• Journal of the Korean Society of Clothing and Textiles
• /
• v.32 no.12
• /
• pp.1837-1847
• /
• 2008

The goal of this study is to express the image of chameleons-that change their colors by light, temperature and its mood-into the sexy styles of corresponding coquettish temperamental people in Wearable Art. The method used in this study was experimenting various production mediums, including creating the textured stretch fabric, in the process of expressing the conceptual characteristics of the chameleon in Wearable Art. The concept of the work was a concoction of 'tempting', 'splendid', 'brilliant', 'fascinating', etc. that highlighted the real disposition of the chameleon. The futuristic preference of the researcher was also implicated. "Comfortable" and "enjoyable" concepts via motions were improved with the its completeness. The point of the design and production is to express symbolically the chameleon in real life, analyzing its sleek body lines, conditional colors changing, outer skins and the cubic textures. The coquettish temperamental image, the conceptual image of the chameleon, was also expressed by implication into the whole work. The entire line of this work is body-conscious silhouette. It was symbolically selected to image the outline of the chameleon that has the slim and sleek body. The exposed back is intended to express symbolically the projected back bones of the chameleon. The hood of gentle triangle line expresses the smooth-lined head part. The irregular hemlines represent the elongated chameleon's tale. The chameleon with its colors of vivid tones is characterized the colors changing by its conditions. This point was importantly treated in the working process by trying the effects that the colors are seen slightly different according to the light and angles. The material was given the effect that its surface colors are seen different in lights and angles because of the wrinkles protruded lumpy-bumpy. The various stones of red and blue tones are very similar to the skin tones of the real chameleon, and their gradation makes the effect that the colors are visibly changed with each move. The textures of the chameleon were produced via the wrinkle effect of smoke-shape, which is the result of using the elastic threads on the basic mediums stitched with 50/50 chiffon and polyester along with velvet dot patterns. The stretching fabric by the impact of the elastic threads is as much suitable for making the body-conscious line. The stones are composed of acrylic cabochon and gemstone. They are symbolically expressed the lumpy and bumpy back skin of the chameleon and produced the effect of the colors visibly different. The primary technique used in this dress is the draping utilizing the biased grains. The front body piece is connected to the hood and joined to the back piece without any seam. For the irregular hemline flares, leaving the several rectangular pieces with bias grains, they were connected by interlocking. What defines the clothes is the person in action. Therefore, what decides the completeness of clothes might be its comfortable and enjoyable feeling by living and acting people. The chameleon dress could also reach its goal of comforting and pleasing Wearable Art in the process of studying the techniques and effects that visibly differentiate the colors. It is considered as a main point of the Wearable Art, which is a comfortable enjoyable clothing tempered with the artistic beauty.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.22 no.4
• /
• pp.259-264
• /
• 2002

DK 754S, a forage corn hybrid is bred by Dekalb plant Genetics Co.. Garst 8255 by Garst Seeds Co., and GW 737 by Crosbyton Co. in US, respectively. These have been tested in Suwon and Chonan for 3 years to test their regional yield trial. In result, we were able to confirm the excellence of above cultivars and these were selected as new recommended cultivars April of 2002 by NACF. The characteristics of these cultivars are as follows ; 1. DK 7545 a. This cultivar is mid-late maturing, high quality, high yielding forage corn hybrid. Its mean tasseling date is the 11th of July. It takes 78 days from emergence to tasseling date, which is almost same with Kwanganok. The culm length and the ear height are 231 cm and 127 cm. It is relatively strong to lodging. b. The color of ear is yellow, the number of ear row is nineteen. DK 7545 shows strength to H maydis and MBSDV has occurred between 0% and 4.1% in Chonan test area but it still does not affect yielding at all. It is relatively resistant to corn borer and its stay green is almost same level comparing to a check hybrid, Kwanganok. c. Dry matter yield of this cultivar is 19.6 tons, TDN is 13.4 tons per a ha, therefore these hybrids are increased by from 6 to 9% comparing to Kwanganok. The percent ear among total dry matters yield is 43.7%. 2. Garst 8255 a. This hybrid is mid-late maturing, high quality, high yielding forage corn like as Kwanganok. Its the mean tasseling date and the period from emergence to tasseling date are almost same with a check hybrid, Kwanganok. The Culm length and the ear height are 259 cm, and 146 cm which are tall. It resists to lodging and shows excellence of stay green. b. Garst 8285 resists to H maydis, and MBSDV, and corn borer as much as Kwanganok has. c. Dry matter yield of this cultivar is 21,735 kg. TDN is 14,627 kg per a ha, therefore this is increased by 21%, 16%, respectively, comparing to a check hybrid, Kwanganok. The percent ear among total dry matters yield is 44.2%. 3. GW 737 a. This hybrid is mid-late maturing, high quality, high yielding forage com hybrid like as Kwanganok. Its mean tasseling date is 13th of July which is 2 days late comparing with a check hybrid, Kwanganok and the period from emergence to tasseling date is 80 days. b. The culm length and the ear height are 274 cm and 150 cm, which are tall. It resists to lodging moderately and shows excellence of stay green. c. GW 737 resists to H maydis and MBSDV very well, corn borer moderately resistance. d. Dry matter yield of this cultivar is 18,025kg, TDN 15,164kg per a ha, therefore this hybrid remarkably increased by 26%, 20%, respectively, comparing to a check hybrid, Kwanganok.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.26 no.2
• /
• pp.270-284
• /
• 1997

