• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.101-116
• /
• 2015

Recently, due to the development of smart devices and social media, vast amounts of information with the various forms were accumulated. Particularly, considerable research efforts are being directed towards analyzing unstructured big data to resolve various social problems. Accordingly, focus of data-driven decision-making is being moved from structured data analysis to unstructured one. Also, in the field of recommendation system, which is the typical area of data-driven decision-making, the need of using unstructured data has been steadily increased to improve system performance. Approaches to improve the performance of recommendation systems can be found in two aspects- improving algorithms and acquiring useful data with high quality. Traditionally, most efforts to improve the performance of recommendation system were made by the former approach, while the latter approach has not attracted much attention relatively. In this sense, efforts to utilize unstructured data from variable sources are very timely and necessary. Particularly, as the interests of users are directly connected with their needs, identifying the interests of the user through unstructured big data analysis can be a crew for improving performance of recommendation systems. In this sense, this study proposes the methodology of improving recommendation system by measuring interests of the user. Specially, this study proposes the method to quantify interests of the user by analyzing user's internet usage patterns, and to predict user's repurchase based upon the discovered preferences. There are two important modules in this study. The first module predicts repurchase probability of each category through analyzing users' purchase history. We include the first module to our research scope for comparing the accuracy of traditional purchase-based prediction model to our new model presented in the second module. This procedure extracts purchase history of users. The core part of our methodology is in the second module. This module extracts users' interests by analyzing news articles the users have read. The second module constructs a correspondence matrix between topics and news articles by performing topic modeling on real world news articles. And then, the module analyzes users' news access patterns and then constructs a correspondence matrix between articles and users. After that, by merging the results of the previous processes in the second module, we can obtain a correspondence matrix between users and topics. This matrix describes users' interests in a structured manner. Finally, by using the matrix, the second module builds a model for predicting repurchase probability of each category. In this paper, we also provide experimental results of our performance evaluation. The outline of data used our experiments is as follows. We acquired web transaction data of 5,000 panels from a company that is specialized to analyzing ranks of internet sites. At first we extracted 15,000 URLs of news articles published from July 2012 to June 2013 from the original data and we crawled main contents of the news articles. After that we selected 2,615 users who have read at least one of the extracted news articles. Among the 2,615 users, we discovered that the number of target users who purchase at least one items from our target shopping mall 'G' is 359. In the experiments, we analyzed purchase history and news access records of the 359 internet users. From the performance evaluation, we found that our prediction model using both users' interests and purchase history outperforms a prediction model using only users' purchase history from a view point of misclassification ratio. In detail, our model outperformed the traditional one in appliance, beauty, computer, culture, digital, fashion, and sports categories when artificial neural network based models were used. Similarly, our model outperformed the traditional one in beauty, computer, digital, fashion, food, and furniture categories when decision tree based models were used although the improvement is very small.

• Journal of the Society of Disaster Information
• /
• v.18 no.1
• /
• pp.202-217
• /
• 2022

Purpose: The recent increased use of Personal Mobility (PM) has been accompanied by a rise in the annual number of accidents. Accordingly, the safety requirements for PM use are being strengthened, but the laws/systems, infrastructure, and management systems remain insufficient for fostering a safe environment. Therefore, this study comprehensively searches the main problems and improvement methods through a review of previous studies that are related to PM. Then the priorities according to the importance of the improvement methods are presented through the Delphi survey. Method: The research method is mainly composed of a literature study and an expert survey (Delphi survey). Prior research and improvement cases (local governments, government departments, companies, etc.) are reviewed to derive problems and improvements, and a problem/improvement classification table is created based on keywords. Based on the classification contents, an expert survey is conducted to derive a priority improvement plan. Result: The PM-related problems were in 'non-compliance with traffic laws, lack of knowledge, inexperienced operation, and lack of safety awareness' in relation to human factors, and 'device characteristics, road-drivable space, road facilities, parking facilities' in relation to physical factors. 'Management/supervision, product management, user management, education/training' as administrative factors and legal factors are divided into 'absence/sufficiency of law, confusion/duplication, reduced effectiveness'. Improvement tasks related to this include 'PM education/public relations, parking/return, road improvement, PM registration/management, insurance, safety standards, traffic standards, PM device safety, PM supplementary facilities, enforcement/management, dedicated organization, service providers, management system, and related laws/institutional improvement', and 42 detailed tasks are derived for these 14 core tasks. The results for the importance evaluation of detailed tasks show that the tasks with a high overall average for the evaluation items of cost, time, effect, urgency, and feasibility were 'strengthening crackdown/instruction activities, education publicity/campaign, truancy PM management, and clarification of traffic rules'. Conclusion: The PM market is experiencing gradual growth based on shared services and a safe environment for PM use must be ensured along with industrial revitalization. In this respect, this study seeks out the major problems and improvement plans related to PM from a comprehensive point of view and prioritizes the necessary improvement measures. Therefore, it can serve as a basis of data for future policy establishment. In the future, in-depth data supplementation will be required for each key improvement area for practical policy application.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.4
• /
• pp.105-120
• /
• 2020

