• International Journal of Contents
• /
• v.17 no.3
• /
• pp.1-14
• /
• 2021

Since the outbreak of the coronavirus disease 2019 (COVID-19) pandemic, a lot of efforts have been made in the field of data science to help combat against this disease. Among them, forecasting the number of cases of infection is a crucial problem to predict the development of the pandemic. Many deep learning-based models can be applied to solve this type of time series problem. In this research, we would like to take a step forward to incorporate spatial data (geography) with time series data to forecast the cases of region-level infection simultaneously. Specifically, we model a single spatio-temporal graph, in which nodes represent the geographic regions, spatial edges represent the distance between each pair of regions, and temporal edges indicate the node features through time. We evaluate this approach in COVID-19 in a Korean dataset, and we show a decrease of approximately 10% in both RMSE and MAE, and a significant boost to the training speed compared to the baseline models. Moreover, the training efficiency allows this approach to be extended for a large-scale spatio-temporal dataset.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.165-165
• /
• 2023

Streamflow prediction is a critical task in water resources management and essential for planning and decision-making purposes. However, the streamflow prediction is challenging due to the complexity and non-linear nature of hydrological processes. The transfer learning is a powerful technique that enables a model to transfer knowledge from a source domain to a target domain, improving model performance with limited data in the target domain. In this study, we apply the transfer learning using the Informer model, which is a state-of-the-art deep learning model for streamflow prediction. The model was trained on a large-scale hydrological dataset in the source basin and then fine-tuned using a smaller dataset available in the target basin to predict the streamflow in the target basin. The results demonstrate that transfer learning using the Informer model significantly outperforms the traditional machine learning models and even other deep learning models for streamflow prediction, especially when the target domain has limited data. Moreover, the results indicate the effectiveness of streamflow prediction when knowledge transfer is used to improve the generalizability of hydrologic models in data-sparse regions.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.34-46
• /
• 2023

A growing number of large scale knowledge graphs raises several issues how knowledge graph data can be organized, discovered, and integrated efficiently. We present a novel semantic-based mashup platform for contents convergence which consists of acquisition, RDF storage, ontology learning, and mashup subsystems. This platform servers a basis for developing other more sophisticated applications required in the area of knowledge big data. Moreover, this paper proposes an entity matching method using graph convolutional network techniques as a preliminary work for automatic classification and discovery on knowledge big data. Using real DBP15K and SRPRS datasets, the performance of our method is compared with some existing entity matching methods. The experimental results show that the proposed method outperforms existing methods due to its ability to increase accuracy and reduce training time.

• Journal of Information Technology Applications and Management
• /
• v.31 no.1
• /
• pp.139-161
• /
• 2024

The Fourth Industrial Revolution has spurred widespread adoption of AI-based services, driving global interest in AI semiconductors for efficient large-scale computation. Text mining research, historically using LDA, has evolved with machine learning integration, exemplified by the 2021 BERTopic technology. This study employs BERTopic to analyze AI semiconductor-related patents and research data, generating 48 topics from 2,256 patents and 40 topics from 1,112 publications. While providing valuable insights into technology trends, the study acknowledges limitations in taking a macro approach to the entire AI semiconductor industry. Future research may explore specific technologies for more nuanced insights as the industry matures.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.753-756
• /
• 2024

This study integrates Rivet and Retrieved Augmented Generation (RAG) technologies to enhance automated report generation, addressing the challenges of large-scale data management. We introduce novel algorithms, such as Dynamic Data Synchronization and Contextual Compression, expected to improve report generation speed by 40% and accuracy by 25%. The application, demonstrated through a model corporate entity, "Company L," shows how such integrations can enhance business intelligence. Empirical validations planned will utilize metrics like precision, recall, and BLEU to substantiate the improvements, setting new benchmarks for the industry. This research highlights the potential of advanced technologies in transforming corporate data processes.

