• The Transactions of the Korean Institute of Power Electronics
• /
• v.27 no.4
• /
• pp.316-324
• /
• 2022

This paper uses seasonal auto-regressive integrated moving average (S-ARIMA), which is efficient in seasonality between time-series models, to predict the degradation tendency for lithium-ion batteries and study a method for improving the predictive performance. The proposed method analyzes the degradation tendency and extracted factors through an electrical characteristic experiment of lithium-ion batteries, and verifies whether time-series data are suitable for the S-ARIMA model through several statistical analysis techniques. Finally, prediction of battery aging is performed through S-ARIMA, and performance of the model is verified through error comparison of predictions through mean absolute error.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.377-379
• /
• 2023

Concept drift detection on data stream is the major issue to maintain the performance of the machine learning model. Since the online stream is to be a function of time, the classical statistic methods are hard to apply. In particular case of seasonal time series, a novel window strategy with Fourier analysis however, gives a chance to adapt the classical methods on the series. We explore the KS-test for an adaptation of the periodic time series and show that this strategy handles a complicate time series as an ordinary tabular dataset. We verify that the detection with the strategy takes the second place in time delay and shows the best performance in false alarm rate and detection accuracy comparing to that of arbitrary window sizes.

• Asian Journal of Turfgrass Science
• /
• v.13 no.1
• /
• pp.37-54
• /
• 1999

This study was initiated to evaluate the seasonal turf performance in a tree shade and to suggest shade-tolerant turfgrasses suitable for domestic climate conditions. Atotal of 21 trufgrasses were tested, comprising of Korean lawngrass, shade-tolerant fine fescues, and newly-developed, shade-tolerant varieties of cool-season grasses. Dirrerences in shade tolerance were observed among varieties, species, and genera. Overall turf performance of C3 turfgrasses was better than that of C4 Korean lawngrass under a tree shade. Coarse-type fescues were excellent in shade tolerance, bluegrasses good, ryegrasses medium, fine-type fescues fair, and zoysiagrasses poor, respectively. Inter-species comparison in relative index of shade tolerance(IRST) demonstrated that tall fescue and fough bluegrass were greatest of 7.3, Poa supina 6.4, perennial ryegrass 5.0, Kentucky bluegrass 4.8, and fine fescues least, respectively. A great variation in RIST was observed with fine fescues; creeping red fescue was 3.6, chewings fescue 2.5, hard fescue 2.1, and sheep fescue 1.4, respectively. Among 21 turfgrasses evaluated, tall fescue 'Rebel Jr.', 'Era', and 'Oixie' and rough bluegrass 'Sabre' were the shade-tolerant varieties under a tree shade in Korea. Tall fescue, 'Rebel Jr.' was considered as the most shade-tolerant variety in the experiment. Fine fescues as creeping red fescue, chewings fescue, hare fescue, and sheep fescue, used as the shade-tolerant species in a cool climate of Europe and North America, were not suitable under domestic climate conditions.

• Journal of the Korean Society for Geothermal and Hydrothermal Energy
• /
• v.13 no.4
• /
• pp.31-38
• /
• 2017

The heating and cooling air conditioning field has been increasing the problems of energy consumption and global warming in the world. A geothermal heat pump has been known as one of the highest efficient heating and cooling system. In this study, the analysis about the test standards of the geothermal heat pump of the Republic of Korea was executed. From the research, the following results were given. It is needed to address the domestic test standard for direct heat exchange geothermal heat pump. Water to air multi geothermal heat pump test standard was only developed in Korea. The test standard to calculate a seasonal energy efficiency ratio for cooling period and heat seasonal performance factor for heating period should be newly developed to estimate actual annual energy consumption and $CO_2$ emission.

• Transactions of the Korean hydrogen and new energy society
• /
• v.29 no.6
• /
• pp.606-619
• /
• 2018

This study focuses on the performance of hydrogen energy based hybrid system in terms of system reliability of electricity generation. With this aim to evaluate the off-grid system of photovoltaic (PV), wind turbine, electrolyzer, fuelcell, $H_2$ tank and storage batteries, 14 different sites in South Korea are simulated using HOMER. Performance analysis includes simulation on the different sites, verification of operational behaviors on regional and seasonal basis, and comparison among a control group. The result shows that the generation performance of hydrogen powered fuelcell is greatly affected by geographical change rather than seasonal effect. In addition, as the latitude of the hybrid systems location decrease, renewable power output and penetration ratio (%) increase under constant electrical load. Therefore, the hydrogen based hybrid system creates the stability of electricity generation, which best suits in the southern part of South Korea.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1069-1079
• /
• 2019