Effects of dietary carotenoids were investigated on the metaboβsm and body pigmentation of rainbow trout(Salmo gairdneri), masu salmon(Oncorhynchus macrostomos), eel(Anguilla japonica), rock fish(Sebastes inermis) and black rock fish(Sebastes schlegeli). Three weeks later after depletion, these fishes were fed diet supplemented with ${\beta}-carotene$, lutein, canthaxanthin', astaxanthin or ${\beta}-apo-8'-carotenal$ for 4 to 5 weeks, respectively. Carotenoids distributed to and changed in integument were analyzed. In the integument of rainbow trout. zeaxanthin, ${\beta}-carotene$ and canthaxanthin were found to be the major carotenoids, while lutein, isocryptoxanthin and salmoxanthin were the minor carotenoids. In the integument of masu salmon, zeaxanthin was found to be the major carotenoids, while triol, lutein, tunaxanthin, ${\beta}-carotene$, ${\beta}-cryptoxanthin$ and canthaxanthin were the minor carotenoids. In the integument of eel, ${\beta}-carotene$ was found to be the major carotenoids, while lutein, zeaxanthin and ${\beta}-cryptoxanthin$ were the minor carotenoids. In the integument of rock fish, zeaxanthin, ${\beta}-carotene$, tunaxanthin$(A{\sim}C)$ and lutein were found to be the major carotenoids, while ${\beta}-cryptoxanthin$, ${\alpha}-cryptoxanthin$ and astaxanthin were the minor carotenoids. Likely in the integument of black rock fish, ${\beta}-carotene$, astaxanthin and zeaxanthin were found to be the major carotenoids, whereas ${\alpha}-cryptoxanthin$, ${\beta}-cryptoxanthin$, lutein and canthaxanthin were the minor contributor. The efficacy of body pigmentation by the accumulation of carotenoids in the integument of rainbow trout and masu salmon were the most effectively shown in the canthaxanthin group and of eel, rock fish and black rock fish were the most effectively shown in the lutein group. Based on these results in the integument of each fish, dietary carotenoids were presumably biotransformed via oxidative and reductive pathways. In the rainbow trout, ${\beta}-carotene$ was oxidized to astaxanthin via successively isocryptoxanthin, echinenone and canthaxanthin. Lutein was oxidized to canthaxanthin. Canthaxanthin was reduced to ${\beta}-carotene$ via isozeaxanthin, and astaxanthin was reduced to zeaxanthin via triol. In the masu salmon, ${\beta}-carotene$ was oxidized to zeaxanthin. Lutein was reduced to zeaxanthin via tunaxanthin. Canthaxanthin was reduced to zeaxanthin via ${\beta}-carotene$. and astaxanthin was reduced to zeaxanthin via triol. In the eel, ${\beta}-carotene$ and lutein were directly deposited but canthaxanthin was reduced to ${\beta}-carotene$, and cholesterol lowering effect by Meju supplementation might be resulted from the modulation of fecal axanthin, astaxanthin and ${\beta}-apo-8'-carotenal$ were oxidized and reduced to tunaxanthin via zeaxanthin. In the black roch fish, ${\beta}-carotene$ was oxidized to ${\beta}-cryptoxanthin$. Lutein was reduced to ${\beta}-carotene$ via ${\alpha}-cryptoxanthin$. Canthaxanthin was reduced to ${\alpha}-cryptoxanthin$ via successively ${\beta}-cryptoxanthin$ and zeaxanthin. Astaxanthin converted to tunaxanthin via isocryptoxanthin and zeaxanthin, and ${\beta}-apo-8'-carotenal$ was reduced to ${\alpha}-cryptoxanthin$ via ${\beta}-cryptoxanthin$ and zeaxanthin.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.89-105
• /
• 2014

