• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.95-110
• /
• 2013

Recently, the amount of unstructured data being generated through a variety of social media has been increasing rapidly, resulting in the increasing need to collect, store, search for, analyze, and visualize this data. This kind of data cannot be handled appropriately by using the traditional methodologies usually used for analyzing structured data because of its vast volume and unstructured nature. In this situation, many attempts are being made to analyze unstructured data such as text files and log files through various commercial or noncommercial analytical tools. Among the various contemporary issues dealt with in the literature of unstructured text data analysis, the concepts and techniques of opinion mining have been attracting much attention from pioneer researchers and business practitioners. Opinion mining or sentiment analysis refers to a series of processes that analyze participants' opinions, sentiments, evaluations, attitudes, and emotions about selected products, services, organizations, social issues, and so on. In other words, many attempts based on various opinion mining techniques are being made to resolve complicated issues that could not have otherwise been solved by existing traditional approaches. One of the most representative attempts using the opinion mining technique may be the recent research that proposed an intelligent model for predicting the direction of the stock index. This model works mainly on the basis of opinions extracted from an overwhelming number of economic news repots. News content published on various media is obviously a traditional example of unstructured text data. Every day, a large volume of new content is created, digitalized, and subsequently distributed to us via online or offline channels. Many studies have revealed that we make better decisions on political, economic, and social issues by analyzing news and other related information. In this sense, we expect to predict the fluctuation of stock markets partly by analyzing the relationship between economic news reports and the pattern of stock prices. So far, in the literature on opinion mining, most studies including ours have utilized a sentiment dictionary to elicit sentiment polarity or sentiment value from a large number of documents. A sentiment dictionary consists of pairs of selected words and their sentiment values. Sentiment classifiers refer to the dictionary to formulate the sentiment polarity of words, sentences in a document, and the whole document. However, most traditional approaches have common limitations in that they do not consider the flexibility of sentiment polarity, that is, the sentiment polarity or sentiment value of a word is fixed and cannot be changed in a traditional sentiment dictionary. In the real world, however, the sentiment polarity of a word can vary depending on the time, situation, and purpose of the analysis. It can also be contradictory in nature. The flexibility of sentiment polarity motivated us to conduct this study. In this paper, we have stated that sentiment polarity should be assigned, not merely on the basis of the inherent meaning of a word but on the basis of its ad hoc meaning within a particular context. To implement our idea, we presented an intelligent investment decision-support model based on opinion mining that performs the scrapping and parsing of massive volumes of economic news on the web, tags sentiment words, classifies sentiment polarity of the news, and finally predicts the direction of the next day's stock index. In addition, we applied a domain-specific sentiment dictionary instead of a general purpose one to classify each piece of news as either positive or negative. For the purpose of performance evaluation, we performed intensive experiments and investigated the prediction accuracy of our model. For the experiments to predict the direction of the stock index, we gathered and analyzed 1,072 articles about stock markets published by "M" and "E" media between July 2011 and September 2011.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.25-38
• /
• 2019

