• 한국멀티미디어학회논문지
• /
• 제25권4호
• /
• pp.575-582
• /
• 2022

In the manufacturing environment, research to minimize robot collisions with human beings have been widespread, but in order to interact with robots, it is important to precisely recognize and predict human actions. In this research, after enhancing performance by applying group normalization to the Hourglass model to detect the operator motion, the skeleton was estimated and data were created using this model. And then, three types of operator's movements were recognized using LSTM. As results of the experiment, the accuracy was enhanced by 1% using group normalization, and the recognition accuracy was 99.6%.

• Communications for Statistical Applications and Methods
• /
• 제30권3호
• /
• pp.273-289
• /
• 2023

In this paper, we develop a new time series model for predicting IPO (initial public offering) data with non-negative integer value. The proposed model is based on integer-valued autoregressive (INAR) model with a Poisson thinning operator. Just as the heterogeneous autoregressive (HAR) model with daily, weekly and monthly averages in a form of cascade, the integer-valued heterogeneous autoregressive (INHAR) model is considered to reflect efficiently the long memory. The parameters of the INHAR model are estimated using the conditional least squares estimate and Yule-Walker estimate. Through simulations, bias and standard error are calculated to compare the performance of the estimates. Effects of model fitting to the Korea's IPO are evaluated using performance measures such as mean square error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) etc. The results show that INHAR model provides better performance than traditional INAR model. The empirical analysis of the Korea's IPO indicates that our proposed model is efficient in forecasting monthly IPO volumes.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2018년도 춘계학술대회
• /
• pp.41-42
• /
• 2018

이 연구는 선박의 내항성능 평가 요소로 사용되는 횡동요 운동특성의 예측에 관한 연구로, 운항중인 선박의 횡동요 RAO를 실시간으로 도출하기 위하여 기계학습 기반의 근사모델을 사용하였다. 근사모델에 의한 예측결과를 테스트데이터와 비교분석함으로서, 횡동요 운동 특성 예측에 적합한 근사모델을 생성하기 위한 근사기법과 데이터 샘플링 조건에 대하여 제시하고자 한다.

• International Journal of Aeronautical and Space Sciences
• /
• 제17권3호
• /
• pp.391-400
• /
• 2016

In satellite operations, stable maneuvering of a satellite's onboard antenna to prevent undesirable vibrations to the satellite body is required for high-quality high-resolution images. For this reason, the onboard antenna's angular rate is typically minimized while still satisfying the system requirement that limits the speed of the onboard antenna. In this study, a simple yet effective method, called the ground station searching method, is proposed to reduce the angular rate of a satellite's onboard antenna. The performance of the proposed method is tested using real flight data from the KOMPSAT-3 satellite. Approximately 83% of arbitrarily selected real flight scenarios from 66 test cases show reductions in the onboard antenna's azimuth angular rates. Additionally, reliable solutions were consistently obtained within a reasonably acceptable computation time while generating an onboard antenna tracking profile. The obtained results indicate that the proposed method can be used in real satellite operations and can reduce the operational loads on a ground operator. Although the current work only considers the KOMPSAT-3 satellite as a test case, the proposed method can be easily modified and applied to other satellites that have similar operational characteristics.

• Transactions on Control, Automation and Systems Engineering
• /
• 제1권2호
• /
• pp.141-146
• /
• 1999

This paper describes the communication method of an auto-startup system. The Auto-Startup system is designed to operate a nuclear power plant automatically during the startup operation . In general , the operations during startup in existing plant have only been manually controlled by the operator. The manual operation caused to the operator mistake. The Auto-Startup system consists of the Distributed Control System(DCS) and G2 (Expert System). Also, Functional Test Facility(FTF) provides the plant's real-data for an Auto-Startup system. So, it is necessary to develop the communication method between these systems. We developed two methods ; one is a network and the other is a hardwire line. To communicate between these systems (DCS-G2 and DCS-FTF) , we developed the communication program. In case of DCS-FTF, we used the TCP/IP and VXI. BUt, in case of DCS-G2 , we , what it called , developed the bridge program using the GSI(G2 Standard Interface). We test to check the function of the important parameter, in time, for analysis of the developed communication method. The results are a good performance when we check the communication time of important parameter. We conclude that Auto-startup system could save heat-up time about at least 5 hours and reduced the change of the reactor operation and trip.

• 방송공학회논문지
• /
• 제27권2호
• /
• pp.240-243
• /
• 2022

프로그램 결함에 대한 위치 추적은 소프트웨어 유지 및 보수를 위해 필수적인 요소이다. 대부분은 버그리포트가 제출되었을 때, 결함 추적이 개발자들의 수작업으로 이루어지기 때문에 비용 소모가 많은 작업에 속한다. 현재까지 많은 연구자가 해당 작업을 자동화시키기 위하여 노력해 왔지만 보고된 결과에 따르면, 현업에서 사용되기에 아직도 부족한 성능을 보이는 추세이다. 이에, 본 연구에서는 많은 양의 버그 리포트 데이터와 관련 최신 연구들을 분석하여, 기존 연구들이 하나의 전처리 방법을 모든 버그 리포트에 일괄적으로 적용하고, 이런 방법은 위치 추적에 악영향을 준다는 것을 파악하였다. 본 논문에서는 이와 같은 문제점을 해결하기 위해 선택적인 전-후처리 방법론을 제안한다.

