• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• Asian-Australasian Journal of Animal Sciences
• /
• v.5 no.4
• /
• pp.741-746
• /
• 1992

The effects of 5%, 10%, 15% and 20% dietary cellulose levels on the nutrient utilization in chickens were investigated. Four experimental diets were alternatively given to 8 colostomized White Leghorn cockerels to make a $4{\times}4$ Latin-square design. The diets of 70 g.day were force-fed once a day, and water was given freely. The digestibilities of DM and energy increased linearly with the increase in dietary cellulose level. The digestibilities of ether extract and nitrogen-free extract were not so much influenced by the dietary cellulose level. The digestibility of acid detergent fiber was very low and not influenced by the dietary cellulose level. The digestibility of neutral detergent fiber was not different among the diets containing 5%-15% cellulose, but that of the 20% cellulose diet was diminished. This might be due to the reduction of hemicellulose digestibility. True digestibility and biological value of protein were also not influenced by the dietary cellulose level from 5% to 20%. In conclusion, no ill-effect was found even when the chicken was fed a diet containing 20% of cellulose.

• KSBB Journal
• /
• v.25 no.4
• /
• pp.363-370
• /
• 2010

Lipid from Scenedesmus sp. was extracted, fractionated and purified by silicic acid column chromatography. Total lipid content of extract was $21.38{\pm}1.03$ wt%, and triacylglycerol, an index lipid for biodiesel production was detected. Ten species of $C_{16}{\sim}C_{22}$ with saturated and unsaturated fatty acid were identified showing the very adequate fatty acid profiles for biodiesel production with a good flow property at low temperature. The fractions of glycolipid, neutral and phospholipid were 52.64, 28.10 and 19.26% of total lipid, respectively. The triacylglycerol of 12.63% and chlorophyll a of 49.47% was fractioned using stepwise elution of n-hexane-diethyl ether (95:5, v/v) solvent. The high content of chlorophyll was considered as a potential source of value-added co-product.

• Fashion & Textile Research Journal
• /
• v.10 no.1
• /
• pp.106-112
• /
• 2008

The purpose of this study is to define optimal conditions for wool blend fabric dyeing using Rhus verniciflua extract. K/S value, surface color change, the fastness to light, fastness to dry-cleaning, metal mordanting effects and antimicrobial activities were investigated. The results were summarized as follows; As the storage time of Rhus verniciflua stokes dyeing solution was longer, K/S was improved. K/S value showed the highest one when dyeing temperature and time were at 100oC and 60 minutes respectively. As for the changes of pH values of the dyeing solution, fabric was dyed well with the pH value of acid or neutral. K/S value recorded the highest at pH6 and the lowest at pH10. Fastness to light showed the unmordanted fabric is 2.84, and Fe is 1.69 on color difference. Antibacterial activities of Rhus verniciflua dyeing solution recorded high figures in both dyed fabric with unmordanted and dyed fabric with mordanting.

• Korean Journal of Pharmacognosy
• /
• v.27 no.3
• /
• pp.254-261
• /
• 1996

A potent immuno-stimulating activity was detected from the watersoluble and ethanol-precipitated crude extract (AG-1) of the root of Angelica gigas Nakai. The crude extract was fractionated into two fractions, an acidic AG-2 and a neutral AG-3 fraction by DEAE-cellulose adsorption. The two fractions contained polysaccharides of which M.W. were 10 Kdal and >2,000 Kdal respectively, proteins, and various inorganic components. The immunostimulating activities of two fractions were not reduced by proteinase K, acid or alkali treatment. The polysaccharides obtained from the root of A. gigas were mainly composed of arabinose, galactose, and galacturonic acid. These results indicated that immuno- stimulating components of the root of A. gigas was a kind of pectic polysaccharides or arabinogalactans.

• Korean Journal of Food Science and Technology
• /
• v.27 no.2
• /
• pp.216-220
• /
• 1995

In order to investigate the possible use of vegetable kimchi stuff as natural preservatives for kimchi, the methanol extracts of 15 kinds of vegetable kimchi stuff were solvent-fractionated and fractions were tested for antimicrobial activities against Leuconostoc mesenteroids, Pediococcus cerevisiae, Lactobacillus plantarum and Saccharomyces cerevisiae. The neutral fractions of the extracts of garlic and leek showed strong antimicrobial activities. The extract of leek showed particularly strong antimicrobial activities against Ped. cerevisiae and L. plantarum that were known to be main microorganism of fermentation and acidification of kimchi. The results suggest the possible use of the leek extract as natural preservatives for kimchi.

