• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2005년도 춘계학술대회논문집
• /
• pp.437-442
• /
• 2005

In this paper, we proposed the 2-dimensional inspection algorithm for micro-BGA(Ball Grid Array) device using a vision system. The proposed method uses the subpixel algorithm for high precision. The proposed algorithm preferentially extracts the package area of device in the input image. After the extraction of package area, each ball areas are extracted by ball search window method. The parameters for inspection are calculated for the extracted ball area. In the simulation results, we have the average error within $17{\mu}m$.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제17권2호
• /
• pp.129-135
• /
• 2017

Purpose: This article provides step-stress accelerated degradation test (ADT) plans based on the Wiener process. Method: Step-stress levels and the stress change times are determined based on the D-optimality criteria to develop test plans. Further, a simple grid search method is provided for obtaining the optimal test plan. Results: Based on the solution procedure, ADT plans which include the stress levels and change times are developed for conducting the reliability test. Conclusion: Optimal step-stress ADT plans are provided for the case where the number of measurements is small.

• 산업공학
• /
• 제14권2호
• /
• pp.190-197
• /
• 2001

Growth curves including Logistic and Gompertz functions are widely used in forecasting the market demand. To estimated the parameters of those functions, we use the non-linear least square method. However, it is difficult to set up the starting points for each parameter. If a wrong starting point is selected, the result reveals the local optimum or does not converge to a certain value. The purpose of this paper is to resolve the problem of selecting a starting point. Especially, rescaling the market data using the national economic index make it possible to figure out the range of parameters and to utilize the grid search method. Applications to some real data are also included.

• 한국정밀공학회지
• /
• 제17권1호
• /
• pp.27-33
• /
• 2000

This paper presents a method for determining machining parameters in 3-dimentional electrical discharge machining(EDM). The parameters are the peak value of currents, the pulse-on time, and the pulse-off time. It is known that they influence the performance of EDM more than the other else. The parameters are determined from the discharge area between a tool electrode and a work piece. The discharge area is directly influenced by the geometry of a tool surface and the tool discharge position. The discharge area on a tool discharge position is calculated from intersection curves between the tool surface and a horizontal plane. The grid search method is applied to determine the intersection curves. An example is introduced to show that the machining parameters are obtained from the surface geometry of a tool electrode.

• 한국산학기술학회논문지
• /
• 제12권3호
• /
• pp.1458-1464
• /
• 2011

본 연구는 유출분석을 위하여 수문학적 모델에 근거한 지형적인 특성을 반영한 TOPMODEL의 적용성을 평가하는 것이다. 적용대상은 섬진강 상류유역에 위치한 산악지역으로서 쌍치 소유역이고, 유역면적은 $126.7km^2$이다. 2006~2009년에 선택된 6시간 간격의 강우-유출 자료를 가지고 Pattern Search 방법에 의한 관측유출자료를 사용하여 모델의 매개변수들을 조정하였다. 쌍치 유역의 지형학적인 인자들은 $100m{\times}100m$ 격자의 수치 표고모델에 의하여 추출하였다. 분석결과에 의하면 모델의 매개변수인 지수저류 매개변수(m), 투수량계수(T0), 불포화대 지체시간(TD)등은 수문학적인 반응에 민감하였으며, 모의된 유출자료는 관측 유출자료와 잘 일치하여 합리적인 적용성을 보인다.

• 한국정보통신학회논문지
• /
• 제10권12호
• /
• pp.2221-2229
• /
• 2006

최근 모바일 단말기의 위치정보를 활용하는 주요 응용 중의 하나인 최적 경로 탐색 시스템은 출발지와 목적지간의 거리뿐만 아니라 탐색 되어지는 구간에 존재하는 많은 교통 상황들을 파악하고 이를 경로 탐색에 활용해야 한다. 그러나 기존의 경로 탐색 알고리즘은 교통상황들을 적절히 이용하지 못하고 있다. 이 논문에서는 새로운 최적 경로 알고리즘을 제안한다. 알고리즘은 최적 경로를 검색하기 위해 교통상황을 고려하고, 연산비용을 줄이기 위해 도로를 그리드 형태로 나누어 각각의 평균속도를 가지고 휴리스틱 가중치를 부여한다. 또한 알고리즘의 전체 수행시간, 노드 접근 횟수, 최적경로의 정확도를 항목으로 하는 실험을 수행하여 기존의 탐색 알고리즘인 Dijkstra 알고리즘과 A*알고리즘과의 성능평가를 실시하였다. 실험 결과 제안한 알고리즘이 타 알고리즘에 대해 좋은 성능을 보여주었다. 제안한 알고리즘은 향상된 응용을 지원하는 텔레매틱스 시스템에 유용하게 사용될 것으로 기대된다.

