• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.275-275
• /
• 2021

A fixed Z-R relationship approach, such as the Marshall-Palmer relationship, for an entire year and for different seasons can be problematic in cases where the relationship varies spatially and temporally throughout a region. From this perspective, this study explores the use of long-term radar reflectivity for South Korea to obtain a nationwide calibrated Z-R relationship and the associated uncertainties within a Bayesian regression framework. This study also investigates seasonal differences in the Z-R relationship and their roles in reducing systematic error. Distinct differences in the Z-R parameters in space are identified, and more importantly, an inverse relationship between the parameters is clearly identified with distinct regimes based on the seasons. A spatially structured pattern in the parameters exists, particularly parameter α for the wet season and parameter β for the dry season. A pronounced region of high values during the wet and dry seasons may be partially associated with storm movements in that season. Finally, the radar rainfall estimates through the calibrated Z-R relationship are compared with the existing Z-R relationships for estimating stratiform rainfall and convective rainfall. Overall, the radar rainfall fields based on the proposed modeling procedure are similar to the observed rainfall fields, whereas the radar rainfall fields obtained from the existing Marshall-Palmer Z-R relationship show a systematic underestimation. The obtained Z-R relationships are validated by testing the predictions on unseen radar-gauge pairs in the year 2018, in the context of cross-validation. The cross-validation results are largely similar to those in the calibration process, suggesting that the derived Z-R relationships fit the radar-gauge pairs reasonably well.

• Computers and Concrete
• /
• v.32 no.6
• /
• pp.577-594
• /
• 2023

Engineered cementitious composites with calcined clay limestone cement (LC³-ECC) as a kind of green, low-carbon and high toughness concrete, has recently received significant investigation. However, the complicated relationship between potential influential factors and LC³-ECC compressive strength makes the prediction of LC³-ECC compressive strength difficult. Regarding this, the machine learning-based prediction models for the compressive strength of LC³-ECC concrete is firstly proposed and developed. Models combine three novel meta-heuristic algorithms (golden jackal optimization algorithm, butterfly optimization algorithm and whale optimization algorithm) with support vector regression (SVR) to improve the accuracy of prediction. A new dataset about LC³-ECC compressive strength was integrated based on 156 data from previous studies and used to develop the SVR-based models. Thirteen potential factors affecting the compressive strength of LC³-ECC were comprehensively considered in the model. The results show all hybrid SVR prediction models can reach the Coefficient of determination (R²) above 0.95 for the testing set and 0.97 for the training set. Radar and Taylor plots also show better overall prediction performance of the hybrid SVR models than several traditional machine learning techniques, which confirms the superiority of the three proposed methods. The successful development of this predictive model can provide scientific guidance for LC³-ECC materials and further apply to such low-carbon, sustainable cement-based materials.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.1
• /
• pp.117-120
• /
• 2011

Purpose: There are 3 warnings for Glucagon tests. First, EDTA tubes that already contain Aprotinin must be used for plasma collection. Second, for freezer storage of centrifuged plasma, glass tubes must be used. Last, glass tubes must be used for testing procedure. So we compared the glucagon results of next 3 situation to those of control group. First, We compared to results by tubes without Aprotinin and with aprotinin. Second, we compared to results by tubes(plastic vs glass) for plasma storage. Third, we compared to results by tubes(plastic vs glass) for testing. We tried to evaluate the results of the 3 different condition. Materials and Methods: 40 healthy adults were studied with normal results on the general medical check up and laboratory tests. We compared the results of 3 different condition belows: Blood were collected in EDTA tube containing aprotinin and plasma was stored in the glass tube for 3 days in a freezer and results were obtained by tests in the glass tubes. Results from EDTA plasma without aprotinin, results from platic tubes for freezer stroage, results from plastic tube when testing. Simple linear regression analysis and paired t-test using SPSS were done for statistical analysis. Commercial glucagon kit(RIA-method)which made by Siemens company were used. Results: Correlation coefficient between results of EDTA tubes with Aprotinin vs without Aprotinin was r=0.783 (p=0.064). Result of specimen in plastic tubes stored 3 days in a freezer showed lower value compared to those in glass tube(r=0.979, p=0.005). Also, results of testing in plastic tubes showed lower values than those testing in glass tubes. (r=0.754, p<0.001). Conclusion: It is recommended for glucagon determination to use EDTA tube with Aprotinin which is a inhibitor of protein breakdown enzyme. Results of plastic tube when storage and testing showed lower value than those of glass tubes, so it is recommended to store and test in glass tubes.

• The Korean Journal of Applied Statistics
• /
• v.27 no.4
• /
• pp.645-653
• /
• 2014

P-value is the probability of observing a current sample and possibly other samples departing equally or more extremely from the null hypothesis toward postulated alternative hypothesis. When p-value is less than a certain level called ${\alpha}$(= 0:05), researchers claim that the alternative hypothesis is supported empirically. Unfortunately, some findings discovered in that way are not reproducible, partly because the p-value itself is a statistic vulnerable to random variation. Boos and Stefanski (2011) suggests calculating the upper limit of p-value in hypothesis testing, using a bootstrap predictive distribution. To determine the sample size of a replication study, this study proposes thought experiments by simulating boosted bootstrap samples of different sizes from given observations. The method is illustrated for the cases of two-group comparison and multiple linear regression. This study also addresses the reproducibility of the points in the given 95% confidence interval. Numerical examples show that the center point is covered by 95% confidence intervals generated from bootstrap resamples. However, end points are covered with a 50% chance. Hence this study draws the graph of the reproducibility rate for each parameter in the confidence interval.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.4
• /
• pp.1861-1864
• /
• 2016

