• 정보기술응용연구
• /
• 제1권
• /
• pp.173-211
• /
• 1999

The task of classification permeates all walks of life, from business and economics to science and public policy. In this context, nonlinear techniques from artificial intelligence have often proven to be more effective than the methods of classical statistics. The objective of knowledge discovery and data mining is to support decision making through the effective use of information. The automated approach to knowledge discovery is especially useful when dealing with large data sets or complex relationships. For many applications, automated software may find subtle patterns which escape the notice of manual analysis, or whose complexity exceeds the cognitive capabilities of humans. This paper explores the utility of a collaborative learning approach involving integrated models in the preprocessing and postprocessing stages. For instance, a genetic algorithm effects feature-weight optimization in a preprocessing module. Moreover, an inductive tree, artificial neural network (ANN), and k-nearest neighbor (kNN) techniques serve as postprocessing modules. More specifically, the postprocessors act as second0order classifiers which determine the best first-order classifier on a case-by-case basis. In addition to the second-order models, a voting scheme is investigated as a simple, but efficient, postprocessing model. The first-order models consist of statistical and machine learning models such as logistic regression (logit), multivariate discriminant analysis (MDA), ANN, and kNN. The genetic algorithm, inductive decision tree, and voting scheme act as kernel modules for collaborative learning. These ideas are explored against the background of a practical application relating to financial fraud management which exemplifies a binary classification problem.

• 한국멀티미디어학회논문지
• /
• 제13권12호
• /
• pp.1786-1797
• /
• 2010

Automatic understanding of contents in document image is a very hard problem due to involvement with mathematically challenging problems originated mainly from the over-determined system induced by document segmentation process. In both academic and industrial areas, there have been incessant and various efforts to improve core parts of content retrieval technologies by the means of separating out segmentation related issues using semi-structured document, e.g., invoice,. In this paper we proposed classification models for text lines on invoice document in which text lines were clustered into the five categories in accordance with their contents: purchase order header, invoice header, summary header, surcharge header, purchase items. Our investigation was concentrated on the performance of machine learning based models in aspect of linear-discriminant-analysis (LDA) and non-LDA (logic based). In the group of LDA, na$\"{\i}$ve baysian, k-nearest neighbor, and SVM were used, in the group of non LDA, decision tree, random forest, and boost were used. We described the details of feature vector construction and the selection processes of the model and the parameter including training and validation. We also presented the experimental results of comparison on training/classification error levels for the models employed.

• Ocean Systems Engineering
• /
• 제4권1호
• /
• pp.53-62
• /
• 2014

The detection of ship wakes image can demonstrate substantial information regarding on a ship, such as its tonnage, type, direction, and speed of movement. Consequently, the wake target recognition is a favorable way for ship identification. This paper proposes a Local Binary Pattern (LBP) approach to extract image features (wakes) for training an Improved Back Propagation Artificial Neural Network (IBPANN) to identify ship speed. This method is applied to sort and recognize the ship wakes of five different speeds images, the result shows that the detection accuracy is satisfied as expected, the average correctness rates of wakes target recognition at the five speeds may be achieved over 80%. Specifically, the lower ship's speed, the better accurate rate, sometimes it's accuracy could be close to 100%. In addition, one significant feature of this method is that it can receive a higher recognition rate than the nearest neighbor classification method.

• 한국멀티미디어학회논문지
• /
• 제9권3호
• /
• pp.279-286
• /
• 2006

주파수 분포벡터를 이용한 분류방법을 국악기 분류 및 인식에 적용하였으며 분류에 사용되는 주파수 분포 벡터 중에서 리듬성분을 수치화한 평균피크값을 제안하였다. 대부분의 주파수 처리함수들은 주파수값의 평균, 통계적특성에 기반을 두고 있으며 국악기자동분류를 위해 신호의 평균, 분산, 영교차율, 균형주파수, 평균 피크값을 이용하여 실험하였다. 국악의 장르 구분을 위한 선행 연구로서 음악신호를 함수처리하고 k-최근접이웃 분류알고리즘을 적용하여 분류하였다. 기존의 주파수 분포벡터를 이용하여 발표되었던 서양음악의 분류 성공률 87%보다 향상된 94.44%의 성공률을 나타냈다.

• 한국멀티미디어학회논문지
• /
• 제14권8호
• /
• pp.1010-1019
• /
• 2011

This was a preliminary research for the goal of understanding between internal structure of Osteogenesis Imperfecta Murine (OIM) bone and its fragility. 54 hyperspectral bone data sets were captured by using JASCO 2000 Raman spectrometer at UMKC-CRISP (University of Missouri-Kansas City Center for Research on Interfacial Structure and Properties). Each data set consists of 1,091 data points from 9 OIM bones. The original captured hyperspectral data sets were noisy and base-lined ones. We removed the noise and corrected the base-lined data for the final efficient classification. High dimensional Raman hyperspectral data on OIM bones was reduced by Principal Components Analysis (PCA) and Linear Discriminant Analysis (LDA) and efficiently classified for the first time. We confirmed OIM bones could be classified such as strong, middle and weak one by using the coefficients of their PCA or LDA. Through experiment, we investigated the efficiency of classification on the reduced OIM bone data by the Bayesian classifier and K -Nearest Neighbor (K-NN) classifier. As the experimental result, the case of LDA reduction showed higher classification performance than that of PCA reduction in the two classifiers. K-NN classifier represented better classification rate, compared with Bayesian classifier. The classification performance of K-NN was about 92.6% in case of LDA.

