• 대한안전경영과학회지
• /
• 제1권1호
• /
• pp.111-121
• /
• 1999

An important problem in process adjustment using feedback is how often to sample the process and when to apply an adjustment. Schemes are designed to minimize the overall cost. The cost is taken the frequency with which they require observations to be made, and the resulting overall length of time between adjustments. In this article, the process adjustment which is based on the adaptive EWMA forecasts is derived. An example is presented to improve the standard variation through the analysis of data series.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.213-214
• /
• 2006

To reduce the feedback overhead of predicted CSI (channel status information) of adaptive OFDM (orthogonal frequency division multiplexing), we use partial data of CSI and employ linear interpolation. Simulation results show estimated CSI and its MSE.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 1999년도 추계학술대회
• /
• pp.237-246
• /
• 1999

An important problem in process adjustment using feedback is how often to sample the process and when to apply an adjustment. Schemes designed to minimize the overall cost. The cost taken the frequency with which they require observations to be made, and the resulting overall length of time between adjustment. In this article, the process adjustment which is based on the adaptive EWMA forecasts are derived. An example is presented to improve confirm standard varation through the analysis of a data series.

• 한국콘텐츠학회논문지
• /
• 제21권12호
• /
• pp.896-905
• /
• 2021

인공지능 기반 보안관제 시스템은 운영환경에서 발생할 수 있는 학습 데이터 오류, 신규 공격 이벤트 발생으로 인한 오탐 증가 등 문제를 해결하기 위해 피드백 기능이 연구되고 있다. 그러나 한정된 관제 인력의 피드백 수행 방식은 모델 개선에 오랜 시간이 걸리고 숙련되지 않은 관제 인력의 피드백은 오히려 모델 성능 저하의 원인이 될 수 있다. 본 논문에서는 관제 인력 한계 극복, 신규 오탐 개선, 빠른 모델 성능 향상을 위한 능동형 보안관제 모델 개선 프로세스를 제안하였다. 운영 중 예측된 유사 이벤트를 군집화 하고, 피드백이 우선적으로 필요한 군집을 계산하여 운영자에게 대표 이벤트 설명이 가능한 인공지능(eXplainable AI) 기반 시각화도 함께 제시하였다. 수신된 대표 피드백은 동일 군집과 다른 데이터를 계산하여 제외하고 피드백 전파 학습 데이터를 생성한다. 준비된 학습 데이터는 초기 모델과 함께 점진적 학습을 통해 모델을 생성함으로써 성능을 향상시키는 프로세스이다. 제안 프로세스의 실효성 검증을 위해 웹 어플리케이션 방화벽 데이터셋 PKDD2007과 CSIC2012를 선택하여 3개의 시나리오를 통해 실험을 진행하였다. 실험 결과 제안된 프로세스는 피드백을 주지 않았거나 소수 운영자 피드백을 적용한 모델 성능에 비해 모든 지표에서 약 30% 이상의 성능 향상을 확인하였다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권6호
• /
• pp.275-284
• /
• 2023

가상 현실 시뮬레이션은 다양한 분야에서의 교육과 훈련에 활용이 되며, 특히 최근에는 의료 분야에서 많이 사용되고 있다. 교육/훈련용 시뮬레이터는 의사가 실제 수술 도구를 이용하여 실제 환자에 대해 처치를 하는 것과 같은 느낌이 나게 하는 촉감/역감 생성 및 영상/음향 출력 하드웨어와 여기에 실감 나는 영상과 촉감을 생성해주는 소프트웨어로 이루어진다. 기존의 시뮬레이터들은 수술 시에 사용되는 다양한 수술 도구들을 모사하기 위해 다양한 형태의 하드웨어들을 사용해야 하므로 복잡하고 비용이 많이 소요되는 문제가 있다. 이 논문에서는 포스 피드백 장치와 변형 가능한 햅틱 컨트롤러를 이용한 치과 수술 시뮬레이션 시스템을 제안한다. 햅틱 하드웨어들은 수술 도구와 수술 부위의 충돌 여부를 파악하고 그에 따른 저항감과 진동감을 제공한다. 특히 길이 변화, 굽힘과 같은 변형이 가능한 햅틱 컨트롤러는 여러 수술 도구들의 형태에 따라 느껴지는 다양한 감각을 표현할 수 있다. 사용자가 햅틱 피드백 장치를 조작하면 햅틱 피드백 장치의 움직임이나 버튼 클릭 등의 이벤트가 시뮬레이션 시스템에 전달되어 치과용 수술 도구와 구강 내부 모델들 사이의 상호작용이 발생하고 이에 따른 햅틱 피드백이 햅틱 피드백 장치로 전달된다. 이러한 기반 기술들을 활용하여 정교한 3차원 모델로 표현된 가상 환경에서 대표적인 치과 수술기법인 매복 사랑니 발치 수술의 현실적인 훈련 경험을 제공한다.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 춘계학술대회 논문집
• /
• pp.567-572
• /
• 2002

