• 한국ITS학회:학술대회논문집
• /
• 한국ITS학회 2008년도 제7회 추계학술대회 및 정기총회
• /
• pp.525-530
• /
• 2008

• 한국정밀공학회지
• /
• 제27권10호
• /
• pp.61-68
• /
• 2010

In order to let the humanoid robot walk on the uneven terrains, the robot's foot should have the similar structure and function as human's. The intelligent foot should be made up of toes and heel. When it walks on the uneven terrains, the foot's sole senses the force and adjusts foot's position before robot losing his balance. In this paper, the force sensors of robot's intelligent foot for having the similar structure and function like human are developed. The heel 3-axis force/moment sensor and toe force sensors for humanoid robot's intelligent foot is developed, and the characteristic tests of them are carried out. As a result of characteristic test, the interference error of the heel 3-axis force/moment sensor is less than 2.2%. It is thought that the developed force sensors could be used to measure the reaction forces which is applied the toes and the heel of a humanoid robot.

• 한국지능시스템학회논문지
• /
• 제15권5호
• /
• pp.538-544
• /
• 2005

유비쿼터스 컴퓨팅 환경에서 사용자를 위한 서비스 지원 구조는 사용자 주변에 공유된 자원을 사용자의 상황에 따라 효율적으로 분배하는 기술이 요구된다. 그러기 위해서는 사용자의 상황 정보에 맞게 제공된 서비스 항목과 자원을 분석하고, 필요한 서비스 및 자원을 적합하게 분배하는 연구가 필요하다. 따라서 본 논문에서는 휴대용 모바일 장치를 이용하여 사용자의 상황을 인식하고, 사용자 상황에 맞도록 서비스된 항목을 공유시킴으로써 지능적인 서비스 지원이 가능한 지능형 P2P 모바일 에이전트 구조를 제안한다. 제안한 구조는 특정 자원에 대한 독점성을 제거하고, 효과적인 사용자 상황 인식 및 서비스 지원을 목적으로 한다.

• 한국지능시스템학회논문지
• /
• 제17권2호
• /
• pp.276-283
• /
• 2007

It has been shown that the structure identification of a neuro-fuzzy model improves their accuracy performances in a various modeling problems. In this paper, we claim that the structure identification of a neuro-fuzzy model can also reduce the degree of inconsistency of its fuzzy rulebase. Thus, the resulting neuro-fuzzy model serves as more like a structured knowledge representation scheme. For this, we briefly review a structure identification method of a neuro-fuzzy model and propose a systematic method to measure inconsistency of a fuzzy rulebase. The proposed method is applied to problems or fuzzy system reproduction and nonlinear system modeling in order to validate our claim.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권4호
• /
• pp.314-318
• /
• 2010

Predicting Alpha-helicies, Beta-sheets and Turns of a proteins secondary structure is a complex non-linear task that has been approached by several techniques such as Neural Networks, Genetic Algorithms, Decision Trees and other statistical or heuristic methods. This project introduces a new machine learning method by combining Bayesian Inference with offline trained Multilayered Perceptron (MLP) models as the likelihood for secondary structure prediction of proteins. With varying window sizes of neighboring amino acid information, the information is extracted and passed back and forth between the Neural Net and the Bayesian Inference process until the posterior probability of the secondary structure converges.

• 한국지능시스템학회논문지
• /
• 제6권4호
• /
• pp.61-70
• /
• 1996

이 논문은 인간의 주관적인 판단에 의한 의식구조문제를 취급한다. 의식구조를모델링하는 방법으로 퍼지구조 모델링법이 있으나, 이 방법은 인간의 주관적인 판단의 일대비교의 회수가 많고, 판단에 대한 전도라고 할 수 있는 정합성을 체크하기 어렵다. 이러한 점들을 개선하기 위한 방법으로서 AHP에서의 일대비교행렬의 개념을 이용한 행렬에 의한 퍼지구조모델링법으로서 의식을 구조화한다. 이 방법의 유효성은 품질시스템구축에 대한 의식 구조그래프에 의하여 보이고자 한다.

• Structural Engineering and Mechanics
• /
• 제29권4호
• /
• pp.381-390
• /
• 2008

This paper proposed a conceptual design of bascule bridge, which is a new kind of movable bridge with an aim of reducing the weight of superstructure. Compared with the traditional bascule bridge, the light bascule bridge chooses cable-stayed bridge with inclined pylon as its superstructure; therefore, the functions of balance-weight and structure will fuse into one. Otherwise, it adopts moving counterweight to adjust its center of gravity (CG) to open or close the bridge. In order to lighten the superstructure, it uses contact springs to auxiliary retract, and intelligent prestressing system (IPS) to control the main girder's deformation. Simultaneously the vibration control scheme of structure is discussed. Starting from establishing the mechanical model of bridge, this article tries to analyze the conditions that the design parameters of structure and attachments should satisfy to. After the design procedure was presented, an example was also adopted to explain the primary design process of this kind bridge.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제9권4호
• /
• pp.309-314
• /
• 2009

This paper presents implementation of the adaptive neuro-fuzzy control method. Control performance of the adaptive neuro-fuzzy control method for a popular inverted pendulum system is evaluated. The inverted pendulum system is designed and built as an education kit for educational purpose for engineering students. The educational kit is specially used for intelligent control education. Control purpose is to satisfy balancing angle and desired trajectory tracking performance. The adaptive neuro-fuzzy controller has the Takagi-Sugeno(T-S) fuzzy structure. Back-propagation algorithm is used for updating weights in the fuzzy control. Control performances of the inverted pendulum system by PID control method and the adaptive neuro-fuzzy control method are compared. Control hardware of a DSP 2812 board is used to achieve the real-time control performance. Experimental studies are conducted to show successful control performances of the inverted pendulum system by the adaptive neuro-fuzzy control method.

• 한국지능시스템학회논문지
• /
• 제17권6호
• /
• pp.838-842
• /
• 2007

In this paper, we define that a fuzzy convergence approach limit and a fuzzy approach Chuchy structure on X. And we investigate the relations between the category CAP and the category FCAP. And we show that the categories $FCAP_{RC}$ and $uFACHY_{cpl}$ are isomorphic.

• 한국지능시스템학회논문지
• /
• 제4권2호
• /
• pp.24-34
• /
• 1994

Scientific involvement in complex decision-making system, characterized by multicriteria phenomena and fuzziness inherent in the structure of information, requires suitable methods. Especially, when powerful dependent criteria are introduced and their weighted value structure is ignorant, the systems are become more complex. This paper presents a fuzzy dependenced relation model and fuzzy measure model for this kind of multicriteria decision-making. The model we propose is based on fuzzy relation and fuzzy measure in fuzzy systems theory. For the application of the model, a numdrical example is quoted.