• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.390-390
• /
• 2019

Application of Hidden Markov Model (HMM) to the hydrological time series would be an innovative way to identify extreme rainfall events in a series. Even though the optimum number of hidden states can be identify based on maximizing the log-likelihood or minimizing Bayesian information criterion. However, occasionally value for the log-likelihood keep increasing with the state which gives false identification of the optimum hidden state. Therefore, this study attempts to identify optimum number of hidden states for Colombo station, Sri Lanka as fundamental approach to identify frequency and percentage of extreme rainfall events for the station. Colombo station consisted of daily rainfall values between 1961 and 2015. The representative station is located at the wet zone of Sri Lanka where the major rainfall season falls on May to September. Therefore, HMM was ran for the season of May to September between 1961 and 2015. Results showed more or less similar log-likelihood which could be identified as maximum for states between 4 to 7. Therefore, measure of central tendency (i.e. mean, median, mode, standard deviation, variance and auto-correlation) for observed and simulated daily rainfall series was carried to each state to identify optimum state which could give statistically compatible results. Further, the method was applied for the second major rainfall season (i.e. October to February) for the same station as a comparison.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.57-66
• /
• 2023

Currently, a new energy system is emerging that implements consumption reduction by improving energy efficiency. Accordingly, as smart grids spread, the rate system by timing is expanding. The rate system by timing is a rate system that applies different rates by season/hour to pay according to usage. In this study, external factors such as temperature/day/time/season are considered and the time series prediction model, LSTM, is used to predict energy power usage data. Based on this energy usage prediction model, energy usage charges are reduced by analyzing usage patterns for each device and transferring power energy from the maximum load time to the light load time. In order to analyze the usage pattern for each device, a clustering technique is used to learn and classify the usage pattern of the device by time. In summary, this study predicts usage and usage fees based on the user's power data usage, analyzes usage patterns by device, and provides customized demand transfer services based on analysis, resulting in cost reduction for users.

• International journal of advanced smart convergence
• /
• v.11 no.1
• /
• pp.19-27
• /
• 2022

Across the world, 'housing' comprises a significant portion of wealth and assets. For this reason, fluctuations in real estate prices are highly sensitive issues to individual households. In Korea, housing prices have steadily increased over the years, and thus many Koreans view the real estate market as an effective channel for their investments. However, if one purchases a real estate property for the purpose of investing, then there are several risks involved when prices begin to fluctuate. The purpose of this study is to design a real estate price 'return rate' prediction model to help mitigate the risks involved with real estate investments and promote reasonable real estate purchases. Various approaches are explored to develop a model capable of predicting real estate prices based on an understanding of the immovability of the real estate market. This study employs the LSTM method, which is based on artificial intelligence and deep learning, to predict real estate prices and validate the model. LSTM networks are based on recurrent neural networks (RNN) but add cell states (which act as a type of conveyer belt) to the hidden states. LSTM networks are able to obtain cell states and hidden states in a recursive manner. Data on the actual trading prices of apartments in autonomous districts between January 2006 and December 2019 are collected from the Actual Trading Price Disclosure System of the Ministry of Land, Infrastructure and Transport (MOLIT). Additionally, basic data on apartments and commercial buildings are collected from the Public Data Portal and Seoul Metropolitan Government's data portal. The collected actual trading price data are scaled to monthly average trading amounts, and each data entry is pre-processed according to address to produce 168 data entries. An LSTM model for return rate prediction is prepared based on a time series dataset where the training period is set as April 2015~August 2017 (29 months), the validation period is set as September 2017~September 2018 (13 months), and the test period is set as December 2018~December 2019 (13 months). The results of the return rate prediction study are as follows. First, the model achieved a prediction similarity level of almost 76%. After collecting time series data and preparing the final prediction model, it was confirmed that 76% of models could be achieved. All in all, the results demonstrate the reliability of the LSTM-based model for return rate prediction.

• Journal of the Korean Society of Safety
• /
• v.16 no.1
• /
• pp.88-93
• /
• 2001

This study discusses frequency analysis based on autoregressive (AR) time series model, and process characterization in orthogonal cutting of a fiber-matrix composite materials. A sparsely distributed idealized composite material, namely a glass reinforced polyester (GFRP) was used as workpiece. Analysis method employs a force sensor and the signals from the sensor are processed using AR time series model. The resulting pattern vectors of AR coefficients are then passed to the feature extraction block. Inside the feature extraction block, only those features that are most sensitive to different types of cutting mechanisms are selected. The experimental correlations between the different chip formation mechanisms and AR model coefficients are established.

