• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• 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.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• 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

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.3
• /
• 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.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.1
• /
• pp.7-13
• /
• 2021

This paper proposes a method to minimize the target's direction detection error using RADAR. The radar system cannot accurately detect the target direction due to the phase error of he received signal. The proposed method of this study obtains a phase by applying an root mean square to each antenna incident signal, and reduces the phase error by using an optimal signal to noise ratio. In the simulation result, the probability of detecting the target direction is the best when the antenna spacing is half wavelength. The conventional method of direction detection probability 10-1.7 and the proposed method is 10-3.3. The target detection direction of the existing method represents [-8°,8°] with an error of 2 degrees. The target detection direction of the proposed method is shown in [-10°,10°], and all target directions are accurately detected. In the future, There is need for a method to reduce the phase error even though the resolution decrease.

• The Journal of Korea Robotics Society
• /
• v.9 no.2
• /
• 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.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• 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.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.1
• /
• pp.69-75
• /
• 2022

Due to the increase in the demand for anomaly detection according to the ageing of power generation facilities, the need for developing an anomaly detection method that can provide high-reliability turbine blade anomaly detection performance has been continuously raised. Additionally, the false detection results caused by a human error accelerates the increase of the need. In this paper, we propose an anomaly detection technique for turbine blades in power plants using deep neural networks. Experimental results prove that the proposed technique achieves stable anomaly detection performance while minimizing human factor intervention.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.4
• /
• 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.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.17 no.2
• /
• 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
• /
• v.3 no.2
• /
• 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.