• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.5
• /
• pp.574-583
• /
• 2021

Predicting shipping markets is an important issue. Such predictions form the basis for decisions on investment methods, fleet formation methods, freight rates, etc., which greatly affect the profits and survival of a company. To this end, in this study, we propose a shipping freight rate prediction model for container ships using gated recurrent units (GRUs) and long short-term memory structure. The target of our freight rate prediction is the China Container Freight Index (CCFI), and CCFI data from March 2003 to May 2020 were used for training. The CCFI after June 2020 was first predicted according to each model and then compared and analyzed with the actual CCFI. For the experimental model, a total of six models were designed according to the hyperparameter settings. Additionally, the ARIMA model was included in the experiment for performance comparison with the traditional analysis method. The optimal model was selected based on two evaluation methods. The first evaluation method selects the model with the smallest average value of the root mean square error (RMSE) obtained by repeating each model 10 times. The second method selects the model with the lowest RMSE in all experiments. The experimental results revealed not only the improved accuracy of the deep learning model compared to the traditional time series prediction model, ARIMA, but also the contribution in enhancing the risk management ability of freight fluctuations through deep learning models. On the contrary, in the event of sudden changes in freight owing to the effects of external factors such as the Covid-19 pandemic, the accuracy of the forecasting model reduced. The GRU1 model recorded the lowest RMSE (69.55, 49.35) in both evaluation methods, and it was selected as the optimal model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.5
• /
• pp.723-737
• /
• 2017

In order to decide the national technical standards policy for national policy/market economy activities, the people in charge commonly make policy decisions based on the current technology level/concentration/utilization by means of major common technology field analysis using patent data. One possible source of such patent data is the domestic mobile carriers through the Korea Intellectual Property Rights Information System (KIPRIS) of the Korean Intellectual Property Office (KIPO). Using this system, we collected 20,294 patents and 152 International Patent Classification (IPC) types and confirmed KTs (9,738 cases / 47.98%), which perform relatively high technology retention activities compared to other mobile carriers through the KIPRIS of KIPO. Based on these data, we performed three analyses (SNA, PCA, ARIMA) and extracted 30 IPC types from the SNA and 4 IPC types from the PCA. Based on the above analysis results, we confirmed that 4 IPC (H04W, H04B, G06Q, H04L) types are the major common technology field of the domestic mobile carriers. Finally, the number of 4 IPC (H04W, H04B, G06Q, H04L) forecast averages of the ARIMA forecast result is lower than the number of existing time series patent data averages.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.136-151
• /
• 2016

Flexible large-scale WLANs are now widely deployed in crowded and highly mobile places such as campus, airport, shopping mall and company etc. But network management is hard for large-scale WLANs due to highly uneven interference and throughput among links. So the traffic is difficult to predict accurately. In the paper, through analysis of traffic in two real large-scale WLANs, Granger Causality is found in both scenarios. In combination with information entropy, it shows that the traffic prediction of target AP considering Granger Causality can be more predictable than that utilizing target AP alone, or that of considering irrelevant APs. So We develops new method -Granger Causality and Vector Auto-Regression (GCVAR), which takes APs series sharing Granger Causality based on Vector Auto-regression (VAR) into account, to predict the traffic flow in two real scenarios, thus redundant and noise introduced by multivariate time series could be removed. Experiments show that GCVAR is much more effective compared to that of traditional univariate time series (e.g. ARIMA, WARIMA). In particular, GCVAR consumes two orders of magnitude less than that caused by ARIMA/WARIMA.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.2
• /
• pp.89-98
• /
• 2020

Prediction of clock behaviors is necessary to generate very high stable system time which is essential for a satellite navigation system. For the purpose, we applied the Auto-Regressive Integrated Moving Average (ARIMA) model to the prediction of two hydrogen masers' behaviors with respect to the rapid Coordinated Universal Time (UTCr). Using the packaged programming language R, we made an analysis and prediction of time series data of [UTCr - clocks]. The maximum variation width of the residuals which were obtained by the difference between the predicted and measured values, was 6.2 ns for 106 days. This variation width was just one-sixth of [UTCr-UTC (KRIS)] published by the BIPM for the same period. Since the two hydrogen masers were found to be strongly correlated, we applied the Vector Auto-Regressive Moving Average (VARMA) model for more accurate prediction. The result showed that the prediction accuarcy was improved by two times for one hydrogen maser.