• 전기학회논문지
• /
• 제67권9호
• /
• pp.1216-1223
• /
• 2018

As field of application of AMI, AMR uses the power line as the primary means of communication. PLC has a big merit without installation of the new network for communication in a field using the power line which is the existing equipment. However, there is a serious obstacle in commercialization for the instability by noise and communication environment. Therefore, the technical method for maintaining the communication state which overcome such demerit and was stabilized is required essentially. PLC routing technology is applied with the alternative plan now. The routing technology currently managed by field includes many problems by applying the algorithm of an elementary level. PLC routing path search problem can be modeled with the problem of searching for optimal solution as similar to such as optimal routing problem and TSP(Travelling salesman problem). In this paper, in order to search for a PLC routing path efficiently and to choose the optimal path, GA(Genetic Algorithm) was applied. Although PLC was similar in optimal solution search as compared with typical GA, it also has a difference point by the characteristic of communication, and presented the new methodology over this. Moreover, the validity of application technology was verified by showing the experimental result to which GA is applied and analyzing as compared with the existing algorithm.

• 소성∙가공
• /
• 제29권4호
• /
• pp.218-228
• /
• 2020

The prediction of final mass and optimized process conditions of injection molded products using Artificial Neural Network (ANN) were demonstrated. The ANN was modeled with 10 input parameters and one output parameter (mass). The input parameters, i.e.; melt temperature, mold temperature, injection speed, packing pressure, packing time, cooling time, back pressure, plastification speed, V/P switchover, and suck back were selected. To generate training data for the ANN model, 77 experiments based on the combination of orthogonal sampling and random sampling were performed. The collected training data were normalized to eliminate scale differences between factors to improve the prediction performance of the ANN model. Grid search and random search method were used to find the optimized hyper-parameter of the ANN model. After the training of ANN model, optimized process conditions that satisfied the target mass of 41.14 g were predicted. The predicted process conditions were verified through actual injection molding experiments. Through the verification, it was found that the average deviation in the optimized conditions was 0.15±0.07 g. This value confirms that our proposed procedure can successfully predict the optimized process conditions for the target mass of injection molded products.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권3호
• /
• pp.285-291
• /
• 2022

The number of people enrolling in universities is rising due to the simplicity of applying and the benefit of earning a bachelor's degree. However, the on-time graduation rate has declined since plenty of students fail to complete their courses and take longer to get their diplomas. Even though there are various reasons leading to the aforementioned problem, it is crucial to emphasize the cause originating from the management and care of learners. In fact, understanding students' difficult situations and offering timely Number of Test data and advice would help prevent college dropouts or graduate delays. In this study, we present a machine learning-based method for early detection at-risk students, using data obtained from graduates of the Faculty of Information Technology, Dainam University, Vietnam. We experiment with several fundamental machine learning methods before implementing the parameter optimization techniques. In comparison to the other strategies, Random Forest and Grid Search (RF&GS) and Random Forest and Random Search (RF&RS) provided more accurate predictions for identifying at-risk students.

• KEPCO Journal on Electric Power and Energy
• /
• 제2권2호
• /
• pp.311-316
• /
• 2016

인공신경망과 같은 기계학습에 기반한 네트워크 침입탐지/방지시스템은 특징 조합에 따라 탐지의 정확성과 효율성 측면에서 크게 영향을 받는다. 하지만 침입탐지에 사용 가능한 여러개의 특징들 중 정확성과 효율성 측면에서 최적의 특징 조합을 추출하는 특징 선택 문제는 많은 계산량을 요구한다. 본 논문에서는 NSL-KDD 데이터 집합에서 제공하는 6가지 서비스 거부 공격과 정상 트래픽을 구분해 내기 위한 최적 특징 조합 선택 문제를 다룬다. 최적 특징 조합 선택 문제를 해결하기 위해 대표적인 메타 휴리스틱 알고리즘 중 하나인 다중 시작 지역탐색 알고리즘에 기반한 최적 특징 선택 알고리즘을 제시한다. 제안한 특징 선택 알고리즘의 성능 평가를 위해 NSL-KDD 데이터를 상대로 41개의 특징 모두를 사용한 경우와 비교한다. 그리고 선택된 특징 조합을 사용했을 때 가장 높은 성능을 보여주는 기계학습 방법을 찾기위해 3가지 잘 알려진 기계학습 방법들 (베이즈 분류기와 인공신경망, 서포트 벡터 머신)을 사용해 성능을 비교한다.