• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.10 s.340
• /
• pp.25-30
• /
• 2005

This paper generalizes the concept of the signal space detection to construct a fixed delay tree search (FDTS) detector which estimates a block of n channel symbols at a time. This technique is applicable to high speed implementation. Two approaches are discussed both of which are based on efficient signal space partitioning. In the first approach, symbol detection is performed based on a multi-class partitioning of the signal space. This approach is a generalization of binary symbol detection based on a two-class pattern classification. In the second approach, binary signal detection is combined with a look-ahead technique, resulting in a highly parallel detector architecture.

• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.5
• /
• pp.393-402
• /
• 2013

The Mahalanobis-Taguchi System (MTS) is a diagnostic and predictive method for multivariate data. In the MTS, the Mahalanobis space (MS) of reference group is obtained using the standardized variables of normal data. The Mahalanobis space can be used for multi-class classification. Once this MS is established, the useful set of variables is identified to assist in the model analysis or diagnosis using orthogonal arrays and signal-to-noise ratios. And other several techniques have already been used for classification, such as linear discriminant analysis and logistic regression, decision trees, neural networks, etc. The goal of this case study is to compare the ability of the Mahalanobis-Taguchi System and logistic regression using a data set.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.52-58
• /
• 2023

Alzheimer's disease is one type of dementia, the symptoms can be treated by detecting the disease at its early stages. Recently, many computer-aided diagnosis using magnetic resonance image(MRI) have shown a good results in the classification of AD. Taken these MRI images and feed to Free surfer software to extra the features. In consideration, using T1-weighted images and classifying using the convolution neural network (CNN) model are proposed. In this paper, taking the subjects from ADNI of subcortical and cortical features of 190 subjects. Consider the study to reduce the complexity of the model by using the single layer in the Res-Net, VGG, and Alex Net. Multi-class classification is used to classify four different stages, CN, EMCI, LMCI, AD. The following experiment shows for respective classification Res-Net, VGG, and Alex Net with the best accuracy with VGG at 96%, Res-Net, GoogLeNet and Alex Net at 91%, 93% and 89% respectively.

• International conference on construction engineering and project management
• /
• 2011.02a
• /
• pp.176-181
• /
• 2011

A role of cost modeler is that of facilitating design process by the systematic application of cost factors so as to maintain sensible and economic relationships between cost, quantity, utility and appearance. These relationships help to achieve the client's requirements within an agreed budget. The purpose of this study is to develop a parametric cost estimating model for the early design stage by using the multi-dimensional system of OLAP (On-line Analytical Processing) based on the case of quantity data related to architectural design features. The parametric cost estimating models have been adopted to support decision making in the early design stage. These models typically use a similar instance or a pattern of historical case. In order to effectively use this type of data model, it is required to set data classification and prediction methods. One of the methods is to find the similar class in line with attribute selection measure in the multi-dimensional data model. Therefore, this research is to analyze the relevance attribute influenced by architectural design features with the subject of case-based quantity data used for the parametric cost estimating model. The relevance attributes can be analyzed by Analytical Characterization. It helps determine what attributes to be included in the OLAP multi-dimension.

• The Korean Journal of Applied Statistics
• /
• v.19 no.3
• /
• pp.587-598
• /
• 2006

The number of variables exceeds the number of samples in microarray data. We propose a nonparametric local linear logistic classification procedure using orthogonal components for classifying high-dimensional microarray data. The proposed method is based on the local likelihood and can be applied to multi-class classification. We applied the local linear logistic classification method using PCA, PLS, and factor analysis components as new features to Leukemia data and colon data, and compare the performance of the proposed method with the conventional statistical classification procedures. The proposed method outperforms the conventional ones for each component, and PLS has shown best performance when it is embedded in the proposed method among the three orthogonal components.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.313-315
• /
• 2021

Timely and accurate diagnosis of lung diseases using Chest X-ray images has been gained much attention from the computer vision and medical imaging communities. Although previous studies have presented the capability of deep convolutional neural networks by achieving competitive binary classification results, their models were seemingly unreliable to effectively distinguish multiple disease groups using a large number of x-ray images. In this paper, we aim to build an advanced approach, so-called Ensemble Knowledge Distillation (EKD), to significantly boost the classification accuracies, compared to traditional KD methods by distilling knowledge from a cumbersome teacher model into an ensemble of lightweight student models with parallel branches trained with ground truth labels. Therefore, learning features at different branches of the student models could enable the network to learn diverse patterns and improve the qualify of final predictions through an ensemble learning solution. Although we observed that experiments on the well-established ChestX-ray14 dataset showed the classification improvements of traditional KD compared to the base transfer learning approach, the EKD performance would be expected to potentially enhance classification accuracy and model generalization, especially in situations of the imbalanced dataset and the interdependency of 14 weakly annotated thorax diseases.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1319-1323
• /
• 2004

