• Journal of Chest Surgery
• /
• v.29 no.3
• /
• pp.303-310
• /
• 1996

From December of 1994 to April of 1995, we, SHUH Department of Pediatric Thoracic and Cardiovascular Surgery, studied effects of aprotinin. 95 patients were randomly divided into two groups : group I (n=47) with aprotinin and group ll (n=48) without aprotinin. Aprotinin was given as one shot injection to cardiopulmonary bypass perfusion solution with dose of 50,000 KIUikg. Laboratory data such as hemoglobin, hematocrit, BUH, creatinine, fibrinogen, electrolyte concentration, aPTT, PT, and AT R was checked preoperatively, 5 minutes after anesthesia, 5 minutes and 35 minutes after CPB circulation, and 5 minutes, 3 hours, and 24 hours after reperfusion. Also, chest-tube drainage, transfused amount of RBC, platelet concentrate, and fresh frozen plasma within first 24 hours postoperatively were checked and analyzed after transition nn body weight demension. Only RBC transfused postoperatively had statistical significance with P value of less than 0.001. Others had no difference statistical wise. Postoperative side effects of aprotinin was not detected weeks after the surgery and there was no reoperated patient due to postoperative bleeding.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.47-55
• /
• 2019

As the damage caused by GPS jamming has been increased, researches for detecting and preventing GPS jamming is being actively studied. This paper deals with a GPS jamming detection method using multiple GPS receiving channels and three-types machine learning techniques. Proposed multiple GPS channels consist of commercial GPS receiver with no anti-jamming function, receiver with just anti-noise jamming function and receiver with anti-noise and anti-spoofing jamming function. This system enables user to identify the characteristics of the jamming signals by comparing the coordinates received at each receiver. In this paper, The five types of jamming signals with different signal characteristics were entered to the system and three kinds of machine learning methods(AB: Adaptive Boosting, SVM: Support Vector Machine, DT: Decision Tree) were applied to perform jamming detection test. The results showed that the DT technique has the best performance with a detection rate of 96.9% when the single machine learning technique was applied. And it is confirmed that DT technique is more effective for GPS jamming detection than the binary classifier techniques because it has low ambiguity and simple hardware. It was also confirmed that SVM could be used only if additional solutions to ambiguity problem are applied.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.3
• /
• pp.236-256
• /
• 2011

Forest carbon stocks change due to land use change is an important data required by UNFCCC(United Nations framework convention on climate change). Spatially explicit estimation of forest carbon stocks based on IPCC GPG(intergovernmental panel on climate change good practice guidance) tier 3 gives high reliability. But a current estimation which was aggregated from NFI data doesn't have detail forest carbon stocks by polygon or cell. In order to improve an estimation remote sensing and GIS have been used especially in Europe and North America. We divided research trends in main countries into 4 categories such as remote sensing, GIS, geostatistics and environmental modeling considering spatial heterogeneity. The easiest way to apply is combination NFI data with forest type map based on GIS. Considering especially complicated forest structure of Korea, geostatistics is useful to estimate local variation of forest carbon. In addition, fine scale image is good for verification of forest carbon stocks and determination of CDM site. Related domestic researches are still on initial status and forest carbon stocks are mainly estimated using k-nearest neighbor(k-NN). In order to select suitable method for forest in Korea, an applicability of diverse spatial data and algorithm must be considered. Also the comparison between methods is required.

• Clinical and Experimental Pediatrics
• /
• v.52 no.11
• /
• pp.1260-1266
• /
• 2009

Purpose : Idiopathic nephrotic syndrome (NS) can be clinically classified as steroid-sensitive and steroid-resistant. The detailed mechanism of glucocorticoid action in NS is currently unknown. Methods : In this study, we investigated 3 known single nucleotide polymorphisms (SNPs) (ER22/23EK, N363S, and BclI) of the glucocorticoid receptor gene (the NR3C1 gene) in 190 children with NS using polymerase chain reaction-restriction fragment length polymorphism and analyzed the correlation between the genotypes and clinicopathologic features of the patients. Results : Eighty patients (42.1%) were initial steroid nonresponders, of which 31 (16.3% of the total) developed end-stage renal disease during follow-up. Renal biopsy findings of 133 patients were available, of which 36 (31.9%) showed minimal changes in NS and 77 (68.1%) had focal segmental glomerulosclerosis. The distribution of the BclI genotypes was comparable between the patient and control groups, and the G allele frequencies in both the groups were almost the same. The ER22/23EK and N363S genotypes were homogenous as ER/ER and NN, respectively, in all the patients and in 100 control subjects. The BclI genotype showed no correlation with the NS onset age, initial steroid responsiveness, renal pathologic findings, or progression to end-stage renal disease. Conclusion : These data suggested that the ER22/23EK, N363S, and BclI SNPs in the NR3C1 gene do not affect the development of NS, initial steroid responsiveness, renal pathologic lesion, and progression to end-stage renal disease in Korean children with NS.

