• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.202-204
• /
• 2001

본 논문에서는 GUI(Graphical User Interface)를 사용하여 사용자가 상호 작용적으로 도형 언어(visual language)의 문법을 기술함으로서 자동으로 공간 파서를 생성하는 공간 파서 생성기 SPG(Spatial falser Generator)의 구현에 대하여 논한다. 본 시스템의 장점은 다음과 같다. (1) 사용자가 도형 언어의 문법을 정의하고 실제로 파싱하고 싶은 도형 언어를 입력하는데 사용되는 도형 에디터를 가지고 있다. (2) 사용자가 도형을 이용하여 대략적인 문법을 자동으로 생성한 뒤, 수정하여 최종적인 문법을 정의하도록 한다. (3) 제약 해소기(Constraint solver)를 가지고 있어서 파싱된 도형 언어들이 그 생성 규칙에 쓰여져 있는 제약을 유지한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.269-272
• /
• 2003

그레이팅이라는 금속제품의 자동 설계 시스템인 GDS (Grating automatic Drawing System)는 기본 설계 도면(Plan Drawing)의 정보들을 바탕으로 여러 세부 도면들을 자동 생성하는 시스템이다. 그러나 GDS를 통해 자동 생성된 도면은 설계자들의 일반적인 치수기입 요령을 부분적으로 만족시키지 못하고 있으며 또 치수 표시간의 겹침 현상이 발생하여 설계자가 도면을 수정해야 하는 번거로움이 있었다. 본 논문은 이러한 문제점을 해결하기 위해, 설계 전문가들의 치수 표시법을 지식으로 하여 규칙 기반 전문가 시스템을 구성하였다.

• Journal of Internet Computing and Services
• /
• v.10 no.4
• /
• pp.105-113
• /
• 2009

The feature models are widely used to model the commonalities and variabilities among the products in the domain engineering phase of software product line developments. The findings and corrections of the errors or consistencies in the feature models are essential to the successful software product line engineering. The aids of the automated tools are needed to perform the validation of the feature models effectively. This paper describes the approach based on JESS rule-base system to validate the feature models and proposes the feature model validation tool using this approach. The tool of this paper validates the feature models in real-time when modeling the feature models. Then it provides the information on existence of errors and the explanations on causes of those errors, which allows the feature modeler to create the error-free feature models. This attempt to validate the feature model using the rule-based system is supposed to be the first time in this research field.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.417-423
• /
• 2002

In this paper, we propose intelligent steering control system that apply LIBL(Linguistic Instruction Based Learning) method to steering system of ship and take the place of process that linguistic instruction such as officer s steering instruction is achieved via ableman. We embody ableman s suitable steering manufacturing model using fuzzy inference rule by specific method of study, and apply LIBL method to present suitable meaning element and evaluation rule to steering system of ship, embody intelligent steering gear control system that respond more efficiently on officer s linguistic instruction. We presented evaluation rule to constructed steering manufacturing model based on ableman s experience, and propose rudder angle for steering system, compass bearing arrival time, meaning element of stationary state, and correct ableman manufacturing model rule using fuzzy inference. Also, we apply LIBL method to ship control simulator and confirmed the effectiveness.

• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.443-448
• /
• 2013

Ant Colony System(ACS) is a meta heuristic approach based on biology in order to solve combinatorial optimization problem. It is based on the tracing action of real ants which accumulate pheromone on the passed path and uses as communication medium. In order to search the optimal path, ACS requires to explore various edges. In existing ACS, the local updating rule assigns the same pheromone to visited edge. In this paper, our local updating rule gives the pheromone according to the total frequency of visits of the currently selected node in the previous iteration. I used the ACS algoritm using subpath for search. Our approach can have less local optima than existing ACS and find better solution by taking advantage of more informations during searching.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.93-97
• /
• 2002

In this paper, we propose intelligent steering control system that apply LIBL(Linguistic Instruction Based Learning) method to steering system of ship and take the place of process that linguistic instruction such as officer's steering instruction is achieved via ableman. We embody ableman's suitable steering manufacturing model using fuzzy inference rule by specific method of study, and apply LIBL method to present suitable meaning element and evaluation rule to steering system of ship, embody intelligent steering gear control system that respond more efficiently on officer's linguistic instruction. We presented evaluation rule to constructed steering manufacturing model based on ableman's experience, and propose rudder angle for steering system, compass bearing arrival time, meaning element of stationary state, and correct ableman manufacturing model rule using fuzzy inference. Also, we apply LIBL method to ship control simulator and confirmed the effectiveness.

