• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.547-554
• /
• 2021

In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.29-45
• /
• 2015

Response modeling is a well-known research issue for those who have tried to get more superior performance in the capability of predicting the customers' response for the marketing promotion. The response model for customers would reduce the marketing cost by identifying prospective customers from very large customer database and predicting the purchasing intention of the selected customers while the promotion which is derived from an undifferentiated marketing strategy results in unnecessary cost. In addition, the big data environment has accelerated developing the response model with data mining techniques such as CBR, neural networks and support vector machines. And CBR is one of the most major tools in business because it is known as simple and robust to apply to the response model. However, CBR is an attractive data mining technique for data mining applications in business even though it hasn't shown high performance compared to other machine learning techniques. Thus many studies have tried to improve CBR and utilized in business data mining with the enhanced algorithms or the support of other techniques such as genetic algorithm, decision tree and AHP (Analytic Process Hierarchy). Ahn and Kim(2008) utilized logit, neural networks, CBR to predict that which customers would purchase the items promoted by marketing department and tried to optimized the number of k for k-nearest neighbor with genetic algorithm for the purpose of improving the performance of the integrated model. Hong and Park(2009) noted that the integrated approach with CBR for logit, neural networks, and Support Vector Machine (SVM) showed more improved prediction ability for response of customers to marketing promotion than each data mining models such as logit, neural networks, and SVM. This paper presented an approach to predict customers' response of marketing promotion with Case Based Reasoning. The proposed model was developed by applying different weights to each feature. We deployed logit model with a database including the promotion and the purchasing data of bath soap. After that, the coefficients were used to give different weights of CBR. We analyzed the performance of proposed weighted CBR based model compared to neural networks and pure CBR based model empirically and found that the proposed weighted CBR based model showed more superior performance than pure CBR model. Imbalanced data is a common problem to build data mining model to classify a class with real data such as bankruptcy prediction, intrusion detection, fraud detection, churn management, and response modeling. Imbalanced data means that the number of instance in one class is remarkably small or large compared to the number of instance in other classes. The classification model such as response modeling has a lot of trouble to recognize the pattern from data through learning because the model tends to ignore a small number of classes while classifying a large number of classes correctly. To resolve the problem caused from imbalanced data distribution, sampling method is one of the most representative approach. The sampling method could be categorized to under sampling and over sampling. However, CBR is not sensitive to data distribution because it doesn't learn from data unlike machine learning algorithm. In this study, we investigated the robustness of our proposed model while changing the ratio of response customers and nonresponse customers to the promotion program because the response customers for the suggested promotion is always a small part of nonresponse customers in the real world. We simulated the proposed model 100 times to validate the robustness with different ratio of response customers to response customers under the imbalanced data distribution. Finally, we found that our proposed CBR based model showed superior performance than compared models under the imbalanced data sets. Our study is expected to improve the performance of response model for the promotion program with CBR under imbalanced data distribution in the real world.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1516-1519
• /
• 1997

With disseminationof Distributed Control Systems(DCS), the huge amounts of process operation data could have been available and led to figure out process behaviors better on the statistical basis. Until now, the statistical modeling technology has been susally applied to process monitoring and fault diagnosis. however, it has been also thought that these process information, extracted from statistical analysis, might serve a great opportunity for process operation improvements and process improvements. This paper proposed a general methodolgy for process operation improvements including data analysis, backing up the result of analysis based on the methodology, and the mapping physical physical phenomena to the Principal Components(PC) which is the most distinguished feature in the methodology form traditional statistical analyses. The application of the proposed methodology to the Balst Furnace(BF) process has been presented for details. The BF process is one of the complicated processes, due to the highly nonlinear and correlated behaviors, and so the analysis for the process based on the mathematical modeling has been very difficult. So the statisitical analysis has come forward as a alternative way for the useful analysis. Using the proposed methodology, we could interpret the complicated process, the BF, better than any other mathematical methods and find the direction for process operation improvement. The direction of process operationimprovement, in the BF case, is to increase the fludization and the permeability, while decreasing the effect of tapping operation. These guide directions, with those physical meanings, could save fuel cost and process operator's pressure for proper actions, the better set point changes, in addition to the assistance with the better knowledge of the process. Open to set point change, the BF has a variety of steady state modes. In usual almost chemical processes are under the same situation with the BF in the point of multimode steady states. The proposed methodology focused on the application to the multimode steady state process such as the BF, consequently can be applied to any chemical processes set point changing whether operator intervened or not.