• Sleep Medicine and Psychophysiology
• /
• v.19 no.2
• /
• pp.68-76
• /
• 2012

Objectives: Sleep disorders cause changes of autonomic nervous system (ANS) which affect cardiovascular system. Primary insomnia (PI) makes acceleration of sympathetic nervous system (SNS) tone by sleep deficiency and arousal. Obstructive sleep apnea syndrome (OSAS) sets off SNS by frequent arousals and hypoxemias during sleep. We aimed to compare the changes of heart rate variability (HRV) indices induced by insomnia or sleep apnea to analyze for ANS how much to be affected by PI or OSAS. Methods: Total 315 subjects carried out nocturnal polysomnography (NPSG) were categorized into 4 groups - PI, mild, moderate and severe OSAS. Severity of OSAS was determined by apnea-hypopnea index (AHI). Then we selected 110 subjects considering age, sex and valance of each group's size [Group 1 : PI (mean age=$41.50{\pm}13.16$ yrs, AHI <5, n=20), Group 2 : mild OSAS (mean age=$43.67{\pm}12.11$ yrs, AHI 5-15, n=30), Group 3 : moderate OSAS (mean age $44.93{\pm}12.38$ yrs, AHI 16-30, n=30), Group 4 : severe OSAS (mean age=$45.87{\pm}12.44$ yrs, AHI >30, n=30)]. Comparison of HRV indices among the four groups was performed with ANCOVA (adjusted for age and body mass index) and Sidak post-hoc test. Results: We found statistically significant differences in HRV indices between severe OSAS group and the other groups (PI, mild OSAS and moderate OSAS). And there were no significant differences in HRV indices among PI, mild and moderate OSAS group. In HRV indices of PI and severe OSAS group showing the most prominent difference in the group comparisons, average RR interval were $991.1{\pm}27.1$ and $875.8{\pm}22.0$ ms (p=0.016), standard deviation of NN interval (SDNN) was $85.4{\pm}6.6$ and $112.8{\pm}5.4$ ms (p=0.022), SDNN index was $57.5{\pm}5.2$ and $87.6{\pm}4.2$ (p<0.001), total power was $11,893.5{\pm}1,359.9$ and $18,097.0{\pm}1,107.2ms^2$(p=0.008), very low frequency (VLF) was $7,534.8{\pm}1,120.1$ and $11,883.8{\pm}912.0ms^2$ (p=0.035), low frequency (LF) was $2,724.2{\pm}327.8$ and $4,351.6{\pm}266.9ms^2$(p=0.003). Conclusions: VLF and LF which were correlated with SNS tone showed more increased differences between severe OSAS group and PI group than other group comparisons. We could suggest that severe OSAS group was more influential to increased SNS activity than PI group.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.8
• /
• pp.535-542
• /
• 2013

Since case-based reasoning(CBR) has many advantages, it has been used for supporting decision making in various areas including medical checkup, production planning, customer classification, and so on. However, there are several factors to be set by heuristics when designing effective CBR systems. Among these factors, this study addresses the issue of selecting appropriate neighbors in case retrieval step. As the criterion for selecting appropriate neighbors, conventional studies have used the preset number of neighbors to combine(i.e. k of k-nearest neighbor), or the relative portion of the maximum similarity. However, this study proposes to use the absolute similarity threshold varying from 0 to 1, as the criterion for selecting appropriate neighbors to combine. In this case, too small similarity threshold value may make the model rarely produce the solution. To avoid this, we propose to adopt the coverage, which implies the ratio of the cases in which solutions are produced over the total number of the training cases, and to set it as the constraint when optimizing the similarity threshold. To validate the usefulness of the proposed model, we applied it to a real-world target marketing case of an online shopping mall in Korea. As a result, we found that the proposed model might significantly improve the performance of CBR.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.1
• /
• pp.75-83
• /
• 2008

We propose a welfare interface using multiple fecial features tracking, which can efficiently implement various mouse operations. The proposed system consist of five modules: face detection, eye detection, mouth detection, facial feature tracking, and mouse control. The facial region is first obtained using skin-color model and connected-component analysis(CCs). Thereafter the eye regions are localized using neutral network(NN)-based texture classifier that discriminates the facial region into eye class and non-eye class, and then mouth region is localized using edge detector. Once eye and mouth regions are localized they are continuously and correctly tracking by mean-shift algorithm and template matching, respectively. Based on the tracking results, mouse operations such as movement or click are implemented. To assess the validity of the proposed system, it was applied to the interface system for web browser and was tested on a group of 25 users. The results show that our system have the accuracy of 99% and process more than 21 frame/sec on PC for the $320{\times}240$ size input image, as such it can supply a user-friendly and convenient access to a computer in real-time operation.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.1
• /
• pp.83-97
• /
• 2021

Wireless sensors that make up the Wireless Sensor Network generally have extremely limited power and resources. The wireless sensor enters the sleep state at a certain interval to conserve power. The Sleep deflation attack is a deadly attack that consumes power by preventing wireless sensors from entering the sleep state, but there is no clear countermeasure. Thus, in this paper, using clustering-based binary search tree structure, the Sleep deprivation attack detection model is proposed. The model proposed in this paper utilizes one of the characteristics of both attack sensor nodes and normal sensor nodes which were classified using machine learning. The characteristics used for detection were determined using Long Short-Term Memory, Decision Tree, Support Vector Machine, and K-Nearest Neighbor. Thresholds for judging attack sensor nodes were then learned by applying the SVM. The determined features were used in the proposed algorithm to calculate the values for attack detection, and the threshold for determining the calculated values was derived by applying SVM.Through experiments, the detection model proposed showed a detection rate of 94% when 35% of the total sensor nodes were attack sensor nodes and improvement of up to 26% in power retention.

• 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.