• 인터넷정보학회논문지
• /
• 제13권5호
• /
• pp.1-8
• /
• 2012

본 논문에서는 수치적 데이터를 이용하여 규칙을 생성하는 시스템에 대해 순차적인 클러스터링 방법을 제안한다. 단일 클러스터링 기법은 방대하고 복잡한 공간 내에서는 원하는 결과를 얻지 못할 수 있다. 이런 문제점을 해결하기 위해 제안된 방법은 서로 다른 클러스터링 기법을 순차적으로 수행하여 장점들은 활용하고 단점들은 보안하는 형태를 제안하였다. Mountain 클러스터링과 Chen 클러스터링을 이용하여 non-parametric 공간에서 자율적으로 클러스터를 구성하였고, global 공간과 local 공간으로 역할을 분담하여 클러스터를 추정한다. 추정된 클러스터들은 신경회로망이나 퍼지 시스템과 같은 지능 시스템의 구조와 초기 파라미터 결정에 활용될 수 있으며, 확장하여 헬스케어와 의료 분야에서의 결정 제공 시스템의 학습에 도움을 줄 수 있다. 제안된 방법을 유용성을 시뮬레이션을 통해 보이고자 한다.

• 한국통신학회논문지
• /
• 제34권8C호
• /
• pp.772-781
• /
• 2009

This paper proposes a novel algorithm for the efficient classification and retrieval of medical images. After color and edge features are extracted from medical images, these two feature vectors are then applied to a multi-class Support Vector Machine, to give membership vectors. Thereafter, the two membership vectors are combined into an ensemble feature vector. Also, to reduce the search time, Correlated Categories Vector is proposed for similarity matching. The experimental results show that the proposed system improves the retrieval performance when compared to other methods.

• 한국정밀공학회지
• /
• 제17권11호
• /
• pp.165-175
• /
• 2000

In recent years, it becomes a very important issue to consider the mechanical systems such as high-speed vehicles and railway trains moving on elastic beam structures. In this paper, a general approach, which can predict the dynamic behavior of constrained mechanical system and elastic beam structure, is proposed. Also, various supporting conditions of a foundation support are considered for the elastic beam structures. The elastic structure is assumed to be a nonuniform and linear Bernoulli-Euler beam with proportional damping effect. Combined Differential-Algebraic Equations of motion are derived using multibody dynamics theory and Finite Element Method. The proposed equations of motion can be solved numerically using generalizd coordinate partitioning method and Predictor-Corrector algorithm, which is an implicit multi-step integration method.

• Journal of electromagnetic engineering and science
• /
• 제16권4호
• /
• pp.241-247
• /
• 2016

This paper proposes the design and measurement of a 6-18 GHz front-end receiver module that has been combined into a one- channel output from a two-channel input for electronic warfare support measures (ESM) applications. This module includes a limiter, high-pass filter (HPF), power combiner, equalizer and amplifier. This paper focuses on the design aspects of reducing the noise figure (NF) and matching the phase and amplitude. The NF, linear equalizer, power divider, and HPF were considered in the design. A broadband receiver based on a combined configuration used to obtain low NF. We verify that our receiver module improves the noise figure by as much as 0.78 dB over measured data with a maximum of 5.54 dB over a 6-18 GHz bandwidth; the difference value of phase matching is within $7^{\circ}$ between ports.

• 한국정밀공학회지
• /
• 제34권2호
• /
• pp.115-123
• /
• 2017

This paper presents the design and the control performance of a novel dynamic compliant-arm support with parallel elastic actuators that was developed to assist with the daily living activities of those whose arms are compromised by muscular disease or the aging process. The parallel elastic-arm support consists of a compliant mechanism with combined passive and active components for human interaction and to reach the user's desired positions. The achievement of these tasks requires impedance control, which can change the virtual stiffness, damping coefficients, and equilibrium points of the system; however, the desired-position tracking by the impedance control is limited when the end-effector weight varies according to the equipping of diverse objects. A prompt algorithm regarding weight calibration and friction compensation is adopted to overcome this problem. A result comparison shows that, by accurately assessing the desired workspace, the proposed algorithm is more effective for the accomplishment of the desired activities.