• Journal of the Korea Computer Graphics Society
• /
• v.18 no.1
• /
• pp.1-9
• /
• 2012

Video-based modeling / rendering developed to produce photo-realistic video contents have been one of the important research topics in computer graphics and computer visions. To smoothly combine original input video clips and 3D graphic models, geometrical information of light sources and cameras used to capture a scene in the real world is essentially required. In this paper, we present a simple technique to estimate the position and orientation of an optimal light source from the topology of objects and the silhouettes of shadows appeared in the original video clips. The technique supports functions to generate well matched shadows as well as to render the inserted models by applying the estimated light sources. Shadows are known as an important visual cue that empirically indicates the relative location of objects in the 3D space. Thus our method can enhance realism in the final composed videos through the proposed shadow generation and rendering algorithms in real-time.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.31-39
• /
• 2006

This paper presents a novel approach to real-time recognition of 3D environment and objects for various applications such as intelligent robots, intelligent vehicles, intelligent buildings,..etc. First, we establish the three fundamental principles that humans use for recognizing and interacting with the environment. These principles have led to the development of an integrated approach to real-time 3D recognition and modeling, as follows: 1) It starts with a rapid but approximate characterization of the geometric configuration of workspace by identifying global plane features. 2) It quickly recognizes known objects in environment and replaces them by their models in database based on 3D registration. 3) It models the geometric details the geometric details on the fly adaptively to the need of the given task based on a multi-resolution octree representation. SIFT features with their 3D position data, referred to here as stereo-sis SIFT, are used extensively, together with point clouds, for fast extraction of global plane features, for fast recognition of objects, for fast registration of scenes, as well as for overcoming incomplete and noisy nature of point clouds.

• Journal of KIISE:Software and Applications
• /
• v.28 no.7
• /
• pp.501-510
• /
• 2001

Generally, it is essential to estimate exact disparity for the 3D modeling from stereo images. Because existing methods calculate disparities from a whole image, they require too much cimputational time and bring about the mismatching problem. In this article, using the characteristic that the disparity vectors in stereo images are distributed not equally in a whole image but only exist about the background and obhect, we do a wavelet transformation on stereo images and estimate coarse disparity fields from the reduced lowpass field using area-based method at first-step. From these coarse disparity vectors, we generate disparity histogram and then separate object from background area using it. Afterwards, we restore only object area to the original image and estimate dense and accurate disparity by our two-step pixel-based method which does not use pixel brightness but use second gradient. We also extract feature points from the separated object area and estimate depth information by applying disparity vectors and camera parameters. Finally, we generate 3D model using both feature points and their z coordinates. By using our proposed, we can considerably reduce the computation time and estimate the precise disparity through the additional pixel-based method using LOG filter. Furthermore, our proposed foreground/background method can solve the mismatching problem of existing Delaunay triangulation and generate accurate 3D model.

• Wind and Structures
• /
• v.8 no.6
• /
• pp.407-426
• /
• 2005

A hybrid RANS/LES approach, based on the Limited Numerical Scales concept, is applied to the numerical simulation of the flow around a square cylinder. The key feature of this approach is a blending between two eddy-viscosities, one given by the $k-{\varepsilon}$ RANS model and the other by the Smagorinsky LES closure. A mixed finite-element/finite-volume formulation is used for the numerical discretization on unstructured grids. The results obtained with the hybrid approach are compared with those given by RANS and LES simulations for three different grid resolutions; comparisons with experimental data and numerical results in the literature are also provided. It is shown that, if the grid resolution is adequate for LES, the hybrid model recovers the LES accuracy. For coarser grid resolutions, the blending criterion appears to be effective to improve the accuracy of the results with respect to both LES and RANS simulations.

• Proceedings of the IEEK Conference
• /
• 2004.06b
• /
• pp.451-454
• /
• 2004

The reconfigurable architecture is increasingly important for design of multi-mode communication systems and computation-intensive DSP systems. The proposed coarse-grain architecture is based on a reconfigurable processing element consisting of a MAC unit, a register file, a context data register, and PE interconnect control blocks. The main feature of the Proposed architecture is the loop context which enables faster configuration. Also, we propose another area-efficient reconfigurable architecture with improved reconfigurability. The SystemC modeling results show that the proposed architecture can reduce 9 clock cycles of 2D DCT compared to existing architectures.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.6
• /
• pp.670-676
• /
• 2004

Most metallic materials and alloys show rate independence or negative rate sensitivity in some temperature region when dynamic strain aging occurs. It is generally recognized that negative rate sensitivity is an essential feature of dynamic strain aging that can depend on strain and/or strain rate. The unified viscoplasticity theory based on overstress is applied to reproduce a change of rate sensitivity type that depends on strain or strain rate. This is accomplished through the introduction of a single new term in the growth law of the equilibrium stress, which is a tensor valued state variable of the model. It is also shown that the new term can be used to reproduce a dramatic increase of rate sensitivity in dynamic plasticity.

• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.839-841
• /
• 1999

This paper presents the method of 3D reconstruction of the depth information from the endoscopic stereo scopic images. After camera modeling to find camera parameters, we performed feature-point based stereo matching to find depth information. Acquired some depth information is finally 3D reconstructed using the NURBS(Non Uniform Rational B-Spline) algorithm. The final result image is helpful for the understanding of depth information visually.