enormis and undue influence or unconscionability. This article also dealt with a comparative analysis with Principles of European Contract Law(PECL) and Common European Sales Law(CESL) which have important legal positions in the area of international commercial contract as well as in terms of close relationship to PICC by linking with recent court or arbitral tribunal rulings.

• Journal of the Korean Society for information Management
• /
• v.25 no.1
• /
• pp.149-171
• /
• 2008

Actually a diffusion of a Semantic Web application and utilization are situations insufficient extremely. Technology most important in Semantic Web application is construction of the Ontology which contents itself with characteristics of Semantic Web. Proposed a suitable a Method of Building Web Ontology for characteristics of Semantic Web and Web Ontology as we compared the existing Ontology construction and Ontology construction techniques proposed for Web Ontology construction, and we analyzed. And modeling did Ontology to bases to Description Logic and the any axiom rule that used an expression way of SWRL, and established Inference-based Web Ontology according to proposed ways. Verified performance of Ontology established through Ontology inference experiment. Also, established an Web Ontology-based Intelligence Image Retrieval System, to experiment systems for performance evaluation of established Web Ontology, and present an example of implementation of a Semantic Web application and utilization. Demonstrated excellence of a Semantic Web application to be based on Ontology through inference experiment of an experiment system.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.559-568
• /
• 2014

Previous polarity classification using sentiment analysis utilizes a sentence rule by product reviews based rating points. It is difficult to be applied to blogs which have not rating of product reviews and is possible to fabricate product reviews by comment part-timers and managers who use web site so it is not easy to understand a product and store reviews which are reliability. Considering to these problems, if we analyze blogs which have personal and frank opinions and classify polarity, it is possible to understand rightly opinions for the product, store. This paper suggests that we extract high frequency vocabularies in blogs by several domains and choose topic words. Then we apply a technique of sentiment analysis and classify polarity about contents of blogs. To evaluate performances of sentiment analysis, we utilize the measurement index that use Precision, Recall, F-Score in an information retrieval field. In a result of evaluation, using suggested sentiment analysis is the better performances to classify polarity than previous techniques of using the sentence rule based product reviews.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.1E
• /
• pp.5-19
• /
• 1996

This paper proposes a loose part monitoring system (LPMS) design with a signal processing method based on fuzzy logic. Considering fuzzy characteristics of metallic impact waveform due to not only interferences from various types of noises in an operating nuclear power plant but also complex wave propagation paths within a monitored mechanical structure, the proposed LPMS design incorporates the comprehensive relation among impact signal features in the fuzzy rule bases for the purposes of alarm discrimination and impact diagnosis improvement. The impact signal features for the fuzzy rule bases include the rising time, the falling time, and the peak voltage values of the impact signal envelopes. Fuzzy inference results based on the fuzzy membership values of these impact signal features determine the confidence level data for each signal feature. The total integrated confidence level data is used for alarm discrimination and impact diagnosis purposes. Through the perpormance test of the proposed LPMS with mock-up structures and instrumentation facility, test results show that the system is effective in diagnosis of the loose part impact event(i.e., the evaluation of possible impacted area and degree of impact magnitude) as well as in suppressing false alarm generation.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.25 no.4
• /
• pp.209-216
• /
• 2014

Objectives : Alcohol use disorder (AUD) is often comorbid with adult attention-deficit hyperactivity disorder (ADHD) and other psychiatric illnesses. When associated with other mental problems, the prognosis of the AUD can be more serious. This study shows research on the clinical and neuropsychological characteristics according to whether or not ADHD symptoms and AUD were comorbid. Methods : A total of 64 adult inpatients who completed AUD scales about adult ADHD, alcohol dependence, depression, anxiety, and impulsiveness. They also completed neuropsychological tests about attention and executive function. According to the Adult ADHD Self-Report Scale score, patients were categorized into two groups (ADHD symptom positive/negative group). Results : Fourteen among the 64 subjects were part of the ADHD symptom positive group (21.9%). They had statistically significant shorter abstinence periods and a higher rate of history of 'rule violation during school' and 'physical damage in childhood' compared to the ADHD symptom negative group. Conclusion : The comorbidity rate with ADHD symptom in adult AUD is higher than the general population. The ADHD symptom positive group suffered from more severe and refractory AUD. Considering the more frequent history of rule violation during school in the ADHD symptom positive group, the association between ADHD and AUD may be mediated by conduct disorder. Therefore we suggest the necessity of careful evaluation and intervention in children and adolescents with ADHD and conduct disorder.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.7
• /
• pp.71-78
• /
• 2017

There are several algorithms to classify emotion, such as Support-vector-machine (SVM), Bayesian decision rule, etc. However, many researchers have insisted that these methods have minor problems. Therefore, in this paper, we propose a novel method for emotion recognition based on Electroencephalogram (EEG) signal using the Gradient method which was proposed by Han. We also utilize a database for emotion analysis using physiological signals (DEAP) to obtain objective data. And we acquire four channel brainwaves, including Fz (${\alpha}$), Fp2 (${\beta}$), F3 (${\alpha}$), F4 (${\alpha}$) which are selected in previous study. We use 4 features which are power spectral density (PSD) of the above channels. According to performance evaluation (4-fold cross validation), we could get 85% accuracy in valence axis and 87.5% in arousal. It is 5-7% higher than existing method's.