• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.1-17
• /
• 2017

The deep learning framework is software designed to help develop deep learning models. Some of its important functions include "automatic differentiation" and "utilization of GPU". The list of popular deep learning framework includes Caffe (BVLC) and Theano (University of Montreal). And recently, Microsoft's deep learning framework, Microsoft Cognitive Toolkit, was released as open-source license, following Google's Tensorflow a year earlier. The early deep learning frameworks have been developed mainly for research at universities. Beginning with the inception of Tensorflow, however, it seems that companies such as Microsoft and Facebook have started to join the competition of framework development. Given the trend, Google and other companies are expected to continue investing in the deep learning framework to bring forward the initiative in the artificial intelligence business. From this point of view, we think it is a good time to compare some of deep learning frameworks. So we compare three deep learning frameworks which can be used as a Python library. Those are Google's Tensorflow, Microsoft's CNTK, and Theano which is sort of a predecessor of the preceding two. The most common and important function of deep learning frameworks is the ability to perform automatic differentiation. Basically all the mathematical expressions of deep learning models can be represented as computational graphs, which consist of nodes and edges. Partial derivatives on each edge of a computational graph can then be obtained. With the partial derivatives, we can let software compute differentiation of any node with respect to any variable by utilizing chain rule of Calculus. First of all, the convenience of coding is in the order of CNTK, Tensorflow, and Theano. The criterion is simply based on the lengths of the codes and the learning curve and the ease of coding are not the main concern. According to the criteria, Theano was the most difficult to implement with, and CNTK and Tensorflow were somewhat easier. With Tensorflow, we need to define weight variables and biases explicitly. The reason that CNTK and Tensorflow are easier to implement with is that those frameworks provide us with more abstraction than Theano. We, however, need to mention that low-level coding is not always bad. It gives us flexibility of coding. With the low-level coding such as in Theano, we can implement and test any new deep learning models or any new search methods that we can think of. The assessment of the execution speed of each framework is that there is not meaningful difference. According to the experiment, execution speeds of Theano and Tensorflow are very similar, although the experiment was limited to a CNN model. In the case of CNTK, the experimental environment was not maintained as the same. The code written in CNTK has to be run in PC environment without GPU where codes execute as much as 50 times slower than with GPU. But we concluded that the difference of execution speed was within the range of variation caused by the different hardware setup. In this study, we compared three types of deep learning framework: Theano, Tensorflow, and CNTK. According to Wikipedia, there are 12 available deep learning frameworks. And 15 different attributes differentiate each framework. Some of the important attributes would include interface language (Python, C ++, Java, etc.) and the availability of libraries on various deep learning models such as CNN, RNN, DBN, and etc. And if a user implements a large scale deep learning model, it will also be important to support multiple GPU or multiple servers. Also, if you are learning the deep learning model, it would also be important if there are enough examples and references.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.4
• /
• pp.233-252
• /
• 2021

This paper is a study to improve the efficiency of mixing technology in the shield TBM chamber. Currently, the number of construction cases using the TBM method is increasing in Korea. According to the increasing use of TBM method, research on TBM method such as Disc Cutter, Cutter bit, and Segment also shows an increasing trend. However, there is little research on the mixing efficiency in chamber and chamber. In order to improve the smooth soil treatment and the behavior of the excavated soil, a study was conducted on the change of the mixing efficiency according to the effective mixing bar arrangement in the chamber. In the scale model experiment, the ground was composed using plastic materials of different colors for ease of identification. In addition, the mixing bar arrangement was different and classified into 4 cases, and the particle size distribution was classified into single particle size and multiple particle size, and the experiment was conducted with a total of 8 cases. The rotation speed of the cutter head of all cases was the same as 5 RPM, and the experiment time was also carried out in the same condition, 1 minute and 30 seconds. In order to check the mixing efficiency, samples at the upper, middle (left or right), and lower positions of each case were collected and analyzed. As a result of the scaled-down model experiment, the mixing efficiency of Case 4 and Case 4-1 increased compared to Case 1 and Case 1-1, which are actually used. Accordingly, it is expected that the mixing efficiency can be increased by changing the arrangement of the mixing bar in the chamber, and it is considered to be effective in saving air as the mixing efficiency increases. Therefore, this study is considered to be an important indicator for the use of shield TBM in Korea.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.75-94
• /
• 2021

