• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.319-324
• /
• 2005

An integrated approach for prostate cancer detection using proteomic data is presented. Due to the high-dimensional feature of proteomic data, the discrete wavelet transform (DWT) is used in the first-stage for data reduction as well as noise removal. After the process of DWT, the dimensionality is reduced from 43,556 to 1,599. Thus, each sample of proteomic data can be represented by 1599 wavelet coefficients. In the second stage, a voting method is used to select a common set of wavelet coefficients for all samples together. This produces a 987-dimension subspace of wavelet coefficients. In the third stage, the Autoassociator algorithm reduces the dimensionality from 987 to 400. Finally, the artificial neural network (ANN) is applied on the 400-dimension space for prostate cancer detection. The integrated approach is examined on 9 categories of 2-class experiments, and also 3- and 4-class experiments. All of the experiments were run 10 times of ten-fold cross-validation (i. e. 10 partitions with 100 runs). For 9 categories of 2-class experiments, the average testing accuracies are between 81% and 96%, and the average testing accuracies of 3- and 4-way classifications are 85% and 84%, respectively. The integrated approach achieves exciting results for the early detection and diagnosis of prostate cancer.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.574-577
• /
• 2007

본 논문에서는 실 시공 중인 PSC 교량에 대하여 풍하중에 의한 상시 진동 계측 자료을 기반으로, 교량의 동특성(고유진동수, 모드형상)을 추정하였으며, 이를 바탕으로 대상 교량의 탄성계수를 추정하여 정적 계측을 통한 탄성계수 결과와 비교하였다. 본 논문에서 사용한 동특성 추정 기법은, 대표적인 주파수 영역 해석 방법인 Frequency Domain Decomposition(FDD) 방법과 시간영역 해석 방법인 Stochastic Subspace Identification(SSI) 방법을 이용하였다. 탄성계수 추정은 유한요소모델과 계측 결과를 이용하여 두 개의 결과 차이가 수렴하도록 하는 반복 계산을 통해 탄성계수를 추정하였다. 우선, 탄성계수 추정 기법의 검증을 위해, 수치 해석을 통하여 그 기법을 검증하였으며, 해석 결과 정확한 탄성계수값을 추정하였으며, 이를 통해 본 논문에서 적용한 탄성계수 추정법에 대한 신뢰도를 확인하였다. 이를 바탕으로 사용된 추정 기법을 실 교량에 적용하기 위해 실제 상시 진동 계측 값을 바탕으로 실교량의 동특성 및 탄성계수를 추정하였다. FDD 및 SSI 기법을 통한 모드 해석 결과, 두 기법 모두 유사한 결과를 나타내어 FDD 및 SSI 두 방법에 대한 결과의 신뢰도를 확인 할 수 있었다. 추정 탄성계수 값은 거더 단면내 설치한 응력계 및 변형률계를 통한 계측 결과값의 범위 내에 있음을 확인하였다. 따라서 본 논문에서 적용한 교량의 상시 진동 데이터를 바탕으로 한동특성 및 탄성계수 추정법이 구조물의 대략적인 탄성계수 및 이에 따른 구조물의 전체적인 건전도를 파악하는데 도움이 되리라 생각된다.

• Korean Journal of Applied Biomechanics
• /
• v.28 no.4
• /
• pp.213-218
• /
• 2018

Objective: The purpose of this study was to examine the effect of the core muscle strength enhancement of the elderly on 8 weeks training using the core exercise equipment for the elderly on the ability to control the whole-body center of mass in posture stabilization. Method: 16 females (10 exercise group, 6 control group) participated in this study. Exercise group took part in the core strength training program for 8 weeks with total of 16 repetitions (2 repetitions per week) using a training device. External perturbation during standing as pulling force applied at the pelvic level in the anterior direction was provided to the subject. In a UCM model, the controller selects within the space of elemental variables a subspace (a manifold, UCM) corresponding to a value of a performance variable that needs to be stabilized. In the present study, we were interested in how movements of the individual segment center of mass (elemental variables) affect the whole-body center of mass (the performance variable) during balance control. Results: At the variance of task-irrelevant space, there was significant $test^*$ group interactions ($F_{1,16}=7.482$, p<.05). However, there were no significant main effect of the test ($F_{1,16}=.899$, p>.05) and group ($F_{1,16}=1.039$, p>.05). At the variance of task-relevant space, there was significant $test^*$ group interactions ($F_{1,16}=7.382$, p<.05). However, there were no significant main effect of the test ($F_{1,16}=.754$, p>.05) and group ($F_{1,16}=1.106$, p>.05). Conclusion: The results of this study showed that the 8 weeks training through the core training equipment for the elderly showed a significant decrease in the $Vcm_{TIR}$ and $Vcm_{TR}$. This result indicates that the core strength training affects the trunk stiffness control strategy to maintain balance in the standing position by minimizing total variability of individual segment CMs.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.421-436
• /
• 2023

This paper presents a vibration displacement measurement and damage identification method for a space truss structure from its vibration videos. Features from Accelerated Segment Test (FAST) algorithm is combined with adaptive threshold strategy to detect the feature points of high quality within the Region of Interest (ROI), around each node of the truss structure. Then these points are tracked by Kanade-Lucas-Tomasi (KLT) algorithm along the video frame sequences to obtain the vibration displacement time histories. For some cases with the image plane not parallel to the truss structural plane, the scale factors cannot be applied directly. Therefore, these videos are processed with homography transformation. After scale factor adaptation, tracking results are expressed in physical units and compared with ground truth data. The main operational frequencies and the corresponding mode shapes are identified by using Subspace Stochastic Identification (SSI) from the obtained vibration displacement responses and compared with ground truth data. Structural damages are quantified by elemental stiffness reductions. A Bayesian inference-based objective function is constructed based on natural frequencies to identify the damage by model updating. The Success-History based Adaptive Differential Evolution with Linear Population Size Reduction (L-SHADE) is applied to minimise the objective function by tuning the damage parameter of each element. The locations and severities of damage in each case are then identified. The accuracy and effectiveness are verified by comparison of the identified results with the ground truth data.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4A
• /
• pp.605-609
• /
• 2006

