• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.133-148
• /
• 2014

Recently, with the advent of various information channels, the number of has continued to grow. The main cause of this phenomenon can be found in the significant increase of unstructured data, as the use of smart devices enables users to create data in the form of text, audio, images, and video. In various types of unstructured data, the user's opinion and a variety of information is clearly expressed in text data such as news, reports, papers, and various articles. Thus, active attempts have been made to create new value by analyzing these texts. The representative techniques used in text analysis are text mining and opinion mining. These share certain important characteristics; for example, they not only use text documents as input data, but also use many natural language processing techniques such as filtering and parsing. Therefore, opinion mining is usually recognized as a sub-concept of text mining, or, in many cases, the two terms are used interchangeably in the literature. Suppose that the purpose of a certain classification analysis is to predict a positive or negative opinion contained in some documents. If we focus on the classification process, the analysis can be regarded as a traditional text mining case. However, if we observe that the target of the analysis is a positive or negative opinion, the analysis can be regarded as a typical example of opinion mining. In other words, two methods (i.e., text mining and opinion mining) are available for opinion classification. Thus, in order to distinguish between the two, a precise definition of each method is needed. In this paper, we found that it is very difficult to distinguish between the two methods clearly with respect to the purpose of analysis and the type of results. We conclude that the most definitive criterion to distinguish text mining from opinion mining is whether an analysis utilizes any kind of sentiment lexicon. We first established two prediction models, one based on opinion mining and the other on text mining. Next, we compared the main processes used by the two prediction models. Finally, we compared their prediction accuracy. We then analyzed 2,000 movie reviews. The results revealed that the prediction model based on opinion mining showed higher average prediction accuracy compared to the text mining model. Moreover, in the lift chart generated by the opinion mining based model, the prediction accuracy for the documents with strong certainty was higher than that for the documents with weak certainty. Most of all, opinion mining has a meaningful advantage in that it can reduce learning time dramatically, because a sentiment lexicon generated once can be reused in a similar application domain. Additionally, the classification results can be clearly explained by using a sentiment lexicon. This study has two limitations. First, the results of the experiments cannot be generalized, mainly because the experiment is limited to a small number of movie reviews. Additionally, various parameters in the parsing and filtering steps of the text mining may have affected the accuracy of the prediction models. However, this research contributes a performance and comparison of text mining analysis and opinion mining analysis for opinion classification. In future research, a more precise evaluation of the two methods should be made through intensive experiments.

• Journal of Korea Water Resources Association
• /
• v.56 no.9
• /
• pp.543-551
• /
• 2023

Snow is an essential climate factor that affects the climate system and surface energy balance, and it also has a crucial role in water balance by providing solid water stored during the winter for spring runoff and groundwater recharge. In this study, statistical analysis of Local Data Assimilation and Prediction System (LDAPS), Modern.-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2), and ERA5-Land snow depth data were used to evaluate the applicability in South Korea. The statistical analysis between the Automated Synoptic Observing System (ASOS) ground observation data provided by the Korea Meteorological Administration (KMA) and the reanalysis data showed that LDAPS and ERA5-Land were highly correlated with a correlation coefficient of more than 0.69, but LDAPS showed a large error with an RMSE of 0.79 m. In the case of MERRA-2, the correlation coefficient was lower at 0.17 because the constant value was estimated continuously for some periods, which did not adequately simulate the increase and decrease trend between data. The statistical analysis of LDAPS and ASOS showed high and low performance in the nearby Gangwon Province, where the average snowfall is relatively high, and in the southern region, where the average snowfall is low, respectively. Finally, the error variance between the four independent snow depth data used in this study was calculated through triple collocation (TC), and a merged snow depth data was produced through weighting factors. The reanalyzed data showed the highest error variance in the order of LDAPS, MERRA-2, and ERA5-Land, and LDAPS was given a lower weighting factor due to its higher error variance. In addition, the spatial distribution of ERA5-Land snow depth data showed less variability, so the TC-merged snow depth data showed a similar spatial distribution to MERRA-2, which has a low spatial resolution. Considering the correlation, error, and uncertainty of the data, the ERA5-Land data is suitable for snow-related analysis in South Korea. In addition, it is expected that LDAPS data, which is highly correlated with other data but tends to be overestimated, can be actively utilized for high-resolution representation of regional and climatic diversity if appropriate corrections are performed.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.19-26
• /
• 2023