• Atmosphere
• /
• v.17 no.1
• /
• pp.1-15
• /
• 2007

A constraint based on climatology is introduced to the cost function of the three-dimensional variational assimilation (3dVar) to correct the error of the zonal mean wind structure in the global data assimilation system at Korea Meteorological Administration (KMA). The revised cost function compels the analysis fit to the chosen climatology while keeping the balance between the variables in the course of analysis. The constraint varies selectively with the vertical level and the horizontal scale of the motion. The zonally averaged wind field from European Centre for Medium-Range Weather Forecasts Re-Analysis 40 (ERA-40) is used as a climatology field in the constraint. The constraint controls only the zonally averaged stratospheric long waves with total wave number less than 20 to fix the error of the large scale wind field in the stratosphere. The constrained 3dVar successfully suppresses the erroneous westerly in the stratospheric analysis promptly, and has been applied on the operational global 3dVar system at KMA.

• New & Renewable Energy
• /
• v.7 no.2
• /
• pp.51-58
• /
• 2011

Saemankeum is well known for its high speed wind, and it is known that the blueprint of a future city around Saemankeum, including new industrial complex, has been planned. As a result, large-scale offshore wind farm, on the basis of the measurement of wind resource for a long time, can be considered, so that generated electricity can be used to meet the energy demand near the wind farm. Wind speed in Kokunsando of Saemankeum is measured and analyzed with its statistical distribution and wind directions. The probability of wind power resource over Kokunsando of Saemangeum is reviewed with the measured data in one island of Kokunsando. According to measured data, the shape and scale factor of Weibull distribution of wind speed are obtained, and then power density is analyzed as well. Through this study, it is clear that the Saemangeum area has a fluent and abundant wind power source to develop the wind farm in Korea.

• Journal of Biosystems Engineering
• /
• v.37 no.6
• /
• pp.385-397
• /
• 2012

Purpose: Drying characteristics of sawdust was studied under batch mode using lab scale microwave dryer. The objective of this study was to investigate the effect of material load and microwave output power on drying characteristics of sawdust. Methods: Material load and microwave output power were varied from 23 to 186 g and 530 to 370 W respectively. Different kinetic models were tested to fit the drying rates of sawdust. Similarly, the activation energy was calculated by employing the Arrhenius equation. Results: The drying efficiency increased considerably, whereas the specific energy consumption significantly decreased with increase in material load and microwave output power. The cumulative energy efficiency increased by 9%, and the specific energy consumption decreased by 8% when the material load was increased from 23 to 186 g. The effective diffusivity increased with decrease in material load and increase in microwave output power. The previously published model gave the best fit for data points with $R^2$ and RMSE values of 0.999 and 0.01, respectively. Conclusions: The data obtained from this study could be used as a basis for modeling of large scale industrial microwave dryers for the pellet production.

• Human Ecology Research
• /
• v.54 no.6
• /
• pp.575-588
• /
• 2016

This study empirically examined the effects of filial piety on motivations for parenthood among Vietnamese and Korean college students, who represent a generation of young adults and prospective parents in both countries. The Vietnamese data were collected from 325 college students enrolled in three universities located in Hanoi and Korean data were collected from 216 students from a single large university in Seoul. Student respondents were asked to complete the self-administered questionnaire including 'Filial Piety Scale' and 'Motivations for Parenthood Scale.' The results revealed that the Vietnamese students reported a significantly higher level of 'general filial piety' than their Korean counterparts. Vietnamese and Korean participants showed no significant difference in total motivations for parenthood. Among the five sub-factors of motivations for parenthood, however, the Vietnamese students were more likely to place a value on the expansion of self-motivation while their Korean counterparts considered the motivation to strengthen biological family ties to be more salient. Finally, after controlling for sociodemographic characteristics, hierarchical regression analysis revealed that the more filial Vietnamese and Korean college students were towards their parents, the more child-related motives they held in general. The results are discussed in relation to each country's degree of modernization and to recommend prospective family planning and population policies in Vietnam based on the experiences of Korea industrialization.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.22 no.4
• /
• pp.55-60
• /
• 2018

The thermal property is one of the most important characteristics in the field of energetic materials. Because energy materials release decomposition heat, differential scanning calorimetry (DSC) is frequently used for thermal analysis. However, thermodynamic events, such as melting can interfere with DSC kinetic analysis. In this study, we use isothermal mode for DSC measurement to avoid thermodynamic issues. We also merge accelerating rate calorimetry(ARC) data with DSC data to obtain a robust prediction results for small scale samples and for large scale samples as well. For the thermal property prediction, advanced kinetics and technology solutions(AKTS) programs are used.