• Journal of KIISE:Software and Applications
• /
• v.30 no.11
• /
• pp.1054-1061
• /
• 2003

Q-Learning, a representative algorithm of reinforcement learning, experiences repeatedly until estimation values about all state-action pairs of state space converge and achieve optimal policies. When the state space is high dimensional or continuous, complex reinforcement learning tasks involve very large state space and suffer from storing all individual state values in a single table. We introduce Q-Map that is new function approximation method to get classified policies. As an agent learns on-line, Q-Map groups states of similar situations and adapts to new experiences repeatedly. State-action pairs necessary for fine control are treated in the form of rule. As a result of experiment in maze environment and mountain car problem, we can achieve classified knowledge and extract easily rules from Q-Map

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.8
• /
• pp.25-31
• /
• 2009

Widely used color information recognition methods based on the RGB color model with static fuzzy inference rules have limitations due to the model itself-the detachment of human vision and applicability of limited environment. In this paper, we propose a method that is based on HSI model with new inference process that resembles human vision recognition process. Also, a user can add, delete, update the inference rules in this system. In our method, we design membership intervals with sine, cosine function in H channel and with functions in trigonometric style in S and I channel. The membership degree is computed via interval merging process. Then, the inference rules are applied to the result in order to infer the color information. Our method is proven to be more intuitive and efficient compared with RGB model in experiment.

• Explosives and Blasting
• /
• v.42 no.2
• /
• pp.1-11
• /
• 2024

The purpose of this study is to suggest amendments for the effective operation of safety and health regulations that stipulate safety standards for the prevention of industrial accidents in blasting and tunneling works. Because the regulations on Occupational Safety and Health Standards have not been revised for a long time, the regulations do not meet the requirements in site, and it is reported that it is difficult to implement the regulations at workplaces due to various deficiencies. Therefore, this study aims to abolish or improve unreasonable regulations that do not fit reality due to changes in the technology environment, or to modify low-operability regulations considering domestic conditions in blasting and tunneling workplaces. By comparing domestic laws and standards related to blasting and tunneling works with foreign ones, the improvement measures were suggested.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.659-663
• /
• 2023

이 논문은 한국어 음성인식 성능을 개선하고자 기존 음성인식 과정을 자모단위 음성인식 모델과 신경망 기반 자모 병합 모델 총 두 단계로 구성하였다. 한국어는 조합어 특성상 음성 인식에 필요한 음절 단위가 약 2900자에 이른다. 이는 학습 데이터셋에 자주 등장하지 않는 음절에 대해서 음성인식 성능을 저하시키고, 학습 비용을 높이는 단점이 있다. 이를 개선하고자 음절 단위의 인식이 아닌 51가지 자모 단위(ㄱ-ㅎ, ㅏ-ㅞ)의 음성인식을 수행한 후 자모 단위 인식 결과를 음절단위의 한글로 병합하는 과정을 수행할 수 있다[1]. 자모단위 인식결과는 초성, 중성, 종성을 고려하면 규칙 기반의 병합이 가능하다. 하지만 음성인식 결과에 잘못인식된 자모가 포함되어 있다면 최종 병합 결과에 오류를 생성하고 만다. 이를 해결하고자 신경망 기반의 자모 병합 모델을 제시한다. 자모 병합 모델은 분리되어 있는 자모단위의 입력을 완성된 한글 문장으로 변환하는 작업을 수행하고, 이 과정에서 음성인식 결과로 잘못인식된 자모에 대해서도 올바른 한글 문장으로 변환하는 오류 수정이 가능하다. 본 연구는 한국어 음성인식 말뭉치 KsponSpeech를 활용하여 실험을 진행하였고, 음성인식 모델로 Wav2Vec2.0 모델을 활용하였다. 기존 규칙 기반의 자모 병합 방법에 비해 제시하는 자모 병합 모델이 상대적 음절단위오류율(Character Error Rate, CER) 17.2% 와 단어단위오류율(Word Error Rate, WER) 13.1% 향상을 확인할 수 있었다.