• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.13-15
• /
• 2006

When we use multilayer perceptron model for pattern classification probmems, we allocate one output node for each class. In this paper, we increase the number of output nodes for each class and investigate the performance of multilayer perceptrons through the simulation of isolated-word recognition problems.

• Journal of the Korean Society for Library and Information Science
• /
• v.22
• /
• pp.259-304
• /
• 1992

This paper examines 'Religion Class' in the scheme of the DDC. The major findings of the study are summerized as follows. 1. The first edition of DDC was published in 1876 in order to classify Amherst College Library collections. In spite of the continuous study and revision of the experts, the frameworks of the DDC systems are still kept unchanged. Only their subdivisions, reflecting those developments in the academic world, are developed and detailed more sophisticatedly. 2. The division of 200 does not function as generalities for all class of religion. Therefore, it is necessary to amend the division of 200 to serve generalities for all the religions of the world. 3. Standard subdivision for the christian religion and for the non-christian religion is different. So, the mnemonic nature has become weakened due to the dual standard subdivisions and the classification number becomes much longer and complicated. Therefore, one standard subdivision for all religions of the world is required. 4. Religion science was organized in late 19 C and developed continuously, but the DDC does not accomodate the religion science as a science. Accodingly, the DDC should be revised recognize religion science as a science not the christian science. 5. The deployment of classification scheme in Dewey's 200 is severely biased. That is to say, 9 division were assigned for christian religion, whereas only 1 division was assigned for non-christian religion. Therefore, an adjustment should be made to allocate subdivisions equally to all religions of the world. 6. General classification order of religion is prehistoric, primitive, ancient, modem and world religion in religion science. But, DDC does not accept this general classification order of religion, sticking to the biased expansion towards christianity. Therefore, DDC must adopt the general classification order of religion in the religion science. 7. Lastly, because of the limitation of decimal notation in DC, DDC does not accomodate new subject equally and classification number becomes longer. Therefore, centesimal expansion is proposed in order to make the classification number short, to enlarge its capacity of inclusion of new subject and to maintain consistency in the scheme.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_3
• /
• pp.2011-2025
• /
• 2021

In high-resolution satellite image classification, when the color values of pixels belonging to one class are different, such as buildings with various colors, it is difficult to determine the color information representing the class. In this paper, to solve the problem of determining the representative color information of a class, we propose a method to divide the color channel of HSV (Hue Saturation Value) and perform object-based classification. To this end, after transforming the input image of the RGB color space into the components of the HSV color space, the Hue component is divided into subchannels at regular intervals. The minimum distance-based image classification is performed for each hue subchannel, and the classification result is combined with the image segmentation result. As a result of applying the proposed method to KOMPSAT-3A imagery, the overall accuracy was 84.97% and the kappa coefficient was 77.56%, and the classification accuracy was improved by more than 10% compared to a commercial software.

• Journal of the Korea Society for Simulation
• /
• v.19 no.1
• /
• pp.143-151
• /
• 2010

Fingerprint classification is a step to increase the efficiency of an 1:N fingerprint recognition system and plays a role to reduce the matching time of fingerprint and to increase accuracy of recognition. It is difficult to classify fingerprints, because the ridge pattern of each fingerprint class has an overlapping characteristic with more than one class, fingerprint images may include a lot of noise and an input condition is an exceptional case. In this paper, we propose a novel approach to design a stochastic model and to accomplish fingerprint classification using a directional characteristic of fingerprints for an effective classification of various qualities. We compute the directional value by searching a fingerprint ridge pixel by pixel and extract a directional characteristic by merging a computed directional value by fixed pixels unit. The modified Markov model of each fingerprint class is generated using Markov model which is a stochastic information extraction and a recognition method by extracted directional characteristic. The weight list of classification model of each class is decided by analyzing the state transition matrixes of the generated Markov model of each class and the optimized value which improves the performance of fingerprint classification using GA (Genetic Algorithm) is estimated. The performance of the optimized classification model by GA is superior to the model before the optimization by the experiment result of applying the fingerprint database of various qualities to the optimized model by GA. And the proposed method effectively achieved fingerprint classification to exceptional input conditions because this approach is independent of the existence and nonexistence of singular points by the result of analyzing the fingerprint database which is used to the experiments.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.4 no.4
• /
• pp.1-7
• /
• 2001

Remotely sensed data is the most fundamental data in acquiring the GIS informations, and may be analyzed to extract useful thematic information. Multi-spectral classification is one of the most often used methods of information extraction. The actual multi-spectral classification may be performed using either supervised or unsupervised approaches. This paper analyze the effect of assigning clever initial values to image classes on the performance of parallelepiped classification algorithm, which is one of the supervised classification algorithms. First, we investigate the effect on serial computing model, then expand it on MIMD(Multiple Instruction Multiple Data) parallel computing model. On serial computing model, the performance of the parallel pipe algorithm improved 2.4 times at most and, on MIMD parallel computing model the performance improved about 2.5 times as clever initial values are assigned to image class. Through computer simulation we find that initial values of image class greatly affect the performance of parallelepiped classification algorithms, and it can be improved greatly when classes on both serial computing model and MIMD parallel computation model.