In this paper, a problem of Thai sign language recognition using a neural network is considered. The paper addresses the problem in classifying certain signs conveying quantitative meaning, e.g., large or small. By treating those signs corresponding to different quantities as derived from different classes, the recognition error rate of the standard multi-layer Perceptron increases if the precision in recognizing different quantities is increased. This is due the fact that, to increase the quantitative recognition precision of those signs, the number of (increasingly similar) classes must also be increased. This leads to an increase in false classification. The problem is due to misinterpreting the amount of quantity the quantitative signs convey. In this paper, instead of treating those signs conveying quantitative attribute of the same quantity type (such as 'size' or 'amount') as derived from different classes, here they are considered instances of the same class. Those signs of the same quantity type are then further divided into different subclasses according to the level of quantity each sign is associated with. By using this two-level classification, false classification among main gesture classes is made independent to the level of precision needed in recognizing different quantitative levels. Moreover, precision of quantitative level classification can be made higher during the recognition phase, as compared to that used in the training phase. A standard multi-layer Perceptron with a back propagation learning algorithm was adapted in the study to implement this two-level classification of quantitative gesture signs. Experimental results obtained using an electronic glove measurement of hand postures are included.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.11
• /
• pp.1681-1689
• /
• 2010

Several studies on the use of Support Vector Machines (SVMs) for diagnosing rotating machinery have been successfully carried out, but the fault classification depends on the input features as well as a multi-classification scheme, binary optimizer, kernel function, and the parameter to be used in the kernel function. Most of the published papers on multiclass SVM applications report the use of the same features to classify the faults. In this study, simple statistical features are determined on the basis of time domain vibration signals for various fault conditions, and the optimal features for each fault condition are selected. Then, the optimal features are used in the SVM training and in the classification of each fault condition. Simulation results using experimental data show that the results of the proposed stepwise classification approach with a relatively short training time are comparable to those for a single multi-class SVM.

• Journal of Korea Game Society
• /
• v.11 no.6
• /
• pp.81-93
• /
• 2011

Identity theft happens frequently in popular MMORPG(Massively Multi-player Online Role Playing Games) where profits can be gained easily. In spite of the importance of security about identity theft in MMORPG, few methods to prevent and detect identity theft in online games have been proposed. In this study, we investigate real identity theft cases of an online game and define the representative patterns of identity theft as the speedy type, cautious type, and bold type. We then propose the automatic identity theft detection model based on the multi-class classification. We verify the system with one of the leading online games in Korea. The multi-class detection model outperforms the existing binary-class one(hacked or not).

• Journal of Korean Academy of Nursing
• /
• v.20 no.1
• /
• pp.16-37
• /
• 1990

A cost analysis for hospitalized patients was carried out based upon Patient Classification System(PCS) in order to determine an appropriate nursing fee. The data were collected from 21 nursing units of three teaching hospitals from April 1 to June 30, 1989. first, all of the 22,056 inpatients were classified into mildly ill(Class Ⅰ), moderately ill(Class Ⅱ), acutely ill(Class Ⅲ), and critically ill(Class Ⅳ) by the PCS which had been carefully developed to be suitable for the Korean nursing units. Second. PCS cost accounting was applied to the above data. The distribution of inpatients, nursing costs, and nursing productivity were as follows : 1) Patient distribution ranged from 45% to class Ⅰ, 36% to class Ⅱ, 15% to class Ⅲ, and 4% to class Ⅳ, the proportion of class Ⅳ in ‘H’ Hospital was greater than that of the other two hospitals. 2) The proportion of Class Ⅲ and Ⅳ in the medical nursing units was greater than that of surgical nursing units. 3) The number of inpatients was greatest on Tuesdays, and least on Sundays. 4) The average nursing cost per hour was W 3,164 for ‘S’ hospital, W 3,511 for ‘H’ hospital and W 4,824 for ‘K’ hospital. The average nursing cost per patient per day was W 14,126 for ‘S’ Hospital, W 15,842 for ‘H’ hospital and W 21,525 for ‘K’ hospital. 5) The average nursing cost calculated by the PCS was W 13,232 for class Ⅰ, W 18,478 for class Ⅱ, W 23,000 for class Ⅲ, and W 25,469 for class Ⅳ. 6) The average nursing cost for the medical and surgical nursing units was W 13,180 and W 13,303 respetively for class Ⅰ, W 18,248 and W 18,707 for class Ⅱ, W 22,303 and W 23,696 for class Ⅲ, and W 24,331 and W 26,606 for class Ⅳ. 7) The nursing costs were composed of 85% for wages and fringe benefits, 3% for material supplies and 12% for overhead. The proportion of wages and fringe benefits among the three Hospitals ranged from 75%, 92% and 98% for the ‘S’, ‘H’, ‘K’ hospitals respectively These findings explain why the average nursing cost of ‘K’ hospital was higher than the others. 8) According to a multi- regression analysis, wages and fringe benefits, material supplies, and overhead had an equal influence on determining the nursing cost while the nursing hours had less influence. 9) The productivity of the medical nursing units were higher than the surgical nursing units, productivity of the D(TS) - nursing units was the lowest while the K(Med) - nursing unit was the highest in 'S' hospital. In ‘H’ hospital, productivity was related to the number of inpatients rather than to the characteristics of the nursing units. The ‘K’ hospital showed the same trend as ‘S’ hospital, that the productivity of the medical nursing unit was higher than the surgical nursing unit. The productivity of ‘S’ hospital was evaluated the highest followed by ‘H’ hospital and ‘K’ hospital. Future research on nursing costs should be extended to the other special nursing areas such as pediatric and psychiatric nursing units, and to ICU or operating rooms. Further, the PCS tool should be carefully evaluated for its appropriateness to all levels of institutions(primary, secondary, tertiary). This study took account only of the quantity of nursing services when developing the PCS tool for evaluating the productivity of nursing units. Future research should also consider the quality of nursing services including the appropriateness of nursing activities.