The equipment of industrial robot in manufacturing and assembly lines has rapidly increased. In order to achieve high productivity and flexibility, it becomes very important to develop the visual feedback control system with Off-Line Programming System(OLPS ). We can save much efforts and time in adjusting robots to newly defined workcells by using Off-Line Programming System. A proposed visual calibration scheme is based on position-based visual feedback. The visual calibration system is composed of a personal computer, an image processing board, a video monitor, and one camera. The calibration program firstly generates predicted images of objects in an assumed end-effector position. The process to generate predicted images consists of projection to screen-coordinates, visible range test, and construction of simple silhouette figures. Then, camera images acquired are compared with predicted ones for updating position and orientation data. Computation of error is very simple because the scheme is based on perspective projection, which can be also expanded to experimental results. Computation time can be extremely reduced because the proposed method does not require the precise calculation of tree-dimensional object data and image Jacobian.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 추계학술대회(한국공작기계학회)
• /
• pp.140-145
• /
• 2001

The equipment of industrial robot in manufacturing and assembly lines has rapidly increased. In order to achieve high productivity and flexibility, it becomes very important to develop the visual feedback control system with Off-Line Programming System(OLPS). We can save much efforts and time in adjusting robots to newly defined workcells by using Off-Line Programming System. A proposed visual calibration scheme is based on position-based visual feedback. The visual calibration system is composed of a personal computer, an image processing board, a video monitor, and one camera. The calibration program firstly generates predicted images of objects in an assumed end-effector position. The process to generate predicted images consists of projection to screen-coordinates, visible range test, and construction of simple silhouette figures. Then, camera images acquired are compared with predicted ones for updating position and orientation data. Computation of error is very simple because the scheme is based on perspective projection, which can be also expanded to experimental results. Computation time can be extremely reduced because the proposed method does not require the precise calculation of tree-dimensional object data and image Jacobian.

• 대한의용생체공학회:의공학회지
• /
• 제35권6호
• /
• pp.219-226
• /
• 2014

This study is to develop a basic life support (BLS) app using the android based smartphone and to evaluate the function of the app. Suggested app contains chest compression feedback function, the map of automated external defibrillator (AED), direct emergency call and the basic knowledge of BLS. Using the accelerometer of the smartphone, we implemented a real-time algorithm that estimates the chest compression depth and rate for high quality cardiopulmonary resuscitation (CPR). The accuracy of algorithm was evaluated by manikin experiment. We made contents which were easy to learn the BLS for the layperson and implemented a function that provides the AED location information based on the user's current location. From the manikin experiment, the chest compression depth and rate were no significant differences between the manikin data and the app's feedback data (p > 0.05). Developed BLS app was uploaded on Google Play Store and it was free to download. We expected that this app is useful to learn the BLS for the layperson.

• 한국정밀공학회지
• /
• 제34권1호
• /
• pp.19-22
• /
• 2017

This paper describes the efficient equipment maintenance that can offer the exact time for repair and change of component in root industry. A conventional method offered the fixed time for repair and change of component because the method is based on early guarantee specification of the component. However the operating condition of manufacturing field is often under worse condition than early guarantee condition for high productivity. So, most components can't use until early guarantee time due to the operation of various different condition. Therefore we suggest the useful method for efficient equipment-maintenance by manufacturing-field analysis and feedback database. For this, the classification of root industry and related equipment is performed and then the detail classification of the process and component for equipment maintenance. And the monitoring module is also designed to gather data for feedback process and the environment is basically implemented for aging and reliability test.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.199-204
• /
• 2007

This research aimed at to develop a quantitative assesment technique which uses the measured displacements at the excavated plane during tunnel construction. Tunnel structure has a feature with long extents comparing to the excavated section so that the tunnel safety assesment is more effective by using the measured data of displacements. Tunnel structures show different structural behaviors due to the mechanical characteristics of ground and supports themselves, excavation methods and construction methods of supports, etc. From this point of view, it has very important meanings on the practical aspects that the measured data from the construction cite represent the features of the interaction effects between ground and supports as they are. In this study, both the stress state and the properties of surrounding ground are analyzed by newly incorporated feedback analysis technique which can use the measured displacements directly. Then, the stress state and the properties of ground will be used to obtain the strain distribution of surrounding ground. Finally the tunnel safety can be assessed by comparing the estimated strain through the analysis to the allowable strain of ground quantitatively.