• Review of Culture and Economy
• /
• v.21 no.3
• /
• pp.59-88
• /
• 2018

This study examines demand of the Korean TV VOD using monthly aggregate data and time series analysis models. In particular, the impact of box office attendance, number of IPTV subscribers, income and price of substitutes on TV VOD market is analyzed. Data on TV VOD download during the period 2013 January to 2018 June are used for the empirical analysis. TV VOD demand shows lower level of seasonality than box office attendance and the share of monthly top1 movie in TV VOD platform is also lower than that of box office attendance. The relationship between a movie's holdback and box office performance does not seem consistent. The empirical result of ARDL model reveals that in the short-run box office attendance, number of IPTV subscribers and price of substitutes have significant impact on TV VOD demand. The result on the long-term relation shows that income is the only determinant of TV VOD demand. The impact of box office attendance on TV VOD is not shown to be robust both for the short-term and long-term.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.322-323
• /
• 2022

The most necessary thing for the optimal operation of a water purification plant is to accurately predict the pattern and amount of tap water used by consumers. The required amount of tap water should be delivered to the drain using a pump and stored, and the required flow rate should be supplied in a timely manner using the minimum amount of electrical energy. The short-term demand forecasting required from the point of view of energy optimization operation among water purification plant volume predictions has been made in consideration of seasons, major periods, and regional characteristics using time series analysis, regression analysis, and neural network algorithms. In this paper, we analyzed energy management methods through AI-based complex sensor applicability analysis such as LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Units), which are types of cyclic neural networks.

• Ocean Science Journal
• /
• v.43 no.1
• /
• pp.1-7
• /
• 2008

Physical and biological environmental variations in the East Sea were investigated by analysing time-series of oceanographic data and meteorological indices. From 1971 to 2000, dominant periodicity in water temperature variations had two apparent periods of 3 to 4 years and of decades, especially in the southwestern part of the East Sea affected by the influence of inflowing Tsushima warm current. Fluctuating water temperature within a certain period appears to respond to El $Ni{\tilde{n}}o$ events with a time lag. It was found that there was a strong correlation between water temperature and El $Ni{\tilde{n}}o$ events with a time lag of 1.5 and 5.5 years for periods of 3 to 6 years and of decades, respectively. Corresponding with El $Ni{\tilde{n}}o$ events, water temperature variability also showed strong correlation with shift and/or changes in biological and chemical environments of nutrient concentrations, zooplankton biomass, and fisheries. However, there also occurred a short-term periodicity of water temperature variations. Within a period of 1 to 4 years, a relatively short-term cycle of water temperature variation had strong correlation with other climate indices such as Pacific Decadal Oscillation and monsoon index. After comparing coherence and phase spectrum between water temperature and different climate indices, we found that there was a shift of coherent periods to another climate index during the years when climate regime shift was reported.

• Environmental and Resource Economics Review
• /
• v.25 no.2
• /
• pp.141-178
• /
• 2016

This paper, using AMR (Automatic Meter Reading) electricity data accurately measured in real time, analyses the characteristics and patterns of temperature effect on the industrial electricity usage. For this goal, the paper constructs and estimates a model which captures the properties of AMR time series including long-term trends, mid-term temperature effects, and short-term special day effects. Based on the estimated temperature response function and the temperature effect, we categorize the whole industry into two groups: one group with sharp temperature effect and the other with weak temperature effect. Furthermore, the industry group with sharp temperature effect is classified into a summer peak industry group and a winter peak industry group, based on the estimates of the temperature response function. These empirical results carry practical policy implications on the real time electricity demand management.

• Nuclear Engineering and Technology
• /
• v.52 no.7
• /
• pp.1429-1435
• /
• 2020

Applying an accurate parametric prediction model to identify abnormal or false pressurizer water levels (PWLs) is critical to the safe operation of marine pressurized water reactors (PWRs). Recently, deep-learning-based models have proved to be a powerful feature extractor to perform high-accuracy prediction. However, the effectiveness of models still suffers from two issues in PWL prediction: the correlations shifting over time between PWL and other feature parameters, and the example imbalance between fluctuation examples (minority) and stable examples (majority). To address these problems, we propose a cost-sensitive mechanism to facilitate the model to learn the feature representation of later examples and fluctuation examples. By weighting the standard mean square error loss with a cost-sensitive factor, we develop a Cost-Sensitive Long Short-Term Memory (CSLSTM) model to predict the PWL of PWRs. The overall performance of the CSLSTM is assessed by a variety of evaluation metrics with the experimental data collected from a marine PWR simulator. The comparisons with the Long Short-Term Memory (LSTM) model and the Support Vector Regression (SVR) model demonstrate the effectiveness of the CSLSTM.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.57-69
• /
• 2024

Crop classification plays a vitalrole in monitoring agricultural landscapes and enhancing food production. In this study, we explore the effectiveness of Long Short-Term Memory (LSTM) models for crop classification, focusing on distinguishing between apple and rice crops. The aim wasto overcome the challenges associatedwith finding phenology-based classification thresholds by utilizing LSTM to capture the entire Normalized Difference Vegetation Index (NDVI)trend. Our methodology involvestraining the LSTM model using a reference site and applying it to three separate three test sites. Firstly, we generated 25 NDVI imagesfrom the Sentinel-2A data. Aftersegmenting study areas, we calculated the mean NDVI values for each segment. For the reference area, employed a training approach utilizing the NDVI trend line. This trend line served as the basis for training our crop classification model. Following the training phase, we applied the trained model to three separate test sites. The results demonstrated a high overall accuracy of 0.92 and a kappa coefficient of 0.85 for the reference site. The overall accuracies for the test sites were also favorable, ranging from 0.88 to 0.92, indicating successful classification outcomes. We also found that certain phenological metrics can be less effective in crop classification therefore limitations of relying solely on phenological map thresholds and emphasizes the challenges in detecting phenology in real-time, particularly in the early stages of crops. Our study demonstrates the potential of LSTM models in crop classification tasks, showcasing their ability to capture temporal dependencies and analyze timeseriesremote sensing data.While limitations exist in capturing specific phenological events, the integration of alternative approaches holds promise for enhancing classification accuracy. By leveraging advanced techniques and considering the specific challenges of agricultural landscapes, we can continue to refine crop classification models and support agricultural management practices.

