• Knowledge Management Research
• /
• v.21 no.3
• /
• pp.177-195
• /
• 2020

The social consciousness on fake reviews has triggered researchers to suggest ways to cope with them by analyzing contents of fake reviews or finding ways to discover them by means of structural characteristics of them. This research tried to collect data from blog posts in Naver and detect habitual patterns users use unconsciously by variables extracted from blogs and blog posts by a machine learning model and wanted to use the technique in predicting fake reviews. Data analysis showed that there was a very high relationship between the number of all the posts registered in the blog of the writer of the related writing and the date when it was registered. And, it was found that, as model to detect advertising reviews, Random Forest is the most suitable. If a review is predicted to be an advertising one by the model suggested in this research, it is very likely that it is fake review, and that it violates the guidelines on investigation into markings and advertising regarding recommendation and guarantee in the Law of Marking and Advertising. The fact that, instead of using analysis of morphemes in contents of writings, this research adopts behavior analysis of the writer, and, based on such an approach, collects characteristic data of blogs and blog posts not by manual works, but by automated system, and discerns whether a certain writing is advertising or not is expected to have positive effects on improving efficiency and effectiveness in detecting fake reviews.

• Economic and Environmental Geology
• /
• v.38 no.3 s.172
• /
• pp.221-236
• /
• 2005

In order to investigate the contamination levels and dispersion patterns of heavy metals such as Cd, Co, Cr, Cu, Fe, Mn, Ni, Pb and Zn by urbanization, soils beneath roadside-trees and leaves of Ginkgo biloba were collected from Seoul area during October to November in 2001. All tree leaves were grouped into washed and unwashed ones. The pH of most soil ranges from 6 to 9 indicating a weak acidic and alkaline. The element couples of Cd-Co, Cr-Ni and Zn-Cu-Pb have good correlation in soils, and contamination sources of Cd-Co, Cr-Ni and Zn-Cu-Pb could be similar. High correlation coefficients among Pb, Cu and Zn in G. biloba indicates that these elements show the similar behavior during the metabolism processes. From the results of pollution index calculation for soils, industrialized and heavy traffic area were severly polluted by heavy metals such as Cd, Cu, Pb and Zn. By the discriminant analysis, industrialized and heavy traffic areas are enriched in the order of Ni> Cr> Pb. Cadmium is useful to discriminate between industrialized and heavy traffic areas, Co and Pb are highly enhanced in heavy traffic area.

• Korean Journal of Food Science and Technology
• /
• v.43 no.3
• /
• pp.291-302
• /
• 2011

The effects of roasting condition and storage time on rancidity of rapeseed oil were studied. Rapeseed oil from rapeseed roasted under different conditions were stored in the dark at $17^{\circ}C$. Volatile compounds of rapeseed oil were analyzed with an electronic nose (E-nose) and gas chromatography-mass spectrometry (GC-MS). The data from the E-nose were analyzed using discriminant function analysis (DFA). As roasting temperature increased from 150 to $240^{\circ}C$ over 20 min, the first discriminant function score (DF1) moved from positive to negative. DF1 decreased with storage time and changes in DF1 were higher between 0 and 2 days and between 20 and 24 days. Twenty-four compounds were identified in rapeseed oil, and hydrocarbons, furans, ketones, acids, benzene, and aldehydes were detected by GC-MS. The number of formed volatile compounds increased as storage time increased, but no increase in these compounds was detected by GC-MS.

