• The Journal of the Korean dental association
• /
• v.15 no.2
• /
• pp.107-110
• /
• 1977

Class I malocclusion is essentially a dental dysplasia. Rotations, individual tooth malpositions, missing teeth, tooth size discrepancies, etc., fall under this classification. There are two types of class I malocclusions. One is identified by and insufficient denture base to accommodate the teeth; the other has more denture base than tooth material, creating spaces in the arch. The tooth material-to denture base discrepancies may be slight, calling for only a little increase in arch length for alignment and the correction of minor rotations. Discrepancies may also be great, in which case it becomes necessary to reduce tooth material by extraction, so as to make the tooth material more in proportion to the size of the denture base. The author had attempted orthodontic treatment of a class I malocclusion case of 13-year old boy in which high canines and impacted mandibular second premolars were involved. The author obtained good results.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.885-894
• /
• 2001

Decision tree methods is the one of data mining techniques. Classification trees are used to predict a class label. When a tree grows, the conventional splitting criteria use the weighted average of the left and the right child nodes for measuring the node impurity. In this paper, new splitting criteria for classification trees are proposed which improve the interpretablity of trees comparing to the conventional methods. The criteria search only for interesting subsets of the data, as opposed to modeling all of the data equally well. As a result, the tree is very unbalanced but extremely interpretable.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.41-51
• /
• 2022

Cables are critical components of cable-stayed bridges. A structural health monitoring system provides real-time cable tension recording for cable health monitoring. However, the measurement data involve multiple sources of variability, i.e., varying environmental and operational factors, which increase the complexity of cable condition monitoring. In this study, a one-class classification method is developed for cable condition assessment using Bayesian factor analysis (FA). The single-peaked vehicle-induced cable tension is assumed to be relevant to vehicle positions and weights. The Bayesian FA is adopted to establish the correlation model between cable tensions and vehicles. Vehicle weights are assumed to be latent variables and the influences of different transverse positions are quantified by coefficient parameters. The Bayesian theorem is employed to estimate the parameters and variables automatically, and the damage index is defined on the basis of the well-trained model. The proposed method is applied to one cable-stayed bridge for cable damage detection. Significant deviations of the damage indices of Cable SJS11 were observed, indicating a damaged condition in 2011. This study develops a novel method to evaluate the health condition of individual cable using the FA in the Bayesian framework. Only vehicle-induced cable tensions are used and there is no need to monitor the vehicles. The entire process, including the data pre-processing, model training and damage index calculation of one cable, takes only 35 s, which is highly efficient.

• Journal of Chest Surgery
• /
• v.12 no.4
• /
• pp.355-360
• /
• 1979

Mitral and aortic valve replacement with tricuspid annuloplasty was undertaken in 5 patients out of 38 valvular surgery between the period from Jan. 1977 to May 1979 in the Dept. of Thoracic and Cardiovascular Surgery in Korea University Hospital. All were male patients with age ranging from 18 to 42 years, and preoperative evaluation revealed one case in Class IV, and four cases in Class III according to the classification of NYHA. Preoperative diagnosis was confirmed by routine cardiac study including retrograde aorto- and left ventriculography, and there were two cases with MSi+ASi+Ti, two cases with MSi+Ai+Ti, and one case with Mi+Ai+Ti. Double valve replacement was performed under the hypothermic cardiopulmonary bypass with total pump time of 247 min. in average ranging from 206 min. to 268 min. During aortic valve replacement, left coronary perfusion was done in the first two cases, and cardiac arrest with cardioplegic solution proposed by Bretschneider was applied in the remained three cases. Starr-Edwards, Bjork-Shiley prosthetic valves and Carpentier-Edwards tissue valve were replaced in the aortic area, and Carpentier-Edwards and Angell-Shiley tissue valves were replaced in the mitral area with each individual combination [three prosthetic and two tissue valves in the aortic, and five tissue valves in the mitral area respectively]. Postoperative recovery was uneventful in all cases except one case with hemopericardium, which was managed with pericardiectomy on the postoperative 10th day in good result. Follow-up after double valve replacement of the all five cases for the period from 6 months to 33 months revealed satisfactory adaptation in social activity and occupation with cardiac function of Class I according to the classification of NYHA In all five cases.

