• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.673-686
• /
• 2022

Deep learning algorithms for Structural Health Monitoring (SHM) have been extracting the interest of researchers and engineers. These algorithms commonly used loss functions and evaluation indices like the mean square error (MSE) which were not originally designed for SHM problems. An updated loss function which was specifically constructed for deep-learning-based structural damage detection problems has been proposed in this study. By tuning the coefficients of the loss function, the weights for damage localization and quantification can be adapted to the real situation and the deep learning network can avoid unnecessary iterations on damage localization and focus on the damage severity identification. To prove efficiency of the proposed method, structural damage detection using convolutional neural networks (CNNs) was conducted on a truss bridge model. Results showed that the validation curve with the updated loss function converged faster than the traditional MSE. Data augmentation was conducted to improve the anti-noise ability of the proposed method. For reducing the training time, the normalized modal strain energy change (NMSEC) was extracted, and the principal component analysis (PCA) was adopted for dimension reduction. The results showed that the training time was reduced by 90% and the damage identification accuracy could also have a slight increase. Furthermore, the effect of different modes and elements on the training dataset was also analyzed. The proposed method could greatly improve the performance for structural damage detection on both the training time and detection accuracy.

• 정보처리학회논문지B
• /
• 제16B권3호
• /
• pp.203-214
• /
• 2009

본 연구에서는 모니터, 카메라 및 눈동자 좌표계간의 복잡한 3차원 관계를 고려하지 않고, 동공의 중심 위치와 모니터의 구석에 설치된 적외선 조명에 의한 네 개의 조명 반사광 사이의 관계를 사용하여 2차원적인 변환 방법으로 사용자의 시선 위치를 파악한다. 동공중심과 조명 반사광을 정확하게 추출하고, 이를 통해 계산된 시선 위치 계산의 정확도에 영향을 줄 수 있는 오차 요소들을 보정하는 것이 본 연구의 목적이다. 이를 위하여, 동공 중심을 통해 계산된 시선위치와 실제 시선 축이 이루는 카파에러를 초기 1회의 사용자 캘리브레이션을 통해 보정하였다. 또한, 칼만 필터를 기반으로 눈의 급격한 움직임 변화에도 각막 조명 반사광을 안정적으로 추적하여 시선 위치를 정확하게 추적한다. 실험 결과, 제안한 연구방법의 시선 위치 추출 오차는 눈의 급격한 움직임 변화에 상관없이 약 1.0$^\circ$ 를 나타냈다.

• 정보과학회 논문지
• /
• 제43권6호
• /
• pp.718-723
• /
• 2016

스트리밍 데이터 분석에서 개념 변화가 일어나는 시점을 정확히 탐지하는 것은 분류 모델의 성능을 유지하는 데 있어서 매우 중요한 작업이다. 오류율은 스트리밍 데이터에서 개념 변화 탐지를 위해 많이 사용되는 척도이다. 그러나 0과 1로 이루어진 이진 값만으로 예측 결과를 묘사하는 것은 분류 모델의 행동 패턴을 나타내는 유용한 정보의 손실을 초래할 수 있다. 이 논문에서는 오류율을 이용하는 대신에 확률 예측치를 사용하여 분류기의 성능 패턴을 묘사하고 급격한 변화를 탐지하는 효과적인 개념 변화 탐지 방법을 제안한다. 합성데이터와 실제 스트리밍 데이터를 이용한 실험 결과는 제안한 방법이 개념 변화 시점을 탐지하는데 뛰어난 성능을 가짐을 보여준다.

• 음성과학
• /
• 제10권2호
• /
• pp.85-95
• /
• 2003

In speech signal processing, it is very important to detect the pitch exactly in speech recognition, synthesis and analysis. If we exactly pitch detect in speech signal, in the analysis, we can use the pitch to obtain properly the vocal tract parameter. It can be used to easily change or to maintain the naturalness and intelligibility of quality in speech synthesis and to eliminate the personality for speaker-independence in speech recognition. In this paper, we proposed a new pitch detection algorithm. First, positive center clipping is process by using the incline of speech in order to emphasize pitch period with a glottal component of removed vocal tract characteristic in time domain. And rough formant envelope is computed through peak-fitting spectrum of original speech signal infrequence domain. Using the roughed formant envelope, obtain the smoothed formant envelope through calculate the linear interpolation. As well get the flattened harmonics waveform with the algebra difference between spectrum of original speech signal and smoothed formant envelope. Inverse fast fourier transform (IFFT) compute this flattened harmonics. After all, we obtain Residual signal which is removed vocal tract element. The performance was compared with LPC and Cepstrum, ACF. Owing to this algorithm, we have obtained the pitch information improved the accuracy of pitch detection and gross error rate is reduced in voice speech region and in transition region of changing the phoneme.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.248-251
• /
• 1992