• Korean Journal of Food Science and Technology
• /
• v.43 no.4
• /
• pp.419-425
• /
• 2011

Changes in the flavor of muskmelons stored at different temperatures were examined to judge aroma patterns during storage. A mass-spectrometry based electric nose was used to distinguish the subtle differences in the muskmelon's volatile compounds. The data were used for a discriminant function analysis (DFA), and then the partial least square algorithm was used for a quantitative analysis. Volatile components in the muskmelons increased with storage, and the first discriminant function score (DF1: $r^2$=99.88%, F=3072.5) moved from a positive position to a negative position as the storage period increased. The proper point of maturity was anticipated as the $28^{th}$ day at 0$^{\circ}C$, $21^{st}C$ day at 4 and 7$^{\circ}C$, and $14^{th}$ day at 10$^{\circ}C$. Also, using the DF1 score we could predict the general tendency (vitamin C, stem moisture, acidity) of the muskmelons. The electronic nose revealed that the major volatile compounds that changed during storage of the melons were ethyl ethyl acetate, butyl acetate, nonanol, dodecanoic acid, hexadecanoic acid and tricosane. The amount of volatile compounds detected increased during storage.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.4
• /
• pp.22-30
• /
• 2001

In this paper we propose three classification algorithms to classify breast tumors that occur in duct into Benign, DCIS(ductal carcinoma in situ) NOS(invasive ductal carcinoma) The general approach for a creating classifier is composed of 2 steps: feature extraction and classification Above all feature extraction for a good classifier is very significance, because the classification performance depends on the extracted features, Therefore in the feature extraction step, we extracted morphology features describing the size of nuclei and texture features The internal structures of the tumor are reflected from wavelet transformed images with 10$\times$ and 40$\times$ magnification. Pariticulary to find the correlation between correct classification rates and wavelet depths we applied 1, 2, 3 and 4-level wavelet transforms to the images and extracted texture feature from the transformed images The morphology features used are area, perimeter, width of X axis width of Y axis and circularity The texture features used are entropy energy contrast and homogeneity. In the classification step, we created three classifiers from each of extracted features using discriminant analysis The first classifier was made by morphology features. The second and the third classifiers were made by texture features of wavelet transformed images with 10$\times$ and 40$\times$ magnification. Finally we analyzed and compared the correct classification rate of the three classifiers. In this study, we found that the best classifier was made by texture features of 3-level wavelet transformed images.

• The Korean Journal of Mycology
• /
• v.42 no.2
• /
• pp.159-164
• /
• 2014

For development of a method for differentiation of Pleurotus eryngii cultivars, simple sequence repeats (SSR) from whole genomic DNA sequence analysis was used for genotyping and two multiplex-SSR primer sets were developed. These SSR primer sets were employed to distinguish 12 cultivars and strains. Five polymorphic markers were selected based on the genotyping results. PCR using each primer produced one to four distinct bands ranging in size from 200 to 300 bp. Polymorphism information content (PIC) values of the five markers were in the range of 0.6627 to 0.6848 with an average of 0.6775. Unweighted pairgroup method with arithmetic mean clustering analysis based on genetic distances using five SSR markers classified 12 cultivars into two clusters. Cluster I and II were comprised of four and eight cultivars, respectively. Two multiplex sets, Multi-1 (SSR312 and SSR366) and Multi-2 (SSR178 and SSR277) completely discriminated 12 cultivars and strains with 21 alleles and a PIC value of 0.9090. These results might be useful in providing an efficient method for the identification of P. eryngii cultivars with separate PCR reactions.

• Journal of the Korean earth science society
• /
• v.38 no.1
• /
• pp.49-63
• /
• 2017

The geochemical results of the Chunyang granites located in the northeastern part of the Yeongnam Massif, indicate that these rocks have characteristics of calc-alkaline series in the sub-alkaline field, I-type and peraluminous. Most of the geochemical features in major and trace elements show systematic trends, which are similar to differentiation trends of the general Jurassic granitoids in South Korea. The Chunyang granite is largely enriched in mobile LILE (Sr, K, Rb and Ba) relatively immobile HFSE. They show LREE enriched patterns [$(La/Lu)_{CN}=41.8-73.2$] with a slightly negative Eu anomaly [$(Eu/Eu^*)_{CN}=0.89-1.10$]. There are no meaningful correlations in major and trace elements between the Chunyang granites and the Buseok plutonic rock which is the main unit of the Yeongju batholith. This result may suggest that these two plutonic rocks be not derived from the same parent magma. Tectonic discrimination diagrams indicate that the Chunyang granite was formed in volcanic arc environments. These geochemical characteristics results suggest that the Chunyang granite must have been generated at the active continental margin during the subduction of the Jurassic proto-Pacific plate.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.43 no.12
• /
• pp.1889-1895
• /
• 2014

