• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Applied Biological Chemistry
• /
• v.45 no.1
• /
• pp.11-17
• /
• 2002

Fermentation characteristics with/without nitrogen source and quality of the fruit distillate of Opuntia ficus-indica var. saboten were investigated during the manufacturing process of a Korean traditional liquor. As the fermentation period increased, acidity, brix degree, and alcohol concentration increased, whereas pH and contents of reducing sugar decreased. Acidity, pH, and brix degree were higher, whereas the content of reducing sugar lower, in the nitrogen source-added distillate than in the distillate without nitrogen source. The growth of yeast increased, while that of bacteria decreased; this trend was more prominent with the addition of a nitrogen source. Sojues, distilled from two types of mashes and diluted with $H_2O$ and tails of distillate into 22% alcohol concentration, showed pH $3.7{\sim}4.0$, acidity $0.02{\sim}0.10$, and $5.4{\sim}6.1$ $^{\circ}Brix$. Analysis through GC using direct injection methods revealed common volatile flavor compounds in sojues, including acetaldehyde, acetyl acetone, acetic acid ethyl ester, ethyl alcohol, 2-propyl alcohol, acetone, n-propyl alcohol, butanoic acid methyl ester, 2-phenyl ethanol, thymol, acetic acid phenyl ester, and vanillic aldehyde. As revealed through the sensory evaluation, no significant difference (p>0.05) in overall acceptability was shown among four experimental groups, while color and flavor showed significant differences(p<0.05).

• Journal of Korean Society of Forest Science
• /
• v.67 no.1
• /
• pp.42-49
• /
• 1984

The elderberry was known to the ancients for its medicinal properties, and in Europe the inner back was formerly administered as a cathartic. The flowers contain a voletile oil, and serve for the distilation of elder-lower water, used in confectionery, perfumes and lotions. The leaves are employed to impart a green colour to fat and oil, and the leaves and bark emit a sickly odour, believed to be repugnant to insect. With its unique flavor and natural food colour, commercial processing companies used the fruit mainly in the making for jam, jelly, pies, juice, and wines. Its vitamin-C content is reported by Andross (1941) as 25-30mg/100g. Harvesting and processing have been mechanized to some extent. However, the cotains with nutritional value has not been reported yet. In the present study the various contains with nutritional value in the fresh elderberry juice is reported by the quantitative analysis. In this study results obtained can be summarized as follows. 1) The fresh elderberry juice contained following mineral elements; calcium 0.012%, magnesium 0.023%, potassium 0.10%, sodium 0.0019%, iron 0.0009%, cobalt 0.0002%, zinc 0.0004%, copper 0.0001%, phosphorus 0.036%, manganese 0.0006%, iodide $1{\mu}g/g$. 2) Five kinds of vitamines were also found ; vitamin-$B_1$ $0.1{\mu}g/g$, vitamin-$B_2$ $0.5{\mu}g/g$, vitamin-C 0.3mg/g, niacin $14{\mu}g/g$, choline chloride 0.3mg/g. 3) Fresh elderberry juice also contains crude protein 1.10%, fat 0.26%, carbohydrate 6.9%, pectin 0.76%, tannin 0.89%, ash 0.80%, water 90.9% and 34.3 cal/100g. 4) The absorption spectrum of the purplishblack color of fresh elderberry juice has a peak between 523-530mm.

• Investigative Magnetic Resonance Imaging
• /
• v.11 no.1
• /
• pp.39-48
• /
• 2007