• Journal of Korean Institute of Industrial Engineers
• /
• v.37 no.4
• /
• pp.358-366
• /
• 2011

Multi-criteria ABC inventory classification, which aims to classify inventory items by considering more than one criterion, is one of the most widely employed techniques for inventory control. The weighted linear optimization (WLO) model proposed by Ramanathan (2006) solves the problem of multi-criteria ABC inventory classification by generating a set of criterion weights for each inventory item and assigning a normalized score to the item for ABC analysis. However, the WLO model has some limitations. First, many inventory items can share the same optimal score, which can hinder a precise classification of inventory items. Second, the model allows too much flexibility in weighting multiple criteria; each item is allowed to choose its own weights so that it can maximize its score. As a result, if an item dominates the others in terms of a certain criterion, it may be classified into a higher class regardless of other criteria by assigning an overwhelming weight to the criterion. Consequently, an item with a high value in an unimportant criterion and low values in others may be inappropriately classified as class A, leading to an inaccurate classification of inventory items. To overcome these shortcomings, we extend the WLO model by using the cross-efficiency method in data envelopment analysis. We claim that the proposed model can provide a more reasonable and accurate classification of inventory items by mitigating the adverse effect of flexibility in the choice of weights and yielding a unique ordering of inventory items.

• Journal of Chest Surgery
• /
• v.27 no.9
• /
• pp.752-758
• /
• 1994

From July 1983 to December 1992, 145 patients with mitral valvular disease underwent open heart surgery at Chonbuk National University Hospital. Of these patients, 89 patients[61.4%] required mitral valve replacement. 56 patients [38.6 %] had mitral valve repair. There were 32 women and 24 men and the mean age was 34.3 years[range 6 years to 62 years].There were 23 cases of pure mitral stenosis, 19 cases of mitral regurgitation and 14 cases of mixedmitral valvular disease. The mean duration of symptom was 4.53 years and mean mitral valvularorifice diameter[in cases of pure stenosis and mixed mitral valvular lesion] was 0.96 cm. According to the NYHA classification, the distribution of patients preoperatively was as follows; class IIa, 15 patients; class lib, 17 patients; class III, 22 patients; class IV, 2 patients. Four patients[7%] had an embolic history preoperatively. 24 patients[ 43 %] were in atrial fibrillation. In cases of pure mitral stenosis, the technique used included open mitral commissurotomy[21atients], open mitral commissurotomy with mitral annuloplasty[2 patients]. In mixed mitral valvular disease, open mitral commissurotomy[ll patients] and open mitral commissurotomy with mitral annuloplasty[l patient] were performed. In cases of mitral regurgitation, mitral annuloplasty[5 patients], mitral valvuloplasty[6 patients], mitral annuloplasty with valvuloplasty [3 patients] and ring annuloplasty [5 patients] were performed.There was one perioperative death related to acute renal failure and sepsis. One late death was occurred related to heart failure after 10 months postoperatively. One patient required reoperation due to restenosis and no embolic episode was occured. After operation, 34 patients were in NYHA functional class I, 20 patients were in class IIa.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.05b
• /
• pp.578-582
• /
• 2005

In this study, the conceptual foundation and development process of the Antecedent soil Moisture Condition(AMC) in SCS runoff curve number method are reviewed. Although the runoff volume is very sensitive with AMC condition, the AMC class limits developed in SCS(1972) are used in rainfall-runoff analysis without careful consideration. Tn this study, following the SCS curve number development process, rainfall-runoff characteristics of the Jang-Pyung subbasin subject to the Pyung-Chang River basin are analyzed to evaluate the reasonability of the AMC class limits at present. The New AMC class limits are proposed by the sensitive analysis of the antecedent rainfall - curve number value. As a result, the classification value of AMC-I with II is 22mm of antecedent 5-day rainfall amount, and the classification of AMC-II with III is 117mm in growing season. When the New AMC class limits are applied to Jang-Pyung subbasin, AMC probability distribution shows that the AMC-II has increased remarkably even though the AMC-I has a little higher value. But the AMC-III has the smallest one. According to the conceptual basis of the curve number method, the AMC probability distribution, the New AMC class limits adopted, gives reasonable results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.3
• /
• pp.614-621
• /
• 2006

We have implemented a multiclassifier learning approach in a GA-based inductive learning environment that learns classification rules that are similar to rules used in PROSPECTOR. In the multiclassifier learning approach, a classification system is constructed with several classifiers that are obtained by running a GA-based learning system several times to improve the overall performance of a classification system. To implement the multiclassifier learning approach, we need a decision-making scheme that can draw a decision using multiple classifiers. In this paper, we introduce two decision-making schemes: one is based on combining posterior odds given by classifiers to each class and the other one is a voting scheme based on ranking assigned to each class by classifiers. We also present empirical results that evaluate the effect of the multiclassifier learning approach on the GA-based inductive teaming environment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.8
• /
• pp.5280-5287
• /
• 2014

This paper proposes a method in which classes are grouped as a hierarchical tree structure for the effective classification of the Raman spectra. As experimental data, the Raman spectra of 28 chemical compounds were obtained, and pre-treated with noise removal and normalization. The spectra that induced a classification error were grouped into the same class and the hierarchical structure class was composed. Each high and low class was classified using a PCA-MAP method. According to the experimental results, the classification of 100% was achieved with 2.7 features on average when the proposed method was applied. Considering that the same classification rates were achieved with 6 features using the conventional method, the proposed method was found to be much better than the conventional one in terms of the total computational complexity and practical application.