• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.713-716
• /
• 2005

In this paper, in order to identify and recognize attack patterns, we propose a Bayesian classification using frequent patterns. In theory, Bayesian classifiers guarantee the minimum error rate compared to all other classifiers. However, in practice this is not always the case owing to inaccuracies in the unrealistic assumption{ class conditional independence) made for its use. Our method addresses the problem of attribute dependence by discovering frequent patterns. It generates frequent patterns using an efficient FP-growth approach. Since the volume of patterns produced can be large, we propose a pruning technique for selection only interesting patterns. Also, this method estimates the probability of a new case using different product approximations, where each product approximation assumes different independence of the attributes. Our experiments show that the proposed classifier achieves higher accuracy and is more efficient than other classifiers.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2007년도 춘계학술발표대회
• /
• pp.10-13
• /
• 2007

모티프는 진화과정을 거치면서 단백질 서열상에서 부분적으로 높게 보존된 지역을 의미한다. 이러한 모티프는 단백질의 기능과 구조를 예측하거나 생물학적으로 관련성이 있는 단백질의 공통적인 특성을 기술하는데 사용된다. 또한, 모티프와 단백질 서열의 상관관계는 생물학적 기능 예측에 필수적이며, 이러한 예측 문제는 모티프 검색을 통해 서열에 존재하는 빈발한 서열패턴과 구조패턴을 통해 단백질 서열에 대한 분석이 가능하다. 이 논문에서는 단백질 서열에 존재하는 2차 구조 특성과 빈발패턴을 검색하고 추출된 정보를 이용하여 단백질 기능 분류에 활용하고자 한다.

• 대한약학회:학술대회논문집
• /
• 대한약학회 2003년도 Proceedings of the Convention of the Pharmaceutical Society of Korea Vol.2-2
• /
• pp.185.2-185.2
• /
• 2003

The typical approach of virtual screening is to prepare a 3D database and dock each member to the receptor, and carry out a post-analysis to make a final selection of compounds to be tested. The biological test of these compounds leads to 'hit'. The size of the 3D database is rate-determining factor because the docking process is still time-consuming method. The number of compounds for biological testing is cost-determining factor because the materials used in the test are cost-consuming. The use of the representative subsets derived from the entire database help reduce runtime of docking procedure. (omitted)

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2000년도 특별강연 및 추계학술발표대회 개요집
• /
• pp.54-57
• /
• 2000

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1995년도 춘계공동학술대회논문집; 전남대학교; 28-29 Apr. 1995
• /
• pp.79-90
• /
• 1995

The material handling equipment selection, that is a key task in the material handling system design, is a complex, difficult task, and requires a massive technical knowledge and systematic analysis. It is invaluable to justify the selected equipment model by the performance evaluation before its actual implementation. This paper presents an intelligent knowledge-based expert system called "IMESE" created by authors, for the selection and evaluation of material handling equipment model suitable for movement and storage of materials in a manufacturing facility. The IMESE is consisted of four modules: a knowledge base to select an appropriate equipment type, a multiple criteria decision making procedure to choose the most favorable commercial model of the selected equipment type, a database to store the list of commercial models of equipment types with their specifications, and simulators to evaluate the performance of the equipment model. The whole process of IMESE is executed under VP-Expert expert system environment.vironment.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.673-676
• /
• 2004

To manage and query moving objects efficiently in MMDBMS, a memory index structure should be used. The most popular index structure for storing trajectories of moving objects is 3DR-tree. The 3DR-tree also can be used for MMDBMS. However, the volume of data can exceed the capacity of physical memory since moving objects report their locations continuously. To accommodate new location reports, old trajectories should be migrated to disk or purged from memory. This paper focuses on migration policies of a main memory index structure. Migration policies consist of two steps: (i) node selection, (ii) node placement. The first step (node selection) selects nodes that should be migrated to disk. The criteria of selection are the performance of insertion or query. The second step (node placement) determines the order of nodes written to disk. This step can be thought as dynamic declustering policies.

• 한국정보통신학회논문지
• /
• 제10권9호
• /
• pp.1612-1616
• /
• 2006

모바일 환경에서 지도 서비스를 위해서는 휴대 단말기의 제한된 자원을 고려한 접근방법 이 요구된다. 모바일 서비스 전용 지도 데이터 베이스를 별도로 개발하여 사용하지 않는다면 지도 데이터를 축소하여 휴대 단말기로 전송할 필요가 있다. 본 논문은 기존의 유선 지도 데이터 베이스로부터 검색한 지도를 휴대 단말기에 출력이 가능하도록 하는 필터링(filtering) 기법을 제안하고 성능을 평가한다. 이 필터링 기법은 지도 일반화(generalization) 기법의 'selection' 연산에 기반하여 휴대폰 환경에 적합하도록 변형 한 것이다.

• 한국컴퓨터정보학회논문지
• /
• 제21권1호
• /
• pp.9-16
• /
• 2016

In this paper, we present a performance evaluation agent based on fuzzy cluster analysis and validity measures. The proposed agent is consists of three modules, fuzzy cluster analyzer, performance evaluation measures, and feature ranking algorithm for feature selection step in CAD system. Feature selection is an important step commonly used to create more accurate system to help human experts. Through this agent, we get the feature ranking on the dataset of mass and calcification lesions extracted from the public real world mammogram database DDSM. Also we design a CAD system incorporating the agent and apply five different feature combinations to the system. Experimental results proposed approach has higher classification accuracy and shows the feasibility as a diagnosis supporting tool.

• 동의생리병리학회지
• /
• 제24권4호
• /
• pp.543-552
• /
• 2010

The objectives of this study are to examine the current status and problems of herb-drug interaction (HDI) information and information database in Korea and suggest the better way to establish useful HDI database. We collected HDI studies that published in Korea and analyzed according to objective, methods, selection criteria of herbs, number of study, correlation between study subject and frequently used herbal medicine (HM). Then we selected representative HM database on the internet made by Korea Food and Drug Administration (KFDA) among the several databases and analyzed its contents related to HDI. Several HDI studies were carried out from laboratory based research to clinical trials and HM databases have been developed for providing information about different aspects of traditional Korean medicine. But the information of HDI and information database are still far from practical applications because there are no coherence to select study subjects and methods among researchers. So, it is necessary to build up HDI database led by the government for providing systematic HDI information. HDI information database is expected to be able to provide useful evidence for health professionals in prescription and consultation to reduce the chance of adverse effects and improve the quality of medical care.

• 한국음향학회지
• /
• 제31권1호
• /
• pp.39-50
• /
• 2012

A voice transformation (VT) method that can make the utterance of a source speaker mimic that of a target speaker is described. Speaker individuality transformation is achieved by altering three feature parameters, which include the LPC cepstrum, pitch period and gain. The main objective of this study involves construction of an optimal sequence of features selected from a target speaker's database, to maximize both the correlation probabilities between the transformed and the source features and the likelihood of the transformed features with respect to the target model. A set of two-pass conversion rules is proposed, where the feature parameters are first selected from a database then the optimal sequence of the feature parameters is then constructed in the second pass. The conversion rules were developed using a statistical approach that employed a maximum likelihood criterion. In constructing an optimal sequence of the features, a hidden Markov model (HMM) was employed to find the most likely combination of the features with respect to the target speaker's model. The effectiveness of the proposed transformation method was evaluated using objective tests and informal listening tests. We confirmed that the proposed method leads to perceptually more preferred results, compared with the conventional methods.