• East Asian Journal of Business Economics (EAJBE)
• /
• v.3 no.4
• /
• pp.9-15
• /
• 2015

The exchange rate is a very important macro variable that has influence on the whole economy and has, therefore, been the topic of many discussions amongst policymakers, academics and other economic agents. The issue of whether to have a fixed, pegged or floating exchange rate regime was highly debated during the 1970s. The purpose of this paper is to investigate what factors determine the exchange rate in Somalia. Quantitative research methodology has been employed to develop regression model using time series data for the period of 12 years. The regression model has been developed based on Quantity theory of money, purchasing power parity and uncovered interest rate parity theory. Somalia is on the countries where the highest exchange rate volatility exists; for example in 2012, the rate jumped 29% percent and two weak later dropped 21%, when Turkish humanitarian aid agencies injected the market a lot of U.S dollar. Based on my study using regression model for time series data of 12 years, the four factors are mainly attributable for the exchange rate volatility of Somalia; these factors include the balance of payment, inflation rate, money supply (mostly come from remittance and NGOs) and Bank profits.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2001.04a
• /
• pp.3-6
• /
• 2001

Various Parameters such as stream velocities, discharges, and dispersion coefficients of dissolved solutes were estimated by fitting 1-D nonreactive solute transport model to the time-series chemistry data. This study was done for the reaches of Mankyung River lower than the Jeonju Wastewater Treatment Plant (Jeonju WTP). Korea. Concentrations of inorganic chemicals in the stream waters are strongly influenced by mixing with the chemically distinct effluent from Jeonju WTP. Sulfate, EC. and the total major cation were proved to be nearly conservative in the study area front their relationships with chloride, the conservative chemical species. The solute transport model was constrained to the time-series concentrations for these 4 conservative species. The variations of concentration and discharge of Jeonju WTP were used as input parameters, and the stream velocities, dispersion coefficients, and concentrations and discharges of some inflows were optimized. The differences between the observed arid simulated values for alkalinities and nitrates are inversely correlated and show diurnal fluctuations, indicating the photosynthesis. The parameters obtained front this mode] range from 550 to 774 kcmd (stream discharge at the outlet of the study area), from 0.06 to 0.10 m/sec (flow velocity), and from 0.7 to 6.4 m$^2$/sec (dispersion coefficient). The history of Jeonju WTP discharge was well predicted when optimized, indicating the validity of the model results.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.5
• /
• pp.523-530
• /
• 2016

Human mind can be divided by conscious and nonconscious. The action that can be seen by eyes express of conscious world, but brain researchers tell us that the world of nonconscious more occupied than world of conscious. In this paper, we divide conscious and nonconscious of world in basic love model of Romeo and Juliet, and then we represent complex number for the conscious and nonconscious. We also display as time series and phase plane for their behavior. Finally, we confirms the existence of nonlinear characteristics in their behavior.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.40 no.4
• /
• pp.49-63
• /
• 2015

Keyword indexed in multidisciplinary journals show trends about science and technology innovation. Nature and Science were selected as multidisciplinary journals for our analysis. In order to reduce the effect of plurality of keyword, stemming algorithm were implemented. After this process, we fitted growth curve of keyword (stem) following bass model, which is a well-known model in diffusion process. Bass model is useful for expressing growth pattern by assuming innovative and imitative activities in innovation spreading. In addition, we construct keyword co-occurrence network and calculate network measures such as centrality indices and local clustering coefficient. Based on network metrics and yearly frequency of keyword, time series analysis was conducted for obtaining statistical causality between these measures. For some cases, local clustering coefficient seems to Granger-cause yearly frequency of keyword. We expect that local clustering coefficient could be a supportive indicator of emerging science and technology.

• Environmental Engineering Research
• /
• v.22 no.2
• /
• pp.162-168
• /
• 2017

Rainfall is one of the most important phenomena of the natural system. In Bangladesh, agriculture largely depends on the intensity and variability of rainfall. Therefore, an early indication of possible rainfall can help to solve several problems related to agriculture, climate change and natural hazards like flood and drought. Rainfall forecasting could play a significant role in the planning and management of water resource systems also. In this study, univariate Seasonal Autoregressive Integrated Moving Average (SARIMA) model was used to forecast monthly rainfall for twelve months lead-time for thirty rainfall stations of Bangladesh. The best SARIMA model was chosen based on the RMSE and normalized BIC criteria. A validation check for each station was performed on residual series. Residuals were found white noise at almost all stations. Besides, lack of fit test and normalized BIC confirms all the models were fitted satisfactorily. The predicted results from the selected models were compared with the observed data to determine prediction precision. We found that selected models predicted monthly rainfall with a reasonable accuracy. Therefore, year-long rainfall can be forecasted using these models.

• Korean Journal of Community Nutrition
• /
• v.8 no.6
• /
• pp.910-918
• /
• 2003

The purposes of this study were to develop a model for university foodservices and to provide management strategies for reducing costs, and increasing productivity and customer satisfaction. The results of this study were as follows : 1) The demands in university food services varied depending on the time series. A fixed pattern was discovered for specific times of the month and semesters. The demand tended to constantly decrease from the beginning of a specific semester to the end, from March to June and from September to December. Moreover, the demand was higher during the first semester than the second semester, within school term than during vacation periods, and during the summer vacation than the winter. 2) Pearson's simple correlation was done between actual customer demand and the factors relating to forecasting the demand. There was a high level of correlation between the actual demand and the demand that had occurred in the previous weeks. 3) By applying the stepwise multiple linear regression analysis to two different university food services providing multiple menu items, a model was developed in terms of four different time series(first semester, second semester, summer vacation, and winter vacation). Customer preference for specific menu items was found to be the most important factor to be considered in forecasting the demand.