• The Korean Journal of Food And Nutrition
• /
• v.9 no.1
• /
• pp.76-84
• /
• 1996

This study was carried out to evaluate the effect of Ganoderma lueuidum (GL) water extract on fat accumulation in the fatted rats Induced by the oral high fat administration for six weeks. Total cholesterol, neutral fat and epididymal fat pad of GL groups were lower than the control group. On the other hand, high density lipoprotein(HDL) -cholesterol was somewhat higher in GL than In the control group. In addition, the same result as the above case was obtained when examining adipose for liver and epididymal fat components. During the feeding experiment, level of low density lipoprotein(LDL) and very low density lipoprotein (VLDL) increased while HDL was decreased in the control group as compared with normal group. The decree of LDL and VLDL was decreased, but HDL was increased in GL group as compared with the control group. Experiment group showed the Increased excretion as compared with the control group, in the excretion. Based on the above results, It was shown that it is possible to improve fat accumulation induced by high fat dietary through using the oral administration of Ganoderma lueidum boiling extract solutions.

• KSBB Journal
• /
• v.18 no.6
• /
• pp.511-516
• /
• 2003

The methanol extract from leaves of Catalpa ovata 6. DoN showed DPPH (1,1-diphenyl-2-picrylhydrazyl) radical-scavenging activity, and its antioxidative compounds were studied. The ethyl acetate-soluble neutral fraction from the methanol extract was successively purified with silica gel adsorption column chromatography, Sephadex LH-20 column chromatography and HPLC. Three antioxidative compounds were isolated and identified as piperitol, pinoresinol and lariciresinol by HR-MS and NMR spectroscopic analyses. The DPPH radical-scavenging activity of the identified compounds decreased in the order of lariciresinol > pinoresinol > piperitol.

• Bulletin of the Korean Chemical Society
• /
• v.28 no.5
• /
• pp.745-750
• /
• 2007

An isotope dilution-liquid chromatography/tandem mass spectrometric method was developed as a candidate reference method for the accurate determination of folic acid in infant milk formula. Sample was spiked with 13C5-folic acid and then extracted with phosphate buffer (pH 6) solution. The extract was further cleaned up by deproteinization followed by a C18 solid-phase extraction cartridge. The extract was analyzed by using LC/ ESI/MS/MS with selectively monitoring the collisionally induced dissociation channels of m/z 442 → m/z 295 and m/z 447 → m/z 295, which are the neutral glutamyl loss from the [M+H]+ ions of folic acid and 13C5-folic acid, respectively. LC/MS/MS chromatograms showed substantially reduced background from chemical noises compared to LC/MS chromatograms. Repeatability and reproducibility studies showed that the LC/MS/ MS method is a reliable and reproducible method which can provide less than 1.5 relative percentage of method precision.

• Natural Product Sciences
• /
• v.22 no.1
• /
• pp.20-24
• /
• 2016

Pentacyclic triterpenes, mainly, asiatic acid, madecassic acid, asiaticoside, and madecassoside are the active constituents of Centella asiatica. A pentacyclic triterpene enriched C. asiatica extract (PRE) was prepared and standardized to contain a total pentacyclic triterpenes not less than 65% w/w. This work was focused on determination of antiinflammatory, antioxidant, and tyrosinase inhibitory activities of PRE and its stability. The PRE exhibited a satisfactory nitric oxide inhibitory effect, with an $IC_{50}$ value of $64.6{\mu}g/mL$. In addition, the PRE inhibited tyrosinase enzyme activity with an $IC_{50}$ value of $104.8{\mu}g/mL$. In contrast, the PRE possessed only weak antioxidant activity. The PRE was stable over a period of four months when stored as a dried powder but only in a well-closed container protected from light at $4^{\circ}C$. An aqueous alcoholic solution of the PRE was stable at pH values of 5.8 and 7.0, but was not stable at a pH of 8.2. Preparations of the PRE in an aqueous solution should be performed in acidic or neutral conditions.