• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.193-199
• /
• 2008

In this paper, it is proposed the implementation of face authentication system based on real-time image processing. We described the process implementing the two steps for real-time face authentication system. At first face detection steps, we describe the face detection by using feature of wavelet transform, LoG operator and hausdorff distance matching. In the second step we describe the new dual-line principal component analysis(PCA) for real-time face recognition. It is combines horizontal line to vertical line so as to accept local changes of PCA. The proposed system is affected a little by the video size and resolution. And then simulation results confirm the effectiveness of out system and demonstrate its superiority to other conventional algorithm. Finally, the possibility of performance evaluation and real-time processing was confirmed through the implementation of face authentication system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.191-196
• /
• 2015

There have been many studies on statistical forecasting on firm's performance and stock price by applying various financial indicators such as debt ratio and sales growth rate. Selecting predictors for constructing a prediction model among the various financial indicators is very important for precise prediction. Most of the previous studies applied variable selection algorithms for selecting predictors. However, the variable selection algorithm is considered to be at risk of eliminating certain amount of information from the indicators that were excluded from model construction. Therefore, we propose a firm's performance prediction model which principal component analysis is applied instead of the variable selection algorithm, in order to reduce dimensionality of input variables of the prediction model. In this study, we constructed the proposed prediction model by using financial data of American IT companies to empirically analyze prediction performance of the model.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.2
• /
• pp.416-424
• /
• 2017

In this study, we propose a design of digits recognition system based on RBFNNs through a comparative study of pre-processing algorithms in order to recognize digits in handwritten. Histogram of Oriented Gradient(HOG) is used to get the features of digits in the proposed digits recognition system. In the pre-processing part, a dimensional reduction is executed by using Principal Component Analysis(PCA) and (2D)2PCA which are widely adopted methods in order to minimize a loss of the information during the reduction process of feature space. Also, The architecture of radial basis function neural networks consists of three functional modules such as condition, conclusion, and inference part. In the condition part, the input space is partitioned with the use of fuzzy clustering realized by means of the Fuzzy C-Means algorithm. Also, it is used instead of gaussian function to consider the characteristic of input data. In the conclusion part, the connection weights are used as the extended type of polynomial expression such as constant, linear, quadratic and modified quadratic. By using MNIST handwritten digit benchmarking database, experimental results show the effectiveness and efficiency of proposed digit recognition system when compared with other studies.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• 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.

• Korean Journal of Applied Biomechanics
• /
• v.27 no.3
• /
• pp.205-210
• /
• 2017

Objective: The aim of the study was to investigate the age-related ability of dynamic balance recovery through perturbation response during standing. Method: Six older and 6 younger adults participated in this study. External perturbation during standing as pulling force applied at the pelvic level in the anterior direction was provided to the subject. The margin of stability was quantified as a measure of postural stability or dynamic balance recovery, and using principal component analysis (PCA), the regularity of the margin of stability (MoS) was calculated. Results: Our results showed that in the older adult group, 60.99% and 28.63% of the total variance were captured using the first and second principal components (PCs), respectively, and in the younger adult group, 81.95% and 10.71% of the total variance were captured using the first and second PCs, respectively. Conclusion: Ninety percent of the total variance captured using the first two PCs indicates that the older adults had decreased regularity of the MoS than the younger adults. Thus, the results of the present study suggest that aging is associated with non-regularity of dynamic postural stability.

