• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• Asia pacific journal of information systems
• /
• v.17 no.3
• /
• pp.105-130
• /
• 2007

Recently, there is a substantial interest in implementing Business Process Management System(BPMS) among enterprises with the purpose of business process innovation. BPMS redesigns and coordinates business processes in terms of both automated steps and human involvement in order to maximize the value of both involved people and systems. The reason why BPMS is getting attention from top managers is that it has the possibility to optimize the business processes by cycling the process of modeling, execution, monitoring, evaluation, and redesigning work processes. Thus, it has created high expectations about not only productivity improvement but also business process innovation. However. having an innovative nature, which is used for process innovation, BPMS implementation has great potential to stir up employee resistance. The analysis and the discussion about the prevention of the resistance against IS(Information Systems) is important because IS change the way people work and also alter the power structure within the organization, in general. The purpose of this study is to investigate factors that have an impact on the effective adoption of BPMS at the enterprise level. To find out these factors, this study considers two characteristics of BPMS: First. BPMS shares some characteristics with other enterprise-wide IS such as ERP. Second, it has special BPMS-specific characteristics. Due to the lack of previous research on BPMS adoption, interviews were carried out with IT-consultants and CIOs who conducted BPMS projects previously to find out BPMS-specific features that would make BPMS unique when compared to other enterprise-wide IS. As a result, the monitoring function was chosen as the main BPMS-specific factor. Thus, this paper reviewed studies both on enterprise-wide IS adoptions, which applied Technology Acceptance Model (TAM) and secondly on computer based monitoring to find out factors that would influence the employees' perception on the monitoring function of BPMS. Based on the literature review, the study suggested three factors that would have an impact on the employee's perception of the monitoring function: fairness of enterprise evaluation system, fairness of the boss, and self-efficacy of their work. Three factors that would impact the enterprise-wide IS adoption were also set: the shared belief in the benefit of BPMS, training, and communication. Then, these factors were integrated with TAM. Structural equation modeling was used to test hypotheses, out factors that would impact the employees' perception on the monitoring function of BPMS. Based on the literature review the study suggested three factors that would have an impact on the employee's perception of the monitoring function: fairness of enterprise evaluation system, fairness of the boss, and self-efficacy of their work. Three factors that would impact the enterprise-wide IS adoption were also set: the shared belief in the benefit of BPMS, training, and communication. Then, these factors were integrated with TAM. Structural equation modeling was used to test hypotheses. The data analysis results showed that two among three monitoring function related factors - enterprise evaluation system and fairness of the boss - were significant. This implies that employees would worry less about the BPMS implementation as long as they perceive the monitoring results will be used fairly for their performance evaluation. However, employees' high self-efficacy on their job was not a significant factor in their perception of the usefulness of BPMS. This is related to cases that showed employees resisted against the information systems because they automated their works (Markus, 1983). One specific case was an electronic company, where the accounting department workers were requested to redefine their job because their working processes were automated due to BPMS implementation.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.141-154
• /
• 2014