This study explores the process of the actual content production and distribution, by creating a YouTube channel to promote the popular music contents produced by the researcher, which thus reflects the reality where the production of video contents rapidly increases. A YouTube channel titled "Alida Music", of which the focus was to promote indie musicians, was created on February 2019. The contents of 10 indie musicians were produced in one-take live format. The information of the indie musicians was displayed in the form of a screen business card, with their e-mail address and SNS account at the top. Therefore, this promotional design was named "Card Live". Promotional video contents marked with the QR code in the lower right on the screen were produced, along with the promotional phrase "Communicate directly with the artist through the QR code", which allows viewers to watch other contents of the indie musician when they scan the QR code. This research conducted a study on how to improve and promote "Card Live" contents of "Alida Music", which were produced through this process. A group interview targeting five indie musicians, among whom one participant deemed significant was selected to conduct a one-to-one in-depth interview. As a result of the study, the following three conclusions were drawn. First, YouTube was found to be the medium with the greatest influence and highest efficiency at the lowest cost. Second, the evaluation of the participants on "Card Live" were divided into the three categories: need for one-take live, the design elements of "Card Live", and scanning issues of the QR code. Third, there is a need for promotional methods that can effectively utilize the media aspects of YouTube: the channel management issues such as raising public awareness as well as the number of subscribers of "Alida Music" should be resolved and measures to effectively use various media including other SNS should be developed. In terms of its content, it is imperative to recruit diverse performers to make various contents, as well as to come up with ways to link "Card Live" contents with offline. Based on these results, "Card Live" contents should be further revised and complemented in order to provide interesting contents to consumers, which will further develop "Alida Music" as a platform where various musicians and companies meet, thereby inducing contracts with popular music agencies and generating advertising revenues. However, since this study was carried out only with the limited number of participants, future studies should include more participants to bring forth a variety of promotional plans and improvement measures. Also, in the era of consuming contents through smart devices, the fact that some features of "Card Live" were available only on PC, did not fully reflect the characteristics of the times. In the future research, various contents that smartphone users can access and view freely without PC should be produced.

• Journal of the Korean Society of Earth Science Education
• /
• v.10 no.3
• /
• pp.262-277
• /
• 2017

Digital textbooks enable learning that is appropriate to the characteristics and level of learners through various interactions. The purpose of this study was to develop an instruction model that can more effectively use digital textbooks in elementary science classes and to verify its effectiveness. The results were as follows. The instruction model for helping learners complete their learning by using digital textbooks needs to receive diagnostic assessment and feedback on entry behavior, to build a self-directed learning environment, and to interact with teachers, students, and digital textbooks as scaffolding. In this study, we developed an instruction model using digital textbooks reflecting these characteristic. The instructional model consists of preparation, practice and solidity step. In the preparation step, the learner performs a diagnostic evaluation using digital textbooks. Based on the results, feedback provided at each level can complement the entry behavior and maintain interest in learning activities. In the practice step, self-directed learning is implemented using diverse functions of digital textbooks and various types of data. In the solidity step, learners can internalize the learning contents by reviewing video clips which are provided by teachers, performing problem-solving activities, and accessing outcomes accumulated by learners in the community online. In order to verify the effectiveness of this model, we selected the "Weather and our Life" unit. This experiment was conducted using 101 students in the 5th grade in B Elementary School in Gwangju Metropolitan City. In the experimental group, 50 students learned using a smart device that embodies digital textbooks applied with the instruction model. In the comparative group, 51 students were taught using the paper textbooks. The results were as follows. First, there was a significant effect on the improvement of the learning achievement in the experimental group with low academic ability compared with the comparative group with low academic ability. Second, there was a significant effect on self-directed learning attitude in the experimental group. Third, in the experimental group, the number of interactions with the learner, teacher, and digital textbook was higher than the comparative group. In conclusion, the digital textbooks based on the instruction model in elementary science classes developed in this study helped to improve learners' learning achievement and self-directed learning attitudes.