• Journal of the Korean Wood Science and Technology
• /
• v.45 no.2
• /
• pp.202-212
• /
• 2017

This study was to establish the interrelation between chemical compositions and near infrared (NIR) spectra for the classification on distinguishability of domestic gymnosperms. Traditional wet chemistry methods and infrared spectral analyses were performed. In chemical compositions of five softwood species including larch (Larix kaempferi), red pine (Pinus densiflora), Korean pine (Pinus koraiensis), cypress (Chamaecyparis obtusa), and cedar (Cryptomeria japonica), their extractives and lignin contents provided the major information for distinction between the wood species. However, depending on the production region and purchasing time of woods, chemical compositions were different even though in same species. Especially, red pine harvested from Naju showed the highest extractive content about 16.3%, whereas that from Donghae showed about 5.0%. These results were expected due to different environmental conditions such as sunshine amount, nutrients and moisture contents, and these phenomena were also observed in other species. As a result of the principal component analysis (PCA) using NIR between five species (total 19 samples), the samples were divided into three groups in the score plot based on principal component (PC) 1 and principal component (PC) 2; group 1) red pine and Korean pine, group 2) larch, and group 3) cypress and cedar. Based on the chemical composition results, it was concluded that extractive content was highly relevant to wood classification by NIR analysis.

• Journal of agriculture & life science
• /
• v.46 no.2
• /
• pp.1-8
• /
• 2012

This study is a precedent study for deriving transfer function model between growing stock and forest management policies. Its goal is to solve the multicollinearity between forest works inducing growing stock changes through principal component analysis using annual time series data from 1997 to 2008. As the results, the total explanatory power showed 91.4% on the summarized 3 principal components. They were renamed 'good forest management' 'pest & insets management' 'forest fires' for conceptualization on the derived each component.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.4
• /
• pp.87-98
• /
• 2011

Detecting a moving object from videos and tracking it are basic and necessary preprocessing steps in many video systems like object recognition, context aware, and intelligent visual surveillance. In this paper, we propose a method that is able to detect a moving object quickly and accurately in a condition that background and light change in a real time. Furthermore, our system detects strongly an object in a condition that the target object is covered with other objects. For effective detection, effective Eigen-space and FCM are combined and employed, and a CONDENSATION algorithm is used to trace a detected object strongly. First, training data collected from a background image are linear-transformed using Principal Component Analysis (PCA). Second, an Eigen-background is organized from selected principal components having excellent discrimination ability on an object and a background. Next, an object is detected with FCM that uses a convolution result of the Eigen-vector of previous steps and the input image. Finally, an object is tracked by using coordinates of an detected object as an input value of condensation algorithm. Images including various moving objects in a same time are collected and used as training data to realize our system that is able to be adapted to change of light and background in a fixed camera. The result of test shows that the proposed method detects an object strongly in a condition having a change of light and a background, and partial movement of an object.

• Journal of the Korean Society of Food Culture
• /
• v.35 no.2
• /
• pp.193-200
• /
• 2020

This study was conducted to understand the sensory characteristics and consumer acceptance for the commercially available clear broth for noodles. Totally, eight different clear broth samples were evaluated in this study. Seven trained panelists developed and evaluated sensory characteristics in the descriptive analysis. Significant differences (p<0.05) were obtained for all 28 attributes evaluated. Descriptive data was obtained by performing multivariate analysis of variance to identify differences between samples. Principal component analysis (PCA) was performed on the mean values of descriptive attributes obtained in the descriptive analysis, and summarizes the sensory characteristics of clear broth for noodles. PCA of the clear broths revealed that the first two principal components are responsible for 80.66% variations. For sensory testing, 160 consumers were recruited, and their acceptance for each sample was assessed. Consumer data was obtained by applying partial least square-regression (PLSR) to establish the relationship between the descriptive data and the consumer acceptance data.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.687-696
• /
• 2019

Conventional feature of seismic classification focuses on strong seismic classification, while it is not suitable for classifying micro-seismic waves. We propose a feature extraction method based on histogram and Principal Component Analysis (PCA) in frequency-time space suitable for classifying seismic waves including strong, micro, and artificial seismic waves, as well as noise classification. The proposed method essentially employs histogram and PCA based features by concatenating the frequency and time information for binary classification which consist strong-micro-artificial/noise and micro/noise and micro/artificial seismic waves. Based on the recent earthquake data from 2017 to 2018, effectiveness of the proposed feature extraction method is demonstrated by comparing it with existing methods.