• 대한임베디드공학회논문지
• /
• 제11권1호
• /
• pp.21-27
• /
• 2016

An integrated display software platform for small UAV is developed based on parallel processing technique in this paper. When the small UAV with high-performance camera and avionic modules is employed to various surveillance-related missions, it is important to reduce the operator's workload and increase the monitoring efficiency. For this purpose, it is needed to develop an efficient monitoring software enable to manipulate the image and flight data obtained during flight within the given processing time and display them simultaneously. In this paper, we set up requirements and suggest the architecture for the software platform. The integrated software platform is implemented with parallel processing scheme. Based on AR drone, we verified that the various data are concurrently displayed by the suggest software platform.

• Journal of Biosystems Engineering
• /
• 제26권1호
• /
• pp.21-28
• /
• 2001

Major deficiencies of current automation scheme including various robots for bioproduction include the lack of task adaptability and real time processing, low job performance for diverse tasks, and the lack of robustness of take results, high system cost, failure of the credit from the operator, and so on. This paper proposed a scheme that could solve the current limitation of task abilities of conventional computer controlled automatic system. The proposed scheme is the man-machine hybrid automation via tele-operation which can handle various bioproduction processes. And it was classified into two categories. One category was the efficient task sharing between operator and CCM(computer controlled machine). The other was the efficient interface between operator and CCM. To realize the proposed concept, task of the object identification and extraction of 3D coordinate of an object was selected. 3D coordinate information was obtained from camera calibration using camera as a measurement device. Two stereo images were obtained by moving a camera certain distance in horizontal direction normal to focal axis and by acquiring two images at different locations. Transformation matrix for camera calibration was obtained via least square error approach using specified 6 known pairs of data points in 2D image and 3D world space. 3D world coordinate was obtained from two sets of image pixel coordinates of both camera images with calibrated transformation matrix. As an interface system between operator and CCM, a touch pad screen mounted on the monitor and remotely captured imaging system were used. Object indication was done by the operator’s finger touch to the captured image using the touch pad screen. A certain size of local image processing area was specified after the touch was made. And image processing was performed with the specified local area to extract desired features of the object. An MS Windows based interface software was developed using Visual C++6.0. The software was developed with four modules such as remote image acquisiton module, task command module, local image processing module and 3D coordinate extraction module. Proposed scheme shoed the feasibility of real time processing, robust and precise object identification, and adaptability of various job and environments though selected sample tasks.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 추계학술대회 논문집 학회본부 A
• /
• pp.110-112
• /
• 1999

Recently the substation automation is actively researched at each country. Since the substation automation is an integrated system that consist of electrical, electronic and computer technologies, performance evaluation is very important to inspect the developed system's applicable possibility for real power system. Most studies are verified using computer simulation, because it is hard to apply them to real power systems. Therefore development of a substation simulator is necessary for the performance evaluation of many application systems such as operator aid system. This paper introduces a substation simulator. An intelligent fault diagnosis and restorative control expert system is also introduced UDP/IP is applied as a protocol for data transport between expert system and SC(station computer). As to the Graphic User Interface, C++ Language and Visual Basic is used in the Windows NT operating system together with four Pentium II systems.

• 한국인터넷방송통신학회논문지
• /
• 제12권4호
• /
• pp.189-194
• /
• 2012

수배전 무효전력 보상 감시 제어시스템은 수배전단에 설치된 유도 모터, 또는 아크 용접기 등과 같은 유도성 부하에서 발생되는 지상무효전력을 보상하고 역률의 개선, 전압 강하의 경감, 전력손실을 감소 시켜줌으로써 전력설비 계통을 경제적이고 안정적으로 운영하도록 도와준다. 그리고 이러한 시스템은 중앙전력감시반이 획득한 수변전설비의 운전상태 및 계측 Data를 근거로 역률 및 위상각을 분석하여 기준 위상각이상으로 전압과 전류의 위상차가 발생 되었을 경우, 무효전력 보상장치의 ON/OFF제어를 수행하여 효율적인 계통관리가 가능하도록 한다. 본 연구에서는 능동데이터베이스를 이용하여 무효전력 보상장치 감시제어 시스템을 구현하는 방안을 제시함으로써, 공장 부하의 지상무효전력이 급격한 증가로 인한 역률 저하, 전압 강하, 손실 발생 등의 징후 발생 시 이에 대한 대처를 사용자(operator)의 개입 없이 데이터베이스 스스로 수행하도록 함으로써 인위에 의한 실수를 최소화 하도록 하였다.