• 한국CDE학회논문집
• /
• 제2권2호
• /
• pp.111-121
• /
• 1997

This study intends to develop a fixture planning module as a part of the planning system for cutting. The fixture module uses machine learning method to reuse previous failure results so that the system can reduce the repeated failures. Machine learning is one of efforts to incorporate human reasoning ability into a computerized system. A human expert designs better than a novice does because he has a wide experience in a specific area. This study implements the machine learning algorithm to have a wide experience in the fixture planning area as a human expert does. When the fixture planner finds a setup failure for the suggested operations by a process planner, it makes the process planner store its attributes and other information for the failed setup. Then the process planner applies the learned knowledge when it meets a similar case so that the planner can reduce possibility of setup failure. Also the system can teach a novice user by showing a failed setup with a modified setup.

• 한국콘텐츠학회논문지
• /
• 제14권4호
• /
• pp.19-28
• /
• 2014

최근 IT산업의 발전은 우리의 삶을 보다 윤택하게 만들어주고 있다. 특히, 스마트폰의 GPS를 이용하여 개인의 위치를 검출하는 다양한 연구가 진행되고 있으며, 긴급구조기관 등에서 적극 활용하려 하고 있다. 하지만 기존 이러한 방식은 임의의 반경 영역을 생성하여 사용자가 해당 영역이 설정된 공간에 진입하거나 이탈하였을 경우 미리 지정된 사용자의 보호자나 관제기관으로 사용자의 위치정보를 전송하는 방법이 시행되고 있지만 특정 길, 놀이동산과 산행 등 정형화되지 않은 공간 및 경로에 대해서는 기존의 반경 영역을 생성하는 방식을 사용할 경우 세부적인 영역 설정이 어려웠다. 본 논문에서는 스마트 기기나 웹에서도 세부적인 영역을 쉽게 설정하기 위해 기존 서비스에서 이용하는 반경 방식을 개선하여 반경과 반경 사이를 연결하여 영역을 설정하는 방법을 제안하였다. 또한 제안하는 위치 기반 영역 설정 방법 및 이탈 검출을 활용하여 사용자의 위치를 검출하는 연산 과정에서 연산 결과를 비교하여 자원 사용을 최적화할 수 있는 방법을 제안한다.

• 대한산업공학회지
• /
• 제21권2호
• /
• pp.217-237
• /
• 1995

One of the most distinguished advantages of five-axis machining is that complex free surfaces(such as impeller) can be machined by one setup. Five-axis CNC machine, however, is very expensive so that its usage is restricted to a few large companies. As an economical approach to five-axis machining, this paper presents a method for machining the five-axis free surfaces(using ball-end mill) on a three-axis CNC machine with an index table. The method developed consists of: a) determining the minimum number of part setups and their interference-free and collision-free potential machining area, b) calculating actual machining area for each setup, and c) generating 3-axis cutter path for each part setup. The method has been successfully tested via computer simulations for several complex surfaces including impeller.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.11-15
• /
• 2020

In a typical initial setup of a PCB component inspection system, operators should manually input various information such as category, position, and inspection area for each component to be inspected, thus causing much inconvenience and longer setup time. Although there are many deep learning based object detectors, RetinaNet is regarded as one of best object detectors currently available. In this paper, a method using an extended RetinaNet is proposed that automatically detects its component category and position for each component mounted on PCBs from a high-resolution color input image. We extended the basic RetinaNet feature pyramid network by adding a feature pyramid layer having higher spatial resolution to the basic feature pyramid. It was demonstrated by experiments that the extended RetinaNet can detect successfully very small components that could be missed by the basic RetinaNet. Using the proposed method could enable automatic generation of inspection areas, thus considerably reducing the setup time of PCB component inspection systems.

• 한국지능시스템학회논문지
• /
• 제26권2호
• /
• pp.105-112
• /
• 2016

본 논문은 대학 캠퍼스를 주행하는 차량의 자율주행을 위한 실험환경 구축에 대해 논한다. 이 차량은 대학이나 공원과 같은 특별한 장소에서 사용되고 근거리를 이동하기 위해 2인이 탑승한다. 정문에서 본부까지 자율주행을 수행하기 위한 실험환경을 구축한다. 초기 단계로 카메라로 바닥의 색깔을 구별하여 선을 검출한다. 빨간색과 노란색의 경계선을 검출하여 로봇차량이 추종할 수 있도록 하였다. 일부 구간의 자율 주행 실험을 통해 가능성을 검증하였다.