In this study, two kinds of smart accelerometers are investigated for the application of smart sensors to the structural health monitoring of infrastructures. Smart optical Fiber Bragg Grating (FBG) type and Micro-Electo-Mechanical System (MEMS) type accelerometers are selected for this study and the high sensitive ICP type accelerometer is used for the reference sensor. Small size shaking table tests were performed with 3-story shear building model using random input ground motions. The output only modal identification was carried out using stochastic subspace identification and the performances of sensors are compared in modal domain indirectly. The modal sensitivity method was applied to update the story stiffness of numerical model and the updated results were verified using the additional experiments for the same structure with additional mass.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.519-527
• /
• 2003

Speech is much influenced by the existence of outliers which are introduced by such an unexpected happenings as additive background noise, change of speaker's utterance pattern and voice detection errors. These kinds of outliers may result in severe degradation of speaker recognition performance. In this paper, we proposed the GMM based on robust principal component analysis (RPCA-GMM) using M-estimation to solve the problems of both ouliers and high dimensionality of training feature vectors in speaker identification. Firstly, a new feature vector with reduced dimension is obtained by robust PCA obtained from M-estimation. The robust PCA transforms the original dimensional feature vector onto the reduced dimensional linear subspace that is spanned by the leading eigenvectors of the covariance matrix of feature vector. Secondly, the GMM with diagonal covariance matrix is obtained from these transformed feature vectors. We peformed speaker identification experiments to show the effectiveness of the proposed method. We compared the proposed method (RPCA-GMM) with transformed feature vectors to the PCA and the conventional GMM with diagonal matrix. Whenever the portion of outliers increases by every 2%, the proposed method maintains almost same speaker identification rate with 0.03% of little degradation, while the conventional GMM and the PCA shows much degradation of that by 0.65% and 0.55%, respectively This means that our method is more robust to the existence of outlier.

• Korean Journal of Remote Sensing
• /
• v.34 no.2_2
• /
• pp.313-326
• /
• 2018

This paper introduces core techniques on ship detection and tracking based on a compact HF radar platform which is necessary to establish a wide-area surveillance network. Currently, most HF radar sites are primarily optimized for observing sea surface radial velocities and bearings. Therefore, many ship detection systems are vulnerable to error sources such as environmental noise and clutter when they are applied to these practical surface current observation purpose systems. In addition, due to Korea's geographical features, only compact HF radars which generates non-uniform antenna response and has no information on target information are applicable. The ship detection and tracking techniques discussed in this paper considers these practical conditions and were evaluated by real data collected from the Yellow Sea, Korea. The proposed method is composed of two parts. In the first part, ship detection, a constant false alarm rate based detector was applied and was enhanced by a PCA subspace decomposition method which reduces noise. To merge multiple detections originated from a single target due to the Doppler effect during long CPIs, a clustering method was applied. Finally, data association framework eliminates false detections by considering ship maneuvering over time. According to evaluation results, it is claimed that the proposed method produces satisfactory results within certain ranges.

• Geophysics and Geophysical Exploration
• /
• v.7 no.2
• /
• pp.148-154
• /
• 2004

This article reviews the development of three-dimensional (3-D) magnetotelluric (MT) modeling. The 3-D modeling of electromagnetic fields is essential in understanding the physics of MT soundings, and in implementing an inversion method to reconstruct a 3-D resistivity image. Although various numerical schemes have been developed over the last two decades, practical methods have been quite limited. However, the recent rapid improvement in computer speed and memory, as well as the advance in iterative solution algorithms for a large system of equations, makes it possible to model the MT responses of complex 3-D structures, which have been very difficult to simulate before. The use of staggered grids in finite difference method has become popular, conserving a magnetic flux and an electric current and allowing for realistic discontinuous fields. The convergence of numerical solutions has been greatly accelerated by adopting Krylov subspace methods, proper preconditioning techniques, and static divergence corrections. The vector finite-element method using edge elements is also free from the discontinuity problem, and seems a natural choice for modeling complex structures including irregular topography because its flexibility allows one to capture full geometric complexity.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.4
• /
• pp.35-41
• /
• 2001

This paper describes Linear Discriminant Analysis and common vector extraction for speech recognition. Voice signal contains psychological and physiological properties of the speaker as well as dialect differences, acoustical environment effects, and phase differences. For these reasons, the same word spelled out by different speakers can be very different heard. This property of speech signal make it very difficult to extract common properties in the same speech class (word or phoneme). Linear algebra method like BT (Karhunen-Loeve Transformation) is generally used for common properties extraction In the speech signals, but common vector extraction which is suggested by M. Bilginer et at. is used in this paper. The method of M. Bilginer et al. extracts the optimized common vector from the speech signals used for training. And it has 100％ recognition accuracy in the trained data which is used for common vector extraction. In spite of these characteristics, the method has some drawback-we cannot use numbers of speech signal for training and the discriminant information among common vectors is not defined. This paper suggests advanced method which can reduce error rate by maximizing the discriminant information among common vectors. And novel method to normalize the size of common vector also added. The result shows improved performance of algorithm and better recognition accuracy of 2％ than conventional method.