Humans have adapted and evolved to natural light. However, as humans stay in indoor longer in modern times, the problem of biorhythm disturbance has been induced. To solve this problem, research is being conducted on lighting that reproduces the correlated color temperature(CCT) of natural light that varies from sunrise to sunset. In order to reproduce the CCT of natural light, multiple LED light sources with different CCTs are used to produce lighting, and then a control index DB is constructed by measuring and collecting the light characteristics of the combination of input currents for each light source in hundreds to thousands of steps, and then using it to control the lighting through the light characteristic matching method. The problem with this control method is that the more detailed the steps of the combination of input currents, the more time and economic costs are incurred. In this paper, an LED lighting control method that applies interpolation and combination calculation based on the minimum spectral power distribution information for each light source is proposed to reproduce the CCT of natural light. First, five minimum SPD information for each channel was measured and collected for the LED lighting, which consisted of light source channels with different CCTs and implemented input current control function of a 256-steps for each channel. Interpolation calculation was performed to generate SPD of 256 steps for each channel for the minimum SPD information, and SPD for all control combinations of LED lighting was generated through combination calculation of SPD for each channel. Illuminance and CCT were calculated through the generated SPD, a control index DB was constructed, and the CCT of natural light was reproduced through a matching technique. In the performance evaluation, the CCT for natural light was provided within the range of an average error rate of 0.18% while meeting the recommended indoor illumination standard.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of Distribution Research
• /
• v.17 no.1
• /
• pp.37-63
• /
• 2012

In franchise business, exclusive sales territory (sometimes EST in table) protection is a very important issue from an economic, social and political point of view. It affects the growth and survival of both franchisor and franchisee and often raises issues of social and political conflicts. When franchisee is not familiar with related laws and regulations, franchisor has high chance to utilize it. Exclusive sales territory protection by the manufacturer and distributors (wholesalers or retailers) means sales area restriction by which only certain distributors have right to sell products or services. The distributor, who has been granted exclusive sales territories, can protect its own territory, whereas he may be prohibited from entering in other regions. Even though exclusive sales territory is a quite critical problem in franchise business, there is not much rigorous research about the reason, results, evaluation, and future direction based on empirical data. This paper tries to address this problem not only from logical and nomological validity, but from empirical validation. While we purse an empirical analysis, we take into account the difficulties of real data collection and statistical analysis techniques. We use a set of disclosure document data collected by Korea Fair Trade Commission, instead of conventional survey method which is usually criticized for its measurement error. Existing theories about exclusive sales territory can be summarized into two groups as shown in the table below. The first one is about the effectiveness of exclusive sales territory from both franchisor and franchisee point of view. In fact, output of exclusive sales territory can be positive for franchisors but negative for franchisees. Also, it can be positive in terms of sales but negative in terms of profit. Therefore, variables and viewpoints should be set properly. The other one is about the motive or reason why exclusive sales territory is protected. The reasons can be classified into four groups - industry characteristics, franchise systems characteristics, capability to maintain exclusive sales territory, and strategic decision. Within four groups of reasons, there are more specific variables and theories as below. Based on these theories, we develop nine hypotheses which are briefly shown in the last table below with the results. In order to validate the hypothesis, data is collected from government (FTC) homepage which is open source. The sample consists of 1,896 franchisors and it contains about three year operation data, from 2006 to 2008. Within the samples, 627 have exclusive sales territory protection policy and the one with exclusive sales territory policy is not evenly distributed over 19 representative industries. Additional data are also collected from another government agency homepage, like Statistics Korea. Also, we combine data from various secondary sources to create meaningful variables as shown in the table below. All variables are dichotomized by mean or median split if they are not inherently dichotomized by its definition, since each hypothesis is composed by multiple variables and there is no solid statistical technique to incorporate all these conditions to test the hypotheses. This paper uses a simple chi-square test because hypotheses and theories are built upon quite specific conditions such as industry type, economic condition, company history and various strategic purposes. It is almost impossible to find all those samples to satisfy them and it can't be manipulated in experimental settings. However, more advanced statistical techniques are very good on clean data without exogenous variables, but not good with real complex data. The chi-square test is applied in a way that samples are grouped into four with two criteria, whether they use exclusive sales territory protection or not, and whether they satisfy conditions of each hypothesis. So the proportion of sample franchisors which satisfy conditions and protect exclusive sales territory, does significantly exceed the proportion of samples that satisfy condition and do not protect. In fact, chi-square test is equivalent with the Poisson regression which allows more flexible application. As results, only three hypotheses are accepted. When attitude toward the risk is high so loyalty fee is determined according to sales performance, EST protection makes poor results as expected. And when franchisor protects EST in order to recruit franchisee easily, EST protection makes better results. Also, when EST protection is to improve the efficiency of franchise system as a whole, it shows better performances. High efficiency is achieved as EST prohibits the free riding of franchisee who exploits other's marketing efforts, and it encourages proper investments and distributes franchisee into multiple regions evenly. Other hypotheses are not supported in the results of significance testing. Exclusive sales territory should be protected from proper motives and administered for mutual benefits. Legal restrictions driven by the government agency like FTC could be misused and cause mis-understandings. So there need more careful monitoring on real practices and more rigorous studies by both academicians and practitioners.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.109-125
• /
• 2020

