• Journal of Mechanical Science and Technology
• /
• 제19권5호
• /
• pp.1080-1086
• /
• 2005

The preliminary design optimization of multi-stage spur gear reduction units has been a subject of considerable interest, since many high-performance power transmission applications (e.g., automotive and aerospace) require high-performance gear reduction units. There are multiple objectives in the optimal design of multi-stage spur gear reduction unit, such as minimizing the volume and maximizing the surface fatigue life. It is reasonable to formulate the design of spur gear reduction unit as a multi-objective optimization problem, and find an appropriate approach to solve it. In this paper an interactive physical programming approach is developed to place physical programming into an interactive framework in a natural way. Class functions, which are used to represent the designer's preferences on design objectives, are fixed during the interactive physical programming procedure. After a Pareto solution is generated, a preference offset is added into the class function of each objective based on whether the designer would like to improve this objective or sacrifice the objective so as to improve other objectives. The preference offsets are adjusted during the interactive physical programming procedure, and an optimal solution that satisfies the designer's preferences is supposed to be obtained by the end of the procedure. An optimization problem of three-stage spur gear reduction unit is given to illustrate the effectiveness of the proposed approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.785-804
• /
• 2017

Due to various factors such as postures, facial expressions and illuminations, face recognition by videos often suffer from poor recognition accuracy and generalization ability, since the within-class scatter might even be higher than the between-class one. Herein we address this problem by proposing a hierarchical cascaded classifier for video face recognition, which is a multi-layer algorithm and accounts for the misclassified samples plus their similar samples. Specifically, it can be decomposed into single classifier construction and multi-layer classifier design stages. In single classifier construction stage, classifier is created by clustering and the number of classes is computed by analyzing distance tree. In multi-layer classifier design stage, the next layer is created for the misclassified samples and similar ones, then cascaded to a hierarchical classifier. The experiments on the database collected by ourselves show that the recognition accuracy of the proposed classifier outperforms the compared recognition algorithms, such as neural network and sparse representation.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1083-1094
• /
• 2020

Recognizing plant species based on leaf images is challenging because of the large inter-class variation and inter-class similarities among different plant species. The effective extraction of leaf descriptors constitutes the most important problem in plant leaf recognition. In this paper, a multi-scale angular description method is proposed for fast and accurate leaf recognition and retrieval tasks. The proposed method uses a novel scale-generation rule to develop an angular description of leaf contours. It is parameter-free and can capture leaf features from coarse to fine at multiple scales. A fast Fourier transform is used to make the descriptor compact and is effective in matching samples. Both support vector machine and k-nearest neighbors are used to classify leaves. Leaf recognition and retrieval experiments were conducted on three challenging datasets, namely Swedish leaf, Flavia leaf, and ImageCLEF2012 leaf. The results are evaluated with the widely used standard metrics and compared with several state-of-the-art methods. The results and comparisons show that the proposed method not only requires a low computational time, but also achieves good recognition and retrieval accuracies on challenging datasets.

• 한국정보처리학회논문지
• /
• 제2권5호
• /
• pp.746-756
• /
• 1995

본 논문은 다중 뷰를 이용한 대화식 시각 프로그래밍 환경에 관한 연구로서, C＋＋언어 프로그래밍을 위한 클래스의 시각화와 호출되는 멤버 함수의 흐름을 시각 화하는 뷰들을 제공한다. 본 연구는 클래스에 대한 새로운 시각 기호를 정의하고, 시 각 기호를 이용한 다양한 뷰의 대화식 시각 프로그래밍 환경을 구성 하였다. 대화식 다중 뷰 시각 프로그래밍 환경은 객체지향 언어에서 클래스의 표현과 객체간의 실행 관계를 시각적으로 표현하므로써 객체지향 프로그램의 전체 구조에 대한 파악이 용이 하여 프로그램의 개발이 손쉬워지고, 초보자를 위한 교육과 훈련에도 유용하게 사용 될 수 있다.

• 한국전기화학회:학술대회논문집
• /
• 한국전기화학회 2000년도 추계총회 및 학술발표회
• /
• pp.51-51
• /
• 2000

• 한국경영과학회지
• /
• 제14권2호
• /
• pp.97-104
• /
• 1989

This paper extends the existence proofs of a Nash equilibrium to a more general class of differentila game models with constraints on the control spaces. With the assumptions of continuity, convexity, and compactness, the existence is proved using Kakutani Theorem and via a path-following approach. Furthermore, the proof for a period-by-period optimization of multi-period problems provides an insight to a numerical solution algorithm to differential game models with constraints.

