• 한국음향학회지
• /
• 제13권6호
• /
• pp.83-90
• /
• 1994

본 논문에서는 코호넨(Kohonen)의 SOFM (Self-Organizing Feature Map) 알고리즘의 단점을 해결하기 위한 새로운 학습 알고리즘 ASOFM(Adaptive Self-Organized Feature Map)을 제안한다. 코호넨의 학습 알고리즘은 초기화된 연결 벡터에 대하여 극소점에 빠지는 경우도 있다. 그러나 제안된 알고리즘에서는 학습과정중에 네트워크의 상태를 평가할 수 있는 목적함수(object function)을 사용하였고, 이 함수의 출력에 따라 학습의 각 시점에서 적응적으로 학습률의 재조정이 가능하였다. 이 결과, 네트워크의 상태가 최소점에 수렴함이 보증 되고 학습률의 적응성에 의해 임의의 학습패턴에 대한 학습의 일반화 능력이 보장되었다. 또한 제안된 알고리즘은 코호넨의 알고리즘보다 약 $70\%$이상의 학습시간을 단축한다.

• 한국정보처리학회논문지
• /
• 제3권6호
• /
• pp.1493-1505
• /
• 1996

인터네트의 사용의 급격한 증가와 멀티미디어 정보의 보편화에 따라 이를 이용하 는 다양한 전자우편 프로토콜들이 나타나고 있다. 이러한 전자우편의 상용화와 전자 우편을 통한 개인정보 및 주요정보 보호를 위해서는 암호화 기법을 이용한 보안기능 이 필수적이다. 논 논문은 멀티미디어를 지원하는 인터네트 전자우편(MIME;Multi -Purpose Internet Mail Extension)에 보안 기능을 추가한 MOSS(MIME Object Security Service)의 효과적 처리에 필요한 라이브러리 함수개발에 관하여 기술하였 다. 이를 위하여 MINE구조로 나타나는 암호화와 복호화, 전자결재 및 검증등의 보안 기능 처리를 위한 MOSS의 특성 및 구조에 관하여 기술하고 이를 실질적으로 개발하기 위한 자료구조 및 필요한 함수들을 정의하였으며 개발시 고려하여야 할 사항들에 대 하여 기술하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1779-1784
• /
• 1991

The problem of fine manipulation is considered in this paper. By fine manipulation, we mean the positioning of the object relative to the palm as opposed to gross manipulation by the arm. The compliance in the fingers and the object is modeled by linear springs. It is shown that the motion of the fingers and object can be predicted by minimizing a quadratic objective function. A method for simulating position control algorithms is developed.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 D
• /
• pp.2667-2670
• /
• 2005

In this Paper is analyzed about FMS(Fieldbus Message Specification) service of FOUNDATION Fieldbus and designed using of UML(Unified Modeling Language). The FMS provides a number of services for reading, writing, and otherwise accessing objects. The FOUNDATION Fieldbus protocol is object oriented. The information in the devices is accessed in the form of objects. In FMS, the objects for configuring device and strategy in a node are listed in an object dictionary(OD). Each object is identified by an index. For example, every function block and every parameter has an index.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
• /
• pp.153-156
• /
• 2003

This paper proposes a video tracking method for a deformable moving object using an active contour model. In order to decide the convergent directions of the contour points automatically, a new energy function based on a frame difference map and an updating rules of the frame difference map are presented. Experimental results on a set of synthetic and real image sequences showed that the proposed method can fully track a speedy deformable object while extracting the boundary of the object exactly in every frame.

• Journal of Electrical Engineering and information Science
• /
• 제1권2호
• /
• pp.27-32
• /
• 1996

In target tracking area, the data association plays an important role and has been studied extensively. In this paper, after defining the data association as a constrained optimization, we introduce a new energy function and thereby an efficient realization of neural networks. As an application, this algorithm is used to detect object boundaries in IR images. The problem is that the IR image noisy, the shape of the object is variable, and the positions of the end points are not predictable. The performance of this algorithm is discussed with the experimental results.

• 호남수학학술지
• /
• 제35권2호
• /
• pp.137-146
• /
• 2013

Motivated essentially by their potential for applications in a wide range of mathematical and physical problems, the log-sine and log-cosine integrals have been evaluated, in the existing literature on the subject, in many different ways. The main object of this paper is to present explicit evaluations of some families of log-sine and log-cosine integrals by making use of the familiar Beta function.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2010년도 하계학술대회
• /
• pp.138-141
• /
• 2010

In this paper, we propose a semi-automatic method for semantic video object extraction which extracts meaningful objects from an input sequence with one correctly segmented training image. Given one correctly segmented image acquired by the user's interaction in the first frame, the proposed method automatically segments and tracks the objects in the following frames. We formulate the semantic object extraction procedure as an energy minimization problem at the fragment level instead of pixel level. The proposed energy function consists of two terms: data term and smoothness term. The data term is computed by considering patch similarity, color, and motion information. Then, the smoothness term is introduced to enforce the spatial continuity. Finally, iterated conditional modes (ICM) optimization is used to minimize energy function in a globally optimal manner. The proposed semantic video object extraction method provides faithful results for various types of image sequences.

• 가정과삶의질연구
• /
• 제30권5호
• /
• pp.149-161
• /
• 2012

Family policy and parents support policy are similar in that they are both object-oriented, not function-oriented. An object-oriented policy, different from a function-oriented policy, is demander-oriented in that it combines the existing policies from the object-perspective. Parents support policy and family policy are very similar in that they are both object-oriented policies and emphasize the perspective of the demanders: the parents and family. As is the case for all policies, if the ministries concerned with the policies are different, the projects are promoted from different delivery systems, so it is difficult to link them together. However, it is essential to relate the two policies because a partnership between families and schools, the subjects of the policy, is the basis of healthy family and a healthy society. Therefore, this research analyzes the current family policy and parents support policy, and examines the necessity and possibility of relating the two policies. This analysis is meaningful in that it seeks consilience between the policy areas, and seeks a new demander-oriented paradigm construction system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권11호
• /
• pp.5496-5521
• /
• 2018

Object detection and tracking is the basic capability of mobile robots to achieve natural human-robot interaction. In this paper, an object tracking system of mobile robot is designed and validated using improved multiple instance learning algorithm. The improved multiple instance learning algorithm which prevents model drift significantly. Secondly, in order to improve the capability of classifiers, an active sample selection strategy is proposed by optimizing a bag Fisher information function instead of the bag likelihood function, which dynamically chooses most discriminative samples for classifier training. Furthermore, we integrate the co-training criterion into algorithm to update the appearance model accurately and avoid error accumulation. Finally, we evaluate our system on challenging sequences and an indoor environment in a laboratory. And the experiment results demonstrate that the proposed methods can stably and robustly track moving object.