The Ministry of National Defense is pushing for the Defense Acquisition Program to build strong defense capabilities, and it spends more than 10 trillion won annually on defense improvement. As the Defense Acquisition Program is directly related to the security of the nation as well as the lives and property of the people, it must be carried out very transparently and efficiently by experts. However, the excessive diversification of laws and regulations related to the Defense Acquisition Program has made it challenging for many working-level officials to carry out the Defense Acquisition Program smoothly. It is even known that many people realize that there are related regulations that they were unaware of until they push ahead with their work. In addition, the statutory statements related to the Defense Acquisition Program have the tendency to cause serious issues even if only a single expression is wrong within the sentence. Despite this, efforts to establish a sentence comparison system to correct this issue in real time have been minimal. Therefore, this paper tries to propose a "Comparison System between the Statement of Military Reports and Related Laws" implementation plan that uses the Siamese Network-based artificial neural network, a model in the field of natural language processing (NLP), to observe the similarity between sentences that are likely to appear in the Defense Acquisition Program related documents and those from related statutory provisions to determine and classify the risk of illegality and to make users aware of the consequences. Various artificial neural network models (Bi-LSTM, Self-Attention, D_Bi-LSTM) were studied using 3,442 pairs of "Original Sentence"(described in actual statutes) and "Edited Sentence"(edited sentences derived from "Original Sentence"). Among many Defense Acquisition Program related statutes, DEFENSE ACQUISITION PROGRAM ACT, ENFORCEMENT RULE OF THE DEFENSE ACQUISITION PROGRAM ACT, and ENFORCEMENT DECREE OF THE DEFENSE ACQUISITION PROGRAM ACT were selected. Furthermore, "Original Sentence" has the 83 provisions that actually appear in the Act. "Original Sentence" has the main 83 clauses most accessible to working-level officials in their work. "Edited Sentence" is comprised of 30 to 50 similar sentences that are likely to appear modified in the county report for each clause("Original Sentence"). During the creation of the edited sentences, the original sentences were modified using 12 certain rules, and these sentences were produced in proportion to the number of such rules, as it was the case for the original sentences. After conducting 1 : 1 sentence similarity performance evaluation experiments, it was possible to classify each "Edited Sentence" as legal or illegal with considerable accuracy. In addition, the "Edited Sentence" dataset used to train the neural network models contains a variety of actual statutory statements("Original Sentence"), which are characterized by the 12 rules. On the other hand, the models are not able to effectively classify other sentences, which appear in actual military reports, when only the "Original Sentence" and "Edited Sentence" dataset have been fed to them. The dataset is not ample enough for the model to recognize other incoming new sentences. Hence, the performance of the model was reassessed by writing an additional 120 new sentences that have better resemblance to those in the actual military report and still have association with the original sentences. Thereafter, we were able to check that the models' performances surpassed a certain level even when they were trained merely with "Original Sentence" and "Edited Sentence" data. If sufficient model learning is achieved through the improvement and expansion of the full set of learning data with the addition of the actual report appearance sentences, the models will be able to better classify other sentences coming from military reports as legal or illegal. Based on the experimental results, this study confirms the possibility and value of building "Real-Time Automated Comparison System Between Military Documents and Related Laws". The research conducted in this experiment can verify which specific clause, of several that appear in related law clause is most similar to the sentence that appears in the Defense Acquisition Program-related military reports. This helps determine whether the contents in the military report sentences are at the risk of illegality when they are compared with those in the law clauses.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.11
• /
• pp.281-290
• /
• 2020

