• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.47-56
• /
• 2023

Hydrogen energy is an eco-friendly energy that produces heat and electricity with high energy efficiency and does not emit harmful substances such as greenhouse gases and fine dust. In particular, smart hydrogen energy is an economical, sustainable, and safe future smart hydrogen energy service, which means a service that stably operates based on 'data' by digitally integrating hydrogen energy infrastructure. In this paper, in order to implement a data-based hydrogen charging station demand forecasting model, three hydrogen charging stations (Chuncheon, Sokcho, Pyeongchang) installed in Gangwon-do were selected, supply and demand data of hydrogen charging stations were secured, and 7 machine learning and deep learning algorithms were used. was selected to learn a model with a total of 27 types of input data (weather data + demand for hydrogen charging stations), and the model was evaluated with root mean square error (RMSE). Through this, this paper proposes a machine learning-based hydrogen charging station energy demand prediction model for optimal hydrogen energy supply and demand.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.861-864
• /
• 2011

Since national GHG reduction target by 2020 has been presented in Korea, the role of railroad has been reinforced within transport system due to the allocation of reduction target into sector. So, it is necessary to manage activity data systematically for the calculation of GHG emission in railroad. Now, the activity data of diesel consumption for NIR(National Inventory Report) are provided from oil supply and demand statistics. On the other hands, the activity data collected directly from railroad operating companies are used for GHG & Energy Target Management Act. This study aimed to assess the GHG emissions using two kinds of activity data related to the diesel consumption of railroad in 2009 and 2010. As a result, GHG emissions based on oil supply and demand statistics was 636 thousands ton $CO_{2e}$, but the activity data collected from railroad operating companies showed 649 thousands ton $CO_{2e}$ in 2009. Also, the gap of $CO_{2e}$ emission was increased in 2010. These trends were caused because oil supply and demand statistics included total diesel sales volume during 1 year and the activity data collected from railroad operating companies were the amount of diesel consumption only at railcar operation and maintenance step. In conclusion, it is important to develop the management and verification system of activity data with high reliability to substitute oil supply and demand statistics in railroad sector.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.61-69
• /
• 2021

On-demand broadcast is an effective data dissemination technique in mobile computing environments. This paper explores the issues for scheduling multi-data queries in on-demand broadcast environments, and proposes a new broadcast scheduling scheme named CASS. The proposed scheme prioritizes queries by reflecting the characteristics of multi-data queries, and selects the data that has not been broadcast in the query for the longest time as the broadcast data according to the query priority. Simulation is performed to evaluate the performance of CASS. The simulation results show that the proposed scheme outperforms other schemes in terms of the average response time since it can show highly desirable characteristics in the aspects of query data adjacency and data conflict rate.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.2
• /
• pp.395-406
• /
• 2017

The purpose of this study is to identify the pattern of daily electricity demand through clustering and classification. The hourly data was collected by KPS (Korea Power Exchange) between 2008 and 2012. The time trend was eliminated for conducting the pattern of daily electricity demand because electricity demand data is times series data. We have considered k-means clustering, Gaussian mixture model clustering, and functional clustering in order to find the optimal clustering method. The classification analysis was conducted to understand the relationship between external factors, day of the week, holiday, and weather. Data was divided into training data and test data. Training data consisted of external factors and clustered number between 2008 and 2011. Test data was daily data of external factors in 2012. Decision tree, random forest, Support vector machine, and Naive Bayes were used. As a result, Gaussian model based clustering and random forest showed the best prediction performance when the number of cluster was 8.

• Journal of Korea Water Resources Association
• /
• v.56 no.7
• /
• pp.439-449
• /
• 2023

Recent advancements in data measuring technology have facilitated the installation of various sensors, such as pressure meters and flow meters, to effectively assess the real-time conditions of water distribution systems (WDSs). However, as cities expand extensively, the factors that impact the reliability of measurements have become increasingly diverse. In particular, demand data, one of the most significant hydraulic variable in WDS, is challenging to be measured directly and is prone to missing values, making the development of accurate data generation models more important. Therefore, this paper proposes an adversarially trained autoencoder (ATAE) model based on generative deep learning techniques to accurately estimate demand data in WDSs. The proposed model utilizes two neural networks: a generative network and a discriminative network. The generative network generates demand data using the information provided from the measured pressure data, while the discriminative network evaluates the generated demand outputs and provides feedback to the generator to learn the distinctive features of the data. To validate its performance, the ATAE model is applied to a real distribution system in Austin, Texas, USA. The study analyzes the impact of data uncertainty by calculating the accuracy of ATAE's prediction results for varying levels of uncertainty in the demand and the pressure time series data. Additionally, the model's performance is evaluated by comparing the results for different data collection periods (low, average, and high demand hours) to assess its ability to generate demand data based on water consumption levels.

