• Progress in Medical Physics
• /
• v.23 no.1
• /
• pp.42-47
• /
• 2012

In this paper, Acousto-Optical tomography is modeled by a linear integral equation and an inverse problem involving a diffusion equation in n-spatial dimensions. We make two-step mathematical model. First, we solve a linear integral equation. Assuming the optical energy fluence rate has been recovered from the previous equation, the absorption coefficient ${\mu}$ is then reconstructed by solving an inverse problem. Numerical experiments are presented for the case n=2. The traditional gradient descent method is used for the numerical simulations. The result of the gradient descent method produces the blurring effect. To get rid of the blurring effect, we suggest the total variation regularization for the minimization problem.

• The Korean Journal of Applied Statistics
• /
• v.36 no.6
• /
• pp.501-514
• /
• 2023

When analyzing high dimensional data such as text data, if we input all the variables as explanatory variables, statistical learning procedures may suffer from over-fitting problems. Furthermore, computational efficiency can deteriorate with a large number of variables. Dimensionality reduction techniques such as feature selection or feature extraction are useful for dealing with these problems. The sparse principal component analysis (SPCA) is one of the regularized least squares methods which employs an elastic net-type objective function. The SPCA can be used to remove insignificant principal components and identify important variables from noisy observations. In this study, we propose a dimension reduction procedure for text data based on the SPCA. Applying the proposed procedure to real data, we find that the reduced feature set maintains sufficient information in text data while the size of the feature set is reduced by removing redundant variables. As a result, the proposed procedure can improve classification accuracy and computational efficiency, especially for some classifiers such as the k-nearest neighbors algorithm.

• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.347-356
• /
• 2017

It is well-known that the face recognition method via sparse representation has been proved very robust and showed good performance. Its weakness is, however, that its time complexity is very high because it should solve $L_1$-minimization problem to find the sparse solution. In this paper, we propose to use the ROMP(Regularized Orthogonal Matching Pursuit) method for the sparse solution, which solves the $L_2$-minimization problem with regularization condition using the greed strategy. In experiments, we shows that the proposed method is comparable to the existing best $L_1$-minimization solver, Homotopy, but is 60 times faster than Homotopy. Also, we proposed C-SCI method for classification. The C-SCI method is very effective since it considers the sparse solution only without reconstructing the test data. It is shown that the C-SCI method is comparable to, but is 5 times faster than the existing best classification method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.2
• /
• pp.99-105
• /
• 2013

In rapidly developing urban areas that include high-rise, large, and complex buildings, indoor and outdoor maps in GIS become a basis for utilizing and sharing information pertaining to various aspects of the real world. Although an indoor mapping has gained much attentions, research efforts are mostly in 2D and 3D modeling of terrain and buildings. Therefore, to facilitate fast and accurate construction of indoor GIS, this paper proposes a semi-automatic method consisting of preprocessing, 2D mapping, and 3D mapping stages. The preprocessing is designed to estimate heights of building interiors and to identify noise data from point clouds. In the 2D mapping, a floor map is extracted with a tracing grid and a refinement method. In the 3D mapping, a 3D wireframe model is created with heights from the preprocessing stage. 3D mesh data converted from noise data is combined with the 3D wireframe model for detail modeling. The proposed method was applied to point clouds depicting a hallway in a building. Experiment results indicate that the proposed method can be utilized to construct 2D and 3D maps for indoor GIS.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.5
• /
• pp.619-628
• /
• 2009

LiDAR has capability of rapid data acquisition and provides useful information for reconstructing surface of the Earth. However, Extracting information from LiDAR data is not easy task because LiDAR data consist of irregularly distributed point clouds of 3D coordinates and lack of semantic and visual information. This thesis proposed methods for automatic extraction of buildings and 3D detail modeling using airborne LiDAR data. As for preprocessing, noise and unnecessary data were removed by iterative surface fitting and then classification of ground and non-ground data was performed by analyzing histogram. Footprints of the buildings were extracted by tracing points on the building boundaries. The refined footprints were obtained by regularization based on the building hypothesis. The accuracy of building footprints were evaluated by comparing with 1:1,000 digital vector maps. The horizontal RMSE was 0.56m for test areas. Finally, a method of 3D modeling of roof superstructure was developed. Statistical and geometric information of the LiDAR data on building roof were analyzed to segment data and to determine roof shape. The superstructures on the roof were modeled by 3D analytical functions that were derived by least square method. The accuracy of the 3D modeling was estimated using simulation data. The RMSEs were 0.91m, 1.43m, 1.85m and 1.97m for flat, sloped, arch and dome shapes, respectively. The methods developed in study show that the automation of 3D building modeling process was effectively performed.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.59-76
• /
• 2023

