• 한국멀티미디어학회논문지
• /
• 제19권5호
• /
• pp.848-855
• /
• 2016

Face recognition has received a great deal of attention for the wide range of applications in real-world scenario. In this scenario, mismatches (so called heterogeneity) in terms of resolution and illumination between gallery and test face images are inevitable due to the different capturing conditions. In order to deal with the mismatch problem, we propose a local feature learning method using deep canonical correlation analysis (DCCA) for heterogeneous face recognition. By the DCCA, we can effectively reduce the mismatch between the gallery and the test face images. Furthermore, the proposed local feature learned by the DCCA is able to enhance the discriminative power by using facial local structure information. Through the experiments on two different scenarios (i.e., matching near-infrared to visible face images and matching low-resolution to high-resolution face images), we could validate the effectiveness of the proposed method in terms of recognition accuracy using publicly available databases.

• Earthquakes and Structures
• /
• 제23권3호
• /
• pp.259-269
• /
• 2022

In this study, we introduce a canonical correlation analysis method to accurately assess the tunnel damage potential of ground motion. The proposed method can retain information relating to the initial variables. A total of 100 ground motion records are used as seismic inputs to analyze the dynamic response of three different profiles of tunnels under deep and shallow burial conditions. Nine commonly used ground motion parameters were selected to form the canonical variables of ground motion parameters (GMP_CCA). Five structural dynamic response parameters were selected to form canonical variables of structural dynamic response parameters (DRP_CCA). Canonical correlation analysis is used to maximize the correlation coefficients between GMP_CCA and DRP_CCA to obtain multivariate ground motion parameters that can be used to comprehensively assess the tunnel damage potential. The results indicate that the multivariate ground motion parameters used in this study exhibit good stability, making them suitable for evaluating the tunnel damage potential induced by ground motion. Among the nine selected ground motion parameters, peck ground acceleration (PGA), peck ground velocity (PGV), root-mean-square acceleration (RMSA), and spectral acceleration (Sa) have the highest contribution rates to GMP_CCA and DRP_CCA and the highest importance in assessing the tunnel damage potential. In contrast to univariate ground motion parameters, multivariate ground motion parameters exhibit a higher correlation with tunnel dynamic response parameters and enable accurate assessment of tunnel damage potential.

• 아동학회지
• /
• 제27권2호
• /
• pp.55-69
• /
• 2006

This study investigated relationship between preservice kindergarten teachers' cognitive strategies and self-determination motivation types. Cognitive strategies were measured by 3 variables surface, deep, and metacognitive strategies; motivation for self-determination was measured by 7 variables; intrinsic motivation(IM) to know, IM to accomplish, IM to experience stimulation, external regulation, introjected regulation, identified regulation, and amotivation. The Motivated Strategies for Learning Questionnaire(Pintirch & DeGroot, 1990) and the Academic Motivation Scale(Vallerand et al., 1992, 1993) were administered to 82 subjects. Data were analyzed by Pearson's correlation, multiple regression analysis, and canonical correlation analysis. Finding were a positive correlation between IM to know and IM to accomplish. IM to accomplish positively predicted surface, deep, and metacognitive strategies, and identified regulation positively predicted deep cognitive strategy. Amotivation negatively predicted deep and metacognitive strategies.

• 자원환경지질
• /
• 제43권4호
• /
• pp.381-391
• /
• 2010

최근 다양하게 제시되고 있는 확률론적 방법에 의한 산사태 예측기법의 경우 전문적 지식을 기반으로 조사 및 분석이 이루어질 경우에만 분석결과의 신뢰성을 확보할 수 있다. 그러나 재해 발생상황에서는 통계분석을 통한 산사태 예측의 전문가뿐만 아니라 공무원, 지질공학자 등 통계적 전문지식을 갖지 않은 재해분야 담당자도 신뢰성 있고 간편한 방법으로 산사태 취약성을 해석할 수 있어야 한다. 따라서 본 논문은 전문가는 물론 비전문가도 쉽게 의미를 이해하고 활용할 수 있으면서도 정확한 분석을 통한 통계적 접근으로 신뢰성 높은 산사태 취약성 평가표를 개발하여 제안하고자 하였다. 이를 위해 기존에 국내에서 산사태가 집중적으로 발생한 지역의 지질, 지형, 토질자료를 토대로 산사태 정준상관분석을 통한 수량화 기법을 이용하여 산사태 취약성 평가표를 개발하였다. 산사태의 현장자료와 실내시험자료를 바탕으로 통계분석을 실시하고, 그 결과를 토대로 영향인자 선정 및 인자별 급간 값을 설정한 것이다. 수량화 분석결과 산사태를 발생시키는 여러 인자 중 사면경사가 가장 큰 중요도를 가지며, 고도, 투수계수, 간극율, 암질, 건조밀도의 순서로 큰 영향을 미치는 것으로 나타났다. 각 평가항목별로 결정된 점수를 기준으로 평가항목 각각의 세부등급에 대한 점수를 할당하여 산사태재해 취약성 평가표를 개발하였다. 산사태재해 취약성 평가표를 이용하여 평가자는 평가대상 지점에 대해 각 평가항목별 해당 속성, 즉 세부등급을 선택하고, 선택된 각 속성별 평가점수를 더하면 산사태 취약성을 점수로 신속하게 파악할 수 있다. 또한, 이 결과를 토대로 GIS 기법을 이용한 산사태 예측지도 또는 취약성지도 등을 작성하여 활용할 수 있다.