• Journal of Biomedical Engineering Research
• /
• v.33 no.1
• /
• pp.15-24
• /
• 2012

Classification of human thought is an emerging research field that may allow us to understand human brain functions and further develop advanced brain-computer interface (BCI) systems. In the present study, we introduce a new approach to classify various mental states from noninvasive electrophysiological recordings of human brain activity. We utilized the full spatial and spectral information contained in the electroencephalography (EEG) signals recorded while a subject is performing a specific mental task. For this, the EEG data were converted into a 2D spatiospectral pattern map, of which each element was filled with 1, 0, and -1 reflecting the degrees of event-related synchronization (ERS) and event-related desynchronization (ERD). We evaluated the similarity between a current (input) 2D pattern map and the template pattern maps (database), by taking the inner-product of pattern matrices. Then, the current 2D pattern map was assigned to a class that demonstrated the highest similarity value. For the verification of our approach, eight participants took part in the present study; their EEG data were recorded while they performed four different cognitive imagery tasks. Consistent ERS/ERD patterns were observed more frequently between trials in the same class than those in different classes, indicating that these spatiospectral pattern maps could be used to classify different mental states. The classification accuracy was evaluated for each participant from both the proposed approach and a conventional mental state classification method based on the inter-hemispheric spectral power asymmetry, using the leave-one-out cross-validation (LOOCV). An average accuracy of 68.13% (${\pm}9.64%$) was attained for the proposed method; whereas an average accuracy of 57% (${\pm}5.68%$) was attained for the conventional method (significance was assessed by the one-tail paired $t$-test, $p$ < 0.01), showing that the proposed simple classification approach might be one of the promising methods in discriminating various mental states.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.1
• /
• pp.59-64
• /
• 2015

In this paper, we found the usefulness of the deep belief network (DBN) in the fields of brain-computer interface (BCI), especially in relation to imagined speech. In recent years, the growth of interest in the BCI field has led to the development of a number of useful applications, such as robot control, game interfaces, exoskeleton limbs, and so on. However, while imagined speech, which could be used for communication or military purpose devices, is one of the most exciting BCI applications, there are some problems in implementing the system. In the previous paper, we already handled some of the issues of imagined speech when using the International Phonetic Alphabet (IPA), although it required complementation for multi class classification problems. In view of this point, this paper could provide a suitable solution for vowel classification for imagined speech. We used the DBN algorithm, which is known as a deep learning algorithm for multi-class vowel classification, and selected four vowel pronunciations:, /a/, /i/, /o/, /u/ from IPA. For the experiment, we obtained the required 32 channel raw electroencephalogram (EEG) data from three male subjects, and electrodes were placed on the scalp of the frontal lobe and both temporal lobes which are related to thinking and verbal function. Eigenvalues of the covariance matrix of the EEG data were used as the feature vector of each vowel. In the analysis, we provided the classification results of the back propagation artificial neural network (BP-ANN) for making a comparison with DBN. As a result, the classification results from the BP-ANN were 52.04%, and the DBN was 87.96%. This means the DBN showed 35.92% better classification results in multi class imagined speech classification. In addition, the DBN spent much less time in whole computation time. In conclusion, the DBN algorithm is efficient in BCI system implementation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.8
• /
• pp.216-223
• /
• 2019

Fault detection during production processes is one of the required operational tasks to run production processes both safely and consistently. Unexpected operational events or undetected process faults can have a serious impact on the production systems and subsequently on the final products' quality. In addition, such situations may lead to malfunctions or breakdowns of production processes. To reliably detect such abnormalities, a new one-class classification-based detection scheme has recently been developed The proposed method consists of four steps:1) noise filtering, 2) feature selection, 3) nonlinear representation and 4) outlier detection. The performance of the proposed scheme was demonstrated using the multivariate data obtained from a simulation process. The results have shown that the proposed method produced reliable monitoring results and outperforms any existing methods with an average improvement of 25.4%. The use of proper feature selection in the proposed framework yielded better detection performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.7
• /
• pp.311-316
• /
• 2019

Classification problem is to predict the class to which an input data belongs. One of the most popular methods to do this is training a machine learning algorithm using the given dataset. In this case, the dataset should have a well-balanced class distribution for the best performance. However, when the dataset has an imbalanced class distribution, its classification performance could be very poor. To overcome this problem, we propose an over-sampling scheme that balances the number of data by using Conditional Generative Adversarial Networks (CGAN). CGAN is a generative model developed from Generative Adversarial Networks (GAN), which can learn data characteristics and generate data that is similar to real data. Therefore, CGAN can generate data of a class which has a small number of data so that the problem induced by imbalanced class distribution can be mitigated, and classification performance can be improved. Experiments using actual collected data show that the over-sampling technique using CGAN is effective and that it is superior to existing over-sampling techniques.