• 한국콘텐츠학회논문지
• /
• 제9권1호
• /
• pp.167-176
• /
• 2009

기존의 클러스터 라우팅 방식은 클러스터 헤드를 선출하여 클러스터 내의 멤버 노드들로부터 정보를 수집하고 압축하여 기지국에 전송함으로써 에너지 효율을 높일 수 있는 대표적인 방식이다. 그러나 클러스터 형성 단계 중 매 라운드마다 셋업 단계에서 선출된 클러스터 헤드와 클러스터 내의 멤버 노드들 간의 빈번한 정보 교환으로 인해 발생하는 불필요한 에너지 소모는 클러스터 라우팅 방식이 해결해야 하는 과제이다. 본 논문에서는 셋업 단계에서의 선출된 클러스터 헤드와 기존의 클러스터 헤드 사이에 변경되지 않는 중첩된 영역에 속한 멤버 노드들을 계산함으로써, 중첩된 멤버 노드들의 셋업 단계에서의 불필요한 송수신 횟수를 줄여 정보 교환을 최소화하였다. 따라서 셋업 단계에서의 소모되는 에너지를 절약하여 안정 단계에서 효율적으로 사용함으로써, 에너지의 효율적인 사용과 전체적인 네트워크의 생존시간을 증가시키고자 하며, 전체 네트워크내의 멤버들에게 클러스터 헤드가 될 수 있는 균등한 기회를 주고자 하는클러스터 헤드 선출 프로토콜을 제안한다.

• 융합신호처리학회논문지
• /
• 제14권2호
• /
• pp.105-109
• /
• 2013

There are the free space model, the direct-path and ground reflected model, Egli model, Okumura-Hata model in the representative propagational models. The measured results at the area of PNG area were used as the experimental data in this paper. The new proposed partial interval analysis method is applied on the measured propagation data in the cellular band. The interval for the analysis is divided from the entire 30 Km distance to 5 Km, and next to 1 Km. The best-fit propagation models are chosen on all partial intervals. The means and standard deviations are calculated for the differences between the measured data and all partial interval models. By using the 5 Km- or 1 Km- partial interval analysis, the standard deviation between the measured data and the partial propagation models was improved more than 1.7 dB.

• Journal of the Korean Data and Information Science Society
• /
• 제28권6호
• /
• pp.1547-1555
• /
• 2017

This paper studies Bayesian test of homogeneity in contingency tables made by discretizing a continuous variable. Sometimes when we are considering events of interest in small area setup, we can think of discretization approaches about the continuous variable. If we properly discretize the continuous variable, we can find invisible relationships between areas (groups) and a continuous variable of interest. The proper discretization of the continuous variable can support the alternative hypothesis of the homogeneity test in contingency tables even if the null hypothesis was not rejected through k-sample tests involving one-way ANOVA. In other words, the proportions of variables with a particular level can vary from group to group by the discretization. If we discretize the the continuous variable, it can be treated as an analysis of the contingency table. In this case, the chi-squared test is the most commonly employed method. However, further discretization gives rise to more cells in the table. As a result, the count in the cells becomes smaller and the accuracy of the test becomes lower. To prevent this, we can consider the Bayesian approach and apply it to the setup of the homogeneity test.

• Journal of the Korean Data and Information Science Society
• /
• 제28권1호
• /
• pp.207-215
• /
• 2017

In this paper we study pooling effects in Bayesian testing procedures of independence for contingency tables from small areas. In small area estimation setup, we typically use a hierarchical Bayesian model for borrowing strength across small areas. This techniques of borrowing strength in small area estimation is used to construct a Bayes test of independence for contingency tables from small areas. In specific, we consider the methods of direct or indirect pooling in multinomial models through Dirichlet priors. We use the Bayes factor (or equivalently the ratio of the marginal likelihoods) to construct the Bayes test, and the marginal density is obtained by integrating the joint density function over all parameters. The Bayes test is computed by performing a Monte Carlo integration based on the method proposed by Nandram and Kim (2002).

• 한국실내디자인학회논문집
• /
• 제22권1호
• /
• pp.174-182
• /
• 2013

This study divided the observation area in an indoor space for area setup to analyse the effect of the difference of design types on the characteristics of observation with the observed time of each area as objects. Though it is thought that the difference of design patterns may be influenced by the factors and material composing the space, no existing approaches have had any quantitatively measuring method. Eye-tracking could be efficiently utilized for observation analysis from the viewpoint of dating observation behavior. The followings are the results of analysing the observation characteristics depending on design pattern. First, 5 observing areas were set up according to concentration of observation time in order for the concentration by area to be examined and the factors of design having effect on the difference of observation patterns by design type could be analysed. Second, as a whole, the observation of modern types showed high observation characteristics. When the difference of observation characteristics by pattern was examined by difference at observation frequency, the observation frequency defined to be more than 50% was seen to be almost same from Area I to III and to get higher from Area IV, and that defined to be 30% was high at Areas III and IV. In Area V, it was very high at natural. Third, that of Area II is no more than 8.2% but had the most observation time. As for observation characteristics, the horizontal observation of the central part was the highest and had more observation frequency at modern type that at natural one. These observation characteristics by area enabled to analyse the observation tendency depending on design characters at relevant area. Fourth, the design factors composing natural type were found to bring more attention when the area showed higher concentration at natural type than at modern one. And the analysis of design factors could make it to be confirmed that the quality of material and background factors in addition to design factors in the area had more effect on sight concentration.