• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.33 no.4
• /
• pp.73-92
• /
• 2022

This study intends to design a model that can effectively service policy data necessary for the implementation of new national agenda in order to provide high-quality policy information services that go beyond those of the existing Policy Information Portal (POINT) of National Sejong Library. To this end, it was determined that providing an integrated search environment, in lieu of data search through individual access, was necessary. Subsequently, four possible models for a national agenda service model were presented. First, designing a computerized system for both interface and electronic information source aspects was proposed for the national agenda service system operation. Second, designing the Linked Open Data system and the time-series service system for national policy information, providing the translation service of overseas original data, and securing the researcher's desired data were presented for the national agenda service information source operation. Third, strengthening public relations for policy users, building and promoting the site brand, operating SNS channels, and reinforcing the activation of auxiliary materials and the accessibility of external services were proposed for public relations of national agenda service. Fourth, expanding the information network with Open API, cloud service, and overseas libraries was proposed for collaborating and cooperating with the agenda service.

• Journal of Bio-Environment Control
• /
• v.31 no.3
• /
• pp.152-162
• /
• 2022

This study developed simulation model for predicting the greenhouse interior environment using artificial intelligence machine learning techniques. Various methods have been studied to predict the internal environment of the greenhouse system. But the traditional simulation analysis method has a problem of low precision due to extraneous variables. In order to solve this problem, we developed a model for predicting the temperature inside the greenhouse using machine learning. Machine learning models are developed through data collection, characteristic analysis, and learning, and the accuracy of the model varies greatly depending on parameters and learning methods. Therefore, an optimal model derivation method according to data characteristics is required. As a result of the model development, the model accuracy increased as the parameters of the hidden unit increased. Optimal model was derived from the GRU algorithm and hidden unit 6 (r² = 0.9848 and RMSE = 0.5857℃). Through this study, it was confirmed that it is possible to develop a predictive model for the temperature inside the greenhouse using data outside the greenhouse. In addition, it was confirmed that application and comparative analysis were necessary for various greenhouse data. It is necessary that research for development environmental control system by improving the developed model to the forecasting stage.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.377-396
• /
• 2023

As the cryptocurrency market continues to grow, it has developed into a new financial market. The need for investment strategy research on the cryptocurrency market is also emerging. This study aims to conduct an empirical analysis on an investment methodology of cryptocurrency that combines short-term trading strategy and deep learning. Daily price data of the Ethereum was collected through the API of Upbit, the Korean cryptocurrency exchange. The investment performance of the experimental model was analyzed by finding the optimal parameters based on past data. The experimental model is a volatility breakout strategy(VBS), a Long Short Term Memory(LSTM) model, moving average cross strategy and a combined model. VBS is a short-term trading strategy that buys when volatility rises significantly on a daily basis and sells at the closing price of the day. LSTM is suitable for time series data among deep learning models, and the predicted closing price obtained through the prediction model was applied to the simple trading rule. The moving average cross strategy determines whether to buy or sell when the moving average crosses. The combined model is a trading rule made by using derived variables of the VBS and LSTM model using AND/OR for the buy conditions. The result shows that combined model is better investment performance than the single model. This study has academic significance in that it goes beyond simple deep learning-based cryptocurrency price prediction and improves investment performance by combining deep learning and short-term trading strategies, and has practical significance in that it shows the applicability in actual investment.

• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.126-137
• /
• 2023

In this study, a recurrent neural network (RNN) was employed as a methodological approach to classify dolphin click signals derived from ocean monitoring data. To improve the accuracy of click signal classification, the single time series data were transformed into fractional domains using fractional Fourier transform to expand its features. Transformed data were used as input for three RNN models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM), which were compared to determine the optimal network for the classification of signals. Because the fractional Fourier transform displayed different characteristics depending on the chosen angle parameter, the optimal angle range for each RNN was first determined. To evaluate network performance, metrics such as accuracy, precision, recall, and F1-score were employed. Numerical experiments demonstrated that all three networks performed well, however, the BiLSTM network outperformed LSTM and GRU in terms of learning results. Furthermore, the BiLSTM network provided lower misclassification than the other networks and was deemed the most practically appliable to field data.

• Tunnel and Underground Space
• /
• v.33 no.3
• /
• pp.169-188
• /
• 2023

Fires in tunnels are characterized by higher temperature rise and higher maximum temperatures compared to ground fires. For this reason, countries such as the Netherlands and Germany have developed separate temperature-time curves for use in tunnel fires. Fires in tunnels cause damage to the tunnel lining, such as loss of section and deterioration of the material properties. This study reviewed the design concept of fire stability of structures, section loss due to spalling, changes in physicochemical and mechanical properties of tunnel lining materials, fireproofing materials for structure safety, and fire damage prediction models. In order to secure the stability of a structure against fire, it is necessary to identify the type of structure and the possible fire load at the design stage, identify the expected section loss and damage range, and prepare for such damage through fireproofing materials. In this study, we have summarized the matters that can be referred to in performing such a series of tasks and presented our opinions on them.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5B
• /
• pp.495-504
• /
• 2008