Selecting high-quality information that meets the interests and needs of users among the overflowing contents is becoming more important as the generation continues. In the flood of information, efforts to reflect the intention of the user in the search result better are being tried, rather than recognizing the information request as a simple string. Also, large IT companies such as Google and Microsoft focus on developing knowledge-based technologies including search engines which provide users with satisfaction and convenience. Especially, the finance is one of the fields expected to have the usefulness and potential of text data analysis because it's constantly generating new information, and the earlier the information is, the more valuable it is. Automatic knowledge extraction can be effective in areas where information flow is vast, such as financial sector, and new information continues to emerge. However, there are several practical difficulties faced by automatic knowledge extraction. First, there are difficulties in making corpus from different fields with same algorithm, and it is difficult to extract good quality triple. Second, it becomes more difficult to produce labeled text data by people if the extent and scope of knowledge increases and patterns are constantly updated. Third, performance evaluation is difficult due to the characteristics of unsupervised learning. Finally, problem definition for automatic knowledge extraction is not easy because of ambiguous conceptual characteristics of knowledge. So, in order to overcome limits described above and improve the semantic performance of stock-related information searching, this study attempts to extract the knowledge entity by using neural tensor network and evaluate the performance of them. Different from other references, the purpose of this study is to extract knowledge entity which is related to individual stock items. Various but relatively simple data processing methods are applied in the presented model to solve the problems of previous researches and to enhance the effectiveness of the model. From these processes, this study has the following three significances. First, A practical and simple automatic knowledge extraction method that can be applied. Second, the possibility of performance evaluation is presented through simple problem definition. Finally, the expressiveness of the knowledge increased by generating input data on a sentence basis without complex morphological analysis. The results of the empirical analysis and objective performance evaluation method are also presented. The empirical study to confirm the usefulness of the presented model, experts' reports about individual 30 stocks which are top 30 items based on frequency of publication from May 30, 2017 to May 21, 2018 are used. the total number of reports are 5,600, and 3,074 reports, which accounts about 55% of the total, is designated as a training set, and other 45% of reports are designated as a testing set. Before constructing the model, all reports of a training set are classified by stocks, and their entities are extracted using named entity recognition tool which is the KKMA. for each stocks, top 100 entities based on appearance frequency are selected, and become vectorized using one-hot encoding. After that, by using neural tensor network, the same number of score functions as stocks are trained. Thus, if a new entity from a testing set appears, we can try to calculate the score by putting it into every single score function, and the stock of the function with the highest score is predicted as the related item with the entity. To evaluate presented models, we confirm prediction power and determining whether the score functions are well constructed by calculating hit ratio for all reports of testing set. As a result of the empirical study, the presented model shows 69.3% hit accuracy for testing set which consists of 2,526 reports. this hit ratio is meaningfully high despite of some constraints for conducting research. Looking at the prediction performance of the model for each stocks, only 3 stocks, which are LG ELECTRONICS, KiaMtr, and Mando, show extremely low performance than average. this result maybe due to the interference effect with other similar items and generation of new knowledge. In this paper, we propose a methodology to find out key entities or their combinations which are necessary to search related information in accordance with the user's investment intention. Graph data is generated by using only the named entity recognition tool and applied to the neural tensor network without learning corpus or word vectors for the field. From the empirical test, we confirm the effectiveness of the presented model as described above. However, there also exist some limits and things to complement. Representatively, the phenomenon that the model performance is especially bad for only some stocks shows the need for further researches. Finally, through the empirical study, we confirmed that the learning method presented in this study can be used for the purpose of matching the new text information semantically with the related stocks.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.11 no.3
• /
• pp.1-15
• /
• 2016

This study has analyzed predication capabilities leveraging multi-variate model, logistic regression model, and artificial neural network model based on financial information of medium-small sized companies list in KOSDAQ. 83 delisted companies from 2009 to 2012 and 83 normal companies, i.e. 166 firms in total were sampled for the analysis. Modelling with training data was mobilized for 100 companies inlcuding 50 delisted ones and 50 normal ones at random out of the 166 companies. The rest of samples, 66 companies, were used to verify accuracies of the models. Each model was designed by carrying out T-test with 79 financial ratios for the last 5 years and identifying 9 significant variables. T-test has shown that financial profitability variables were major variables to predict a financial risk at an early stage, and financial stability variables and financial cashflow variables were identified as additional significant variables at a later stage of insolvency. When predication capabilities of the models were compared, for training data, a logistic regression model exhibited the highest accuracy while for test data, the artificial neural networks model provided the most accurate results. There are differences between the previous researches and this study as follows. Firstly, this study considered a time-series aspect in light of the fact that failure proceeds gradually. Secondly, while previous studies constructed a multivariate discriminant model ignoring normality, this study has reviewed the regularity of the independent variables, and performed comparisons with the other models. Policy implications of this study is that the reliability for the disclosure documents is important because the simptoms of firm's fail woule be shown on financial statements according to this paper. Therefore institutional arragements for restraing moral laxity from accounting firms or its workers should be strengthened.

