• 한국컴퓨터정보학회논문지
• /
• 제10권2호
• /
• pp.215-221
• /
• 2005

최근에는 단백질 시퀀스, 소매점 거래 데이터, 웹 로그 등과 같은 상업적이거나 과학적인 데이터의 폭발적인 증가를 볼 수 있다. 이런 데이터들은 순서적인 면을 가지고 있는 시퀀스 데이터들이다. 본 논문에서는 이런 시퀀스 데이터들을 분류하는 문제를 다룬다. 분류 기법 으로는 의사결정 나무나 베이지안 분류기, K-NN방법 등 석러 종류가 있는데, 본 연구에서는 또-U방법을 이용하여 시퀀스들을 분류한다. 또한, 시퀀스들간의 유사도를 구하기 위한 새로운 계산 방법과 효율적인 계산 방법도 제안한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.174-176
• /
• 1997

This paper proposes a unit commitment scheduling method based on hybrid genetic algorithm(GA). When the systems are scaled up, conventional genetic algorithms suffer from computational time limitations because of the growth of the search space. So greatly reduce the search space of the GA and to efficiently deal with the constraints of the problem, priority list unit ordering scheme are incorporated as the initial solution and the minimum up and down time constraints of the units are included. The violations of other constraints are handled by integrating penalty factors. To show the effectiveness of the proposed method. test results for system of 10 units is compared with results obtained using other methods.

• 한국컴퓨터정보학회논문지
• /
• 제11권5호
• /
• pp.321-327
• /
• 2006

최근 들어 상업적이거나 과학적인 데이터들의 폭발적인 증가를 볼 수 있다. 이런 데이터들은 항목들 간의 순서적인 면을 가지고 있는 시퀀스 데이터들이다. 그러나 항목들 간의 순서적인 면을 고려한 클러스터링 연구는 많지 않다. 본 논문에서는 이들 시퀀스 데이터들 간의 유사도를 계산하는 방법과 클러스터링 방법을 연구한다. 특히 다양한 조건을 고려한 확장된 유사도 계산 방법을 제안한다. splice 데이터 셋을 이용하여 본 논문에서 제안하는 클러스터링 방법이 기존 방법 보다 우수하다는 것을 보여준다.

• 디지털산업정보학회논문지
• /
• 제5권4호
• /
• pp.161-168
• /
• 2009

There are many research for efficient, robust and invisible watermarking system that protects the digital contents like a image and animation according to growth of IT industry. First of all, frequency domain watermarking system like DWT(Descrete Wavelet Transform) is excellent because of minimum loss of original image and robustness of external attack. But, if we raise the insertion strength of watermark, then blazing of image occurs on existing DWT watermarking system and we should have a regular square image. In this study, we research the overflow check for preventing image from blazing and a robust and invisible watermarking algorithm. And we research a free-size DWT watermarking system using padding bytes, without a dependency of size.

• 한국경영과학회지
• /
• 제25권1호
• /
• pp.27-36
• /
• 2000

We perform a computational complexity analysis of a heuristic algotithm proposed in the literature for the combinatorial optimization problems extended with a single side-constraint. This algorithm, although such a view was not given in the original work, is a disguised version of an optimal Lagrangian dual solution technique. It also has been observed to be a very efficient heuristic producing near-optimal solutions for the primal problems in some experiments. Especially, the number of iterations grows sublinearly in terms of the network node size so that the heuristic seems to be particularly suitable for the applicatons such as routing with semi-real time requirements. The goal of this paper is to establish a polynomal worst-case complexity of the algorithm. In particular, the obtained complexity bound suports the sublinear growth of the required iterations.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2004년도 추계학술대회
• /
• pp.221-229
• /
• 2004

Recently, there has been enormous growth in the amount of commercial and scientific data, such as protein sequences, retail transactions, and web-logs. Such datasets consist of sequence data that have an inherent sequential nature. However, only a few of the existing clustering algorithms consider sequentiality. This study presents a method for clustering such sequence datasets. The similarity between sequences must be decided before clustering the sequences. This study proposes a new similarity measure to compute the similarity between two sequences using a sequence element. Two clustering algorithms using the proposed similarity measure are proposed: a hierarchical clustering algorithm and a scalable clustering algorithm that uses sampling and a k-nearest neighbor method. Using a splice dataset and synthetic datasets, we show that the quality of clusters generated by our proposed clustering algorithms is better than that of clusters produced by traditional clustering algorithms.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2005년도 전력전자학술대회 논문집
• /
• pp.185-188
• /
• 2005

The recent growth in the use of impactive and nonlinear loads, electronic devices sensitive to power quality has caused many power quality problems. Dynamic voltage restorers(DVR) are known as the best effective and economic means to compensate for power quality problems(especially, voltage sag and swell). In this paper, we addresses the detecting algorithms of an voltage sag and phase for operating DVR. Experimental results are included to illustrate the efficacy of the proposed algorithm.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 춘계학술발표대회
• /
• pp.129-132
• /
• 2016

The importance of the infusion pump monitoring system has become amplified in accordance with the growth of IoT(Internet of Things) technology and medical devices. A monitoring system can be described as an essential part of infusion pump system because the patient must be observed all the time. Infusion pump monitoring system is significant to have better safety and efficiency. In this paper, we propose an efficient algorithm and scheme in the infusion monitoring system. In particular, the proposed algorithm based on the time of the database interlocking part was found to have a 30% higher efficiency than the conventional method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.513-515
• /
• 1995

Based on the concept of Load Supplying Capability of a transmission network, we provides an information concerning network adequacy. In particular this paper describes an algorithm regarding load supplying margin of transmission networks. And a different growth rate is assigned to each load point so that various demand characteristics can be taken into consideration at respective locations. In addition to this, in this paper, both generation and transmission equipment will be considered in determining the system capability. A 10 bus model system is used to demonstrate the capability of the proposed algorithm.

• ETRI Journal
• /
• 제32권4호
• /
• pp.638-641
• /
• 2010

With the growth of memory capacity and density, memory testing and repair with the goal of yield improvement have become more important. Therefore, the development of high efficiency redundancy analysis algorithms is essential to improve yield rate. In this letter, we propose an improved built-in redundancy analysis (BIRA) algorithm with a minimized binary search tree made by simple calculations. The tree is constructed until finding a solution from the most probable branch. This greatly reduces the search spaces for a solution. The proposed BIRA algorithm results in 100% repair efficiency and fast redundancy analysis.