Although early diagnosis of thyroid nodule type is very important, the diagnostic accuracy of standard tests is a challenging issue. We here aimed to find an optimal combination of factors to improve diagnostic accuracy for distinguishing malignant from benign thyroid nodules before surgery. In a prospective study from 2008 to 2012, 345 patients referred for thyroidectomy were enrolled. The sample size was split into a training set and testing set as a ratio of 7:3. The former was used for estimation and variable selection and obtaining a linear combination of factors. We utilized smoothly clipped absolute deviation (SCAD) logistic regression to achieve the sparse optimal combination of factors. To evaluate the performance of the estimated model in the testing set, a receiver operating characteristic (ROC) curve was utilized. The mean age of the examined patients (66 male and 279 female) was $40.9{\pm}13.4years$ (range 15- 90 years). Some 54.8% of the patients (24.3% male and 75.7% female) had benign and 45.2% (14% male and 86% female) malignant thyroid nodules. In addition to maximum diameters of nodules and lobes, their volumes were considered as related factors for malignancy prediction (a total of 16 factors). However, the SCAD method estimated the coefficients of 8 factors to be zero and eliminated them from the model. Hence a sparse model which combined the effects of 8 factors to distinguish malignant from benign thyroid nodules was generated. An optimal cut off point of the ROC curve for our estimated model was obtained (p=0.44) and the area under the curve (AUC) was equal to 77% (95% CI: 68%-85%). Sensitivity, specificity, positive predictive value and negative predictive values for this model were 70%, 72%, 71% and 76%, respectively. An increase of 10 percent and a greater accuracy rate in early diagnosis of thyroid nodule type by statistical methods (SCAD and ANN methods) compared with the results of FNA testing revealed that the statistical modeling methods are helpful in disease diagnosis. In addition, the factor ranking offered by these methods is valuable in the clinical context.

• International Journal of Human Ecology
• /
• v.6 no.2
• /
• pp.25-35
• /
• 2005

The purpose of this study was to examine the effects of family-school relations on children's school adjustment with divorced mothers. Subcategories of the family-school relations were family participation in decision making, family help for schools, learning activities at home, school help for families, and school-home communication adopted from Epstein's parent involvement theory. Sub categories of children's school adjustment were delinquent behavior and academic achievement. The sample of this study included 3,367 children from first to fifth grade who lived either in a two-parent or one-parent home. Among them, 411 children with divorced mothers were analyzed. Independent t-test, Pearson's correlations, stepwise regression analysis were all conducted. Findings suggested that children with divorced mothers showed higher delinquency and lower academic achievement than children in intact families. Sub categories of family involvement and school involvement were correlated in divorced families. Children's delinquency was predicted by three of the family-school relation factors, which were school-home communication, family help for schools, and school help for families. Children's academic achievement was predicted by ail factors.

• Journal of Korean Society of Steel Construction
• /
• v.15 no.2
• /
• pp.117-124
• /
• 2003

Wind-induced motions, like acceleration for instance, often influence designs for high-rise buildings. As a consequence, correct assessment of natural frequency becomes important. The empirical expressions used to quantify this parameter at the design phase tend to yield values that are significantly different from each other. This paper is concerned with the natural periods of steel buildings. It describes the vibration measurement methods that were employed for testing buildings. This paper will also present reliable methods of assessing the natural period from ambient vibration tests. Data from measurements on 21 buildings in Seoul were provided while 21 buildings were tested by ambient vibration measurements to obtain the natural periods. While regression formulas of natural periods for steel-frarried tall buildings were suggested,the obtained formula was compared with the empirical expressions of structural standards and the Eigen-value analysis.

• Clinical and Experimental Pediatrics
• /
• v.53 no.7
• /
• pp.766-769
• /
• 2010

Dense deposit disease (DDD) is a rare disorder characterized by the deposition of abnormal electron-dense material within the glomerular basement membrane of the kidneys. The diagnosis is made in most patients between 5 and 15 years of age, and within 10 years, approximately half of the affected patients progress to end-stage renal disease. We report a rare case of regressive DDD without C3 deposition after steroid therapy in an 11-year-old boy. The patient presented with edema, gross hematuria, and nephrotic-range proteinuria. Laboratory testing revealed a serum creatinine level of 1.17 mg/dL, albumin level of 2.3 g/dL, and serum C3 level of 125 mg/dL (range 90-180 mg/dL). The results of the renal biopsy were consistent with DDD without C3 deposition. After 6 weeks of steroid therapy, the nephrotic syndrome completely resolved. The follow-up renal biopsy showed a significant reduction in mesangial proliferation and disappearance of electron-dense deposits in the GBM.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.30 no.1
• /
• pp.21-33
• /
• 2012

This research attempts to analyze the effect of printed-saving coupons distributed by major discount store on consumer purchasing intention. Those consumers having used printed-saving coupon in major discount store in Daejeon were selected as respondents. 121 copies were retreated from 150 questionnaires. For data analysis, frequency analysis for respondents' characteristics, Cronbach's alpha for reliability of analysis, and $X^2$ test of multi-regression analysis for testing hypothesis were utilized. The result of analysis shows 1) the way of using coupon is respectively different according to sex, age group, marital status, term of coupon, and the number of using coupon; 2) Attributes of coupon partially influence on purchasing intention of consumers. Only shopping cost cutting is insignificant, while keeping convenience, impulse buying, scheduled purchasing are significant. The most effective variable is scheduled purchasing, keeping convenience, and impulse buying influence on purchasing intension of consumers. Therefore, offering printed-coupon by major discount store is useful tool to induce consumers to planned purchasing.