• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.693-694
• /
• 2014

This short paper briefly describes the proposed music recommendation method that provides suitable music pieces to a listener depending on both listeners' ratings and content of music pieces. The proposed method consists of two methods. First, listeners' ratings prediction method is a combination the traditional user-based and item-based collaborative filtering methods. Second, genre classification method is a combination of feature extraction and classification procedures. The feature extraction step obtains audio signal information and stores it in data structure, while the second one classifies the music pieces into various genres using decision tree algorithm.

• Food Science and Preservation
• /
• v.22 no.3
• /
• pp.428-436
• /
• 2015

Five extraction conditions (AE, autoclave extraction; OE, oven extraction; HWSE, hot water and sonication extraction; HWASE, hot water acidified with 0.5% (v/v) acetic acid and sonication extraction; and BE, boiling extraction) were examined to compare the effects of different hot water extraction methods on the antioxidant properties of blueberries. The extraction yields of the AE, OE, HWSE, HWASE, and BE were 7.94%, 8.35%, 8.55% 9.15%, and 8.50%, respectively. The polyphenol and flavonoid contents of AE were 3.47 mg GAE/g and 1.59 mg RE/g, respectively, which were highest centents among others. Those of OE were ranked second to the highest. The total anthocyanin content of HWSE (5.29 mg/g) was significantly higher than that of others whereas that of AE showed the lowest content (0.96 mg/g). The order of ABTS radical and alkyl radical scavenging activities was as follows: AE > BE > OE > HWSE > HWASE. The antioxidant properties were considerably correspondent with the total polyphenol and flavonoid content. DPPH radical scavenging activity was quite high in HWSE, AE, and BE extraction, however, there were no significant differences among the five extraction methods in the aspect of $Fe^{2+}$ ion chelating activities. Moreover, AE showed the highest SOD activity, and protected the dermal fibroblast the best against $H_2O_2$-induced cytotoxicity. In conclusion, it was suggested that the autoclave extraction (AE) would be the most effective method for preparing blueberry hot water extracts with relatively high antioxidant activities.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.6
• /
• pp.995-1001
• /
• 1995

The structure of a typical pattern recognition consists a pre-processing, a feature extraction(algorithm) and classification or recognition. In classification, when widely varying patterns exist in same category, we need the clustering which organize the similar patterns. Clustering algorithm is two approaches. Firs, statistical approaches which are k-means, ISODATA algorithm. Second, neural network approach which is T. Kohonen's LVQ(Learning Vector Quantization). Nikhil R. Palet al proposed the GLVQ(Generalized LVQ, 1993). This paper suggest the efficient feature extraction methods of handwritten numerals in GLVQ clustering network. We use the handwritten numeral data from 21's authors(ie, 200 patterns) and compare the proportion of misclassified patterns for each feature extraction methods. As results, when we use the projection combination method, the classification ratio is 98.5%.

• Journal of Acupuncture Research
• /
• v.33 no.2
• /
• pp.97-108
• /
• 2016

Objectives : This study was performed to investigate the analgesic effect of Styrax japonica pharmacopuncture on formalin induced pain in rats and to figure out efficient extraction method. Methods : The subjects were divided into 5 groups ; normal group(treated with normal saline at KI03, and injected normal saline at right hindpaw after 35 minutes), control group(treated with normal saline at KI03, and injected with formalin at right hindpaw after 35 minutes), water group(treated by hot water extraction pharmacopuncture at KI03, and injected with formalin at right hindpaw after 35 minutes), ethanol group(treated with ethanol extraction pharmacopuncture at KI03, and injected with formalin at right hindpaw after 35 minutes), and ultrasound group(treated with ultrasound extraction pharmacacupuncture and injected with fromalin formalin at right hindpaw after 35 minutes). We conducted a formalin test with ultrasonic vocalization( USV), and after the test checked for substance P, Aspartate aminotransferase(AST), and Alanine aminotransferase(ALT) concentration in the blood for each of the groups. Results : There was a significant analgesic effect of Styrax japonica pharmacopuncture in the early phase of the formalin test, and pharmacopuncture made with an ultrasound extracting method was observed to have a better analgesic effect than other extracting methods in early phases. The substance P concentration decreased significantly in the Styrax japonica pharmacopuncture treated group and no difference was found in the AST and ALT concentration of each group. Conclusion : These results demonstrated that Styrax japonica pharmacopuncture had analgesic effects in noxious nociceptors stimulation. Also pharmacopuncture made with an ultrasound extracting method had a better analgesic effect than others.

• The Journal of the Korea Contents Association
• /
• v.16 no.8
• /
• pp.395-403
• /
• 2016

Recently, Image processing has been used in many areas. In the image processing techniques that a lot of research is tracking of moving object in real time. There are a number of popular methods for tracking an object such as HOG(Histogram of Oriented Gradients) to track pedestrians, and Codebook to subtract background. However, object extraction has difficulty because that a moving object has dynamic background in the image, and occurs severe lighting changes. In this paper, we propose a method of object extraction using depth image and color image features based on ROI(Region of Interest). First of all, we look for the feature points using the color image after setting the ROI a range to find the location of object in depth image. And we are extracting an object by creating a new contour using the convex hull point of object and the feature points. Finally, we compare the proposed method with the existing methods to find out how accurate extracting the object is.