• Journal of Life Science
• /
• v.18 no.8
• /
• pp.1132-1139
• /
• 2008

A CpG island is a short stretch of DNA in which the frequency of the CG dinucleotide is higher than other regions. CpG islands are present in the promoters and exonic regions of approximately $30{\sim}60$% of mammalian genes so they are useful markers for genes in organisms containing 5-methylcytosine in their genomes. Recent evidence supports the notion that the hypermethylation of CpG island, by silencing tumor suppressor genes, plays a major causal role in cancer, which has been described in almost every tumor types. In this respect, CpG island search by computational methods is very helpful for cancer research and computational promoter and gene predictions. I therefore developed a window program (called CpGi) on the basis of CpG island criteria defined by D. Takai and P. A. Jones. The program 'CpGi' was implemented in Visual C++ 6.0 and can determine the locations of CpG islands using diverse parameters (%GC, Obs (CpG)/Exp (CpG), window size, step size, gap value, # of CpG, length) specified by user. The analysis result of CpGi provides a graphical map of CpG islands and G+C% plot, where more detailed information on CpG island can be obtained through pop-up window. Two human contigs, i.e. AP00524 (from chromosome 22) and NT_029490.3 (from chromosome 21), were used to compare the performance of CpGi and two other public programs for the accuracy of search results. The two other programs used in the performance comparison are Emboss-CpGPlot and CpG Island Searcher that are web-based public CpG island search programs. The comparison result showed that CpGi is on a level with or outperforms Emboss-CpGPlot and CpG Island Searcher. Having a simple and easy-to-use user interface, CpGi would be a very useful tool for genome analysis and CpG island research. To obtain a copy of CpGi for academic use only, contact corresponding author.

• Journal of Biomedical Engineering Research
• /
• v.28 no.2
• /
• pp.235-243
• /
• 2007

Hepatocellular carcinoma is significant worldwide public health problem with an estimated annually mortality of 1,000,000 people. Radiofrequency (RF) ablation is an interventional technique that in recent years has come to be used for treatment of the hepatocellualr carcinoma, by destructing tumor tissues in high temperatures. Numerous studies have been attempted to prove excellence of RF ablation and to improve its efficiency by various methods. However, the attempts are sometimes paradox to advantages of a minimum invasive characteristic and an operative simplicity in RF ablation. The aim of the current study is, therefore, to suggest an improved RF ablation technique by identifying an optimum RF pattern, which is one of important factors capable of controlling the extent of high temperature region in lossless of the advantages of RF ablation. Three-dimensional finite element (FE) model was developed and validated comparing with the results reported by literature. Four representative Rf patterns (sine, square, exponential, and simulated RF waves), which were corresponding to currents fed during simulated RF ablation, were investigated. Following parameters for each RF pattern were analyzed to identify which is the most optimum in eliminating effectively tumor tissues. 1) maximum temperature, 2) a degree of alteration of maximum temperature in a constant time range (30-40 second), 3) a domain of temperature over $47^{\circ}C$ isothermal temperature (IT), and 4) a domain inducing over 63% cell damage. Here, heat transfer characteristics within the tissues were determined by Bioheat Governing Equation. Developed FE model showed 90-95% accuracy approximately in prediction of maximum temperature and domain of interests achieved during RF ablation. Maximum temperatures for sine, square, exponential, and simulated RF waves were $69.0^{\circ}C,\;66.9^{\circ}C,\;65.4^{\circ}C,\;and\;51.8^{\circ}C$, respectively. While the maximum temperatures were decreased in the constant time range, average time intervals for sine, square, exponential, and simulated RE waves were $0.49{\pm}0.14,\;1.00{\pm}0.00,\;1.65{\pm}0.02,\;and\;1.66{\pm}0.02$ seconds, respectively. Average magnitudes of the decreased maximum temperatures in the time range were $0.45{\pm}0.15^{\circ}C$ for sine wave, $1.93{\pm}0.02^{\circ}C$ for square wave, $2.94{\pm}0.05^{\circ}C$ for exponential wave, and $1.53{\pm}0.06^{\circ}C$ for simulated RF wave. Volumes of temperature domain over $47^{\circ}C$ IT for sine, square, exponential, and simulated RF waves were 1480mm3, 1440mm3, 1380mm3, and 395mm3, respectively. Volumes inducing over 63% cell damage for sine, square, exponential, and simulated RF waves were 114mm3, 62mm3, 17mm3, and 0mm3, respectively. These results support that applying sine wave during RF ablation may be generally the most optimum in destructing effectively tumor tissues, compared with other RF patterns.