• 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.54 no.10
• /
• pp.835-848
• /
• 2021

In Jeju Island which has peculiarity for its geological features and hydrology system, hydrological factor analysis for the effective water management is necessary. Because in-situ hydro-meteorological data is affected by surrounding environment, the in-situ dataset could not be the spatially representative for the study area. For this reason, remote sensing data may be used to overcome the limit of the in-situ data. In this study, applicability assessment of MOD16 evapotranspiration data, Globas Land Data Assimilation System (GLDAS) based evapotranspiration/soil moisture data, and Advanced SCATterometer (ASCAT) soil moisture product which were evaluated their applicability on other study areas was conducted. In the case of evapotranspiration, comparison with total precipitation and flux-tower based evapotranspiration were conducted. And for soil moisture, 6 in-situ data and ASCAT soil moisture product were compared on each site. As a result, 57% of annual precipitation was calculated as evapotranspiration, and the correlation coefficient between MOD16 evapotranspiration and GLDAS evapotranspiration was 0.759, which was a robust value. The correlation coefficient was 0.434, indicating a relatively low fit. In the case of soil moisture, in the case of the GLDAS data, the RMSE value was less than 0.05 at all sites compared to the in-situ data, and a statistically significant result was obtained as a result of the significance test of the correlation coefficient. However, for satellite data, RMSE over than 0.05 were found at Wolgak and there was no correlation at Sehwa and Handong points. It is judged that the above results are due to insufficient quality control and spatial representation of the evapotranspiration and soil moisture sensors installed in Jeju Island. It is estimated as the error that appears when adjacent to the coast. Through this study, the necessity of improving the existing ground observation data of hydrometeorological factors is emphasized.

• Journal of Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.819-833
• /
• 2021

This study is to evaluate applicability of linkage modeling using PHABSIM (Physical Habitat Simulation System) and SWAT (Soil and Water Assessment Tool) and to estimate ecological flow for target fishes of Andong downstream (4,565.7 km²). The SWAT was established considering 2 multi purpose dam (ADD, IHD) and 1 streamflow gauging station (GD). The SWAT was calibrated and validated with 9 years (2012 ~ 2020) data of 1 stream (GD) and 2 multi-purpose dam (ADD, IHD). For streamflow and dam inflows (GD, ADD and IHD), R², NSE and RMSE were 0.52 ~ 0.74, 0.48 ~ 0.71, and 0.92 ~ 2.51 mm/day respectively. As a result of flow duration analysis for 9 years (2012 ~ 2020) using calibrated streamflow, the average Q185 and Q275 were 36.5 m³/sec (-1.4%) and 23.8 m³/sec (0%) respectively compared with the observed flow duration and were applied to flow boundary condition of PHABSIM. The target stream was selected as the 410 m section where GD is located, and stream cross-section and hydraulic factors were constructed based on Nakdong River Basic Plan Report and HEC-RAS. The dominant species of the target stream was Zacco platypus and the sub-dominant species was Puntungia herzi Herzenstein, and the HSI (Habitat Suitability Index) of target species was collected through references research. As the result of PHABSIM water level and velocity simulation, error of Q185 and Q275 were analyzed -0.12 m, +0.00 m and +0.06 m/s, +0.09 m/s respectively. The average WUA (Weighted Usable Area) and ecological flow of Zacco platypus and Puntungia herzi Herzenstein were evaluated 76,817.0 m²/1000m, 20.0 m³/sec and 46,628.6 m²/1000m, 9.0 m³/sec. This results indicated Zacco platypus is more adaptable to target stream than Puntungia herzi Herzenstein.

• Journal of Bio-Environment Control
• /
• v.30 no.4
• /
• pp.419-428
• /
• 2021

In order to develope a mobile-based greenhouse energy calculation program, firstly, the overall thermal transmittance of 10 types of major covers and 16 types of insulation materials were measured. In addition, to estimate the overall thermal transmittance when the cover and insulation materials were installed in double or triple layers, 24 combinations of double installations and 59 combinations of triple installations were measured using the hotbox. Also, the overall thermal transmittance value for a single material and the thermal resistance value were used to calculate the overall thermal transmittance value at the time of multi-layer installation of covering and insulating materials, and the linear regression equation was derived to correct the error with the measured values. As a result of developing the model for estimating thermal transmittance when installing multiple layers of coverings and insulating materials based on the value of overall thermal transmittance of a single-material, the model evaluation index was 0.90 (good when it is 0.5 or more), indicating that the estimated value was very close to the actual value. In addition, as a result of the on-site test, it was evaluated that the estimated heat saving rate was smaller than the actual value with a relative error of 2%. Based on these results, a mobile-based greenhouse energy calculation program was developed that was implemented as an HTML5 standard web-based mobile web application and was designed to work with various mobile device and PC browsers with N-Screen support. It had functions to provides the overall thermal transmittance(heating load coefficient) for each combination of greenhouse coverings and thermal insulation materials and to evaluate the energy consumption during a specific period of the target greenhouse. It was estimated that an energy-saving greenhouse design would be possible with the optimal selection of coverings and insulation materials according to the region and shape of the greenhouse.