After emergence of Internet, social media with highly interactive Web 2.0 applications has provided very user friendly means for consumers and companies to communicate with each other. Users have routinely published contents involving their opinions and interests in social media such as blogs, forums, chatting rooms, and discussion boards, and the contents are released real-time in the Internet. For that reason, many researchers and marketers regard social media contents as the source of information for business analytics to develop business insights, and many studies have reported results on mining business intelligence from Social media content. In particular, opinion mining and sentiment analysis, as a technique to extract, classify, understand, and assess the opinions implicit in text contents, are frequently applied into social media content analysis because it emphasizes determining sentiment polarity and extracting authors' opinions. A number of frameworks, methods, techniques and tools have been presented by these researchers. However, we have found some weaknesses from their methods which are often technically complicated and are not sufficiently user-friendly for helping business decisions and planning. In this study, we attempted to formulate a more comprehensive and practical approach to conduct opinion mining with visual deliverables. First, we described the entire cycle of practical opinion mining using Social media content from the initial data gathering stage to the final presentation session. Our proposed approach to opinion mining consists of four phases: collecting, qualifying, analyzing, and visualizing. In the first phase, analysts have to choose target social media. Each target media requires different ways for analysts to gain access. There are open-API, searching tools, DB2DB interface, purchasing contents, and so son. Second phase is pre-processing to generate useful materials for meaningful analysis. If we do not remove garbage data, results of social media analysis will not provide meaningful and useful business insights. To clean social media data, natural language processing techniques should be applied. The next step is the opinion mining phase where the cleansed social media content set is to be analyzed. The qualified data set includes not only user-generated contents but also content identification information such as creation date, author name, user id, content id, hit counts, review or reply, favorite, etc. Depending on the purpose of the analysis, researchers or data analysts can select a suitable mining tool. Topic extraction and buzz analysis are usually related to market trends analysis, while sentiment analysis is utilized to conduct reputation analysis. There are also various applications, such as stock prediction, product recommendation, sales forecasting, and so on. The last phase is visualization and presentation of analysis results. The major focus and purpose of this phase are to explain results of analysis and help users to comprehend its meaning. Therefore, to the extent possible, deliverables from this phase should be made simple, clear and easy to understand, rather than complex and flashy. To illustrate our approach, we conducted a case study on a leading Korean instant noodle company. We targeted the leading company, NS Food, with 66.5% of market share; the firm has kept No. 1 position in the Korean "Ramen" business for several decades. We collected a total of 11,869 pieces of contents including blogs, forum contents and news articles. After collecting social media content data, we generated instant noodle business specific language resources for data manipulation and analysis using natural language processing. In addition, we tried to classify contents in more detail categories such as marketing features, environment, reputation, etc. In those phase, we used free ware software programs such as TM, KoNLP, ggplot2 and plyr packages in R project. As the result, we presented several useful visualization outputs like domain specific lexicons, volume and sentiment graphs, topic word cloud, heat maps, valence tree map, and other visualized images to provide vivid, full-colored examples using open library software packages of the R project. Business actors can quickly detect areas by a swift glance that are weak, strong, positive, negative, quiet or loud. Heat map is able to explain movement of sentiment or volume in categories and time matrix which shows density of color on time periods. Valence tree map, one of the most comprehensive and holistic visualization models, should be very helpful for analysts and decision makers to quickly understand the "big picture" business situation with a hierarchical structure since tree-map can present buzz volume and sentiment with a visualized result in a certain period. This case study offers real-world business insights from market sensing which would demonstrate to practical-minded business users how they can use these types of results for timely decision making in response to on-going changes in the market. We believe our approach can provide practical and reliable guide to opinion mining with visualized results that are immediately useful, not just in food industry but in other industries as well.

