• Communications for Statistical Applications and Methods
• /
• 제22권1호
• /
• pp.55-67
• /
• 2015

An important problem in cluster analysis is the selection of variables that define cluster structure that also eliminate noisy variables that mask cluster structure; in addition, outlier detection is a fundamental task for cluster analysis. Here we provide an automated K-means clustering process combined with variable selection and outlier identification. The Automated K-means clustering procedure consists of three processes: (i) automatically calculating the cluster number and initial cluster center whenever a new variable is added, (ii) identifying outliers for each cluster depending on used variables, (iii) selecting variables defining cluster structure in a forward manner. To select variables, we applied VS-KM (variable-selection heuristic for K-means clustering) procedure (Brusco and Cradit, 2001). To identify outliers, we used a hybrid approach combining a clustering based approach and distance based approach. Simulation results indicate that the proposed automated K-means clustering procedure is effective to select variables and identify outliers. The implemented R program can be obtained at http://www.knou.ac.kr/~sskim/SVOKmeans.r.

• 산업공학
• /
• 제24권2호
• /
• pp.156-163
• /
• 2011

The radiopharmaceutical synthesis for PET (positron emission tomography) is composed of chemical reactions using automated synthetical equipment. Due to the radioactive material, the automated equipment is being frequently developed to replace human operators who conduct dangerous, repetitive and dexterous operations. As to operation, the manipulating program is commonly coded using the spread sheet while the whole actuators are mapped in every step. The process map (program) is changed according to such parameters as temperature of reactor, keeping time, mixture sequence and amount of reagent. In cases of customizing the automated synthetical equipment or developing the new radiopharmaceuticals, lots of experiments should be conducted and the programming mistake is not allowed as it can lead abnormal control of the equipment to leak the radioactive materials. The exact process map has depended on trial and error manner. Thus, this study developed the methodology to tabulate the synthetical process to convert the process map automatically while the synthetical module formation is represented by a network model. The proposed method is validated using the actual radiopharmaceutical synthetical procedure.

• 자동차안전학회지
• /
• 제13권3호
• /
• pp.102-110
• /
• 2021

As an alternative to solving safety, environments, and aging problems, ADS (Automated driving system) in the global automotive market is actively being developed as a new growth industry. In time for the appearance of ADS, relevant regulations and assessment programs must also be developed. For example, safety standards for the Level 3 automated driving system were promulgated in December 2019 by the Ministry of Land, Infrastructure and Transport of Korean government. However, assessment programs such as KNCAP for autonomous functions of ADS have not yet been introduced in Korea as well as globally. The autonomous driving functions of ADS at Level 3 or higher must be capable to recognize, judge and respond to objects and events in a wide variety of complex situations. In this paper, we examined and studied the complex situations, considerations and assessment items that ADS must respond to in the interest of safety for passengers, pedestrians and other road users. We hope this paper will be helpful to develop an execution program in the future.

• 대한치과교정학회지
• /
• 제52권2호
• /
• pp.102-111
• /
• 2022

Objective: To develop and explore the usefulness of an artificial intelligence system for the prediction of the need for dental extractions during orthodontic treatments based on gender, model variables, and cephalometric records. Methods: The gender, model variables, and radiographic records of 214 patients were obtained from an anonymized data bank containing 314 cases treated by two experienced orthodontists. The data were processed using an automated machine learning software (Auto-WEKA) and used to predict the need for extractions. Results: By generating and comparing several prediction models, an accuracy of 93.9% was achieved for determining whether extraction is required or not based on the model and radiographic data. When only model variables were used, an accuracy of 87.4% was attained, whereas a 72.7% accuracy was achieved if only cephalometric information was used. Conclusions: The use of an automated machine learning system allows the generation of orthodontic extraction prediction models. The accuracy of the optimal extraction prediction models increases with the combination of model and cephalometric data for the analytical process.