• Journal of the Korean Society of Radiology
• /
• v.13 no.4
• /
• pp.503-508
• /
• 2019

In short a binary value according to a change in the tube voltage by using one of VOLUME AXIAL MODE of scanning techniques of chest CT image quality evaluation in order to obtain high image and to present the appropriate tube voltage. CT instruments were GE Revolution (GE Healthcare, Wisconsin USA) model and Phantom used Pediatric Whole Body Phantom PBU-70. The test method was examined in Volume Axial mode using the pediatric protocol used in the Y university hospital of mass-produced material. The tube voltage was set to 70kvp, 80kvp, 100kvp, and mAs was set to smart mA-ODM. The mean SNR difference of the heart was $-4.53{\pm}0.26$ at 70 kvp, $-3.34{\pm}0.18$ at 80 kvp, $-1.87{\pm}0.15$ at 100 kvp, and SNR at 70 kvp was about -2.66 higher than 100 kvp and statistically significant (p<0.05) In the Lung SNR mean difference analysis, $-78.20{\pm}4.16$ at 70 kvp, $-79.10{\pm}4.39$ at 80 kvp, $-77.43{\pm}4.72$ at 100 kvp, and SNR at 70 kvp at about -0.77 higher than 100 kvp were statistically significant. (p<0.05). Lung CNR mean difference was $73.67{\pm}3.95$ at 70 kvp, $75.76{\pm}4.25$ at 80 kvp, $75.57{\pm}4.62$ at 100 kvp and 20.9 CNR at 80 kvp higher than 70 kvp and statistically significant (p<0.05) At 100 kvp of tube voltage, the SNR was close to 1 while maintaining the quality of the heart image when 70 kvp and 80 kvp were compared. However, there is no difference in SNR between 70 kvp and 80 kvp, and 70 kvp can be used to reduce the radiation dose. On the other and, CNR showed an approximate value of 1 at 70 kvp. There is no difference between 80 kvp and 100 kvp. Therefore, 80 kvp can reduce the radiation dose by pediatric chest CT. In addition, it is possible to perform a scan with a short scan time of 0.3 seconds in the volume axial mode test, which is useful for pediatric patients who need to move or relax.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.3
• /
• pp.82-98
• /
• 2019

The importance of spatial information is rapidly rising. In particular, 3D spatial information construction and modeling for Real World Objects, such as smart cities and digital twins, has become an important core technology. The constructed 3D spatial information is used in various fields such as land management, landscape analysis, environment and welfare service. Three-dimensional modeling with image has the hig visibility and reality of objects by generating texturing. However, some texturing might have occlusion area inevitably generated due to physical deposits such as roadside trees, adjacent objects, vehicles, banners, etc. at the time of acquiring image Such occlusion area is a major cause of the deterioration of reality and accuracy of the constructed 3D modeling. Various studies have been conducted to solve the occlusion area. Recently the researches of deep learning algorithm have been conducted for detecting and resolving the occlusion area. For deep learning algorithm, sufficient training data is required, and the collected training data quality directly affects the performance and the result of the deep learning. Therefore, this study analyzed the ability of detecting the occlusion area of the image using various image quality to verify the performance and the result of deep learning according to the quality of the learning data. An image containing an object that causes occlusion is generated for each artificial and quantified image quality and applied to the implemented deep learning algorithm. The study found that the image quality for adjusting brightness was lower at 0.56 detection ratio for brighter images and that the image quality for pixel size and artificial noise control decreased rapidly from images adjusted from the main image to the middle level. In the F-measure performance evaluation method, the change in noise-controlled image resolution was the highest at 0.53 points. The ability to detect occlusion zones by image quality will be used as a valuable criterion for actual application of deep learning in the future. In the acquiring image, it is expected to contribute a lot to the practical application of deep learning by providing a certain level of image acquisition.