The adoption of International Financial Reporting Standards (IFRS) is the one of important issues in the recent accounting research because the change from local GAAP (Generally Accepted Accounting Principles) to IFRS has a substantial effect on accounting information. Over 100 countries including Australia, China, Canada and the European Union member countries adopt IFRS (International Financial Reporting Standards) for financial reporting purposes, and several more including the United States and Japan are considering the adoption of IFRS (International Financial Reporting Standards). In Korea, 61 firms voluntarily adopted Korean International Financial Reporting Standard (K-IFRS) in 2009 and 2010 and all listed firms mandatorily adopted K-IFRS (Korea-International Financial Reporting Standards) in 2011. The adoption of IFRS is expected to increase financial statement comparability, improve corporate transparency, increase the quality of financial reporting, and hence, provide benefits to investors This study investigates whether recognized accounts receivable discounting (AR discounting) under Korean International Financial Reporting Standard (K-IFRS) is more value relevant than disclosed AR discounting under Korean Generally Accepted Accounting Principles (K-GAAP). Because more rigorous standards are applied to the derecognition of AR discounting under K-IFRS(Korea-International Financial Reporting Standards), most AR discounting is recognized as a short term debt instead of being disclosed as a contingent liability unless all risks and rewards are transferred. In this research, I try to figure out industrial responses to the changes in accounting rules for the treatment of accounts receivable toward more strict standards in the recognition of sales which occurs with the adoption of Korea International Financial Reporting Standard. This study examines whether accounting information is more value-relevant, especially information on accounts receivable discounting (hereinafter, AR discounting) is value-relevant under K-IFRS (Korea-International Financial Reporting Standards). First, note that AR discounting involves the transfer of financial assets. Under Korean Generally Accepted Accounting Principles (K-GAAP), when firms discount AR to banks before the AR maturity, firms conventionally remove AR from the balance-sheet and report losses from AR discounting and disclose and explain the transactions in the footnotes. Under K-IFRS (Korea-International Financial Reporting Standards), however, most firms keep AR and add a short-term debt as same as discounted AR. This process increases the firms' leverage ratio and raises the concern to the firms about investors' reactions to worsening capital structures. Investors may experience the change in perceived risk of the firm. In the study sample, the average of AR discounting is 75.3 billion won (maximum 3.6 trillion won and minimum 18 million won), which is, on average 7.0% of assets (maximum 38.6% and minimum 0.002%), 26.2% of firms' accounts receivable (maximum 92.5% and minimum 0.003%) and 13.5% of total liabilities (maximum 69.5% and minimum 0.004%). After the adoption of K-IFRS (Korea-International Financial Reporting Standards), total liabilities increase by 13%p on average (maximum 103%p and minimum 0.004%p) attributable to AR discounting. The leverage ratio (total liabilities/total assets) increases by an average 2.4%p (maximum 16%p and minimum 0.001%p) and debt-to-equity ratio increases by average 14.6%p (maximum 134%p and minimum 0.006%) attributable to the recognition of AR discounting as a short-term debt. The structure of debts and equities of the companies engaging in factoring transactions are likely to be affected in the changes of accounting rule. I suggest that the changes in accounting provisions subsequent to Korea International Financial Reporting Standard adoption caused significant influence on the structure of firm's asset and liabilities. Due to this changes, the treatment of account receivable discounting have become critical. This paper proposes an intelligent diagnostic system for estimating negative impact on stock value with self-organizing maps and case based reasoning. To validate the usefulness of this proposed model, real data was analyzed. In order to get the significance of this proposed model, several models were compared to the research model. I found out that this proposed model provides satisfactory results with compared models.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.187-201
• /
• 2011

KOSPI200 index is the Korean stock price index consisting of actively traded 200 stocks in the Korean stock market. Its base value of 100 was set on January 3, 1990. The Korea Exchange (KRX) developed derivatives markets on the KOSPI200 index. KOSPI200 index futures market, introduced in 1996, has become one of the most actively traded indexes markets in the world. Traders can make profit by entering a long position on the KOSPI200 index futures contract if the KOSPI200 index will rise in the future. Likewise, they can make profit by entering a short position if the KOSPI200 index will decline in the future. Basically, KOSPI200 index futures trading is a short-term zero-sum game and therefore most futures traders are using technical indicators. Advanced traders make stable profits by using system trading technique, also known as algorithm trading. Algorithm trading uses computer programs for receiving real-time stock market data, analyzing stock price movements with various technical indicators and automatically entering trading orders such as timing, price or quantity of the order without any human intervention. Recent studies have shown the usefulness of artificial intelligent systems in forecasting stock prices or investment risk. KOSPI200 index data is numerical time-series data which is a sequence of data points measured at successive uniform time intervals such as minute, day, week or month. KOSPI200 index futures traders use technical analysis to find out some patterns on the time-series chart. Although there are many technical indicators, their results indicate the market states among bull, bear and flat. Most strategies based on technical analysis are divided into trend following strategy and non-trend following strategy. Both strategies decide the market states based on the patterns of the KOSPI200 index time-series data. This goes well with Markov model (MM). Everybody knows that the next price is upper or lower than the last price or similar to the last price, and knows that the next price is influenced by the last price. However, nobody knows the exact status of the next price whether it goes up or down or flat. So, hidden Markov model (HMM) is better fitted than MM. HMM is divided into discrete HMM (DHMM) and continuous HMM (CHMM). The only difference between DHMM and CHMM is in their representation of state probabilities. DHMM uses discrete probability density function and CHMM uses continuous probability density function such as Gaussian Mixture Model. KOSPI200 index values are real number and these follow a continuous probability density function, so CHMM is proper than DHMM for the KOSPI200 index. In this paper, we present an artificial intelligent trading system based on CHMM for the KOSPI200 index futures system traders. Traders have experienced on technical trading for the KOSPI200 index futures market ever since the introduction of the KOSPI200 index futures market. They have applied many strategies to make profit in trading the KOSPI200 index futures. Some strategies are based on technical indicators such as moving averages or stochastics, and others are based on candlestick patterns such as three outside up, three outside down, harami or doji star. We show a trading system of moving average cross strategy based on CHMM, and we compare it to a traditional algorithmic trading system. We set the parameter values of moving averages at common values used by market practitioners. Empirical results are presented to compare the simulation performance with the traditional algorithmic trading system using long-term daily KOSPI200 index data of more than 20 years. Our suggested trading system shows higher trading performance than naive system trading.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.