The low birth rate and shortened military service period are causing concerns about selecting excellent military officers. The Republic of Korea entered a low birth rate society in 1984 and an aged society in 2018 respectively, and is expected to be in a super-aged society in 2025. In addition, the troop-oriented military is changed as a state-of-the-art weapons-oriented military, and the reduction of the military service period was implemented in 2018 to ease the burden of military service for young people and play a role in the society early. Some observe that the application rate for military officers is falling due to a decrease of manpower resources and a preference for shortened mandatory military service over military officers. This requires further consideration of the policy of securing excellent military officers. Most of the related studies have used social scientists' methodologies, but this study applies the methodology of text mining suitable for large-scale documents analysis. This study extracts words of discriminative characteristics from the Republic of Korea Air Force Non-Commissioned Officer Applicant cover letters and analyzes the polarity of pass and fail. It consists of three steps in total. First, the application is divided into general and technical fields, and the words characterized in the cover letter are ordered according to the difference in the frequency ratio of each field. The greater the difference in the proportion of each application field, the field character is defined as 'more discriminative'. Based on this, we extract the top 50 words representing discriminative characteristics in general fields and the top 50 words representing discriminative characteristics in technology fields. Second, the number of appropriate topics in the overall cover letter is calculated through the LDA. It uses perplexity score and coherence score. Based on the appropriate number of topics, we then use LDA to generate topic and probability, and estimate which topic words of discriminative characteristic belong to. Subsequently, the keyword indicators of questions used to set the labeling candidate index, and the most appropriate index indicator is set as the label for the topic when considering the topic-specific word distribution. Third, using L-LDA, which sets the cover letter and label as pass and fail, we generate topics and probabilities for each field of pass and fail labels. Furthermore, we extract only words of discriminative characteristics that give labeled topics among generated topics and probabilities by pass and fail labels. Next, we extract the difference between the probability on the pass label and the probability on the fail label by word of the labeled discriminative characteristic. A positive figure can be seen as having the polarity of pass, and a negative figure can be seen as having the polarity of fail. This study is the first research to reflect the characteristics of cover letters of Republic of Korea Air Force non-commissioned officer applicants, not in the private sector. Moreover, these methodologies can apply text mining techniques for multiple documents, rather survey or interview methods, to reduce analysis time and increase reliability for the entire population. For this reason, the methodology proposed in the study is also applicable to other forms of multiple documents in the field of military personnel. This study shows that L-LDA is more suitable than LDA to extract discriminative characteristics of Republic of Korea Air Force Noncommissioned cover letters. Furthermore, this study proposes a methodology that uses a combination of LDA and L-LDA. Therefore, through the analysis of the results of the acquisition of non-commissioned Republic of Korea Air Force officers, we would like to provide information available for acquisition and promotional policies and propose a methodology available for research in the field of military manpower acquisition.