• Applied Biological Chemistry
• /
• v.15 no.3
• /
• pp.213-219
• /
• 1972

In order to utilize sweet potatoes for the material of Takju, brewing experiments with raw sweet potatoes, sweet potato chips powder and its koji were conducted; and various tests were carried out on effect of the treatments of acid, alkali, polyphenol oxidase inhibitor, oxidizing and reducing agents upon the prevention against coloring of sweet potato chips by steaming, and on peeling effect of sweet potatoes by the alkali and heat treatments. The results obtained were as follows. 1) In the case of brewing with raw sweet potatose, each plot showed low acid and ethanol content, and its finished Takju had an undersirable color and odor. The plots which were mashed after peeling showed higher ethanol contents than the plots mashed without peeling. 2) In the case of brewing with sweet potato chips powder, each plot contained considerably more amount of ethanol than the plots brewed with raw sweet potatoes, white it contained less amount of acid. The ethanol contents of the plots using wheat bran koji were $10.5{\sim}11.4$ per cent 4 days after mashing, and were higher than those of the plots using malts powder. Their finished Takju was inferior in quality because of the lack of acid and being darkened gradually in process of time. 3) The kojies which were made of sweet potato chips powder with Neurospora sitophila or Aspergillus oryzae had good appearance, but the Takju mashes brewed with these contained remarkably less amount of ethanol. 4) Effect of the treatments of acid, alkali, polyphenol oxidase inhibitor and organic solvents such as ether and ethanol upon the prevention against coloring of sweet potato chips was not recognized. Alum and burnt alum were effective a little on the decolorization, and among the oxidizing and reducing agents tested, potassium permanganate was most effective. 5) Darkening of sweet potato chips powder in course of heating after mixing with water was not affected by pectin and amino acids, but by tannin. 6) Sweet potatoes were not peeled easily by friction after soaking in the boiling solution of 3 per cent alkali for 6 minutes and peeled in boiling water for 12 minutes. From the viewpoint of the results above mentioned, it seems to be necessary to study further on the isolation of microorganisms which are able to decompose the coloring substances and yeasts which are adequate for the fermentation of sweet potatoes in order to utilize sweet potatoes for Takju brewing, because brewing with raw sweet potatoes, sweet potato chips powder and its koji was unsuccessful, and effect of the various treatments on the decolorization of sweet potatoes was not recognized.

• Asian Journal of Turfgrass Science
• /
• v.17 no.4
• /
• pp.129-146
• /
• 2003

Research was initiated to compare establishment vigor, uniformity, rooting potential and turf quality in sods of cool-season grasses (CSG). Several turfgrasses grown under pure sand soil were tested. Establishment vigor, uniformity, rooting potential and turf quality were evaluated in the study. Turfgrass entries were comprised of three blends from Kentucky bluegrass (KB, Poa pratensis L.), perennial ryegrass (PR, Lolium perenne L.), and tall fescue (TF, Festuca arundinacea Schreb.), respectively and three mixtures among them. Differences by treatments were significantly observed in establishment vigor, uniformity, rooting potential and turf quality. Early establishment vigor was mainly influenced by germination speed, being fastest with PR, intermediate with TF and slowest with KB. In a late stage of growth, however, it was affected more by growth habit, resulting in highest with KB and slowest with TF. There were considerable variations in sod uniformity among turfgrasses. Best uniformity among monostand sods was associated with KB, while poorest one with TF. PR sod produced intermediate uniformity between KB and TF. The uniformity of polystand sods of CSG mixtures was inferior to that of monostands of KB, PR and TF, due to characteristics of mixtures comprised of a variety of color, density, texture and growth habit. The greatest potential of sod rooting was found with PR and the poorest with KB. Intermediate potential between PR and KB was associated with TF. In CSG mixtures, it was variable, depending on turfgrass mixing rates. Generally, the higher the PR in mixtures, the greater the sod rooting potential. At the time of sod harvest, however, turfgrass quality of KB was superior to that of PR. because of its characteristics of uniform surface, high density and good mowing quality. These results suggest that a careful expertise based on turf quality as well as sod characteristics like establishment vigor, uniformity and rooting potential be strongly required for the success of golf course or athletic field in establishment.

