• Journal of the Korean Wood Science and Technology
• /
• v.29 no.2
• /
• pp.91-99
• /
• 2001

In this study the possibility of classifying wood surface defects by image processing technique was investigated. An algorithm for the classification of wood surface defects, such as knot, check, and bark, on three Korean domestic species, Pinus densiflora, Quercus acutissima, and Carpinus laxiflora was also developed. Filtering was executed to separate dummies from the labels including real defect. Error rates in classifying knots on Pinus densiflora and Quercus acutissima were lower than 1% and error rates. In classifying check and bark in Quercus acutissima and Carpinus laxiflora could be lowered to below 13%.

• Science of Emotion and Sensibility
• /
• v.21 no.4
• /
• pp.77-90
• /
• 2018

Behavioral studies of emotion recognition in autism spectrum disorders (ASD) have yielded mixed results. Most of the studies focused on emotion recognition abilities with regard to ASD using stimuli with unisensory modality, making it difficult to determine difficulties in real life emotion perception in ASD. Herein, we review the recent behavioral and cognitive neuroscience studies on emotion recognition functions in ASD, including both unisensory and multisensory emotional information, to elucidate the possible difficulties in emotion recognition in ASD. In our study, we discovered that people with ASD have problems in the process of integrating emotional information during emotion recognition tasks. The following four points are discussed: (1) The restrictions of previous studies, (2) deficits in emotion recognition in ASD especially in recognizing multisensory information, (3) possible compensation mechanisms for emotion recognition in ASD, and (4) the possible roles of attention and language functions in emotion recognition in ASD. The compensatory mechanisms proposed herein for ASD with regard to emotion recognition abilities could contribute to a therapeutic approach for improving emotion recognition functions in ASD.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.65-72
• /
• 2007

In this study, we used nondestructive test based on ultrasonic test as inspection method and compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as pattern recognition algorithm of weld flaws. For this purpose, variables are applied the same to two algorithms. Where, feature variables are zooming flaw signals of reflected whole signals from weld flaws in time domain. Through this process, we compared advantages/ disadvantages of two algorithms and confirmed application methods of two algorithms.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1443-1444
• /
• 2007

지속적으로 증가되는 전기에너지 공급의 신뢰성을 높이기 위하여 전력설비 주요 사고 원인인 부분방전(PD : Partial Discharge)을 검출하고 결함원의 패턴인식 방법의 개발 필요성 날로 증가되고 있다. 본 논문은 부분방전의 패턴인식 확률을 높이기 위하여 검출된 부분방전의 주파수 분석을 이용하여 Conventional PRPD Analysis 방법의 결함 판독확률을 향상시키기 위하여 Advanced PRPD를 제안 한다. 이를 위하여, GIS(Gas Insulated Switchgear)의 주요 사고원인으로 인식되어 있는 결함들을 인위적으로 제작 후 삽입하여 부분방전을 발생시켜 자체 설계 개발된 UHF 내장형 센서를 이용하여 검출하였다. 새로이 제안하는 방법과 기존의 PRPD 방법의 인식률을 상호 비교하기 위하여, 두 가지 그룹을, 즉, 기존의 방법에 의한 것과 부분방전의 주파수 분석이 포함된 방법에 의한 데이터그룹을 구축하고 학습방법은 동일한 인공신경망 MLP (Multilayer Perceptron)를 이용하여 인식률과 학습시간을 동시에 비교하였다. 상호 비교 결과에 의하면, 후자의 방법이 인식확률 뿐만아니라 학습시간도 좋은 결과가 나타났다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.1725-1728
• /
• 2005