• Journal of Korean Academy of Nursing Administration
• /
• v.6 no.3
• /
• pp.389-404
• /
• 2000

This study was designed to determine the cost and measurement of nursing care hours for hospice patients hostpitalized in one university hospital. 314 inpatients in the hospice unit 11 nursing manpower were enrolled. Study was taken place in C University Hospital from 8th to 28th, Nov, 1999. Researcher and investigator did pilot study for selecting compatible hospice patient classification indicators. After modifying patient classification indicators and nursing care details for general ward, approved of content validity by specialist. Using hospice patient classification indicators and per 5 min continuing observation method, researcher and investigator recorded direct nursing care hours, indirect nursing care hours, and personnel time on hospice nursing care hours, and personnel time on hospice nursing care activities sheet. All of the patients were classified into Class I(mildly ill), Class II (moderately ill), Class III (acutely ill), and Class IV (critically ill) by patient classification system (PCS) which had been carefully developed to be suitable for the Korean hospice ward. And then the elements of the nursing care cost was investigated. Based on the data from an accounting section (Riccolo, 1988), nursing care hours per patient per day in each class and nursing care cost per patient per hour were multiplied. And then the mean of the nursing care cost per patient per day in each class was calculated. Using SAS, The number of patients in class and nursing activities in duty for nursing care hours were calculated the percent, the mean, the standard deviation respectively. According to the ANOVA and the $Scheff{\'{e}$ test, direct nursing care hours per patient per day for the each class were analyzed. The results of this study were summarized as follows : 1. Distribution of patient class : class IN(33.5%) was the largest class the rest were class II(26.1%) class III(22.6%), class I(17.8%). Nursing care requirements of the inpatients in hospice ward were greater than that of the inpatients in general ward. 2. Direct nursing care activities : Measurement ${\cdot}$ observation 41.7%, medication 16.6%, exercise ${\cdot}$ safety 12.5%, education ${\cdot}$ communication 7.2% etc. The mean hours of direct nursing care per patient per day per duty were needed ; 69.3 min for day duty, 64.7 min for evening duty, 88.2 min for night duty, 38.7 min for shift duty. The mean hours of direct nursing care of night duty was longer than that of the other duty. Direct nursing care hours per patient per day in each class were needed ; 3.1 hrs for class I, 3.9 hrs for class II, 4.7 hrs for class III, and 5.2 hrs for class IV. The mean hours of direct nursing care per patient per day without the PCS was 4.1 hours. The mean hours of direct nursing care per patient per day in class was increased significantly according to increasing nursing care requirements of the inpatients(F=49.04, p=.0001). The each class was significantly different(p<0.05). The mean hours of direct nursing care of several direct nursing care activities in each class were increased according to increasing nursing care requirements of the inpatients(p<0.05) ; class III and class IV for medication and education ${\cdot}$ communication, class I, class III and class IV for measurement ${\cdot}$ observation, class I, class II and class IV for elimination ${\cdot}$ irrigation, all of class for exercise ${\cdot}$ safety. 3. Indirect nursing care activities and personnel time : Recognization 24.2%, house keeping activity 22.7%, charting 17.2%, personnel time 11.8% etc. The mean hours of indirect nursing care and personnel time per nursing manpower was 4.7 hrs. The mean hours of indirect nursing care and personnel time per duty were 294.8 min for day duty, 212.3 min for evening duty, 387.9 min for night duty, 143.3 min for shift duty. The mean of indirect nursing care hours and personnel time of night duty was longer than that of the other duty. 4. The mean hours of indirect nursing care and personnel time per patient per day was 2.5 hrs. 5. The mean hours of nursing care per patient per day in each class were class I 5.6 hrs, class II 6.4 hrs, class III 7.2 hrs, class IV 7.7 hrs. 6. The elements of the nursing care cost were composed of 2,212 won for direct nursing care cost, 267 won for direct material cost and 307 won for indirect cost. Sum of the elements of the nursing care cost was 2,786 won. 7. The mean cost of the nursing care per patient per day in each class were 15,601.6 won for class I, 17,830.4 won for class II, 20,259.2 won for class III, 21,452.2 won for class IV. As above, using modified hospice patient classification indicators and nursing care activity details, many critical ill patients were hospitalized in the hospice unit and it reflected that the more nursing care requirements of the patients, the more direct nursing care hours. Emotional ${\cdot}$ spiritual care, pain ${\cdot}$ symptom control, terminal care, education ${\cdot}$ communication, narcotics management and delivery, attending funeral ceremony, the major nursing care activities, were also the independent hospice service. But it is not compensated by the present medical insurance system. Exercise ${\cdot}$ safety, elimination ${\cdot}$ irrigation needed more nursing care hours as equal to that of intensive care units. The present nursing management fee in the medical insurance system compensated only a part of nursing car service in hospice unit, which rewarded lower cost that that of nursing care.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.29-45
• /
• 2012

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.