• Journal of the Economic Geographical Society of Korea
• /
• v.23 no.1
• /
• pp.1-17
• /
• 2020

The study aims to identify economic interdependencies between regions and define functional economic areas of Korea by analyzing inter-firm transaction networks. Previous research has relied on pre-given administrative boundaries or cultural homogeneity and used data such as commuting, population movement, and cargo flows which could not fully explain economic activities. To overcome the limitations, this study applies a community detection method to inter-firm transaction networks derived from the CRETOP+ database of Korean corporate data. The novel dataset and the network analysis enables us to identify Korea's functional economic areas based on actual inter-firm linkages. The result shows that there are six to seven economic blocs in the networks as of 2018. In particular, one huge economic bloc is formed integrating the Seoul metropolitan area, Chungcheong, and Gangwon provinces. Meanwhile, North Jeolla and South Jeolla provinces form two economic blocs separately rather than being tied up in one bloc due to the low frequency of transactions between each other. The two big economic blocs of Daegu-Gyeongbuk and Busan-Gyeongnam exist, and interestingly, Ulsan, Gyeongju, and Pohang form a separate middle-sized bloc across the administrative boundaries. The results reveal that the future balanced national development policies should be implemented based on functional economic areas derived from empirical data.

• Journal of Korea Water Resources Association
• /
• v.31 no.6
• /
• pp.821-832
• /
• 1998

This study investigates the prediction of daily water supply, which is a necessary for the efficient management of water distribution system. Fuzzy neuron, namely artificial intelligence, is a neural network into which fuzzy information is inputted and then processed. In this study, daily water supply was predicted through an adaptive learning method by which a membership function and fuzzy rules were adapted for daily water supply prediction. This study was investigated methods for predicting water supply based on data about the amount of water supplied to the city of Kwangju. For variables choice, four analyses of input data were conducted: correlation analysis, autocorrelation analysis, partial autocorrelation analysis, and cross-correlation analysis. Input variables were (a) the amount of water supplied (b) the mean temperature, and (c)the population of the area supplied with water. Variables were combined in an integrated model. Data of the amount of daily water supply only was modelled and its validity was verified in the case that the meteorological office of weather forecast is not always reliable. Proposed models include accidental cases such as a suspension of water supply. The maximum error rate between the estimation of the model and the actual measurement was 18.35% and the average error was lower than 2.36%. The model is expected to be a real-time estimation of the operational control of water works and water/drain pipes.

• Journal of Digital Convergence
• /
• v.18 no.1
• /
• pp.137-146
• /
• 2020

NLP means the technology that mechanically analyzes a language spoken by a human and makes it into a form that can be understood by a computer. This is important because it is a core technology for communication between humans and devices, which is the basis of artificial intelligence. In this paper, I analyzed patent information of US and Korea in order to identify technical trends related to NLP, especially semantic analysis. and the purpose of this study is to provide meaningful information for future research on NLP. In conclusion, the number of Korea patents is 7.9% compared to the USA and the different frequencies of the major keywords were found to differ from country to country in technical direction. In addition, the upward or downward keywords are twice as many in the U.S. as in Korea, and reflect the trend of the times relatively more. Based on these results, in future study, I will analysis how upward trending keywords are described in actual patents for concrete technology prediction.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.7
• /
• pp.291-305
• /
• 2008

Previous study about Mobile Music Contents was mainly focused on Industry factors & enterprise factors like Technology. This study is not only focused on Technology factors, but also Customer & System factors like TAM of original, and also, this study first tried to find the Mobile Internet medium's customer purchase by each property's Mobile Music Contents from assorting the Mobile music Contents property and defining them. So to speak of this study have tried to concretely verify the factors of purchase. And also, I proposed an transformated model, and added independent variable factors, 'distinction', 'speed of system', 'speed of network', 'a career of use', 'amount of use', 'preservation', 'customization', 'information', 'confidence', 'omni presentation', 'potential possibility of reproduce'. By applying TAM this study has measured how the product property. user property, and system property causes effect to customer purchase of Mobile Music Contents. In results, First, success 8 factors were determined to be the purchase of 'Ringtone'. Second, 8 factors were determined to be the purchase of 'Ring-Back tone', but, 'The use of convenience' was not influenced 'Intention of Purchase'. Third, 6 factors were determined to be the purchase of 'Full Track Download of Music'. At the Conclusion this study presented a scheme that these study results could be applied in actual company and academic world.

• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.67-75
• /
• 2016

The study analyzed big data extracted from Google and social media to identify factors related to searches on cyber bullying in Korea and America. Korea's cyber bullying analysis was conducted social big data collected from online news sites, blogs, $caf{\acute{e}}s$, social network services and message for between January 1, 2011 and March 31, 2013. Google search trends for the search words of stress, exercise, drinking, and cyber bullying were obtained for January 1, 2004 and December 22, 2013. The main results of this study were as follows: first, the significant factors stress were cyber bullying that Korea more than America. Secondly, a positive relationship was found between stress and drinking, exercise and cyber bullying both Korea and America. Thirdly, significant differences were found all path both Korea and America. The study shows that both adults and teenagers are influenced in Korea. We need to develop online application that if cyber bullying behavior was predicted can intervene in real time because these actual cyber bullying-related exposure to psychological and behavioral characteristic.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.789-795
• /
• 2020

Many deaths have been reported due to the worldwide pandemic of COVID-19. In order to prevent the further spread of COVID-19, it is necessary to quickly and accurately read images of suspected patients and take appropriate measures. To this end, this paper introduces a deep learning-based COVID-19 chest X-ray reading technique that can assist in image reading by providing medical staff whether a patient is infected. First of all, in order to learn the reading model, a sufficient dataset must be secured, but the currently provided COVID-19 open dataset does not have enough image data to ensure the accuracy of learning. Therefore, we solved the image data number imbalance problem that degrades AI learning performance by using a Stacked Generative Adversarial Network(StackGAN++). Next, the DenseNet-based classification model was trained using the augmented data set to develop the reading model. This classification model is a model for binary classification of normal chest X-ray and COVID-19 chest X-ray, and the performance of the model was evaluated using part of the actual image data as test data. Finally, the reliability of the model was secured by presenting the basis for judging the presence or absence of disease in the input image using Grad-CAM, one of the explainable artificial intelligence called XAI.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.7B
• /
• pp.578-585
• /
• 2012

Location tracking system through GPS and Wi-Fi is available at no additional cost in an environment of IEEE 802.11-based wireless network. It is useful for many applications in outdoor environment. However, a previous systems used for general device to tag. It is unsuitable for power aware location tracking system because general devices is more expensive and non-optimized for tracking. The hand-off method of IEEE 802.11 standard is not enough considering power consumption. This thesis analyzes the previous location tracking systems and proposes power aware system. First, we designed and implemented tag to optimize location tracking. Next, we propose low-power hand-off method and low-power behavior model in implemented tag. The proposed hand-off method resolve power problem by using the location information and behavior model minimize power consumption of tag through power-saving mode and the concept of duty cycle. To evaluating proposed methods and system performance, we perform simulations and experiments in real environment. And then, we calculate tag's power consumption based on the actual measured current consumption of each operation. In a simulation result, the proposed behavior model and hand-off method reduced about 98%, 59% than the standard's hand-off and default behavior model.

• Journal of Korea Technology Innovation Society
• /
• v.9 no.4
• /
• pp.627-653
• /
• 2006

The purpose of this study lies in understanding how the spectrum assigned for each mobile operator affects the consumers of mobile service. For this purpose, we have observed the change of path coefficient in the structural equation, using control variables. However, the structure of the mobile service market in Korea has become fixed. Considering this tendency and the conclusion of this study, the 'lock-in effect' occurs seriously in the mobile service market in Korea. It can be explained by the fact that CS(Customer Satisfaction) of the cellular subscribers little affects customer loyalty but the market dominance of the cellular service in the actual market has continued for a long time. In this study, we figured out a strong prejudice about call quality, which is caused by spectrum difference among competitors. Cellular subscribers tends to believe that call quality of their cellular service is better than that of PCS. In addition, we found that PCS operators can catch customer's retention by investment into network in order to increase call quality.

• The KIPS Transactions:PartC
• /
• v.8C no.6
• /
• pp.831-838
• /
• 2001

Mobile information service aims to provide some degree of effective information for real life activities of mobile users. Due to the user mobility and actual realism, it becomes very important technical issue to support an adaptive information service methodology to current situations of the terminal and/or user. This paper deals with a prefetching scheme for location-aware, out of the various context-aware which can be considered in mobile information service. It makes use of the velocity-based mobility model to shape the terminal and/or user's mobility behavior. Based on the moving speed and direction, the prefetching zone is proposed to define the number of prefetched information, so as to limit effectively the prefetched information whilst to preserve the location-aware adaptability. Using a simulator, the proposed scheme has been evaluated in the effectiveness point of view. The idea in this paper is expected to be able to extended to the other mobile service contexts, such as service time, I/O types of mobile terminals, network bandwidth.

• Journal of Korean Society of Transportation
• /
• v.26 no.4
• /
• pp.135-147
• /
• 2008

One of the efforts both to prevent urban sprawling development patterns and to promote use of public transportation is known as Transit-Oriented Development (TOD), including such planning elements as the density and diversity of land use and pedestrian-friendly urban design around a transit center. The aim of this study is thus to conduct impact analyses of TOD planning elements on transit ridership in the Seoul rail station areas. First, the authors investigate and draw out various actual elements of TOD planning by using GIS-based data and Smart Card data. Then the authors analyze impacts of TOD planning elements on transit ridership for the Seoul rail station areas. After condensing 34 variables presumably influencing transit ridership into seven factors by using factor analyses, the study utilizes multiple regression modeling methods to identify their impacts on transit ridership. The analysis results demonstrate that transit ridership tends to increase more in rail station areas where there is a non-residential high density, mixed use of land and narrow and small-size road network patterns. The implementation of TODs should be a useful method in inducing a Transit-Oriented City through redevelopment and new development.