• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.601-606
• /
• 2006

The image data amount that used in medical institution with great development of medical technology is increasing rapidly. Therefore, people need automation method that use image processing description than macrography of doctors for analysis many medical image. In this paper. we propose that acquire texture information to using GLCM about liver area of abdomen CT image, and automatically detects liver tumor using PCA from this data. Method by one feature as intensity of existent liver humor detection was most but we changed into 4 principal component accumulation images using GLCM's texture information 8 feature. Experiment result, 4 principal component accumulation image's variance percentage is 89.9%. It was seen this compare with liver tumor detecting that use only intensity about 92%. This means that can detect liver tumor even if reduce from dimension of image data to 4 dimensions that is the half in 8 dimensions.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.105-112
• /
• 2006

In this study, we propose a simple preprocessing method for classification of basal cell carcinoma (BCC), which is one of the most common skin cancer. The preprocessing step consists of data clipping with a half Hanning window and dimension reduction with principal components analysis (PCA). The application of the half Hanning window deemphasizes the peak near $1650cm^{-1}$ and improves classification performance by lowering the false negative ratio. Classification results with various classifiers are presented to show the effectiveness of the proposed method. The classifiers include maximum a posteriori probability (MAP), k-nearest neighbor (KNN), probabilistic neural network (PNN), multilayer perceptron(MLP), support vector machine (SVM) and minimum squared error (MSE) classification. Classification results with KNN involving 216 spectra preprocessed with the proposed method gave 97.3% sensitivity, which is very promising results for automatic BCC detection.

• Geophysics and Geophysical Exploration
• /
• v.1 no.3
• /
• pp.170-175
• /
• 1998

A systematic methodology is developed for the prediction of the lithology using electrofacies classification from wireline log data. Multivariate statistical techniques are adopted to segment well log measurements and group the segments into electrofacies types. To consider corresponding contribution of each log and reduce the computational dimension, multivariate logs are transformed into a single variable through principal components analysis. Resultant principal components logs are segmented using the statistical zonation method to enhance the quality and efficiency of the interpreted results. Hierarchical cluster analysis is then used to group the segments into electrofacies. Optimal number of groups is determined on the basis of the ratio of within-group variance to total variance and core data. This technique is applied to the wells in the Korea Continental Shelf. The results of field application demonstrate that the prediction of lithology based on the electrofacies classification works well with reliability to the core and cutting data. This methodology for electrofacies determination can be used to define reservoir characterization which is helpful to the reservoir management.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.102-112
• /
• 2012

In this paper, we propose a texture classification using wavelet-domain BDIP (block difference of inverse probabilities) and BVLC (block variance of local correlation coefficients) features with WPCA (whitened principal component analysis) classifier. In the proposed method, the wavelet transform is first applied to a query image. The BDIP and BVLC operators are next applied to the wavelet subbands. Global moments for each subband of BDIP and BVLC are then computed and fused into a feature vector. In classification, the WPCA classifier, which is usually adopted in the face identification, searches the training feature vector most similar to the query feature vector. Experimental results show that the proposed method yields excellent texture classification with low feature dimension for test texture image DBs.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.2 no.1
• /
• pp.9-14
• /
• 1965

Ship designers make every efforts to get faster ships in accordance with the development of the Naval Architecture. But for the speed lying over factor length ratio 2.5-3.0, we could put a powerful engine into the conventional round bottom displacement type vessels, but it is very difficult in view point of economy, weight and volume. The principal cause of these speed obstacles is the wave making resistance and researchers are trying to decrease this resistance. One of the resolving ways, planing hulls were applied to small high boats. Planing hull's advantage is not restricted to speed, but the workmanship of the planing hull is easier than those of displacement type vessels of round bottom. Planing hull, therefore, are widely applicable to the intermediate speed boats, which don't have enough high speed to take planing advantage, as well as high speed boats. We will discuss related phenomena of the planing hull in details and this paper we particularly interested in the interjection point(speed length ratio 3.0-3.5 by Mr. D. De Groots) between semi-planing and full planing hulls on the resistance characteristic curve. The paper by Prof. Keuck Chun Kim, "Some Characteristics of Straight Framed V-bottom Hull Forms", Journal of the society of Naval Architects of Korea, Vol.1, No.1, Dec.5, 1964, is referred to the V-bottom hull forms belonging to low speed region and determines practical applicable limit of the speed length ratio combined with construction costs, under which are still used by large commercial vessels. This is the interesting contrast between his and authors. We will further discuss the speed length ratio which is considered as a beginning point to planing effect. For this analysis, we choose 3 model ships: Model (1) and (2) have the same principal dimensions, model 3 varied dimension. Model (1) is full-planing hull, (2) is semi-planing hull and (3) is complete planing hull. They are aimed to collect proper design data for purposed ships.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.7 no.2
• /
• pp.270-287
• /
• 2015