• Radiation Oncology Journal
• /
• v.18 no.1
• /
• pp.67-72
• /
• 2000

Background :The authors have developed a Digital image chart(DIC) and digital Radiotherapy Record System (DRRS). We have evaluated the DIC and DRRS for reliability, usefulness, ease of use, and efficiency. Materials and Methods :The basic design of the DIC and DRRS was to build an digital image database of radiation therapy Patient records for a more efficient and timely flow of critical image information throughout the department. This system is a submit of comprehensive radiation oncology management system (C-ROMS) and composed of a picture archiving and communication system (PACS), a radiotherapy information database, and a radiotherapy imaging database. The DIC and DRRS were programmed using Delphi under a Windows 95 environment and is capable of displaying the digital images of patients identification photos, simulation films, radiotherapy setup, diagnostic radiology images, gross lesion Photos, and radiotherapy Planning isodose charts with beam arrangements. Twenty-three clients in the department are connected by Ethernet (10 Mbps) to the central image server (Sun Ultra-sparc 1 workstation). Results :From the introduction of this system in February 1998 through December 1999, we have accumulated a total of 15,732 individual images for 2,556 patients. We can organize radiation therapy in a 'paperless' environment in 120 patients with breast cancer. Using this system, we have succeeded in the prompt, accurate, and simultaneous access to patient care information from multiple locations throughout the department. This coordination has resulted in improved operational efficiency within the department. Conclusion :The authors believe that the DIC and DRRS has contributed to the improvement of radiation oncology department efficacy as well as to time and resource savings by providing necessary visual information throughout the department conveniently and simultaneously. As a result, we can also achieve the 'paperless' and 'filmless' practice of radiation oncology with this system.

• Journal of Korean Society of Forest Science
• /
• v.108 no.3
• /
• pp.382-391
• /
• 2019

This study was conducted to verify whether smartphone hiking apps, which generate social network data including location information, are useful tools for analyzing the use characteristics of a forest recreation area. For this purpose, the study identified the functions and service characteristics of smartphone hiking apps. Also, the use characteristics of the area of Daegwallyoung were analyzed, compared with the results of the field survey, and the applicability of hiking apps was reviewed. As a result, the service types of hiking apps were analyzed in terms of three categories: "information offering," "hiking record," and "information sharing." This study focused on an app that is one of the "hiking record" types with the greatest number of users. Analysis of the data from hiking apps and a field survey in the Daegwallyoung area showed that both hiking apps and the field survey can be used to identify the movement patterns, but hiking apps based on a global positioning system (GPS) are more efficient and objective tools for understanding the use patterns in a forest recreation area, as well as for extracting user-generated photos. Second, although it is advantageous to analyze the patterns objectively through the walking-speed data generated, field surveys and observation are needed as complements for understanding the types of activities in each space. The hiking apps are based on cellphone use and are specific to "hiking" use, so user bias can limit the usefulness of the data. It is significant that this research shows the applicability of hiking apps for analyzing the use patterns of forest recreation areas through the location-based social network data of app users who record their hiking information voluntarily.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.97-113
• /
• 2016

Due to the growth of internet data and the rapid development of internet technology, "big data" analysis is actively conducted to analyze enormous data for various purposes. Especially in recent years, a number of studies have been performed on the applications of text mining techniques in order to overcome the limitations of existing structured data analysis. Various studies on sentiment analysis, the part of text mining techniques, are actively studied to score opinions based on the distribution of polarity of words in documents. Usually, the sentiment analysis uses sentiment dictionary contains positivity and negativity of vocabularies. As a part of such studies, this study tries to construct sentiment dictionary which is customized to specific data domain. Using a common sentiment dictionary for sentiment analysis without considering data domain characteristic cannot reflect contextual expression only used in the specific data domain. So, we can expect using a modified sentiment dictionary customized to data domain can lead the improvement of sentiment analysis efficiency. Therefore, this study aims to suggest a way to construct customized dictionary to reflect characteristics of data domain. Especially, in this study, movie review data are divided by genre and construct genre-customized dictionaries. The performance of customized dictionary in sentiment analysis is compared with a common sentiment dictionary. In this study, IMDb data are chosen as the subject of analysis, and movie reviews are categorized by genre. Six genres in IMDb, 'action', 'animation', 'comedy', 'drama', 'horror', and 'sci-fi' are selected. Five highest ranking movies and five lowest ranking movies per genre are selected as training data set and two years' movie data from 2012 September 2012 to June 2014 are collected as test data set. Using SO-PMI (Semantic Orientation from Point-wise Mutual Information) technique, we build customized sentiment dictionary per genre and compare prediction accuracy on review rating. As a result of the analysis, the prediction using customized dictionaries improves prediction accuracy. The performance improvement is 2.82% in overall and is statistical significant. Especially, the customized dictionary on 'sci-fi' leads the highest accuracy improvement among six genres. Even though this study shows the usefulness of customized dictionaries in sentiment analysis, further studies are required to generalize the results. In this study, we only consider adjectives as additional terms in customized sentiment dictionary. Other part of text such as verb and adverb can be considered to improve sentiment analysis performance. Also, we need to apply customized sentiment dictionary to other domain such as product reviews.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.1
• /
• pp.3-9
• /
• 2011