무선 센서 네트워크는 컴퓨팅 용량 및 전력 자원이 매우 제약적인 특징을 가지고 있으며, 이로 인하여 동작시 실패하려는 경향(Error-prone)을 지닌다. 이를 해결하기 위하여 센서 네트워크에 적용 가능한 결함 허용 기법이 요구되며, 현재 노드의 참가(Join), 삭제(Delete), 사망(Death) 및 상태 오염(State Corruption)으로 인하여 발생하는 결함을 처리하기 위하여 노드의 물리적 위치를 기반으로 클러스터를 구성한 후 발생 결함을 지역화하여 처리하는 기법이 제안되었다[1]. 본 논문에서는 결함을 처리하기 위한 기존의 위치 인식 노드 클러스터 시스템에서 발생할 수 있는 헤드 노드의 결함을 효율적으로 처리하기 위한 개선된 기법을 제안하여 전체 센서 네트워크 시스템의 실질적인 가용도(Availability)를 높이고자 하며, 이를 위한 간단한 분석을 수행한 후 효용성을 검증한다.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.15 no.4
• /
• pp.531-539
• /
• 1996

The research for the classification of the artificial defects in welding parts is performed using the pattern recognition technology of ultrasonic signal. The signal pattern recognition package including the user defined function is developed to perform the digital signal processing, feature extraction, feature selection and classifier selection. The neural network classifier and the statistical classifiers such as the linear discriminant function classifier and the empirical Bayesian classifier are compared and discussed. The pattern recognition technique is applied to the classification of artificial defects such as notchs and a hole. If appropriately learned, the neural network classifier is concluded to be better than the statistical classifiers in the classification of the artificial defects.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6A
• /
• pp.873-880
• /
• 2008

When checking the state of deterioration or damage structures, regular visual inspection has very important role. At this point, a visual inspection is performed mainly by sketch or photography with a camera of inspectors. If that happens, it takes a lot of effort and time to inspect appearance damages. The purpose of this study is to develop the automatic recognition system for a more efficient and effective inspection of appearance damages. In the process, the image processing technology and the data management & analysis system for damage recognition are mainly developed and applied. This automatic recognition system enables inspectors or clients to obtain correct data that can recognize a damage, such as, crack, water leakage, efflorescence, delamination (peeling), spalling, etc. In addition, this study takes aim at the effect of secure safety, functional maintenance and extension of design lifetime according to build up continuous and systematic data management system.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.17 no.1
• /
• pp.11-22
• /
• 1997

It is very essential to get the accurate classification of defects in primary pressure vessel and piping welds for the safety of nuclear power plant. Ultrasonic testing has been widely applied to inspect primary pressure vessel and piping welds of nuclear power plants during PSI / ISI. Classification of flaws in weldments from their ultrasonic scattering signals is very important in quantitative nondestructive evaluation. This problem is ideally suited to a modern ultrasonic Pattern recognition technique. Here, a brief discussion on systematic approach to this methodology is presented including ultrasonic feature extraction, feature selection and classification. A stronger emphasis is placed on Fuzzy-UTSCS (UT signal classification system) as efficient classifiers for many practical classification problems. As an example Fuzzy-UTSCS is applied to classify flaws in ferrite pressure vessel weldments into two types such as linear and volumetric. It is shown that Fuzzy-UTSCS is able to exhibit higher performance than other classifiers in the defect classification.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1746-1747
• /
• 2007

본 논문에서는 다층 퍼셉트론(Multi-Layer Perceptron)을 이용한 하드 디스크 결함 분포의 패턴 인식 기법을 제시한다. 결함 분포로부터 5 가지의 특징들을 추출하고, 이를 이용하여 퍼셉트론의 입력을 구성하였으며, 미리 분류된 표준 패턴 클래스를 이용하여 퍼셉트론의 출력을 구성하였다. 테스트 결과, 제시된 신경망은 하드 디스크의 패턴 분류에 만족할 만한 성능을 나타내었다.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.13 no.2
• /
• pp.11-19
• /
• 1993

It is very essential to get the accurate classification of defects in primary pressure vessel weld for the safety of nuclear power plant. The signal analysis using the digital signal processing and pattern recognition is performed to classify UT defects extracting feature vector from ultrasonic signals. The minimum distance classifier and the maximum likelihood classifier based on statistics were applied in this experiment to discriminate ultrasonics data obtained form both the training specimens (slit, hole) and the testing specimens(crack, slag). The classification rate was measured using pattern classifier. Results of this study show the promise in solving the many flaw classification problems that exist today.