Radiation-induced hydrocarbon contents of dried anchovy, jiri anchovy, and large-eyed herring were evaluated following electron-beam irradiation at doses of 1, 3, 5, 7, and 10 kGy. GC/MS identification of the induced hydrocarbons by irradiation was conducted after lipid separation by soxtec, followed by florosil column chromatography. 1-Tetradecene ($C_{14:1}$) and pentadecane ($C_{15:0}$) derived from palmitic acid, 1-hexadecene ($C_{16:1}$) and heptadecane ($C_{17:0}$) from stearic acid, and 8-heptadecene ($C_{17:1}$) and 1,7-hexadecadiene ($C_{16:2}$) from oleic acid were the major induced hydrocarbons in irradiated dried anchovy, jiri anchovy, and large-eyed herring samples. At the same irradiation dose, concentration of induced hydrocarbons differed from fatty acid composition and increased in accordance with radiation dose level. Radiation-induced hydrocarbons, such as 1-tetradecene ($C_{14:1}$), 1-hexadecene ($C_{16:2}$), 8-heptadecene ($C_{17:1}$), and 1,7-hexadecadiene ($C_{16:2}$), were confirmed as irradiation marker compounds. Therefore, these marker compounds could be used to distinguish electron-beam irradiated dried anchovy, jiri anchovy, and large-eyed herring from non-irradiated ones.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.7
• /
• pp.230-238
• /
• 2014

In this paper, we propose the possible way of accurate analysis and examination of ITO sensor to discriminate whether mutual capacitance ITO sensor is defective by using mutual capacitance of data in each node which consists of electrodes inside of ITO sensor. We have analyzed the structure characteristic of mutual capacitance ITO sensor which is used as an input device for not only small size electronics like mobile phone and tablets but also big size electronics and designed the circuit to inspect ITO sensor using touch screen panel IC. Set a variable related with mutual capacitance of charge and discharge and Implement to find and analyze accurate position when defect is made through the data from each node of ITO sensor. First, we can set a yield effective range through the first experiment data of mutual capacitance ITO sensor and by using the data of each node of ITO sensor which is the result from the second experiment, we can verify accuracy and effectiveness of effective range from the first experiment as a sample which is used in this experiment.

• Korean Journal of Food Science and Technology
• /
• v.42 no.6
• /
• pp.699-704
• /
• 2010

Rapeseed oil was stored under different conditions such as in the dark, with UV treatment, and with prooxidantscytochrome C and copper ion. The rapeseed oils stored at different temperatures were analyzed by a mass spectrometrybased electronic nose and discriminant function analysis (DFA). Volatile components in the rapeseed oil increased with storage time, and the discriminant function first score (DF1) moved from a positive position to a negative position as storage time increased. Changes in DF1 were higher under UV treatment than under the dark condition (DF1: $r^2$=0.9481, F=307.03). The different DF1 values (F1) under the dark condition were 0.099, 0.187, and 0.278 as storage temperature increased. The different values under UV treatment were 0.554, 0.588, and 0.542, as storage temperature increased from 4 to $26^{\circ}C$. As concentrations of prooxidants copper ion and cytochrome C increased, amounts of volatile components also increased. These were confirmed by DFA. Furthermore, changes in responses at each ion fragment agreed with reported results for GC/MS, which formed after rancidity of the oil, including pentane, pentanal, 1-pentanol, hexanal, n-octane, 2-hexenal, heptanal, 2-heptenal, decane, 2-octenal, undecane, and dodecane.