• Journal of Information Processing Systems
• /
• 제10권3호
• /
• pp.395-411
• /
• 2014

Temporal medical data is often collected during patient treatments that require personal analysis. Each observation recorded in the temporal medical data is associated with measurements and time treatments. A major problem in the analysis of temporal medical data are the missing values that are caused, for example, by patients dropping out of a study before completion. Therefore, the imputation of missing data is an important step during pre-processing and can provide useful information before the data is mined. For each patient and each variable, this imputation replaces the missing data with a value drawn from an estimated distribution of that variable. In this paper, we propose a new method, called Newton's finite divided difference polynomial interpolation with condition order degree, for dealing with missing values in temporal medical data related to obesity. We compared the new imputation method with three existing subspace estimation techniques, including the k-nearest neighbor, local least squares, and natural cubic spline approaches. The performance of each approach was then evaluated by using the normalized root mean square error and the statistically significant test results. The experimental results have demonstrated that the proposed method provides the best fit with the smallest error and is more accurate than the other methods.

• 대한원격탐사학회지
• /
• 제31권4호
• /
• pp.303-319
• /
• 2015

The objectives of this paper are to measure surface imperviousness using three different classification methods: per-pixel, sub-pixel, and object-oriented classification. They are tested on high-spatial resolution QuickBird data at 2.4 meters (four spectral bands and three principal component bands) as well as a medium-spatial resolution Landsat TM image at 30 meters. To measure impervious surfaces, we selected 30 sample sites with different land uses and residential densities across image representing the city of Phoenix, Arizona, USA. For per-pixel an unsupervised classification is first conducted to provide prior knowledge on the possible candidate spectral classes, and then a supervised classification is performed using the maximum-likelihood rule. For sub-pixel classification, a Linear Spectral Mixture Analysis (LSMA) is used to disentangle land cover information from mixed pixels. For object-oriented classification several different sets of scale parameters and expert decision rules are implemented, including a nearest neighbor classifier. The results from these three methods show that the object-oriented approach (accuracy of 91%) provides more accurate results than those achieved by per-pixel algorithm (accuracy of 67% and 83% using Landsat TM and QuickBird, respectively). It is also clear that sub-pixel algorithm gives more accurate results (accuracy of 87%) in case of intensive and dense urban areas using medium-resolution imagery.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2011년도 제40회 동계학술대회 초록집
• /
• pp.309-309
• /
• 2011

There have been large research activities on the high quality oxide films for the realization oxide based electronics. However, the interface interdiffusion prohibits achieving high quality oxide films, when the oxide films are grown on non-oxide substrates. In the case of Si substrates, there exist lattice mismatch and interface interdiffusion when oxide films deposited on direct Si surface. In this presentation, we report the interface characteristics of yttria-stabilized zirconia films grown on silicon substrates. From x-ray reflectivity analysis we found that the film thickness and interface roughness decreased as the growth temperature increased, indicating that the growth mechanism varies and the chemical reaction is limited to the interface as the growth condition varies. Furthermore, the packing density of the film increased as the growth temperature increased and the film thickness decreased. X-ray photoelectron spectroscopy analysis of very thin films revealed that the amount of chemical shift increased as the growth temperature increased. Intriguingly, the direction of the chemical shift of Zr was opposite to that of Si due to the second nearest neighbor interaction.

• 정보보호학회논문지
• /
• 제24권4호
• /
• pp.617-624
• /
• 2014

스마트폰 사용이 급증하였고 스마트폰에 탑재되는 OS 중 안드로이드가 차지하는 비중이 가장 높아졌다. 그러나 오픈소스로 제공되는 안드로이드의 특성이 악의적인 사용자들에게 유용하게 사용되어 스마트폰 사용자들의 프라이버시를 위협하고 있다. 이 논문에서 우리는 안드로이드 앱에서 요구하는 권한 정보를 사용하여 효율적인 악성앱 감지법을 제안한다. 이를 위하여 주성분 분석과 kNN 분류자를 사용하였으며, 새로운 앱들의 특성들을 분류자에 실시간으로 반영하기 위한 incremental kNN 분류자를 제안한다. 또한 이 분류자들의 정확률을 측정하기 위하여 k-묶음 교차 검증법을 사용하였다. 실험에 사용된 실제 악성앱 샘플을 얻기 위하여 Contagio에 요청하였으며 이를 이용하여 분류자의 정확률을 측정하였다.

• Bulletin of the Korean Chemical Society
• /
• 제28권11호
• /
• pp.2069-2074
• /
• 2007

The 27Al multiple quantum magic angle spinning (MQMAS) nuclear magnetic resonance (NMR) spectra of mordenite zeolites were simulated using the point charge model (PCM). The spectra simulated by the PCM considering nearest neighbor atoms only (PCM-n) or including atoms up to the 3rd layer (PCM-m) were not different from those generated by the Hartree-Fock (HF) molecular orbital calculation method. In contrast to the HF and density functional theory methods, the PCM method is simple and convenient to use and does not require sophisticated and expensive computer programs along with specialists to run them. Thus, our results indicate that the spectral simulation of the 27Al MQMAS NMR spectra obtained with the PCM-n is useful, despite its simplicity, especially for porous samples like zeolites with large unit cells and a high volume density of pores. However, it should be pointed out that this conclusion might apply only for the atomic sites with small quadrupole coupling constants.