• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.265-282
• /
• 2022

Sea surface temperature (SST) is a factor that greatly influences ocean circulation and ecosystems in the Earth system. As global warming causes changes in the SST near the Korean Peninsula, abnormal water temperature phenomena (high water temperature, low water temperature) occurs, causing continuous damage to the marine ecosystem and the fishery industry. Therefore, this study proposes a methodology to predict the SST near the Korean Peninsula and prevent damage by predicting abnormal water temperature phenomena. The study area was set near the Korean Peninsula, and ERA5 data from the European Center for Medium-Range Weather Forecasts (ECMWF) was used to utilize SST data at the same time period. As a research method, Long Short-Term Memory (LSTM) algorithm specialized for time series data prediction among deep learning models was used in consideration of the time series characteristics of SST data. The prediction model predicts the SST near the Korean Peninsula after 1- to 7-days and predicts the high water temperature or low water temperature phenomenon. To evaluate the accuracy of SST prediction, Coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) indicators were used. The summer (JAS) 1-day prediction result of the prediction model, R²=0.996, RMSE=0.119℃, MAPE=0.352% and the winter (JFM) 1-day prediction result is R²=0.999, RMSE=0.063℃, MAPE=0.646%. Using the predicted SST, the accuracy of abnormal sea surface temperature prediction was evaluated with an F1 Score (F1 Score=0.98 for high water temperature prediction in summer (2021/08/05), F1 Score=1.0 for low water temperature prediction in winter (2021/02/19)). As the prediction period increased, the prediction model showed a tendency to underestimate the SST, which also reduced the accuracy of the abnormal water temperature prediction. Therefore, it is judged that it is necessary to analyze the cause of underestimation of the predictive model in the future and study to improve the prediction accuracy.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.3 no.1 s.4
• /
• pp.45-52
• /
• 2004

There are many cities installing ITS(Intelligent Transportation Systems) and running TMC(Trafnc Management Center) to improve mobility and safety of roadway transportation by providing roadway information to drivers. There are many devices in ITS which collect real-time traffic data. We can obtain many valuable traffic data from the devices. But it's impossible to avoid missing traffic data for many reasons such as roadway condition, adversary weather, communication shutdown and problems of the devices itself. We couldn't do any secondary process such as travel time forecasting and other transportation related research due to the missing data. If we use the traffic data to produce AADT and DHV, essential data in roadway planning and design, We might get skewed data that could make big loss. Therefore, He study have explored some imputation techniques such as heuristic methods, regression model, EM algorithm and time-series analysis for the missing traffic volume data using some evaluating indices such as MAPE, RMSE, and Inequality coefficient. We could get the best result from time-series model generating 5.0$\%$, 0.03 and 110 as MAPE, Inequality coefficient and RMSE, respectively. Other techniques produce a little different results, but the results were very encouraging.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2779-2784
• /
• 2015

The prediction of the accurate traffic information can provide an optimal route from the place of departure to a destination, therefore, this makes it possible to obtain a saving of time and money. To predict traffic information, we use a Bayesian network method based on probability model in this paper. Existing researches predicting the traffic information based on a Bayesian network generally used to study the data for all time. In this paper, however, only data corresponding to same time and day of the week to predict selectively will be used for learning. In fact, the experiment was carried out for 14 links zone in Seoul, also, the accuracy of the prediction results of the two different methods should be tested with MAPE (Mean Absolute Percentage Error) which is commonly used. In view of MAPE, experimental results show that the proposed method may calculate traffic prediction value with a higher accuracy than the method used to learn the data for all time zones.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.1
• /
• pp.26-37
• /
• 2017

The study is to develop safety performance functions(SPFs) for urban intersections using random effects Tobit regression model and to analyze correlations between crashes and factors. Also fixed effects Tobit regression model was estimated to compare and analyze model validation with random effects model. As a result, AADT, speed limits, number of lanes, land usage, exclusive right turn lanes and front traffic signal were found to be significant. For comparing statistical significance between random and fixed effects model, random effects Tobit regression model of total crash rate could be better statistical significance with $R^2_p$ : 0.418, log-likelihood at convergence: -3210.103, ${\rho}^2$: 0.056, MAD: 19.533, MAPE: 75.725, RMSE: 26.886 comparing with $R^2_p$ : 0.298, log-likelihood at convergence: -3276.138, ${\rho}^2$: 0.037, MAD: 20.725, MAPE: 82.473, RMSE: 27.267 for the fixed model. Also random effects Tobit regression model of injury crash rate has similar results of model statistical significant with random effects Tobit regression model.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_2
• /
• pp.1881-1890
• /
• 2021