• Sleep Medicine and Psychophysiology
• /
• v.21 no.1
• /
• pp.5-13
• /
• 2014

Objectives: Depression, sleep complaints and cognitive impairments are commonly observed in the elderly. Elderly subjects with depressive symptoms have been found to show both poor cognitive performances and sleep disturbances. However, the relationship between sleep complaints and cognitive dysfunction in elderly depression is not clear. The aim of this study is to identify the association between sleep disturbances and cognitive decline in late-life depression. Methods: A total of 282 elderly people who underwent nocturnal polysomnography in a sleep laboratory were enrolled in the study. The Korean version of the Neuropsychological Assessment Battery developed by the Consortium to Establish a Registry for Alzheimer's Disease (CERAD-K) was applied to evaluate cognitive function. Depressive symptoms were assessed with the geriatric depression scale (GDS) and subjective sleep quality was measured using the Pittsburg sleep quality index (PSQI). Results: The control group ($GDS{\leq}9$) when compared with mild ($10{\leq}GDS{\leq}16$) and severe ($17{\leq}GDS$) depression groups, had significantly different scores in the Trail making test part B (TMT-B), Benton visual retention test part A (BVRT-A), and Stroop color and word test (SCWT)(all tests p<0.05). The PSQI score, REM sleep duration, apnea-hypopnea index and oxygen desaturation index were significantly different across the three groups (all indices, p<0.05). A stepwise multiple regression model showed that educational level, age and GDS score were predictive for both TMT-B time (adjusted $R^2$=35.6%, p<0.001) and BVRT-A score (adjusted $R^2$=28.3%, p<0.001). SCWT score was predicted by educational level, age, apnea-hypopnea index (AHI) and GDS score (adjusted $R^2$=20.6%, p<0.001). Poor sleep quality and sleep structure alterations observed in depression did not have any significant effects on cognitive deterioration. Conclusion: Older adults with depressive symptoms showed mild sleep alterations and poor cognitive performances. However, we found no association between sleep disturbances (except sleep apnea) and cognitive difficulties in elderly subjects with depressive symptoms. It is possible that the impact of sleep disruptions on cognitive abilities was hindered by the confounding effect of age, education and depressive symptoms.

• (The)Study of the Eastern Classic
• /
• no.73
• /
• pp.185-217
• /
• 2018

This research is a part of basic research on Gyeonggi Kamyoung focused on reconstruct personnel organization and facility of Gyeonggi Kamyoung, the only Kamyoung without a Kamyoung Record, which should have been recorded on it. Excluding Gyeonggi Kamyoung, other 7 Kamyoung each have its Kamyoung Record that shows their detailed history and set up. Due to lack of information about Gyeonggi Kamyoung, this research set objective on reconstructing Kamyoung Record of it with fragments of information on multiple historical records. By doing this, this research will also be a background for general research on distinguishing administrative unity from regional uniqueness of all 8 provinces Kamyoung. Kamyoung's personnel organization is sorted into government official from central government and Yeongli and staff. The information about the government official on this research is based on "Ki-Yung-Jang-Gae- Deung-Rok"'s personal assessment. According to it, Dosa Junggun Geomlyul had the same task and position as others in different provinces did. The difference Gyeonggi Kamyoung had was an absence of Sim Yak since 1700 while others still had it. The information about Yeongli and staff's organization was based on "Ki-Yeong-Sin-Jeong-Sa-Le". In Gyeonggi Kamyoung, along 6-Bang, there were 208 Yeongli and staff categorized into 50 different official duties. Also, compared to other Kamyoungs, Youngli's scale was smaller. Kamyoung's facility inside Pojeongmun and wall is distinguished from other Kamyoung related facilities in this research. Organization of facilities inside Pojeongmun and wall is based on "Gyeonggi-Kamyoung-Do". Like other Kamyoungs in different provinces, Seonhwadang, which is the main building, is located in the center and had a similar organization. Significant point was that Gyeonggi Kamyoung had both Youngli-Cheong and Hyeongli-Cheong at the same time. In the dense and developed area outside of Seodaemun, Gyeonggi Kamyoung had its related facility around it in small scale.