• Applied Biological Chemistry
• /
• v.13 no.2
• /
• pp.111-129
• /
• 1970

As a series of studies on the nucleic acids and their related substances 210 samples were collected from 76 places such as farm soil, compost of heap, nuruk and meju to obtain microbial strains which produce 5'-phosphodiesterase. From these samples total of 758 strains were isolated by the use of dilution pour plate method. For all isolated strains primary screening of the productivity of RNA depolymerase was performed and useful strains with regard to 5'-phosphodiesterase productivities were identified. For these useful strains optimum condition, the effect of various compounds on the activity of 5'-phosphodiesterase, and the optimum condition for enzyme reaction were discussed. The quantitative of 5'-mononucleotides produced by the action of 5'-phosphodiesterase was performed using anion-exchange column chromatography and their identified was done by paper chromatography, thinlayer chromatography, ultra violet spectrophotometry, and characteristic color reaction using carbazole and schiff's reagent. (1) Penicillium citreo-viride PO 2-11 and Streptomyces aureus SOA 4-21 from soil were identified as a potent 5'-phosphodiesterase producing strains. (2) Optimum culture conditions for Penicillium citreo-viride PO 2-11 strain isolated were found to be pH 5.0 and $30^{\circ}C$, and the optimum conditions for enzyme action of 5'-phosphodiesterase were pH 4.2 and $60^{\circ}C$. Best carbon source for the production of 5'-phosphodiesterase was found to be sucrose and ammonium nitrate for nitrogen source. Addition of 0.01% corn steep liquor or yeast extract exhibited 20% increase in the amount of 5'-phosphodiesterase production compared to the control. 5'-phosphodiesterase produced by this strain was activated by $Mg^{++},\;Ca^{++},\;Zn^{++},\;Mn^{++}$ and was inhibited by EDTA, citrate, $Cu^{++},\;CO^{++}$. 5'-phosphodiesterase produced 5'-mononucleotide from RNA at a rate of 65.81%, and among the 5'-mononucleotides accumulated 5'-GMP only was found to have flavorous and the strain was also found lack of 5'-AMP deaminase. Productivity of flavorous 5'-GMP was found to be 186.7mg per gram of RNA. (3) Optimum culture canditions for the isolated Streptomyces aureus SOA 4-21 strain were pH 7.0 and $28^{\circ}C$, and the optimum conditions for the action of 5'-phosphodiesterase were pH 7.3 and $50^{\circ}C$. The best carbon source for 5'-phosphodiesterase production was found to be glucose and that of nitrogen was asparagine. Addition of 0.01% yeast extract exhibited increased productivity of 5'-phosphodiesterase by 40% compared to the non-added control. 5'-phosphodiesterase produced by this strain was activated by $Ca^{++},\;Zn^{++},\;Mn^{++}$ and was inhibited by citrate, EDTA, $Cu^{++}$. It was also found that the strain produce 5'-AMP deaminase in addition to 5'-phosphodiesterase. For this reason although decomposition rate was 63.58% the accumulation of 5'-AMP, 5'-CMP, 5'-GMP and 5'-UMP occurred by the breakdown of RNA. In the course of these reaction 5'-AMP deaminase converted 60% of 5'-AMP thus produced into 5'-IMP and flavorous 5'-mono nucleotide production was significantly increased by this strain over the above mentioned one. Production rates were found to be 171.8mg per grain of RNA for 5'-IMP and 148.2mg per gram of RNA for 5'-GMP, respectively.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.18 no.2
• /
• pp.131-138
• /
• 1985