Purpose : To determine the diagnostic accuracy of four different sequences : moderately T2 weighted, two heavily T2-weighted single shot turbo spin-echo sequence and breath-hold axial-2D balanced turbo field-echo sequence(bFFE) for characterization of focal lesions. Materials and Methods : During the 3-month period between June and August 2005, seventy-six patients were proved to have ninety-three focal hepatic lesions on MR imaging. The patients consisted of 49 men and 27 women (age range, 15-75 years; mean age, 56.23 years). All MR images were acquired on a 1.5-T MR using the following sequences: 1. A breath-hold axial T2-weighted single shot turbo spin-echo sequence, 2. a breath-hold axial-2D balanced turbo field-echo sequence. Two radiologists performed quantitative analysis. Another radiologist measured the lesion-to-liver contrast-to-noise ratio at the region-of-interest in the four sequences. Results : There was no significant difference in inter-observer variability between the four sequences. The accuracy for both cyst and malignancy of moderate T2 weighted MRI (echo time: 80 msec) was also highest. There was significant difference for lesion characterization between moderate T2 weighted MRI and balanced steady state procession (p-value: 0.004) in the second reader. For longer echo time, the CNR of cystic lesions were markedly increased in comparison to lesions of other component. Conclusion : The accuracy and inter-observer variability of single shot turbo spin echo T2 weighted sequence was higher than bFFE. Although there was no statically significant difference, moderate T2 weighted MRI (echo time: 80 msec) was more accurate than heavily T2 weighted sequence (echo time: 300 msec). If the results for lesion characterization is equivocal in TE 80, the addition of heavily T2 weighted MRI (echo time: 180 msec) can be helpful.

• Journal of Life Science
• /
• v.15 no.2 s.69
• /
• pp.169-175
• /
• 2005

Resveratrol (3,4',5-trihydroxy-trans-stilbene), a phytoalexin found in grape skins, peanuts, and red wine, has been reported to have a wide range of biological and pharmacological properties. $Amyloid-\beta$ deposition and senile plaque-associated astrocytes are common neuropathological features of Alzheimer's disease. In this study, we have explored the effects of resveratrol on $amyloid-\beta-peptide-mediated$ cytotoxicity in vitro and modulation of cell growth-regulatory gene products in astroglioma C6 cells to elucidate its possible mechanism for anti-cytotoxicity. Exposure of C6 cells to $Amyloid-\beta$ resulted in dose-dependent growth inhibition and morphological changes of C6 cells, which were recovered by pre-treatment with resveratrol. The anti-proliferative effect of $amyloid-\beta$ was associated with the induction of tumor suppressor p53 and cyclin-dependent kinase (Cdk) inhibitor p21 (WAF1/CIP1) expression assessed by RT-PCR and Western blot analysis in time-dependent manner in C6 cells. In addition, the pro-apoptotic Bax expression was also up-regulated in $amyloid-\beta-treated$ C6 cells without alteration of anti-apoptotic Bcl-2 and $Bcl-X_L$ expression. However, pre-treatment of resveratrol significantly inhibited $amyloid-\beta-induced$ p53, p21 and Bax levels, suggesting that the modulation of p53, p21 and Bax levels could be one of the possible pathways by which resveratrol functions as anti-cytotoxic agent. Our results demonstrate that resveratrol may enhance the protection against $amyloid-\beta-induced$ cytotoxicity by promoting the survival of glial cells.

• Microbiology and Biotechnology Letters
• /
• v.35 no.3
• /
• pp.238-244
• /
• 2007

To identify the useful biological activities and the superiority in quality of Korean traditional liquors, we prepared the alcohol-free concentrates from different types of commercial traditional liquors, Takju ($T1{\sim}T3$), Yakju/Cheongju ($Y-1{\sim}Y-5$), Fruit wine (F-1) and Soju (S-1, S-2), respectively. We investigate their compositions as well as antimicrobial, antioxidant, and anti-thrombosis activity. Among the 11 traditional liquors, Y-3, Y-4, Y-5 and F-1 showed higher total-polyphenol, total-flavonoids and reducing sugars than the others. The strong antibacterial and anti-thrombosis activities were identified in Y-3, Y-4, Y-5 and F-1, and a minor antioxidant activity was found in F-l. The antibacterial activity of the Y-3, Y-4, Y-5 and F-1 alcohol-free concentrates showed a broad-spectrum, and growth inhibition was found in gram-positive, gram-negative, and ampicillin-resistant bacteria. The sequential solvent fractionation of Y-3, Y-4, Y-5 and F-1, and following analysis showed that ethyl acetate fractions of Y-3, Y-4, Y-5 and F-1 possess strong antibacterial and anti-thrombosis activity. Especially, the ethyl acetate fractions of Y-3, Y-4 and F-1 showed superior anti-thrombosis activity compared than that of aspirin. Our results suggest that the useful substances are produced from substrates and edible plant added during the fermentation, and the Korean traditional liquors could be developed as strong antibacterial and anti-thrombosis agents.