Evapotranspiration (ET) is an important state variable while simulating daily streamflow in hydrological models. In the estimation of ET, for example, when using FAO Penman Monteith equation, the LAI (Leaf Area Index) value reflecting the conditions of vegetation generally affects considerably. Recently in evaluating the vegetation condition as a fixed quantity, the remotely sensed LAI from MODIS satellite data is available, and the time series values of spatial LAI coupled with land use classes are utilized for ET evaluation. Four years (2001-2004) of MODIS LAI was prepared for the evaluation of Penman Monteith ET in the continuous hydrological model, SLURP (Semi-distributed Land Use-based Runoff Processes). The model was applied for simulating the dam inflow of Chungju watershed ($6661.3km^2$) located in the upstream of Han river basin. For four years (2001-2004) dam inflow data and meteorological data, the model was calibrated and verified using MODIS LAI data. The average Nash-Sutcliffe model efficiency was 0.66. The 4 years watershed average Penman Monteith ETs of deciduous, coniferous, and mixed forest were 639.1, 422.4, and 631.6 mm for average MODIS LAI values of 3.64, 3.50, and 3.63 respectively.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.1-14
• /
• 2023

Soybeans are one of the world's top five staple crops and a major source of plant-based protein. Due to their susceptibility to climate change, which can significantly impact grain production, the National Agricultural Science Institute is conducting research on crop phenotypes through growth analysis of various soybean varieties. While the process of capturing growth progression photos of soybeans is automated, the verification, recording, and analysis of growth stages are currently done manually. In this paper, we designed and trained a YOLOv5s model to detect soybean leaf objects from image data of soybean plants and a Convolution Neural Network (CNN) model to judgement the unfolding status of the detected soybean leaves. We combined these two models and implemented an algorithm that distinguishes layers based on the coordinates of detected soybean leaves. As a result, we developed a program that takes time-series data of soybeans as input and performs growth analysis. The program can accurately determine the growth stages of soybeans up to the second or third compound leaves.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1125-1134
• /
• 2023

Out of the total 17,000 reservoirs in Korea, 13,600 small agricultural reservoirs do not have hydrological measurement facilities, making it difficult to predict water storage volume and appropriate operation. This paper examined univariate and multivariate long short-term memory (LSTM) modeling to predict the storage rate of agricultural reservoirs using remote sensing and artificial intelligence. The univariate LSTM model used only water storage rate as an explanatory variable, and the multivariate LSTM model added n-day accumulative precipitation and date of year (DOY) as explanatory variables. They were trained using eight years data (2013 to 2020) for Idong Reservoir, and the predictions of the daily water storage in 2021 were validated for accuracy assessment. The univariate showed the root-mean square error (RMSE) of 1.04%, 2.52%, and 4.18% for the one, three, and five-day predictions. The multivariate model showed the RMSE 0.98%, 1.95%, and 2.76% for the one, three, and five-day predictions. In addition to the time-series storage rate, DOY and daily and 5-day cumulative precipitation variables were more significant than others for the daily model, which means that the temporal range of the impacts of precipitation on the everyday water storage rate was approximately five days.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.6
• /
• pp.201-214
• /
• 2023

This study attempted to analyze the impact of individual entrepreneurial capabilities on entrepreneurial intention targeting small and medium-sized business employees, and sought to confirm the mediating effect of entrepreneurial efficacy and entrepreneurial mentoring between entrepreneurial capabilities and entrepreneurial intention. The sub-variables of entrepreneurship competency were analyzed separately into creativity, problem solving, communication, and marketing. 368 questionnaires collected from employees at small and medium-sized manufacturing companies located across the country were used for empirical analysis. A parallel dual mediation model with no causal relationship between parameters was used for empirical analysis using SPSS v26.0 and PROCESS macro v4.2. As a result of the analysis, first, among the start-up competencies, creativity, communication, and marketing were confirmed to have a significant positive (+) effect on start-up efficacy. Second, among the start-up competencies, creativity, communication, and marketing were tested to have a significant positive influence on start-up mentoring. Third, both startup efficacy and startup mentoring were found to have a significant positive influence on startup intention. Fourth, among start-up capabilities, creativity and marketing were confirmed to have a significant positive (+) effect on start-up intention. Fifth, startup efficacy and startup mentoring were found to have a mediating effect on startup intention except for problem solving among startup competencies. As a result, it was confirmed that in order to strengthen the intention to start a business among small and medium-sized business employees, start-up efficacy and start-up mentoring are important factors, and that marketing and creativity have an important influence among individual start-up capabilities, so education and prior preparation for these are necessary. As follow-up research, it will be necessary to apply multivariate models, analyze time series data, research considering external environmental factors, and test the difference between start-up capabilities and performance considering detailed population characteristics.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.150-157
• /
• 2024

In this paper, we propose a novel algorithm for predicting the number of apples on an apple tree using a deep learning-based object detection model and a polynomial regression model. Measuring the number of apples on an apple tree can be used to predict apple yield and to assess losses for determining agricultural disaster insurance payouts. To measure apple fruit load, we photographed the front and back sides of apple trees. We manually labeled the apples in the captured images to construct a dataset, which was then used to train a one-stage object detection CNN model. However, when apples on an apple tree are obscured by leaves, branches, or other parts of the tree, they may not be captured in images. Consequently, it becomes difficult for image recognition-based deep learning models to detect or infer the presence of these apples. To address this issue, we propose a two-stage inference process. In the first stage, we utilize an image-based deep learning model to count the number of apples in photos taken from both sides of the apple tree. In the second stage, we conduct a polynomial regression analysis, using the total apple count from the deep learning model as the independent variable, and the actual number of apples manually counted during an on-site visit to the orchard as the dependent variable. The performance evaluation of the two-stage inference system proposed in this paper showed an average accuracy of 90.98% in counting the number of apples on each apple tree. Therefore, the proposed method can significantly reduce the time and cost associated with manually counting apples. Furthermore, this approach has the potential to be widely adopted as a new foundational technology for fruit load estimation in related fields using deep learning.