According to the increase of the operating cost and material cost of a ship due to the change of international oil price, a demand for the lightening of the ship weight is being made from various parties such as shipping companies, ship owners, and shipyards. To satisfy such demand, many studies for a light ship are being made. As one of them, an optimal design method of an existing hull structure, that is, a method for lightening the ship weight based on the optimization technique was proposed in this study. For this, we selected a hatch cover of a bulk carrier as an optimization target and formulated an optimization problem in order to determine optimal principal dimensions of the hatch cover for lightening the bulk carrier. Some dimensions representing the shape of the hatch cover were selected as design variables and some design considerations related to the maximum stress, maximum deflection, and geometry of the hatch cover were selected as constraints. In addition, the minimization of the weight of the hatch cover was selected as an objective function. To solve this optimization problem, we developed an optimization program based on the Sequential Quadratic Programming (SQP) using C++ programming language. To evaluate the applicability of the developed program, it was applied to a problem for finding optimal principal dimensions of the hatch cover of a deadweight 180,000 ton bulk carrier. The result shows that the developed program can decrease the hatch cover's weight by about 8.5%. Thus, this study will be able to contribute to make energy saving and environment-friendly ship in shipyard.

• 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.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.1
• /
• pp.225-231
• /
• 2013

In this study, we propose the design of optimized pRBFNNs-based night vision face recognition system using PCA algorithm. It is difficalt to obtain images using CCD camera due to low brightness under surround condition without lighting. The quality of the images distorted by low illuminance is improved by using night vision camera and histogram equalization. Ada-Boost algorithm also is used for the detection of face image between face and non-face image area. The dimension of the obtained image data is reduced to low dimension using PCA method. Also we introduce the pRBFNNs as recognition module. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned by using Fuzzy C-Means clustering. In the conclusion part of rules, the connection weights of pRBFNNs is represented as three kinds of polynomials such as linear, quadratic, and modified quadratic. The essential design parameters of the networks are optimized by means of Differential Evolution.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.4
• /
• pp.682-691
• /
• 2017

In this paper, we propose the fusion design methodology of both pedestrian detection and object tracking system realized with the aid of HOG-PCA based RBFNN pattern classifier. The proposed system includes detection and tracking parts. In the detection part, HOG features are extracted from input images for pedestrian detection. Dimension reduction is also dealt with in order to improve detection performance as well as processing speed by using PCA which is known as a typical dimension reduction method. The reduced features can be used as the input of the FCM-based RBFNNs pattern classifier to carry out the pedestrian detection. FCM-based RBFNNs pattern classifier consists of condition, conclusion, and inference parts. FCM clustering algorithm is used as the activation function of hidden layer. In the conclusion part of network, polynomial functions such as constant, linear, quadratic and modified quadratic are regarded as connection weights and their coefficients of polynomial function are estimated by LSE-based learning. In the tracking part, object tracking algorithms such as mean shift(MS) and cam shift(CS) leads to trace one of the pedestrian candidates nominated in the detection part. Finally, INRIA person database is used in order to evaluate the performance of the pedestrian detection of the proposed system while MIT pedestrian video as well as indoor and outdoor videos obtained from IC&CI laboratory in Suwon University are exploited to evaluate the performance of tracking.

• 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.