In this study, we developed a $PM_{10}$ forecasting model using DNN and Membership Function, and improved the forecasting performance. The model predicts the $PM_{10}$ concentrations of the next 3 days in the Seoul area by using the weather and air quality observation data and forecast data. The best model(RM14)'s accuracy (82%, 76%, 69%) and false alarm rate(FAR:14%,33%,44%) are good. Probability of detection (POD: 79%, 50%, 53%), however, are not good performance. These are due to the lack of training data for high concentration $PM_{10}$ compared to low concentration. In addition, the model dose not reflect seasonal factors closely related to the generation of high concentration $PM_{10}$. To improve this, we propose Julian date membership function as inputs of the $PM_{10}$ forecasting model. The function express a given date in 12 factors to reflect seasonal characteristics closely related to high concentration $PM_{10}$. As a result, the accuracy (79%, 70%, 66%) and FAR (24%, 48%, 46%) are slightly reduced in performance, but the POD (79%, 75%, 71%) are up to 25% improved compared with those of the RM14 model. Hence, this shows that the proposed Julian forecast model is effective for high concentration $PM_{10}$ forecasts.

• The Journal of Society for e-Business Studies
• /
• v.24 no.1
• /
• pp.1-16
• /
• 2019

Recently, since responding to meteorological changes depending on increasing greenhouse gas and electricity demand, the importance prediction of photovoltaic power (PV) is rapidly increasing. In particular, the prediction of PV power generation may help to determine a reasonable price of electricity, and solve the problem addressed such as a system stability and electricity production balance. However, since the dynamic changes of meteorological values such as solar radiation, cloudiness, and temperature, and seasonal changes, the accurate long-term PV power prediction is significantly challenging. Therefore, in this paper, we propose PV power prediction model based on deep learning that can be improved the PV power prediction performance by learning to use meteorological and seasonal information. We evaluate the performances using the proposed model compared to seasonal ARIMA (S-ARIMA) model, which is one of the typical time series methods, and ANN model, which is one hidden layer. As the experiment results using real-world dataset, the proposed model shows the best performance. It means that the proposed model shows positive impact on improving the PV power forecast performance.

• Journal of Animal Reproduction and Biotechnology
• /
• v.36 no.4
• /
• pp.261-269
• /
• 2021

Because sows are industrially vital for swine production, monitoring for their health or disorder status is important to ensure high reproductive performance. Especially, ambient temperature changes in different season, especially during summer, are directly influenced to the reproductive performance of sows. Although the serum biochemical parameters are widely applied in the veterinary medicine with wide ranges for the physiological process, the values are also influenced by several factors such as age, breed, gender, and stress. In addition, domestic sows in Korea-specific reference interval (RI) for serum biochemistry has not been established yet. Therefore, the present study was aimed to evaluate seasonal variation of RIs in the serum biochemistry in domestic sows in Korea at different seasons and to establish normal RIs using a RI finding program (Reference Value Advisor). Significant difference (p < 0.05) on the different seasons were identified in several serum biochemical parameters including BUN, CRE, GGT, GLU, ALB, TP, LDH and Na in sows. Therefore, we further established RIs, specific in domestic sows in Korea regardless of season. The established RIs based on the serum biochemical values provide a baseline for interpreting biochemical results in the domestic sows in Korea, regardless of seasonal effect. It may contribute to develop a strategy for better reproductive performance by improving breeding management practice and evaluating health of pig herds, which facilitate to avert the economic loss in summer infertility in sows.

• Transactions of the KSME C: Technology and Education
• /
• v.4 no.1
• /
• pp.3-10
• /
• 2016

Heat pump unit performance is represented by the COP(Coefficient of Performance) and expressed by the one point design condition according to KS C 9306. However, when heat pump operated to the real buildings, the simulations are changed continuously according to the actual weather conditions, the building load and heat pump source conditions. The purpose of this paper is to evaluate the APF(Annual performance factor) for a climate dependent building integrated air-to-air heat pump system in major cities in Korea. TRNSYS simulation tool with an international MV standard based IPMVP 4.4.2 was utilized to perform the annual performance analysis. The APF with the multi-performance data based method was calculated as 2.29 for Daejeon residential building case while Busan residential building case appeared as the highest with 2.36.

• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.1-17
• /
• 2013

In this article, several types of hybrid forecasting models are suggested. In particular, hybrid models using the generalized additive model (GAM) are newly suggested as an alternative to those using neural networks (NN). The prediction performances of various hybrid and non-hybrid models are evaluated using simulated time series data. Five different types of seasonal time series data related to an additive or multiplicative trend are generated over different levels of noise, and applied to the forecasting evaluation. For the simulated data with only seasonality, the autoregressive (AR) model and the hybrid AR-AR model performed equivalently very well. On the other hand, if the time series data employed a trend, the SARIMA model and some hybrid SARIMA models equivalently outperformed the others. In the comparison of GAMs and NNs, regarding the seasonal additive trend data, the SARIMA-GAM evenly performed well across the full range of noise variation, whereas the SARIMA-NN showed good performance only when the noise level was trivial.