Since the COVID-19 era, the rise in apartment prices has been unconventional. In this uncertain real estate market, price prediction research is very important. In this paper, a model is created to predict the actual transaction price of future apartments after building a vast data set of 870,000 from 2015 to 2020 through data collection and crawling on various real estate sites and collecting as many variables as possible. This study first solved the multicollinearity problem by removing and combining variables. After that, a total of five variable selection algorithms were used to extract meaningful independent variables, such as Forward Selection, Backward Elimination, Stepwise Selection, L1 Regulation, and Principal Component Analysis(PCA). In addition, a total of four machine learning and deep learning algorithms were used for deep neural network(DNN), XGBoost, CatBoost, and Linear Regression to learn the model after hyperparameter optimization and compare predictive power between models. In the additional experiment, the experiment was conducted while changing the number of nodes and layers of the DNN to find the most appropriate number of nodes and layers. In conclusion, as a model with the best performance, the actual transaction price of apartments in 2021 was predicted and compared with the actual data in 2021. Through this, I am confident that machine learning and deep learning will help investors make the right decisions when purchasing homes in various economic situations.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Journal of Korean Society for Geospatial Information Science
• /
• v.11 no.4 s.27
• /
• pp.21-27
• /
• 2003

The rational polynomial coefficients(RPC) model is a generalized sensor model that is used as an alternative for the physical sensor model for IKONOS-2 and QuickBird. As the number of sensors increases along with greater complexity, and as the need for standard sensor model has become important, the applicability of the RPC model is also increasing. The RPC model can be substituted for all sensor models, such as the projective camera the linear pushbroom sensor and the SAR This paper is aimed at generating a RPC model from the physical sensor model of the KOMPSAT-1(Korean Multi-Purpose Satellite) and aerial photography. The KOMPSAT-1 collects $510{\sim}730nm$ panchromatic images with a ground sample distance (GSD) of 6.6m and a swath width of 17 km by pushbroom scanning. We generated the RPC from a physical sensor model of KOMPSAT-1 and aerial photography. The iterative least square solution based on Levenberg-Marquardt algorithm is used to estimate the RPC. In addition, data normalization and regularization are applied to improve the accuracy and minimize noise. And the accuracy of the test was evaluated based on the 2-D image coordinates. From this test, we were able to find that the RPC model is suitable for both KOMPSAT-1 and aerial photography.

• Journal of Digital Convergence
• /
• v.20 no.1
• /
• pp.203-211
• /
• 2022

This study is to examine the causes of research misconduct such as plagiarism, forgery, redundant publication, unfair author expression, and incapacitation of the research ethics system of university researchers and to suggest improvement plan. It basically relied on literature research. In order to supplement the deficiencies in literature research, I sought advice from an expert professor who had experience working in a research-related field in university or who is currently in a position related to research ethics through the delphi-method. As a result of the study, from the perspective of individual researchers, the complacent attitude, dishonesty, and greed for research funds were identified as the main reasons. In terms of organization, it was analyzed for reasons such as lack of detail and application of regulations, lack of verification system, and performance-oriented research environment. In order to overcome research misconduct caused by the researcher's personal reasons, regularization, increase in the number of research ethics education, and strengthening personal penalties were suggested. As a way to overcome irregularities arising from institutional reasons, the reinforcement of the verification system, the reinforcement of the whistle-blower's personal protection system, the omission of promotion, and the quality and quantitative balance of research evaluation was suggested.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.192-207
• /
• 2020

We acquire seismic data with regularly or irregularly missing traces, due to economic, environmental, and mechanical problems. Since these missing data adversely affect the results of seismic data processing and analysis, we need to reconstruct the missing data before subsequent processing. However, there are economic and temporal burdens to conducting further exploration and reconstructing missing parts. Many researchers have been studying interpolation methods to accurately reconstruct missing data. Recently, various machine learning technologies such as support vector regression, autoencoder, U-Net, ResNet, and generative adversarial network (GAN) have been applied in seismic data interpolation. In this study, by reviewing these studies, we found that not only neural network models, but also support vector regression models that have relatively simple structures can interpolate missing parts of seismic data effectively. We expect that future research can improve the interpolation performance of these machine learning models by using open-source field data, data augmentation, transfer learning, and regularization based on conventional interpolation technologies.