• 인터넷정보학회논문지
• /
• 제9권2호
• /
• pp.89-105
• /
• 2008

지금까지 테스트 데이터를 자동으로 생성하기 위한 대부분의 연구는 프로그램에 포인터가 존재하지 않는 경우만을 대상으로 하였다. 최근에 포인터가 있는 경우에도 테스트 데이터를 자동으로 생성할 수 있는 방법들이 제안되었지만 테스트할 프로그램 경로를 완전하게 명시해야 하는 경로 기반 방법이거나 프로그램을 실제 실행해야 하는 방법들이다. 이 논문에서는 프로그램 경로를 완전하게 명시하지 않아도 포인터가 있는 프로그램에 대하여 테스트 데이터를 생성할 수 있는 새로운 방법을 제안한다. 제안된 방법은 테스트 데이터 생성 문제를SAT(SATisfiability) 문제로 변환하고 SAT 해결도구를 이용하여 자동으로 테스트 데이터를 생성하는 정적 방법이다. 이를 위해 프로그램을 1차 관계 논리 언어인 Alloy로 변환하고 Alloy 분석기를 통하여 테스트 데이터를 생성한다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2014년도 춘계 종합학술대회 논문집
• /
• pp.239-240
• /
• 2014

Researchers in KISTI have been participating in the WISET Fellow Mentoring program since 2009 [1]. We describe the history and future of WISET Fellow Mentoring program from KISTI. We have communicated with mentees more freely and effectively using complementary online and offline system. In addition, we designed a automated matching process in order to help mentors and mentees to begin mentoring with satisfaction [2-6]. In the future, we plan to use our automated matching process for matching candidate mentors and mentees in order to obtain more satisfaction in mentoring.

• 한국CDE학회논문집
• /
• 제17권5호
• /
• pp.364-374
• /
• 2012

In this paper, we proposed a data structure to represent structural components of solid rocket motors (SRM) in an automated design program. To propose the data structure, we searched the necessary functions for the automated design program should have. In order to design the structural components of solid rocket motors sufficiently with a design program, it should have the functions to represent the shapes of the components, the drawing and analysis models, the design variables, various product structures, interferences, characteristic properties, design equations, and tightening sets. By modifying the data structure of an element object that is a general purpose data structure to represent a general component of a product, a new data structure was proposed to satisfy all the necessary functions with optimum. Finally, a design program for the structural components of solid rocket motors was developed successfully with the proposed data structure.

• 한국항공우주학회지
• /
• 제35권8호
• /
• pp.685-692
• /
• 2007

본 연구에서는 헬리콥터 하중 해석을 위한 통합해석코드에서 사용되는 에어포일의 공력 성능 테이블 작성 자동화를 위한 GUI 프로그램을 개발하였다. 개발 후 상용화를 위해 PC환경에서 사용이 보편화 되어 있는 윈도우 운영체제 기반으로 프로그램을 개발하였다. 또한, 별도의 과정을 거치지 않고도 계산 과정 및 생성된 격자 표시등의 결과를 확인할 수 있는 후처리 기능을 포함하여 사용자의 편의를 도모하였다. 기 검증된 기존의 전산유체역학 코드를 기본으로 하여 다양한 받음각과 마하수 영역에서 공력해석이 자동적으로 수행되도록 하였으며, 계산 격자는 에어포일 표면 좌표가 입력되면 자동으로 생성되도록 하였다. FORTRAN 으로 작성된 전산유체역학 코드를 별도의 변환 과정 없이 C++ 기반의 GUI 프로그램과 연동시키기 위하여 Mixed-Language 기법을 사용하였다.

• 경영과학
• /
• 제11권1호
• /
• pp.1-21
• /
• 1994

We usually use the simulation technique in the evaluation and the test of a design alternative of Automated Guided Vehicle System. In this paper, we introduce a simulation code generator which can assist simulation programmer in model development and programming. It consists of user interface, program editor, and program sorter. SIMAN is used as the target language.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2008년도 춘계종합학술대회 A
• /
• pp.556-559
• /
• 2008

용접부 내에 존재하는 결함의 형태, 위치, 크기 등의 정보를 정량적으로 파악하기 위하여 초음파 탐상 검사가 많이 활용되는데, 최근 들어 용접부의 결함 탐상을 위해, 검사과정을 기계적 스캐너로 자동화한 자동 초음파 탐상 시스템이 많은 산업분야에서 활용되고 있고, 특히 배관 용접부의 건전성 평가를 위한 비 파괴안전진단에서 그 활용 폭이 커지고 있다. 배관 용접부 건전성 제고를 위해 본 연구를 통해 용접부 결함 영상화 프로그램을 구현하였다.