• Nuclear Engineering and Technology
• /
• 제55권2호
• /
• pp.603-622
• /
• 2023

Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.675-676
• /
• 2007

This Paper presents circuit improvement of 345kV Bus bar protection panel by using VDD (Voltage disturbance detection) relay with distinctive ability between human error in the field test and real facility faults. Therefore, We expect that this improvement of circuit helps decrease of blackout coming from human error. In order to guarantee electric power system reliability, consistent study of human error prevention in the event of field test is necessarily required

• 전기학회논문지
• /
• 제68권3호
• /
• pp.471-479
• /
• 2019

This research proposes a indoor magnetic map matching algorithm that improves the position accuracy by employing multiple magnetic sensors and probabilistic candidate weighting function. Since the magnetic field is easily distorted by the surrounding environment, the distorted magnetic field can be used for position mapping, and multiple sensor configuration is useful to improve mapping accuracy. Nevertheless, the position error is likely to increase because the external magnetic disturbances have repeated pattern in indoor environment and several points have similar magnetic field distortion characteristics. Those errors cause large position error, which reduces the accuracy of the position detection. In order to solve this problem, we propose a method to reduce the error using multiple sensors and likelihood boundaries that uses human walking characteristics. Also, to reduce the maximum position error, we propose an algorithm that weights according to their importance. We performed indoor walking tests to evaluate the performance of the algorithm and analyzed the position detection error rate and maximum distance error. From the results we can confirm that the accuracy of position detection is greatly improved.

• 한국정보전자통신기술학회논문지
• /
• 제14권1호
• /
• pp.7-13
• /
• 2021

본 연구에서는 표적의 방향 탐지 오차를 최소화 시키는 방법을 제안한다. 수신 신호 위상차에 오차가 발생하면 표적 방향을 정확히 탐지 할 수 없다. 본 연구 제안 방법은 각 안테나에 입산한 신호에 대해서 실효치를 적용하여 위상을 획득한 후 최적의 신호 대 잡음비를 이용하여 위상 오차를 감소시킨다. 모의실험결과에서 안테나 간격이 반파장일 때, 표적 방향 탐지 확률이 가장 우수하고 신호 대 잡음비가 25dB일 때 방향 탐지 확률의 기존방법은 10-1.7이고 제안 방법은 10-3.3이다. 기존 방법의 표적 탐지 방향은 [-8°,8°]로서 2도의 오차를 나타내고, 제안 방법의 표적 탐지 방향은 [-10°,10°]로서 표적방향을 모두 정확히 탐지한다. 향후 분해능 감소에 따른 위상오차를 감소시키는 방법에 대한 연구가 필요하다.

• 로봇학회논문지
• /
• 제9권2호
• /
• pp.111-116
• /
• 2014

Human-robot co-operation becomes increasingly frequent due to the widespread use of service robots. However, during such co-operation, robots have a high chance of colliding with humans, which may result in serious injury. Thus, many solutions were proposed to ensure collision safety, and among them, collision detection algorithms are regarded as one of the most practical solutions. They allow a robot to quickly detect a collision so that the robot can perform a proper reaction to minimize the impact. However, conventional collision detection algorithms required the precise model of a robot, which is difficult to obtain and is subjected to change. Also, expensive sensors, such as torque sensors, are often required. In this study, we propose a novel collision detection algorithm which only requires motor encoders. It detects collisions by monitoring the high-pass filtered version of the velocity error. The proposed algorithm can be easily implemented to any robots, and its performance was verified through various tests.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2022년도 제34회 한글 및 한국어 정보처리 학술대회
• /
• pp.225-231
• /
• 2022

최근 기계번역 분야는 괄목할만한 발전을 보였으나, 번역 결과의 오류가 불완전한 의미의 왜곡으로 이어지면서 사용자로 하여금 불편한 반응을 야기하거나 사회적 파장을 초래하는 경우가 존재한다. 특히나 오역에 의해 변질된 의미로 인한 경제적 손실 및 위법 가능성, 안전에 대한 잘못된 정보 제공의 위험, 종교나 인종 또는 성차별적 발언에 의한 파장은 실생활과 문제가 직결된다. 이러한 문제를 완화하기 위해, 기계번역 품질 예측 분야에서는 치명적 오류 감지(Critical Error Detection, CED)에 대한 연구가 이루어지고 있다. 그러나 한국어에 관련해서는 연구가 존재하지 않으며, 관련 데이터셋 또한 공개된 바가 없다. AI 기술 수준이 높아지면서 다양한 사회, 윤리적 요소들을 고려하는 것은 필수이며, 한국어에서도 왜곡된 번역의 무분별한 증식을 낮출 수 있도록 CED 기술이 반드시 도입되어야 한다. 이에 본 논문에서는 영어-한국어 기계번역 분야에서의 치명적 오류를 감지하는 KoCED(English-Korean Critical Error Detection) 데이터셋을 구축 및 공개하고자 한다. 또한 구축한 KoCED 데이터셋에 대한 면밀한 통계 분석 및 다국어 언어모델을 활용한 데이터셋의 타당성 실험을 수행함으로써 제안하는 데이터셋의 효용성을 면밀하게 검증한다.