With the spread of smartphones, services that want to use personalized data are increasing. In particular, healthcare-related services deal with a variety of data, and data visualization techniques are used to effectively show this. As data visualization techniques are used, interactions in visualization are also naturally emphasized. In the PC environment, since the interaction for data visualization is performed with a mouse, various filtering for data is provided. On the other hand, in the case of interaction in a mobile environment, the screen size is small and it is difficult to recognize whether or not the interaction is possible, so that only limited visualization provided by the app can be provided through a button touch method. In order to overcome the limitation of interaction in such a mobile environment, we intend to enable data visualization interactions through conversations with chatbots so that users can check individual data through various visualizations. To do this, it is necessary to convert the user's query into a query and retrieve the result data through the converted query in the database that is storing data periodically. There are many studies currently being done to convert natural language into queries, but research on converting user queries into queries based on visualization has not been done yet. Therefore, in this paper, we will focus on query generation in a situation where a data visualization technique has been determined in advance. Supported interactions are filtering on task x-axis values and comparison between two groups. The test scenario utilized data on the number of steps, and filtering for the x-axis period was shown as a bar graph, and a comparison between the two groups was shown as a line graph. In order to develop a natural language processing model that can receive requested information through visualization, about 15,800 training data were collected through a survey of 1,000 people. As a result of algorithm development and performance evaluation, about 89% accuracy in classification model and 99% accuracy in query generation model was obtained.

• Korean Security Journal
• /
• no.33
• /
• pp.51-80
• /
• 2012

This study is to summarize main contents which was mentioned by Beomseok Kim' doctoral dissertation. The purpose of this study focuses on presenting the outplacement countermeasure and retention level examination analysis about outplacement competency of special security government official through implement of questionnaire method. The questionnaire for retention level examination including four groups of outplacement competency and twenty subcategories was implemented in the object of six hundered persons relevant to outplacement more than forty age and five grade administration official of special security government officials, who have outplacement experiences as outplacement successors, outplacement losers, and outplacement expectants, in order to achieve this research purpose effectively. The questionnaire examination items are four groups of outplacement competency and twenty subcategories which are the group of knowledge competency & four subcategories including expert knowledge, outplacement knowledge, self comprehension, and organization comprehension, the group of skill competency & nine subcategories including job skill competency, job performance skill, problem-solving skill, reforming skill, communication skill, organization management skill, crisis management skill, career development skill, and human network application skill, the group of attitude-emotion competency & seven subcategories including positive attitude, active attitude, responsibility, professionalism, devoting-sacrificing attitude, affinity, and self-controlling ability, and the group of value-ethics competency & two subcategories including ethical consciousness and morality. The respondents highly regard twenty-two outplacement competency and they consider themselves well-qualified for the subcategories valued over 4.0 such as the professional knowledge, active attitude, responsibility, ethics and morality while they mark the other subcategories below average still need to be improved. Thus, the following is suggestions for successful outplacement. First, individual effort is essential to strengthen their capabilities based on accurate self evaluation, for which the awareness and concept need to be redefined to help them face up to the reality by readjusting career goal to a realistic level. Second, active career development plan to improve shortcoming in terms of outplacement competency is required. Third, it is necessary to establish the infrastructure related to outplacement training such as ON-OFF Line training system and facilities for learning to reinforce user-oriented outplacement training as a regular training course before during after the retirement.

• Journal of Korea Spatial Information System Society
• /
• v.6 no.1 s.11
• /
• pp.73-85
• /
• 2004

Recently, as the growth of the wireless Internet, PDA and HPC, the focus of research and development related with GIS(Geographic Information System) has been changed to the Real-Time Mobile GIS to service LBS. To offer LBS efficiently, there must be the Real-Time GIS platform that can deal with dynamic status of moving objects and a location index which can deal with the characteristics of location data. Location data can use the same data type(e.g., point) of GIS, but the management of location data is very different. Therefore, in this paper, we studied the Real-Time Mobile GIS using the HBR-tree to manage mass of location data efficiently. The Real-Time Mobile GIS which is developed in this paper consists of the HBR-tree and the Real-Time GIS Platform HBR-tree. we proposed in this paper, is a combined index type of the R-tree and the spatial hash Although location data are updated frequently, update operations are done within the same hash table in the HBR-tree, so it costs less than other tree-based indexes Since the HBR-tree uses the same search mechanism of the R-tree, it is possible to search location data quickly. The Real-Time GIS platform consists of a Real-Time GIS engine that is extended from a main memory database system. a middleware which can transfer spatial, aspatial data to clients and receive location data from clients, and a mobile client which operates on the mobile devices. Especially, this paper described the performance evaluation conducted with practical tests if the HBR-tree and the Real-Time GIS engine respectively.