Particulate matter (PM) affects the human, ecosystems, and weather. Motorized vehicles and combustion generate fine particulate matter (PM_2.5), which can contain toxic substances and, therefore, requires systematic management. Consequently, it is important to monitor and predict PM_2.5 concentrations, especially in large cities with dense populations and infrastructures. This study aimed to predict PM_2.5 concentrations in large cities using meteorological and chemical variables as well as satellite-based aerosol optical depth. For PM_2.5 concentrations prediction, a random forest (RF) model showing excellent performance in PM concentrations prediction among machine learning models was selected. Based on the performance indicators R², RMSE, MAE, and MAPE with training accuracies of 0.97, 3.09, 2.18, and 13.31 and testing accuracies of 0.82, 6.03, 4.36, and 25.79 for R², RMSE, MAE, and MAPE, respectively. The variables used in this study showed high correlation to PM_2.5 concentrations. Therefore, we conclude that these variables can be used in a random forest model to generate reliable PM_2.5 concentrations predictions, which can then be used to assess the vulnerability of schools to PM_2.5.

• Advanced Industrial SCIence
• /
• v.1 no.1
• /
• pp.7-15
• /
• 2022

To adopt the development in the medical scenario IoT developed towards the advancement with the processing of a large amount of medical data defined as an Internet of Medical Things (IoMT). The vast range of collected medical data is stored in the cloud in the structured manner to process the collected healthcare data. However, it is difficult to handle the huge volume of the healthcare data so it is necessary to develop an appropriate scheme for the healthcare structured data. In this paper, a machine learning mode for processing the structured heath care data collected from the IoMT is suggested. To process the vast range of healthcare data, this paper proposed an MTGPLSTM model for the processing of the medical data. The proposed model integrates the linear regression model for the processing of healthcare information. With the developed model outlier model is implemented based on the FinTech model for the evaluation and prediction of the COVID-19 healthcare dataset collected from the IoMT. The proposed MTGPLSTM model comprises of the regression model to predict and evaluate the planning scheme for the prevention of the infection spreading. The developed model performance is evaluated based on the consideration of the different classifiers such as LR, SVR, RFR, LSTM and the proposed MTGPLSTM model and the different size of data as 1GB, 2GB and 3GB is mainly concerned. The comparative analysis expressed that the proposed MTGPLSTM model achieves ~4% reduced MAPE and RMSE value for the worldwide data; in case of china minimal MAPE value of 0.97 is achieved which is ~ 6% minimal than the existing classifier leads.

• Korean Chemical Engineering Research
• /
• v.60 no.3
• /
• pp.363-370
• /
• 2022

In this paper, an estimation algorithm for state of charge (SOC) was applied using an equivalent circuit model (ECM) and an Extended Kalman Filter (EKF) to improve the estimation accuracy of the battery system states. In particular, an observer was designed to estimate SOC along with the aged capacity. In the case of the fresh battery, when SOC was estimated by Kalman Filter (KF), the mean absolute percentage error (MAPE) was 0.27% which was smaller than MAPE of 1.43% when the SOC was calculated by the model without the observer. In the driving mode of the vehicle, the general KF or EKF algorithm cannot be used to estimate both SOC and capacity. Considering that the battery aging does not occur in a short period of time, a strategy of periodically estimating the battery capacity during charging was proposed. In the charging mode, since the current is fixed at some intervals, a strategy for estimating the capacity along with the SOC in this situation was suggested. When the current was fixed, MAPE of SOC estimation was 0.54%, and the MAPE of capacity estimation was 2.24%. Since the current is fixed when charging, it is feasible to estimate the battery capacity and SOC simultaneously using the general EKF. This method can be used to periodically perform battery capacity correction when charging the battery. When driving, the SOC can be estimated using EKF with the corrected capacity.

• 한국ITS학회:학술대회논문집
• /
• 2003.11a
• /
• pp.221-225
• /
• 2003

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.1
• /
• pp.131-136
• /
• 2014

In this paper, we develop a fashion products demand forecasting algorithm using ARIMA model and Wavelet Neural Networks model. To show effectiveness of the proposed method, we analyzed characteristics of time-series data collected in "H" company during 2008-2012 and then performed the proposed method through various analyses. As noted in experimental results, the performance of three types model such as ARIMA, Wavelet Neural Networks and ARIMA + Wavelet Neural Networks show 5.179%, 4.553%, and 4.448.% with respect to MAPE(Mean Absolute Percentage Error), respectively. Thus, it is noted that the proposed method can be used to predict fashion products demand for efficient of operation.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.275-284
• /
• 2016

Accurate electricity demand forecasts is essential in reducing energy spend and preventing imbalance of the power supply. In forcasting electricity demand, we considered double seasonal Holt-Winters model and TBATS model with sliding window. We selected a specific time zone as the reference line of daily electric demand because it is least likely to be influenced by external factors. The forecasting performance have been evaluated in terms of RMSE and MAPE criteria. We used the observations ranging January 4, 2009 to December 31 for testing data. For validation data, the records has been used between January 1, 2012 and December 29, 2012.