Purpose: Generally dual energy X-ray absorptiometry has been used for the purpose of evaluation of osteoporosis and treatment. Recently the interest of obesity came to be high and body percent fat test is increasing. Existing measure of body fat have to scan the whole body can be evaluated, but only lumbar spine and hip measurements was assumed to be whole body fat as well as improving the software. It tries to check whether the part measured value not being whole body measurement has the validity or not compared with the value calculated with the method that it is different, it forgives through a correlation with a (BIA) and (BMI). Materials and Methods: In 2010, the body percent fat was measured among the examinee coming to the Asan Medical Center public health care center from March till August against 90 females more than 40 years old through (DXA) and BIA. BMI utilized the value which wrote an hight and weight measured through the body measuring instrument in the examinee information and is automatically calculated. In addition, it classified as the low weight ($13-18.5kg/m^2$), normal ($18.5-25kg/m^2$), and corpulence ($25-30kg/m^2$) based on BMI and so that it could check whether there was the difference according to the weight or not BMI and BIA and correlation between DXA were analyzed in each group. The statistical program for the analysis used SPSS 12.0. Results: The comparison of DXA at 3 which it divides into the low weight and normal and corpulence groups and BIA did not show the difference noted statistically in all groups and the between group comparison was exposed to do not have a meaning. The body percent fat measured by the correlation analysis result DXA at the state that it doesn't divide into the group showed the high correlation (r=0.908, p0.01) noted statistically compared with BMI and showed the high correlation noted statistically in a comparison with BIA (r=0.927, p0.01). Conclusion: It confirmed that the whole body percent fat presumed from the part bone density measurement showed the excel correlation compared with BIA and BMI and information is high. There is still no clear standard about the presumed whole body percent fat and it is difficult to evaluate the fat evaluation by the bone mineral density measurement. However, it is determined that the information offering which is more objective through the comparative study with the body percent fat which is very efficient and in that it can obtain till the information about a fat as well as diagnosis of the osteoporosis through the bone density checkup is measured by the afterward telegraph bone density checkup and is clinically useful is possible.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.10 no.1
• /
• pp.8-14
• /
• 2012

Purpose: The Tox-Info system is a poisonous substance information database developed by the Korean National Institute of Food and Drug Safety Evaluation. The aim of this study was to estimate the coverage effectiveness of the Tox-Info system by comparing the toxic substances included in the database with the distribution of the toxic substances implicated in the cases of intoxicated patients presenting to emergency departments. The secondary aim of the study was to propose any additional substances that should be added to the database. Methods: We retrospectively reviewed the medical records of patients suffering with toxic exposure who had visited any of 12 selected emergency departments in Korea from January 2010 to December 2011. The identified toxic substances were classified into groups including prescription drugs, agricultural chemicals, household products, animals or plants, herbal drugs, and others. We calculated the coverage rate of the Tox-Info database relative to the number of intoxication cases and the type of toxic substances involved. Results: A total of 5,840 intoxicated patient records were collected. Their mean age was $46.6{\pm}20.5$ years and 56.2% were female. Of the total intoxication cases, 87.8% of the identified toxic substances were included in the Tox-Info database, while only 41.6% of all of the types of identified toxic substances were included. Broken down by category, 122 prescription drugs, 15 agricultural chemicals, 12 household products, 14 animals or plants and 2 herbal drugs involved in poisoning cases were not included in the Tox-info database. Conclusion: This study demonstrated the clinical usefulness of the Tox-Info system. While 87.8% of the substances involved in the cases were included in the Tox-Info database, the database should be continuously updated in order to include even the most uncommon toxic substances.