• Journal of Information Display
• /
• 제2권2호
• /
• pp.13-21
• /
• 2001

We propose a universal image processor for a-Si TFT LCD of UXGA class that can display the full screen on the LCD panel with low resolution of video sources such as NTSC, VGA, SVGA, XGA, and SXGA by using the proposed interpolation filter. In addition, we propose a real-time contrast controller for image improvement of multi-gray scale image. The operation of the proposed methods has been verified using Synopsys VHDL and computer simulation. Results show that the proposed methods might be suitable for a UXGA LCD controller for real-time image improvement.

• 호남수학학술지
• /
• 제8권1호
• /
• pp.21-49
• /
• 1986

A class of singular quadratic control problem is considered. The state is governed by a higher order system of ordinary linear differential equations and very general nonstandard boundary conditions. These conditions in many important cases reduce to standard boundary conditions and because of the conditions the usual controllability condition is not needed. In the special case where the coefficient matrix of the control variable in the cost functional is a time-independent singular matrix, the corresponding optimal control law as well as the optimal controller are computed. The method of investigation is based on the theory of least-squares solutions of multi-valued operator equations.

• 지능정보연구
• /
• 제27권3호
• /
• pp.175-197
• /
• 2021

최근 딥 러닝 기술의 발전으로 뉴스, 블로그 등 다양한 문서에 포함된 텍스트 분석에 딥 러닝 기술을 활용하는 연구가 활발하게 수행되고 있다. 다양한 텍스트 분석 응용 가운데, 텍스트 분류는 학계와 업계에서 가장 많이 활용되는 대표적인 기술이다. 텍스트 분류의 활용 예로는 정답 레이블이 하나만 존재하는 이진 클래스 분류와 다중 클래스 분류, 그리고 정답 레이블이 여러 개 존재하는 다중 레이블 분류 등이 있다. 특히, 다중 레이블 분류는 여러 개의 정답 레이블이 존재한다는 특성 때문에 일반적인 분류와는 상이한 학습 방법이 요구된다. 또한, 다중 레이블 분류 문제는 레이블과 클래스의 개수가 증가할수록 예측의 난이도가 상승한다는 측면에서 데이터 과학 분야의 난제로 여겨지고 있다. 따라서 이를 해결하기 위해 다수의 레이블을 압축한 후 압축된 레이블을 예측하고, 예측된 압축 레이블을 원래 레이블로 복원하는 레이블 임베딩이 많이 활용되고 있다. 대표적으로 딥 러닝 모델인 오토인코더 기반 레이블 임베딩이 이러한 목적으로 사용되고 있지만, 이러한 기법은 클래스의 수가 무수히 많은 고차원 레이블 공간을 저차원 잠재 레이블 공간으로 압축할 때 많은 정보 손실을 야기한다는 한계가 있다. 이에 본 연구에서는 오토인코더의 인코더와 디코더 각각에 스킵 연결을 추가하여, 고차원 레이블 공간의 압축 과정에서 정보 손실을 최소화할 수 있는 레이블 임베딩 방법을 제안한다. 또한 학술연구정보서비스인 'RISS'에서 수집한 학술논문 4,675건에 대해 각 논문의 초록으로부터 해당 논문의 다중 키워드를 예측하는 실험을 수행한 결과, 제안 방법론이 기존의 일반 오토인코더 기반 레이블 임베딩 기법에 비해 정확도, 정밀도, 재현율, 그리고 F1 점수 등 모든 측면에서 우수한 성능을 나타냄을 확인하였다.

• Journal of Communications and Networks
• /
• 제10권3호
• /
• pp.351-361
• /
• 2008

This paper presents a delay-margin based traffic engineering (TE) approach to provide end-to-end quality of service (QoS) in multi-protocol label switching (MPLS) networks using differentiated services (DiffServ) at the link level. The TE, including delay, class, and route assignments, is formulated as a nonlinear optimization problem reflecting the inter-class and inter-link dependency introduced by DiffServ and end-to-end QoS requirements. Three algorithms are used to provide a solution to the problem: The first two, centralized offline route configuration and link-class delay assignment, operate in the convex areas of the feasible region to consecutively reduce the objective function using a per-link per-class decomposition of the objective function gradient. The third one is a heuristic that promotes/demotes connections at different links in order to deal with concave areas that may be produced by a trunk route usage of more than one class on a given link. Approximations of the three algorithms suitable for on-line distributed TE operation are also derived. Simulation is used to show that proposed approach can increase the number of users while maintaining end-to-end QoS requirements.