The preservative effect of modified-atmosphere storage on the shelf-life of packed semi-salted and dried mackerel, Scomber japonicus, was examined. The semi-salted and dried mackerel fillets were packed in laminated plastic film bags (polyester/nylon/casted polypropylene: $12{\mu}m/15{\mu}m/60{\mu}m,\;15{\times}16cm$) filled with air (control, C), nitrogen gas (N), deoxygenized air (O) prepared by using free-oxygen absorber enclosed in the bag, in vacuum(V), and stored at $5^{\circ}C$. The quality of packed sample during the storage were examined in terms of viable cell counts of bacteria, thiobarbituric acid(TBA) value, perozide value(POV), volatile basic nitrogen(VBN), trimethylamine(TMA), adenosine triphosphate(ATP) and its related compounds and sensory evaluation. The results obtained are as follows: The pH of all the samples was in the range of $6.1{\pm}0.2$, and the contents of VBN and amino nitrogen of them increased during storage. In color values, L value(lightness) decreased while a and b values (red and yellow) revealed a tendency to increase during storage. The viable cell counts of the control sample(C) increased to $3.0{\times}10^6/g$ after 15 days storage but those of the other samples(V, N and O)were in the range of $2{\sim}6{\times}10^5/g$ after 20 days storage. The content of TMA increased during storage, but the histamine content showed a little change during storage and its content of all samples were less than 16 mg/100g. The inosinic acid(IMP) was rapidly degraded while inosine and hypoxanthine increased during storage. The TBA value of the control(C) reached a peak in 9 days and then decreased gradually while that of the sample(O) showed a little change during storage. The changes in POV of all the samples during storage showed a similar tendency to the TBA value. Fatty acid composition of raw mackerel consists of $35.6\%$ of saturated acid, $30.3\%$ of monoenoic acid and $34.2\%$ of polyenoic acid. The major fatty acid of the sample products were oleic acid($C_{18:1}$), palmitic acid($C_{16:0}$), docosahexaenoic acid($C_{22:6}$). The contents of polyenoic acid such as $C_{22:6},\;C_{20:5}$ decreased during storage while the other fatty acids showed a little change. From the results of sensory evaluation, the shelf-life of the control sample(C) was about 7 days and that of sample(V), (N) and (O) was about 15 days. It was concluded that deoxygenized atmosphere(free-oxygen absorber enclosed in the bag) was a good condition for preserving the quality of semi-salted and dried mackerel.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.

• Korean Journal of Agricultural Science
• /
• v.4 no.2
• /
• pp.126-140
• /
• 1977

Present studies were carried out for breeding cold resistant clones of Citrus, improving overwintering techniques of Citrus in Jeju island as well as other southern region, Result obtained were as follows 1. In the vinyl house covered with two sheets of straw mat, 12 indivuals were found as non-injury and 15 were slightly injured by leaf freeging test at $-9^{\circ}C$ for 2 hours treatment. 2. In the condition of vinyl house covered with straw mat and viny film mulching and heat-in by sun-light, the inside temperature of vinyl house were not lowered below $-3^{\circ}C$ and the ground temperatura in vinyl house keeps above $0^{\circ}C$ during winter though outdoor temperature were lower by $-15^{\circ}C$(Daejeon area). 3. The vinyl tunnel inside the vinyl house and vinyl film mulching on ground position showed greater effectiveness for preventing heat loss from house but there were no significant difference between the color of vinyl film covered the tunnel. 4. In the vertical distribution of maximum temperature in vinyl house, the upper space was slightly higher than the lower position at high temperature condition, while minimum temperature was distributed as higher as the middle position, ground surface and upper position in order at low temperature condition 5. In the horizontal distribution of temperature in vinyl house, ground and surface-temperature of north side was lower than the other sides, and citrus planted within 30cm from north side wall died by cold injury and in the other side near wall appeared slight symptom of cold injury. 6. The insulating trench ($30{\times}30{\times}30cm$) packed with straw bundle installed under north wall might be effective to prevent heat loss of ground temperature. 7. In cloudy and snowy day, the temperature difference between indoor and outdoor were less, and the indoor temperature were maintained highly during night due to the effect of prevention of heat loss. 8. The highest temperature in a day was observed at about P.M. 3 both inside and outside of vinyl house and the lowest temperature was observed at about A.M. 6. The difference between the highest and lowest temperature of indoor in a sunny day was $19^{\circ}C$, compared with $9^{\circ}C$ on a cloudy or snowy day in late November. Especially, lowering of temperature in a snowy day was so less that the curve of temperature change was comparatively constant, 9. If the effective methods of citrus cultivation in vinyl house with improved clone such as hardiness. semi-dwarf and spur type are applied, it might be possible to cultivate the citrus tree safely in Jeju island as well as other southern rejion and to magnity the cultivation of citrus tree.