• Journal of Global Scholars of Marketing Science
• /
• v.17 no.2
• /
• pp.55-73
• /
• 2007

Festivals are an indispensable feature of cultural tourism(Formica & Uysal, 1998). Cultural tourism festivals are increasingly being used as instruments promoting tourism and boosting the regional economy. So much research related to festivals is undertaken from a variety of perspectives. Plans to revisit a particular festival have been viewed as an important research topic both in academia and the tourism industry. Therefore festivals have frequently been leveled as cultural events. Cultural tourism festivals have become a crucial component in constituting the attractiveness of tourism destinations(Prentice, 2001). As a result, a considerable number of tourist studies have been carried out in diverse cultural tourism festivals(Backman et al., 1995; Crompton & Mckay, 1997; Park, 1998; Clawson & Knetch, 1996). Much of previous literature empirically shows the close linkage between tourist satisfaction and behavioral intention in festivals. The main objective of this study is to investigate the effects of evaluation attributes of cultural tourism festivals on satisfaction and behavioral intention. accomplish the research objective, to find out evaluation items of cultural tourism festivals through the literature study an empirical study. Using a varimax rotation with Kaiser normalization, the research obtained four factors in the 18 evaluation attributes of cultural tourism festivals. Some empirical studies have examined the relationship between behavioral intention and actual behavior. To understand between tourist satisfaction and behavioral intention, this study suggests five hypotheses and hypothesized model. In this study, the analysis is based on primary data collected from visitors who participated in '2006 Gwangju Kimchi Festival'. In total, 700 self-administered questionnaires were distributed and 561 usable questionnaires were obtained. Respondents were presented with the 18 satisfactions item on a scale from 1(strongly disagree) to 7(strongly agree). Dimensionality and stability of the scale were evaluated by a factor analysis with varimax rotation. Four factors emerged with eigenvalues greater than 1, which explained 66.40% of the total variance and Cronbach' alpha raging from 0.876 to 0.774. And four factors named: advertisement and guides, programs, food and souvenirs, and convenient facilities. To test and estimate the hypothesized model, a two-step approach with an initial measurement model and a subsequent structural model for Structural Equation Modeling was used. The AMOS 4.0 analysis package was used to conduct the analysis. In estimating the model, the maximum likelihood procedure was used.In this study Chi-square test is used, which is the most common model goodness-of-fit test. In addition, considering the literature about the Structural Equation Modeling, this study used, besides Chi-square test, more model fit indexes to determine the tangibility of the suggested model: goodness-of-fit index(GFI) and root mean square error of approximation(RMSEA) as absolute fit indexes; normed-fit index(NFI) and non-normed-fit index(NNFI) as incremental fit indexes. The results of T-test and ANOVAs revealed significant differences(0.05 level), therefore H1(Tourist Satisfaction level should be different from Demographic traits) are supported. According to the multiple Regressions analysis and AMOS, H2(Tourist Satisfaction positively influences on revisit intention), H3(Tourist Satisfaction positively influences on word of mouth), H4(Evaluation Attributes of cultural tourism festivals influences on Tourist Satisfaction), and H5(Tourist Satisfaction positively influences on Behavioral Intention) are also supported. As the conclusion of this study are as following: First, there were differences in satisfaction levels in accordance with the demographic information of visitors. Not all visitors had the same degree of satisfaction with their cultural tourism festival experience. Therefore it is necessary to understand the satisfaction of tourists if the experiences that are provided are to meet their expectations. So, in making festival plans, the organizer should consider the demographic variables in explaining and segmenting visitors to cultural tourism festival. Second, satisfaction with attributes of evaluation cultural tourism festivals had a significant direct impact on visitors' intention to revisit such festivals and the word of mouth publicity they shared. The results indicated that visitor satisfaction is a significant antecedent of their intention to revisit such festivals. Festival organizers should strive to forge long-term relationships with the visitors. In addition, it is also necessary to understand how the intention to revisit a festival changes over time and identify the critical satisfaction factors. Third, it is confirmed that behavioral intention was enhanced by satisfaction. The strong link between satisfaction and behavioral intentions of visitors areensured by high quality advertisement and guides, programs, food and souvenirs, and convenient facilities. Thus, examining revisit intention from a time viewpoint may be of a great significance for both practical and theoretical reasons. Additionally, festival organizers should give special attention to visitor satisfaction, as satisfied visitors are more likely to return sooner. The findings of this research have several practical implications for the festivals managers. The promotion of cultural festivals should be based on the understanding of tourist satisfaction for the long- term success of tourism. And this study can help managers carry out this task in a more informed and strategic manner by examining the effects of demographic traits on the level of tourist satisfaction and the behavioral intention. In other words, differentiated marketing strategies should be stressed and executed by relevant parties. The limitations of this study are as follows; the results of this study cannot be generalized to other cultural tourism festivals because we have not explored the many different kinds of festivals. A future study should be a comparative analysis of other festivals of different visitor segments. Also, further efforts should be directed toward developing more comprehensive temporal models that can explain behavioral intentions of tourists.