• 한국정보전자통신기술학회논문지
• /
• 제15권1호
• /
• pp.69-75
• /
• 2022

지금까지 발전 설비 터빈 블레이드의 이상 탐지는 사람에 의해 진행되어왔다. 하지만 발전 설비 노후화로 인한 이상 탐지 수요 증가와 터빈 블레이드의 이상을 검사하는 검사자 간의 기량 차로 인해 발생하는 검출 결과의 상이성으로 인해, 이러한 터빈 블레이드 이상 탐지 수요 증가와 인적 요소로 인해 발생하는 오류를 줄이고 높은 신뢰성의 터빈 블레이드 이상 검출성능을 안정적으로 제공할 수 있는 기법 개발의 필요성이 지속해서 제기되어 왔다. 이번 논문에서는 최근 다양한 분야에서 인상적인 성능 향상을 달성한 깊은 신경망을 이용한 발전 설비 터빈 블레이드의 이상 탐지 기술을 제안한다. 실험 결과는 제안된 기술이 인적 요소의 개입을 최소화함과 동시에 안정적인 이상 검출성능을 달성함을 증명한다.

• 제어로봇시스템학회논문지
• /
• 제15권4호
• /
• pp.379-384
• /
• 2009

A human gaze detection and tracing method is importantly required for HMI(Human-Machine-Interface) like a Human-Serving robot. This paper proposed a novel three-dimension (3D) human gaze estimation method by using a face recognition, an orientation estimation and SVMs (Support Vector Machines). 2,400 images with the pan orientation range of $-90^{\circ}{\sim}90^{\circ}$ and tilt range of $-40^{\circ}{\sim}70^{\circ}$ with intervals unit of $10^{\circ}$ were used. A stereo camera was used to obtain the global coordinate of the center point between eyes and Gabor filter banks of horizontal and vertical orientation with 4 scales were used to extract the facial features. The experiment result shows that the error rate of proposed method is much improved than Liddell's.

• 한국항공운항학회지
• /
• 제17권2호
• /
• pp.62-67
• /
• 2009

LOSA is a flight safety program that analyses human errors in normal operations. Trained pilot observers monitor the normal flights at the observer seat. LOSA is a proactive non jeopardy data collection tool using threat and error management(TEM) as a framework. With the analysis of crew behaviors through LOSA with The LOSA collaborative(TLC), the airlines can identify the behaviors of the crew during normal operations. The major objective of LOSA is to measure how the crew manage threats, errors and undesired aircraft deviations in the cockpit on day to day operations. The airlines are able to set up effective TEM training with practical six generation Crew recourse management(CRM) with data of error from LOSA instead of theoretical CRM courses. The Airlines can use TEM as an integral part of a Safety Management System(SMS) and uses monitoring and cross-checking skills in the flight operations to manage threats and errors effectively when we know the errors we make in the cockpit on daily operation. The result of LOSA indicates that the error detection rate should be enhanced since around the half of the errors went undetected. The areas which should be focused for enhancing the error detection are monitor, cross-check, the management of workload, automation and taxiway/ runway to manage errors effectively.

• KIEAE Journal
• /
• 제3권2호
• /
• pp.59-66
• /
• 2003

To be the design method supporting aesthetic ability of human, CAAD system should essentially recognize architectural form in the same way of human. In this study, visual perception process of human was analyzed to search proper computational method performing similar step of perception of it. Through the analysis of visual perception, vision was separated to low-level vision and high-level vision. Edge detection and neural network were selected to model after low-level vision and high-level vision. The 24 images of building, tree and landscape were processed by edge detection and trained by neural network. And 24 new images were used to test trained network. The test shows that trained network gives right perception result toward each images with low error rate. This study is on the meaning of artificial intelligence in design process rather than on the design automation strategy through artificial intelligence.