• Journal of Life Science
• /
• v.17 no.11
• /
• pp.1562-1570
• /
• 2007

This experiment was conducted to develop fertilizer which promotes plant growth as well as suppressing pathogenic fungi. The fertilizer was made from the mixture of Ju-Back (Korean rice wine cake) and indigenous rhizosphere-bacterium. The main ingredients of Ju-Back were investigated as 6.04% total nitrogen, 42.59% total carbohydrate, 1.01% available phosphate, 73.42% organic matter, 7.72% potassium oxide, 1.35% calcium oxide, 0.53% magnesium oxide. The enzyme activities of Ju-Back were estimated to be 980 units/g for ${\alpha}-amylase$, 300 units/g for glucoamylase, and 1800 units/g for acid pretense. Indigenous rhizosphere bacteria which produced antifungal agent were isolated from soil, and was selected KMU-13 strain which can antagonize against various plant pathogenic fungi (Botrytis cinerea KACC 40573, Sclerotinia sclerotiorum KACC 41065, Fusairum oxysporum KACC 40052, Pythium aphanidermatum KACC 40156, Phytophthora capsici KACC 40476 and Glomerella cingulata KACC 40299). KMU-13 strain was identified as Bacillus subtilis KMU-13 by biochemical and 16s rDNA analysis. The organic fertilizer was made as prototype which was composed 20% Ju-Back, 70% carrier, 9.7% microorganism cultivated solution, 0.3% trace-element. We also investigated an application of fertilizer using Ju-Back for cultivating lettuce (Lactuca sativar) which were grown in three soil conditions that had chemical fertilizer, barnyard manure, lime power, urea, potassium chloride and superphosphate as a control, the whole quantity (80 kg/10a) of posted fertilizer with the control and the half quantity (40 kg/10a) with the control. The growth characteristics were examined and analysed with several weeks interval from 3 weeks to 8 weeks on head length (cm), head width (cm/head), number of leaf and fresh weight (g/plant). The results are summarized as follows. The head width and fresh weight of lettuce were the highest at posted fertilizer 1 (whole quantity) was applied chemical, organic matter (Ju-Back) and carrier. The head length was the highest at posted fertilizer 2 (whole quantity) was applied Ju-Back only.

• Journal of Life Science
• /
• v.24 no.9
• /
• pp.967-972
• /
• 2014

In the present study, we prepared eighty-five different kinds of lees extracts and their solvent fractions and investigated their anti-proliferative activities against human colorectal cancer HCT116 cells. HCT116 cells were treated with eighty-five solvent fractions of lees extracts and then cell viability was measured using MTS assay. Among the treated solvent fractions, three solvent fractions (KSD-E1-3, KSD-E2-3, and KSD-E4-3) were selected based on cell viability assay. In addition, we performed an oligo DNA microarray analysis to analyze the gene expression changes by treatment of KSD-E1-3 in HCT116 cells. Among the upregulated genes, we selected 4 genes (NAG-1, ATF3, p21, and DDIT3) and performed RT-PCR using gene-specific primers. Among the treated solvent fractions, KSD-E1-3 dramatically induced the expressions of the four selected genes. In addition, we investigated whether the upregulations of those genes were dependent on the transcription factor p53's presence using p53 null HCT116 cells. The results indicate that the upregulations of NAG-1, ATF3, and DDIT3 are not dependent on the p53 presence, whereas p21 is dependent on the p53 presence. These findings may help to understand the molecular mechanisms of the anti-proliferative activity mediated by rice wine lees in human colorectal cancer cells.