In this paper, the RedMAP, i.e. a redundant Mini-MAP system for high reliability is proposed. Redundancy is implemented for LLC, MAC, and Physical layer of ISL-Mini -MAP. The detection of error of the network, the broadcasting of the error event, and the network change sequence are three major functions for the dualized Mini-MAP system. The abnormal operation of the network is mainly detected indirectly with the function of the TBC( token bus controller). The time delay to be required for the change of the networks must be minimized. With the RedMAP, we can achieve successful transmission only with short additional recovery time.

• 한국인터넷방송통신학회논문지
• /
• 제12권1호
• /
• pp.195-200
• /
• 2012

본 논문에서는 동시통화에 강인한 특성을 갖는 알고리즘의 추적성능을 개선시킬 수 있는 새로운 방법을 제안하였다. 반향경로의 변화를 검출하는 방법과 적응필터의 계수 적응식을 변경하는 방법을 제안하였다. 오차신호 대 스케일 파라메터의 비는 반향경로가 변화한 경우와 동시통화가 발생한 경우에 지속시간이 다른 특성을 가지며 이를 이용하여 반향경로 변화를 검출한다. 제안한 적응필터계수 적응식은 잘못된 오차신호선택을 방지하도록 하여 추적 성능을 개선시킨다. 실제 음성신호와 ITU-T G.168에서 제공하는 반향경로를 사용한 실험을 통하여 제안한 방법이 기존의 방법에 비해 4dB 이상 성능을 개선시킴을 확인하였다.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2006년도 춘계학술발표회 논문집
• /
• pp.133-138
• /
• 2006

Currently high resolution satellite imagery has been used in lots of fields of terrain analysis, ocean development, change detection, cartography, classification, environmental monitoring, earth resource observation, meteorological observation as well as military The accuracy of the 3-D modeling of SPOT-5 stereopair images using these ground control points is about 5m in planimetric distance error and about 2m in height error. This study demonstrates the available ground control points for North Korea, of which accuracy is as good as to generate the digital map at the scale of 1:25,000.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.658-663
• /
• 2005

This study presents the empirical results of comparing several demand forecasting methods for Supply Chain Management(SCM). Adaptive exponential smoothing using change detection statistics (Jun) is compared with Trigg and Leach's adaptive methods and SAS time series forecasting systems using weekly SCM demand data. The results show that Jun's method is superior to others in terms of one-step-ahead forecast error and eight-step-ahead forecast error. Based on the results, we conclude that the forecasting performance of SCM solution can be improved by the proposed adaptive forecasting method.

• 산업공학
• /
• 제18권3호
• /
• pp.343-349
• /
• 2005

This study presents the empirical results of comparing several demand forecasting methods for Supply Chain Management(SCM). Adaptive exponential smoothing using change detection statistics (Jun) is compared with Trigg and Leach's adaptive methods and SAS time series forecasting systems using weekly SCM demand data. The results show that Jun's method is superior to others in terms of one-step-ahead forecast error and eight-step-ahead forecast error. Based on the results, we conclude that the forecasting performance of SCM solution can be improved by the proposed adaptive forecasting method.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.295-295
• /
• 2000

In this paper, the measurement algorithm of PCB alignment error is developed using image processing. The X-Y-$\theta$ table correcting PCB alignment error is driven by drive module based on microprocessor according to calculation results obtained through image processing procedure. In order to recognize the X-Y-$\theta$ position errors, two fiducial points are marked on PCB and two cameras of ultraviolet rays types are used for detection of the points to capture exactly fiducial points under disturbance of illumination change. Through application for a practical screen printer, the precision control using the developed position control system can be realized about 2.5${\mu}{\textrm}{m}$ in table moving range and 8${\mu}{\textrm}{m}$ in camera processing precision.