• Geophysics and Geophysical Exploration
• /
• v.13 no.3
• /
• pp.243-248
• /
• 2010

Two suspicious events, which were claimed as underground nuclear tests by North Korea, were detected in the northern Korean Peninsula on October 9, 2006 and May 25, 2009. The KIGAM and Korea-China Joint seismic stations are distributed uniformly along the boundaries between North Korea and adjacent countries. In this study, the data from broadband stations with the distance of 200 to 550 km from the test site are used to analyze and compare two nuclear tests of North Korea. By comparing the time differences of the Pn-wave arrival times of 1st and 2nd tests at multiple stations, the relative locations of two test sites could be calculated precisely. From the geometrical calculation with the velocity of Pn wave $V_{Pn}$ = 8 km/s, the 2nd test site is estimated to move in the WNW direction from 1st one with the distance of 2 km. Body wave magnitude, mb of the 2nd test, which was announced officially as the network average of 4.5, varies widely with the directional location of stations from 4.1 to 5.2. The magnitude obtained from Lg wave, $m_b$(Lg), shows less variation between 4.3 to 4.7 with the average of 4.6. The moving-window spectra of time traces of 1st and 2nd tests show very similar pattern with different scale level. In addition, the corner frequencies of P wave of 1st and 2nd tests at each station show no or negligible difference. This indicates the burial depths of two tests might be very similar. The relative yield amount of the 2nd test is estimated 8 times larger than that of the 1st from the weighted average of ground-velocity amplitude ratios.

• Korea Science and Art Forum
• /
• v.37 no.2
• /
• pp.239-250
• /
• 2019

Along with changes in the industrial structure, revitalizing decrepit or abandoned industrial-age infrastructures are actively under way on a global scale. This study was motivated by an interest in investigating currently idle industrial infrastructures and revitalizing the abandoned passenger ferry terminal in Geoje's Jangseungpo and surrounding areas. The main aims of this study were to examine regional features for the purpose of establishing urban renewal plans and field opinions of the local residents on how to proceed with the restoration of the passenger ferry terminal. To this end, this paper looked into previous case studies of converting decrepit industrial infrastructures into new cultural venues, depending on each region's special circumstances. This paper's findings are as follows: First, as a result of this investigation, the author found that in all cases in Korea and elsewhere revitalization focused on creating modern cultural spaces appropriate for the region while retaining its traditional value. At the same time, they sought sustainable cultural and economic revival. Second, as a result of the investigation on Geoje City's local characteristics, the author found that the surrounding areas' commercial districts were depressed after the terminal's closure. At the time of the investigation, the city government was trying to reopen the terminal as a major port offering multiple international ferry destinations while attracting tourists. Third, as a result of the surveys on the local residents, it was found that more than half of the residents were in agreement with the city government's plan to reopen the terminal and expressed their wishes that they want the terminal to have other uses such as cultural venues. Based on these research results, the author makes proposals, including expanding the passenger ferry terminal and offering cultural spaces within and near the terminal, based on the local residents' opinions and in reflection of local circumstances. As part of this effort, the author also recommends a new brand name and design plan for the new passenger ferry terminal so that Geoje City can improve its local community value.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1465-1483
• /
• 2020

