• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.173-178
• /
• 2021

In this paper, we find a suitable methodology for Korean Sentiment Analysis through a comparative experiment in which methods of embedding and natural network models are learned at the highest accuracy and fastest speed. The embedding method compares word embeddeding and Word2Vec. The model compares and experiments representative neural network models CNN, RNN, LSTM, GRU, Bi-LSTM and Bi-GRU with IKEA review data. Experiments show that Word2Vec and BiGRU had the highest accuracy and second fastest speed with 94.23% accuracy and 42.30 seconds speed. Word2Vec and GRU were found to have the third highest accuracy and fastest speed with 92.53% accuracy and 26.75 seconds speed.

• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1213-1220
• /
• 2022

The Emergency Diesel Generator (EDG) is a critical and essential part of the Nuclear Power Plant (NPP). Due to past catastrophic disasters, critical systems of NPP like EDG are designed to meet high dependability requirements. Therefore, we propose a framework for the dynamic reliability assessment using the Fault Tree and the Dynamic Bayesian Network. In this framework, the information of the component's failure probability is updated based on observed data. The framework is powerful to perform qualitative as well as quantitative analysis of the system. The validity of the framework is done by applying it on several NPP systems.

• Journal of Korean Institute of Industrial Engineers
• /
• v.42 no.1
• /
• pp.1-19
• /
• 2016

Recently, the emergence of smartphone foster the technological convergence. This convergence no longer takes place within technologies only. Rather, convergence phenomena happen as a form of embodied services. However, previous research on convergence has been subject to the technology-oriented studies, including suggesting patent-based indexes or analyzing technological characteristics. However, investigating technology-service convergence is critical since most of new smart services are technology-based convergence services. Therefore, we analyze the pattern of technology-service convergence which occurs in the smartphone application services. We divided the smatphone application services into four categories, and employ a network analysis to represent the convergence phenomena of each category. Our study is expected to provide meaningful implication in new service development practice.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.235-240
• /
• 2016

In this study, we use the data collected from Twitter, as an SNS(Social Networking Service), for service innovation. This data was collected and processed by Flume. The data set in May 2016 was 4,766 and 15,543 from company S and company X, respectively. We were able to figure out the emotional atmosphere of the two companies through the sentiment analysis(SA) and to find out about the vertical relationship through the bibliometric analysis(BA). Furthermore, we were able to grasp the horizontal relationship through the social network analysis(SNA). It was concluded that SNS was worth while to derive an innovative item.

• Journal of Convergence for Information Technology
• /
• v.9 no.3
• /
• pp.68-74
• /
• 2019

The purpose of this study was to identify research trends of 892 domestic articles (2009-2018) related to emotional labor by using text-mining and network analysis. To this end, the keyword of these papers were collected and coded and eventually converted to 871 nodes and 2625 links for network text analysis. First, network text analysis revealed that the top four main keyword, according to co-occurrence frequency, were burnout, turnover intention, job stress, and job satisfaction in order and that the frequency and the top four core keyword by degree centrality were all relatively the high. Second, based on the top four core keyword of degree centrality the ego network analysis was conducted and the keyword for connection centroid of each network were presented.

• Journal of Advanced Navigation Technology
• /
• v.25 no.5
• /
• pp.409-414
• /
• 2021

The growing concerns on the emission of particulate matter has prompted a demand for highly reliable particulate matter forecasting. Currently, several studies on particulate matter prediction use various deep learning algorithms. In this study, we compared the predictive performances of typical neural networks used for particulate matter prediction. We used deep neural network(DNN), recurrent neural network, and long short-term memory algorithms to design an optimal predictive model on the basis of a hyperparameter search. The results of a comparative analysis of the predictive performances of the models indicate that the variation trend of the actual and predicted values generally showed a good performance. In the analysis based on the root mean square error and accuracy, the DNN-based prediction model showed a higher reliability for prediction errors compared with the other prediction models.

• Journal of Korea Technology Innovation Society
• /
• v.18 no.4
• /
• pp.693-718
• /
• 2015

This paper examines the presence of network structures among convergence technologies focusing on national R&D projects performed by GRIs(Government-sponsored Research Institutes) in Korea. The dataset of convergence technology projects, which were conducted by 24 GRIs over 3 years (2011-2013), are analysed using the network analysis method. In this paper, a convergence technology project is defined as a project that consists of 2 or more then 2 technologies according to the intermediate classification of National Standard Classification of S&T. The research results confirm that convergence researches of government-sponsored research institutes are performed more actively than the entire convergence researches of national R&D projects. Furthermore, technological fields of GRIs' convergence projects are found to be much more varied. This paper also shows that in-house researches are more active than collaborative ones with external organizations. According to the network centrality analysis, it is identified that the network central characteristics of convergence technologies can be classified into internally oriented technologies and externally oriented technologies. Convergence technologies do not just mean simple mixture of different technologies. Therefore Korean government-sponsored research institutes should make more efforts to create convergence research areas which could generate new technologies and industries more effectively than simple multidisciplinary technology researches. From this perspective, some policy suggestions can be derived on the role of government-sponsored research institutes for activating convergence researches through the analysis of status of convergence researches and networks of institutions.

• Journal of Advanced Navigation Technology
• /
• v.22 no.5
• /
• pp.375-383
• /
• 2018

In order to apply the Network RTK (real time kinematics) technology, which has been used for positioning of stationary points, to the navigation of vehicles, its infrastructure should provide correction data with a quality indicator that can show the expected accuracy in real time. In this paper, we analyzed various indicator generation algorithms such as I95 (ionospheric index 95) / G95 (geodetic index 95), SBI (semivariance based index) and RIU (residual interpolation uncertainty). We also applied them to the raw observables from the reference stations of National Geographic Information Institute and VRS (virtual reference station) users, and then examined its feasibility to be used as a real-time performance index of the Network RTK rover. 24 hour data analysis shows that the RIU index, which can represent the non-linearty of the correction, has the strongest correlation with the Network RTK rover accuracy. Therefore, RIU index is expected to be used as a real-time performance index of the Network RTK rover.

• Journal of Information Technology Services
• /
• v.14 no.3
• /
• pp.49-65
• /
• 2015

As South Korean large business groups, also known as Chaebol, have broadened their influence in the domestic economy, it is important to analyze the influence of internal transactions among Chaebol affiliates on their performance. In this paper, relationship between internal transactions and efficiency of Chaebol affiliates has been analyzed. Top five Chaebol groups in South Korea are selected; they include Samsung, Hyundai Motors, LG, SK, and Lotte group. Based on internal transactions among affiliates, social networks are constructed for each Chaebol group to analyze centrality, network structures and cliques. Data Envelopment Analysis (DEA) was conducted to examine the efficiency of the Chaebol affiliates. Then, correlations between the degree centrality and the efficiency of Chaebol affiliates were analyzed, and the network structures of Chaebol groups are presented. The result shows that positive correlations between degree centrality and efficiency are observed among four Chaebol Groups. This paper shows that the Social Network Analysis (SNA) techniques can be used in the empirical research for the analysis of internal transactions of Chaebol groups.

• Journal of Industrial Technology
• /
• v.12
• /
• pp.37-49
• /
• 1992

We proposed an integrated simulator scheme for communication networks. The network modeling and Analysis methologies are firstly discussed along the design procedure of a network simulator, and then, the structure, kernel, and user interfaces are defined for the simulator. Finally, for the verification of our approach, simulations are performed for a simple queueing network and a pure ALOHA system using Ptolemy, a multi-paradigm simulation enviroment.