• Journal of Food Hygiene and Safety
• /
• v.26 no.1
• /
• pp.25-30
• /
• 2011

In this study, predictive mathematical models were developed to predict the kinetics of Listeria monocytogenes growth in the mixed fresh-cut vegetables, which is the most popular ready-to-eat food in the world, as a function of temperature (4, 10, 20 and $30^{\circ}C$). At the specified storage temperatures, the primary growth curve fit well ($r^2$=0.916~0.981) with a Gompertz and Baranyi equation to determine the specific growth rate (SGR). The Polynomial model for natural logarithm transformation of the SGR as a function of temperature was obtained by nonlinear regression (Prism, version 4.0, GraphPad Software). As the storage temperature decreased from $30^{\circ}C$ to $4^{\circ}C$, the SGR decreased, respectively. Polynomial model was identified as appropriate secondary model for SGR on the basis of most statistical indices such as mean square error (MSE=0.002718 by Gompertz, 0.055186 by Baranyi), bias factor (Bf=1.050084 by Gompertz, 1.931472 by Baranyi) and accuracy factor (Af=1.160767 by Gompertz, 2.137181 by Baranyi). Results indicate L. monocytogenes growth was affected by temperature mainly, and equation was developed by Gompertz model (-0.1606+$0.0574^*Temp$+$0.0009^*Temp^*Temp$) was more effective than equation was developed by Baranyi model (0.3502-$0.0496^*Temp$+$0.0022^*Temp^*Temp$) for specific growth rate prediction of L.monocytogenes in the mixed fresh-cut vegetables.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_1
• /
• pp.763-774
• /
• 2020

Wind data forecasted from the numerical weather prediction (NWP) model is generally used as the first-guess of the target tracking process to obtain the atmospheric motion vectors(AMVs) because it increases tracking accuracy and reduce computational time. However, there is a contradiction that the NWP model used as the first-guess is used again as the reference in the AMVs verification process. To overcome this problem, model-independent first guesses are required. In this study, we propose the AMVs derivation from Lucas and Kanade optical flow method and then using it as the first guess. To retrieve AMVs, Himawari-8/AHI geostationary satellite level-1B data were used at 00, 06, 12, and 18 UTC from August 19 to September 5, 2015. To evaluate the impact of applying the optical flow method on the AMV derivation, cross-validation has been conducted in three ways as follows. (1) Without the first-guess, (2) NWP (KMA/UM) forecasted wind as the first-guess, and (3) Optical flow method based wind as the first-guess. As the results of verification using ECMWF ERA-Interim reanalysis data, the highest precision (RMSVD: 5.296-5.804 ms^-1) was obtained using optical flow based winds as the first-guess. In addition, the computation speed for AMVs derivation was the slowest without the first-guess test, but the other two had similar performance. Thus, applying the optical flow method in the target tracking process of AMVs algorithm, this study showed that the optical flow method is very effective as a first guess for model-independent AMVs derivation.

