• Journal of Plant Biotechnology
• /
• v.49 no.3
• /
• pp.240-249
• /
• 2022

Measuring chlorophyll fluorescence (CF) is a useful tool for assessing a plant's ability to tolerate abiotic stresses such as drought, waterlogging and high temperature. Korean ginseng is highly sensitive to water stress in paddy fields. To evaluate the possibility of non-destructively diagnosing waterlogging stress using chlorophyll fluorescence (CF) imaging techniques, we screened 57 ginseng accessions for waterlogging tolerance. To evaluate waterlogging tolerance among the 2-year-old Korean ginseng accessions, we treated ginseng plants with water stress for 25 days. The physiological disorder rate was characterized through visual assessment (an assigned score of 0-5). The physiological disorder rates of Geumjin, Geumsun and GS00-58 were lower than that of other accessions. In contrast, lines GS97-62, GS97-69 and GS98-1-5 were deemed susceptible. Root traits, chlorophyll content and the reduction rates decreased in most ginseng accessions. Further, these metrics were significantly lower in susceptible genotypes compared to resistant ones. All CF parameters showed a positive or negative response to waterlogging stress, and this response continuously increased over the treatment time among the genotypes. The CF parameter Fv/Fm was used to screen the 57 accessions, and the results showed clear differences in Fv/Fm between the susceptible and resistant genotypes. Susceptible genotypes had an especially low Fv/Fm value of less than 0.8, reflecting damage to the reaction center of photosystem II. It is concluded that Fv/Fm can be used as a CF parameter index for screening waterlogging stress tolerance in ginseng genotypes.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.18 no.1
• /
• pp.110-114
• /
• 2014

Purpose: The advancement in PET/CT test devices has decreased the test time and popularized the test, and PET/CT tests have continuously increased. However, this increases the exposure dose of radiation workers, too. This study aims to measure the radiation shielding rate of $^{18}F-FDG$ with a strong energy and the shielding effect when worker wore an apron during the PET/CT test. Also, this study compared the shielding rate with $^{99m}TC$ to minimize the exposure dose of radiation workers. Materials and Methods: This study targeted 10 patients who visited in this hospital for the PET/CT test for 8 days from May 2nd to 10th 2013, and the $^{18}F-FDG$ distribution room, patient relaxing room (stand by room after $^{18}F-FDG$ injection) and PET/CT test room were chosen as measuring spots. Then, the changes in the dose rate were measured before and after the application of the APRON. For an accurate measurement, the distance from patients or sources was fixed at 1M. Also, the same method applied to $^{99m}TC's$ Source in order to compare the reduction in the dose by the Apron. Results: 1) When there was only L-block in the $^{18}F-FDG$ distribution room, the average dose rate was $0.32{\mu}Sv$, and in the case of L-blockK+ apron, it was $0.23{\mu}Sv$. The differences in the dose and dose rate between the two cases were respectively, $0.09{\mu}Sv$ and 26%. 2) When there was no apron in the relaxing room, the average dose rate was $33.1{\mu}Sv$, and when there was an apron, it was $22.3{\mu}Sv$. The differences in the dose and dose rate between them were respectively, $10.8{\mu}Sv$ and 33%. 3) When there was no APRON in the PET/CT room, the average dose rate was $6.9{\mu}Sv$, and there was an APRON, it was $5.5{\mu}Sv$. The differences in the dose and dose rate between them were respectively, $1.4{\mu}Sv$ and 25%. 4) When there was no apron, the average dose rate of $^{99m}TC$ was $23.7{\mu}Sv$, and when there was an apron, it was $5.5{\mu}Sv$. The differences in the dose and dose rate between them were respectively, $18.2{\mu}Sv$ and 77%. Conclusion: According to the result of the experiment, $^{99m}TC$ injected into patients showed an average shielding rate of 77%, and $^{18F}FDG$ showed a relatively low shielding rate of 27%. When comparing the sources only, $^{18F}FDG$ showed a shielding rate of 17%, and $^{99m}TC$'s was 77%. Though it had a lower shielding effect than $^{99m}TC$, $^{18}F-FDG$ also had a shielding effect on the apron. Therefore, it is considered that wearing an apron appropriate for high energy like $^{18}F-FDG$ would minimize the exposure dose of radiation workers.

• 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.