• Journal of Food Hygiene and Safety
• /
• v.34 no.6
• /
• pp.557-561
• /
• 2019

This study investigated the efficacy of DNA extraction methods for real-time PCR detection of foodborne pathogenic bacteria in livestock manure composts. Livestock manure composts were inoculated with Escherichia coli O157:H7, Salmonella Typhimurium, Listeria monocytogenes, Bacillus cereus and incubated in enrichment broth. For DNA extraction, enriched samples were treated following boiling method, by chloroform, C₁₈ powder, and proteinase K. As a result, 4 species of bacteria were detected by real-time PCR when subjected to boiling for 30 min and treated with proteinase K. These results suggest that detection of foodborne pathogens by real-time PCR from livestock manure composts could be applicable using effective DNA extraction methodology such as the boiling method or proteinase K.

• Korean Journal of Food Science and Technology
• /
• v.50 no.4
• /
• pp.357-361
• /
• 2018

This study aimed to explore efficient DNA extraction methods using tree nuts. Four different DNA extraction procedures, including silica membrane method, modified silica method, cetyltrimethylammonium bromide (CTAB) method, and modified CTAB method were examined for their relative efficiency in extracting DNA from pistachio, pine nut, almond, hazelnut, cashew nut, walnut, and peanut. The quality and quantity of the extracted DNA were subsequently assessed by spectrometric measurements, gel electrophoresis, and PCR amplifications. CTAB method was the most appropriate one for extracting DNA from pine nut, cashew nut, pistachio, and peanut. However, it could be replaced by the silica membrane method for walnut and modified CTAB method for almond and hazelnut.

• Mass Spectrometry Letters
• /
• v.8 no.1
• /
• pp.18-22
• /
• 2017

Products containing any one or more of 26 fragrance allergens likely to cause contact allergies, are required under the 2008 domestic cosmetic law to be labeled when their concentrations exceed a certain range. This study focuses on the comparison and development of analytical methods based on headspace-solid phase micro extraction (HS-SPME) and liquid-liquid extraction (LLE) methods followed by GC-MS/MS for 24 of the fragrance allergens excepting for two natural materials in water samples. Using the developed HS-SPME method, 15 of the 24 fragrance allergens were analyzed and 9 compounds which have relatively low $logK_{OW}$ values (below about 2.5) were not extracted, and the correlation coefficient ($r^2$) of the calibration curve for quantification showed linearity of 0.9969 or more, and the method detection limits (MDL) and the limits of quantification (LOQ) were $0.078{\sim}0.582{\mu}g/L$ and $0.261{\sim}1.940{\mu}g/L$, respectively. In the case of using the optimized LLE method, all 24 fragrance allergens were analyzed, and the correlation coefficient ($r^2$) of the calibration curve for quantification showed linearity of 0.9957 or more, MDL and LOQ were $0.020{\sim}0.138{\mu}g/L$ and $0.065{\sim}0.440{\mu}g/L$, respectively.

• Journal of Society of Preventive Korean Medicine
• /
• v.22 no.1
• /
• pp.45-59
• /
• 2018

Objectives : The purpose of this study is to present trends and contents of herbal Korean Medicine patches by analyzing the herbal patches in Korean patents. Methods : Electronic search for herbal patch patents was conducted in KIPRIS (Korea Intellectual Property Rights Information Service). Korean patents that were registered by January 1, 2018 were selected in study. Patents that were not using herbal medicine or not related to patch were excluded in this study. The applicant, application date, International Patent Classification (IPC), contents and adhesive site of patches, target diseases, model of experiment and extraction methods were analyzed. Results : A total of 17 patents were included in this study. In applicant analysis, 61.5% of applicants were corporations. All IPCs in patents were involved in Section A (Human necessities & Agriculture) and 66.7% of IPCs were A61K (Preparations formedical, dental, ortoiletpurposes). In types of patch, 8 patents were hydrogel patches (47.1%), followed by 3 heating patches (17.6%). Skin related symptoms were the most targeted diseases (52.9%), Human was the most used model in experiments. Solvent extraction and hot water extraction were used frequently, and some patents had no limit for extraction were also existed. Conclusions : The study results will be helpful to diversify formulation of herbal medicine, to expand market scale of patent and to develop new application using Korean medicine. In order to establish sufficient data for utilizing patent technologies, more patent studies providing analyzed patent information are needed.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.3
• /
• pp.71-81
• /
• 1995

In this paper, feature vector extraction methods and classification algorithms for the automatic classification of transient signals in underwater are discussed. A feature vector extraction method using wavelet transform, which shows good performance with small number of coefficients, is proposed and compared with the existing classical methods. For the automatic classification, artificial neural networks such as multilayer perceptron (MLP), radial basis function (RBF), and MLP-Class are utilized, where those neural networks as well as extracted feature vectors are combined to improve the performance and reliability of the proposed algorithm. It is confirmed by computer simulation with Traco's standard transient data set I and simulated data that the proposed feature vector extraction method and classification algorithm perform well, assuming that the energy of a given transient signal is sufficiently larger than that of a ambient noise, that there are the finite number of noise sources, and that there does not exist noise sources more than two simultaneously.