• 동력기계공학회지
• /
• 제20권4호
• /
• pp.69-74
• /
• 2016

Recently, in order to meet the stricter emission regulations, the proportion of after-treatments for vehicle and vessel is increasing gradually. The purpose of this study is to investigate the de-$CH_4$ characteristics of NGOC in front of proposed combined system according to additive catalyst and support ratio. In the case of Pd addition, the de-$CH_4$ performance of 2Pt-2Pd-3MgO/$Al_2O_3$ NGOC was improved by approximately 10 to 20% for the HC components. The de-$CH_4$ performance of 2Pt-2Pd-3Cr-3MgO/$Al_2O_3$ NGOC was higher compared to five kinds of NGOC catalysts, because Cr particle was smaller and dispersion of Pd was increased. The NGOC(Zeolite:$Al_2O_3$(80%:20%)｝catalyst according to support ratio, was improved performance at low temperature region on CO and NO conversion rate.

• 인터넷정보학회논문지
• /
• 제8권3호
• /
• pp.65-74
• /
• 2007

기업에서 데이터베이스, 데이터웨어하우스, 데이터마트, OLAP 등의 활용이 증가함에 따라 데이터베이스 통합은 일반적이며 해결해야하는 문제가 되었다. 데이터베이스를 통합하여 공유하는 방법은 여러 가지가 있지만 데이터베이스 시스템의 진정한 상호작동은 각 시스템의 데이터베이스를 의미적으로 비교하여 합병하여야 한다. 본 연구는 기존의 데이터베이스 연합 방식을 개선하여 데이터베이스 관리자가 데이터베이스의 의미를 쉽고 효율적으로 찾아내는 통합 시스템을 제안한다. 연구에서 데이터베이스 의미 정보 통합은 전역 뷰를 생성하는 도구를 사용하여 해결하였다. 전역 뷰를 구성하는 것은 복잡한 지식과 경험을 요구하기 때문에 아직까지 구성 도구가 개발된 사례가 많지 않은 핵심적인 문제이다. 제안된 기법과 도구는 데이터베이스 관리자가 사용하기에 간단하고 고기능이며 대부분의 통합 질의를 지원하도록 충분한 표현력을 갖도록 하였다.

• 한국음향학회지
• /
• 제30권2호
• /
• pp.100-106
• /
• 2011

음원의 디지털화가 진행되면서 음악 데이터베이스가 방대해지고 있다. 따라서, 음악 데이터를 보다 효과적으로 관리하기 위해 음악의 특성에 따라 장르별로 자동 분류해주는 시스템이 필요하다. 기존 장르 분류 시스템은 대부분 Mel-Frequency Cepstral Coefficient (MFCC)를 특징 벡터로 이용하고 있다. 본 논문에서는 Auditory Filter Bank를 이용한 Decorrelated Filter Bank (DFB)와 Octave-based Spectral Contrast (OSC)에 texture window를 적용하여 특징을 추출한 후, Support Vector Machine (SVM)을 이용하여 장르 분류를 시도하였다. 기존의 Marsyas 장르 분류 시스템과 비교한 결과 DFB와 OSC로 복합적인 특징 벡터를 구성하면 더 적은 차수의 특징벡터를 사용함에도 4.2 %의 향상된 분류 성공률을 얻을 수 있었다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.1048-1052
• /
• 2004

The ubiquitous environment is to support people in their everyday life in an inconspicuous and unobtrusive way. This requires that information of the person and her preferences, liking, and habits are available in the ubiquitous system. In this paper, we propose the context aware system that can provide the tailored information service for user in ubiquitous computing environment. The system architecture is composed of 4 domain models that can perform some pre-defined tasks independently. And we suggest the hybrid algorithm combined with fuzzy and Bayesian network to reason what information is suitable for user environment. Finally, we apply to agent based RGA(Research Guide Assistant).

• 한국CDE학회논문집
• /
• 제11권5호
• /
• pp.365-374
• /
• 2006

The ubiquitous environment is to support people in their everyday life in an inconspicuous and unobtrusive way. This environment requires information such as the person, his/her preferences, and habits which is available in the ubiquitous system. In this paper, we propose the context aware system that can provide the tailored information service for user in ubiquitous computing environment. Our system architecture is divided into 4 domain models such as context awareness, presentation, interface and inference domain. Each domain model can perform some predefined tasks independently. And we suggest the hybrid algorithm combined with fuzzy and Bayesian method in order to reason what is the suitable information for user. We show the possibility for the real application through applying the system to the TGA (Tour Guide Assistant) for Kyoungju historical site.