• Journal of Animal Science and Technology
• /
• v.55 no.5
• /
• pp.343-349
• /
• 2013

Data including 1,372,050 milk records pertaining to 438,019 cows from 1983 to 2011 collected during performance tests conducted by the National Livestock Cooperative Dairy Improvement Center were used to calculate milk income and profit of individuals and investigate the effects of production levels of early lactation (parity 1 and 2, respectively). Individuals with a moderate level of early lactation stayed longer in herds. Among parity 1, the 9,000 kg or higher group had a lower mean number of lactations than the overall mean of 3.13. The 7,000 kg or lower and 10,000 kg or higher groups had lower mean life time milking days than the overall mean of 1,076.8 days. Standard deviations of lifetime traits tended to decrease as production levels increased. For parity 2, the 11,000 kg or higher group had a lower mean number of lactation than the overall mean of 3.43. The lifetime milking days was highest in the 12,000 kg group (1,212.0 days), and generally smaller in the lower groups. Profit increased as the production level of groups increased for both parity 1 and 2. In groups with low production levels, profit of parity 1 was higher than that of parity 2, while the reverse was true in groups with high production levels. These results suggest that individuals in the low production groups had a greater likelihood to be culled due to reproductive or other problems. Furthermore, the accuracy of the prediction of lifetime profit of individuals with a milk yield of 305 days seems to be higher for parity 2 than parity 1; therefore, it is desirable to predict lifetime profit using the 305d milk yield of parity 2. In conclusion, breeding goals are based on many factors in functions for the estimation of profit; however, production levels during early lactation (parity 1 and 2) can be used as indicators of profit to extend profitability.

• Korean Journal of Ecology and Environment
• /
• v.49 no.3
• /
• pp.197-207
• /
• 2016

This study aims at providing basic data to objectively evaluate the areas suitable for reintroduction of the species of Asiatic black bear (Ursus thibetanus) in order to effectively preserve the Asiatic black bears in the Korean protection areas including national parks, and for the species restoration success. To this end, this study predicted the potential habitats in East Asia, Southeast Asia and India, where there are the records of Asiatic black bears' appearances using the Maxent model and environmental variables related with climate, topography, road and land use. In addition, this study evaluated the effects of the relevant climate and environmental variables. This study also analyzed inhabitation range area suitable for Asiatic black and geographic change according to future climate change. As for the judgment accuracy of the Maxent model widely utilized for habitat distribution research of wildlife for preservation, AUC value was calculated as 0.893 (sd=0.121). This was useful in predicting Asiatic black bears' potential habitat and evaluate the habitat change characteristics according to future climate change. Compare to the distribution map of Asiatic black bears evaluated by IUCN, Habitat suitability by the Maxent model were regionally diverse in extant areas and low in the extinct areas from IUCN map. This can be the result reflecting the regional difference in the environmental conditions where Asiatic black bears inhabit. As for the environment affecting the potential habitat distribution of Asiatic black bears, inhabitation rate was the highest, according to land coverage type, compared to climate, topography and artificial factors like distance from road. Especially, the area of deciduous broadleaf forest was predicted to be preferred, in comparison with other land coverage types. Annual mean precipitation and the precipitation during the driest period were projected to affect more than temperature's annual range, and the inhabitation possibility was higher, as distance was farther from road. The reason is that Asiatic black bears are conjectured to prefer more stable area without human's intervention, as well as prey resource. The inhabitation range was predicted to be expanded gradually to the southern part of India, China's southeast coast and adjacent inland area, and Vietnam, Laos and Malaysia in the eastern coastal areas of Southeast Asia. The following areas are forecast to be the core areas, where Asiatic black bears can inhabit in the Asian region: Jeonnam, Jeonbuk and Gangwon areas in South Korea, Kyushu, Chugoku, Shikoku, Chubu, Kanto and Tohoku's border area in Japan, and Jiangxi, Zhejiang and Fujian border area in China. This study is expected to be used as basic data for the preservation and efficient management of Asiatic black bear's habitat, artificially introduced individual bear's release area selection, and the management of collision zones with humans.