• The Research Journal of the Costume Culture
• /
• v.23 no.4
• /
• pp.604-615
• /
• 2015

The objectives of this study were to investigate whether heel height changes in the U.S. market occur in a cyclical pattern and heel heights show greater within-year variability over time. Heel height data from U.S. Vogue's spring and fall editions were analyzed over the time period 1950~2014. A total of 1581 pieces of data were measured in millimeter units using Adobe Illustrator and standardized by dividing the height of the heel by the shoe length through the curved sole line. To analyze the cycle pattern of heel heights, the yearly averages were standardized by using three-year moving average technique to average out the irregular components of time series data and give a better indication of the long-term fluctuation of heel height. To identify the degree of within-year variability of heel height, the standard deviation of the average measurements for a year was calculated, and then decade averages were drawn from the yearly averaged standard deviation. One-way ANOVA was conducted to compare the within-year variability of data in heel height over the time period studied by decade. The results showed: First, there was a trend toward higher heels from the early 1950s to 2011. Second, four cyclical movements of heel height were observed from 1950 to 2007, and heel heights gradually decreased after 2008. Third, the within-year variability significantly increased over time, especially after the 1980s.

• Journal of Korea Water Resources Association
• /
• v.46 no.12
• /
• pp.1249-1263
• /
• 2013

In order to minimize the damages caused by long-term drought, appropriate drought management plans of the basin should be established with the drought forecasting technology. Further, in order to build reasonable adaptive measurement for future drought, the duration and severity of drought must be predicted quantitatively in advance. Thus, this study, attempts to forecast drought in Korea by using an Artificial Neural Network Model, and drought index, which are the representative statistical approach most frequently used for hydrological time series forecasting. SPI (Standardized Precipitation Index) for major weather stations in Korea, estimated using observed historical precipitation, was used as input variables to the MLP (Multi Layer Perceptron) Neural Network model. Data set from 1976 to 2000 was selected as the training period for the parameter calibration and data from 2001 to 2010 was set as the validation period for the drought forecast. The optimal model for drought forecast determined by training process was applied to drought forecast using SPI (3), SPI (6) and SPI (12) over different forecasting lead time (1 to 6 months). Drought forecast with SPI (3) shows good result only in case of 1 month forecast lead time, SPI (6) shows good accordance with observed data for 1-3 months forecast lead time and SPI (12) shows relatively good results in case of up to 1~5 months forecast lead time. The analysis of this study shows that SPI (3) can be used for only 1-month short-term drought forecast. SPI (6) and SPI (12) have advantage over long-term drought forecast for 3~5 months lead time.

• Korean System Dynamics Review
• /
• v.17 no.2
• /
• pp.5-32
• /
• 2016

Purpose of this paper is to review series of Limits to Growth studies from its original Rome Club Report published in 1972 to the most recent one in 2012 by Jorgen Randers and finds its implications on concept and strategy of sustainable development. For this purpose first, this paper reviewed series of Limits to Growth studies in details with focus on scenarios used in simulation of world model. Second, response to the original Limit to Growth was reviewed and to see validity of its scenario based simulations, simulated results of interest variables and actual historical data up to the year 2010 was compared. Third, structure and key arguments in both studies, Limit to Growth studies and Our Common Future was explained and compared. Finally, implications of the Limit to Growth studies on concept and strategy for sustainable development was discussed. Based on the comparison, this paper argued that even if the term sustainable development was not used in the Limit to Growth at all, concept and strategies for sustainable development implied in the Limit to Growth are more clear and specific than those of Our Common Future. Since Limit to Growth studies were simulation based ones that produce detailed behaviors on interest variables, it clarifies more clearly the abstract concept of sustainable development and thus, provides specific guidelines for the direction of sustainable policy which has been suffering long from vagueness of concept of sustainable development.

• Journal of Korean Society of Forest Science
• /
• v.108 no.1
• /
• pp.10-20
• /
• 2019

The purpose of this study is to identify the long-term area changes in the subalpine coniferous forests in Korea in order to understand the changes in the subalpine forest ecosystems vulnerable to climate change. We analyzed 20 years of time-series Landsat satellite images (mid 1990s, mid 2010s) for change detection of coniferous forests and compared with the long term changes of climate information to identify their relationship in the study area. As a result, the area of coniferous forests in the study region decreased by 25% over 20 years. The regions with largest changes are Seoraksan, Baegunsan-Hambaeksan-Jangsan, Jirisan, and Hallasan. The region with the largest decrease in area was Baegunsan (reduced area: 542 ha), and the region with large decrease in area and the largest rate of decrease was Hallasan (rate of decrease: 33.3%). As the Jeju region has the most rapid temperature rise, it is projected that Hallasan is the most vulnerable forest ecosystem affected by climate change. The result of this study shows that from a long-term perspective the overall coniferous forests in the subalpine region are declining, but the trend varies in each region. This national and long-term information on the change of coniferous forests in the subalpine region can be utilized as baseline data for the detailed survey of endangered subalpine coniferous trees in the future.