• The Journal of Korean Medicine
• /
• v.19 no.2
• /
• pp.5-16
• /
• 1998

Hwabyung is a common emotional disorder which has symptoms expressed like firt's explosion in middle-aged after long period of emotional suppression among Koreans. It is similar in its characteristics such as neurosis, anxiety, panic attacks in Western Medicine, though the treatment method was not effective. So we have done a clinical research on Oriental Medical Method, especially on Acupuncture Therapy, and obtained following results. 1. Patients with Hwabyung complained of pressure pain around the Chunjung(?中, CV-17) point distinctively. About 70% of those were located on the CV-17 point, 25% were 1cm upper than the CV-17 point and 5% of those were 1cm lower point than the CV-17 point. 2. Degrees of pressure pain were divided into 5 grades from ade 1(feeling pain with slight pressure) to grade 5(feeling no pain with severe pressure), respectively. 3. Patients with Hwabyung showed various symptoms compared to fire's explosion such as anger, chest discomfort, difficulty in breathing. tachycardia. and feeling of epigasfric mass etc., and the degrees were divided into 5 grades according to the severities from grade 1(can't keep their usual living) to grade 5(no complaints with heavy stresses), respectively. 4. For the treatment of Hwabyung in this study, we had given Acupuncture therapy on some points such as Chunjung:?中:CV-17, Jungwan:中脘:CV-12) and Chunchu:天樞:S-25, etc. for 15 minutes a time twice a week. And Bunshimkiumgmnihang(分心氣飮加味方) was administered 3 times a day. 5. About 40% of the patients took treatment for more than 2 months, 29% of those took 1 to 2 months and 31% of those took less than 1 month. In this study, we excluded those who stopped treatment within a month without any expected effects. 6. We evaluated the changes of severity of pain according to the following categories such as - for no change, + for 1 grade, ++ for 2 grades, +++ for 3 grades, and ++++ for 4 grades of improvements. Among the patients taken 1 to 2 months of treatment. 48% of the those showed +, 7% of those showed ++, 3% of those showed +++ and 41% of those showed no change. Among the patients taken less than 2 months of treatment, 20%of those showed +, 40% of those showed ++, 28% of those showed +++ and 13% of those showed no change. 7. We evaluate the changes of symptoms according to the following categories such as - for no change, + for 1 grade, ++ for 2 grades, +++ for 3 grades and +++ for 4 grades of improvements. Among the patients taken 1 to 2 months of treatment, 34% of those showed +, 14% of those showed ++ and 52% of those showed no change. Among the patients taken more than 2 months of treatment, 20% of those showed +, 43% of those showed 20% of those showed +++, 3% of those showed +++ and 15% of those showed no change. 8. When we compare the changes of pain and symptoms according to the periods of treatment, the changes in quantity of pain in 1 to 2 months group was $0.72{\pm}0.75$, in more than 2 months group was $1.83{\pm}0.98$, and the changes in quantity of symptoms in 1 to 2 months group was $0.62{\pm}0.73$, in more than 2 months group was $1.75{\pm}1.03$. According to the above results, we have concluded that more than 2 months of treatment is more beneficial than 1 to 2 months of treatment.

• 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.