• Environmental and Resource Economics Review
• /
• v.27 no.2
• /
• pp.287-313
• /
• 2018

This paper measures and analyzes cooling and heating demand in Korean electricity demand using time-varying temperature response functions and cooling and heating temperature effects. We fit the model to Korean data for residential and commercial sector over 1999:01~2016:12 and the estimation results show that the growth rate of heating demand is much higher than that of base and cooling demand, and especially the growth rate of heating demand in commercial sector is much higher. And we define the temperature-normalized demand conditioning that monthly temperatures are assumed as average monthly temperatures. The growth rate of heating demand in the estimated temperature-normalized demand is higher than that in the real demand. Our results are expected to be a base data for Winter Demand Management and short-term electricity demand forecasting.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.11 no.2
• /
• pp.252-259
• /
• 2005

Purpose: Asthma is the most common chronic disease of childhood. It's important mother's caring for management of children with asthma. This study was to provide the evidenced data for preparing an educational program by identifying the knowledge level and educational demand about pediatric asthma of mothers of children with asthma. Method: The subjects were 91 mothers of children with asthma who admitted at 3 hospital in Busan. The data were collected through a self-reporting questionnaire from Feburary to May, 2005. The data was analyzed by SPSS 10.0 program. Results: The total mean percentage of correct answer of knowledge about pediatric asthma was 55.6% and the total mean $score{\pm}SD$ of educational demand about pediatric asthma was $4.40{\pm}0.50$. The knowledge level was statistically different by recurrence number(F=3.08, p=.049). There was not correlation between knowledge level and eucational demand. Conclusions: The mothers of children with asthma had a medium knowledge level and a high educational demand. Based on the results, mothers' knowledge is an important part of children with asthma management. Therefore nursing intervention program for mothers of children with asthma should be developed and the mothers should cope with asthma effectively.

• The Research Journal of the Costume Culture
• /
• v.16 no.4
• /
• pp.681-695
• /
• 2008

This study was accomplished to investigate the preference of clothing materials and the clothing demand performance for underwear and everyday dress of atopic patients. As this study was the research study by a use of a questionnaire, the finally total 987 copies of the collected questionnaires were used to analyze the data. SPSS was used for the statistical analysis of data. To analyze the data, frequency analysis, percentage, $X^2$-test, reliability analysis, factor analysis, t-test, ANOVA and Duncan's multiple comparisons were used. The results obtained are as follows. In factor analysis for clothing materials and the demand performance which atopic patients favor, the preference factors for underwear materials were classified as pliability/a sense of weight, a sense of cold and warmth, tactility, and elasticity. Those for everyday wear were classified as pliability/surface roughness, a sense of cold and warmth, a sense of weight, and elasticity. And the demand performance factors for underwears were classified as thermophysiology, care convenience, and skin contact. Those for everyday wear were classified as comfortableness and care convenience. In the difference analysis for the preference and the demand performance, Both everyday wear and underwear showed a significant difference for the preference and the demand performance according to gender, age, income, education level, and occupation.

• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.164-172
• /
• 2020

The interest and importance of the convergence services for healthcare expand more and more as the average life expectancy increases. Convergence of ICT and healthcare technology unfold efficient and quick health services. Recently, healthcare services provide to clients with apps over web. On-demand wireless data broadcast supports any number of clients to access their desired data items dynamically by responding the needs for data items from the clients. In this paper, we propose an on-demand system to broadcast FHIR bundles for efficient healthcare services. We use time-parameterized replacing policy for renewing the bundle items on the wireless broadcast channel. The policy lets the on-demand broadcasting dynamic by controlling the time duration for the bundles to reside over the wireless channel. With simulation studies using an implemented testbed, we evaluate the performances of the proposed system in access time and tuning time. For evaluation, we compare the time-parameterized replacing policy of the proposed system with regular-number replacing policy. The proposed time-parameterized replacing policy shows shorter access time than the regular-number replacing policy because the policy responds more actively and dynamically to the change of the needs of the clients for FHIR bundles.

• Journal of Information Technology Applications and Management
• /
• v.30 no.3
• /
• pp.1-13
• /
• 2023

Demand forecasting is a crucial task for an online retail where has to manage daily fresh foods effectively. Failing in forecasting results loss of profitability because of incompetent inventory management. This study investigated the optimal performance of different forecasting models for a very short shelf-life product. Demand data of 13 perishable items with aging of 210 days were used for analysis. Our comparison results of four methods: Trivial Identity, Seasonal Naïve, Feed-Forward and Autoregressive Recurrent Neural Networks (DeepAR) reveals that DeepAR outperforms with the lowest MAPE. This study also suggests the managerial implications by employing coefficient of variation (CV) as demand variation indicators. Three classes: Low, Medium and High variation are introduced for classify 13 products into groups. Our analysis found that DeepAR is suitable for medium and high variations, while the low group can use any methods. With this approach, the case can gain benefit of better fill-rate performance.