Evapotranspiration is a concept that includes the evaporation from soil and the transpiration from the plant leaf. It is an essential factor for monitoring water balance, drought, crop growth, and climate change. Actual evapotranspiration (AET) corresponds to the consumption of water from the land surface and the necessary amount of water for the land surface. Because the AET is derived from multiplying the crop coefficient by the reference evapotranspiration (ET0), an accurate calculation of the ET0 is required for the AET. To date, many efforts have been made for gridded ET0 to provide multiple products now. This study presents a comparison between the ET0 products such as FAO56-PM, LDAPS, PKNU-NMSC, and MODIS to find out which one is more suitable for the local-scale hydrological and agricultural applications in Korea, where the heterogeneity of the land surface is critical. In the experiment for the period between 2016 and 2019, the daily and 8-day products were compared with the in-situ observations by KMA. The analyses according to the station, year, month, and time-series showed that the PKNU-NMSC product with a successful optimization for Korea was superior to the others, yielding stable accuracy irrespective of space and time. Also, this paper showed the intrinsic characteristics of the FAO56-PM, LDAPS, and MODIS ET0 products that could be informative for other researchers.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.111-126
• /
• 2017

Recommender systems based on association rule mining significantly contribute to seller's sales by reducing consumers' time to search for products that they want. Recommendations based on the frequency of transactions such as orders can effectively screen out the products that are statistically marketable among multiple products. A product with a high possibility of sales, however, can be omitted from the recommendation if it records insufficient number of transactions at the beginning of the sale. Products missing from the associated recommendations may lose the chance of exposure to consumers, which leads to a decline in the number of transactions. In turn, diminished transactions may create a vicious circle of lost opportunity to be recommended. Thus, initial sales are likely to remain stagnant for a certain period of time. Products that are susceptible to fashion or seasonality, such as clothing, may be greatly affected. This study was aimed at expanding association rules to include into the list of recommendations those products whose initial trading frequency of transactions is low despite the possibility of high sales. The particular purpose is to predict the strength of the direct connection of two unconnected items through the properties of the paths located between them. An association between two items revealed in transactions can be interpreted as the interaction between them, which can be expressed as a link in a social network whose nodes are items. The first step calculates the centralities of the nodes in the middle of the paths that indirectly connect the two nodes without direct connection. The next step identifies the number of the paths and the shortest among them. These extracts are used as independent variables in the regression analysis to predict future connection strength between the nodes. The strength of the connection between the two nodes of the model, which is defined by the number of nodes between the two nodes, is measured after a certain period of time. The regression analysis results confirm that the number of paths between the two products, the distance of the shortest path, and the number of neighboring items connected to the products are significantly related to their potential strength. This study used actual order transaction data collected for three months from February to April in 2016 from an online commerce company. To reduce the complexity of analytics as the scale of the network grows, the analysis was performed only on miscellaneous goods. Two consecutively purchased items were chosen from each customer's transactions to obtain a pair of antecedent and consequent, which secures a link needed for constituting a social network. The direction of the link was determined in the order in which the goods were purchased. Except for the last ten days of the data collection period, the social network of associated items was built for the extraction of independent variables. The model predicts the number of links to be connected in the next ten days from the explanatory variables. Of the 5,711 previously unconnected links, 611 were newly connected for the last ten days. Through experiments, the proposed model demonstrated excellent predictions. Of the 571 links that the proposed model predicts, 269 were confirmed to have been connected. This is 4.4 times more than the average of 61, which can be found without any prediction model. This study is expected to be useful regarding industries whose new products launch quickly with short life cycles, since their exposure time is critical. Also, it can be used to detect diseases that are rarely found in the early stages of medical treatment because of the low incidence of outbreaks. Since the complexity of the social networking analysis is sensitive to the number of nodes and links that make up the network, this study was conducted in a particular category of miscellaneous goods. Future research should consider that this condition may limit the opportunity to detect unexpected associations between products belonging to different categories of classification.