• Journal of Aerospace System Engineering
• /
• v.14 no.2
• /
• pp.50-56
• /
• 2020

In this study, we investigated whether long short-term memory (LSTM) can be used in the future to predict F10.7 index data; the F10.7 index is a space environment factor affecting atomic oxygen erosion. Based on this, we compared the prediction performances of LSTM, the Autoregressive integrated moving average (ARIMA) model (which is a traditional statistical prediction model), and the similar pattern searching method used for long-term prediction. The LSTM model yielded superior results compared to the other techniques in the prediction period starting from the max/min points, but presented inferior results in the prediction period including the inflection points. It was found that efficient learning was not achieved, owing to the lack of currently available learning data in the prediction period including the maximum points. To overcome this, we proposed a method to increase the size of the learning samples using the sunspot data and to upgrade the LSTM model.

• Journal of Korean Society of Rural Planning
• /
• v.17 no.1
• /
• pp.1-11
• /
• 2011

본 연구에서는 ARIMA(Autoregressive Integrated Moving Average) 모델을 이용하여 농촌관광마을의 월별 관광객을 추정하였다. 단일 마을에 대한 시계열 자료를 경상북도 안동시에 위치한 하회마을을 대상으로 구축하였다. 월별 시계열 자료는 2000년부터 2010년까지 구성되었는데(2008년도 누락), 2000년에서 2007년까지 자료는 최적 모델의 도출에 나머지는 예측치의 검정에 사용되었다. 연구 결과 최적모델에 필요한 시계열 자료의 길이는 6년으로 나타났으며, 최적모델은 계절성을 고려한 SARIMA(2,1,1)(1,1,2)12로 나타났다. 최적 시계열 년수로 나타난 6년을 사용하여 2000-2005, 2001-2006, 그리고 2002-2007의 자료로부터 각각 SARIMA(2,1,1)(1,1,2)12를 도출하여, 차기년도들에 대한 예측결과를 비교한 결과, 높은 $R^2$값을 보였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.12
• /
• pp.565-572
• /
• 2017

Traditional method for time series analysis, autoregressive integrated moving average (ARIMA) allows to mine significant patterns from the past observations using autocorrelation and to forecast future sequences. However, Korean baseball games do not have regular intervals to analyze relationship among the past attendance observations. To address this issue, we propose artificial neural network (ANN) based attendance prediction model using various measures including performance, team characteristics and social influences. We optimized ANNs using grid search to construct optimal model for regression problem. The evaluation shows that the optimal and ensemble model outperform the baseline model, linear regression model.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.133-144
• /
• 2016

This paper proposes a parsimonious periodic autoregressive (PAR) model. The proposed model performance is evaluated through an analysis of Korean unemployment rate series that is compared with existing models. We exploit some common features among each seasonality and confirm it by LR test for the parsimonious PAR model in order to impose a parsimonious structure on the PAR model. We observe that the PAR model tends to be superior to existing seasonal time series models in mid- and long-term forecasts. The proposed parsimonious model significantly improves forecasting performance.

• The Korean Journal of Applied Statistics
• /
• v.26 no.2
• /
• pp.237-252
• /
• 2013

An estimation model for premiums and components is essential to determine reasonable insurance premiums. In this study, we introduce diverse models for the estimation of property damage premiums(premium, depth and frequency) that include a regression model using a dummy variable, additive independent variable model, autoregressive error model, seasonal ARIMA model and intervention model. In addition, the actual property damage premium data was used to estimate the premium, depth and frequency for each model. The estimation results of the models are comparatively examined by comparing the RMSE(Root Mean Squared Errors) of estimates and actual data. Based on real data analysis, we found that the autoregressive error model showed the best performance.

• International conference on construction engineering and project management
• /
• 2011.02a
• /
• pp.1-6
• /
• 2011

As large-scale building projects have recently increased for the residential, commercial and office facilities, construction costs for these projects have become a matter of great concern, due to their significant construction cost implications, as well as unpredictable market conditions and fluctuations in the rate of inflation during the projects' long-term construction periods. In particular, recent volatile fluctuations of construction material prices fueled such problems as cost forecasting. This research develops a time series model using the Box-Jenkins approach and material price time series data in Korea in order to forecast trends in the unit prices of required materials. Building information modeling (BIM) approaches are also used to analyze injection times of construction resources and to conduct quantity take-off so that total material prices can be forecast. To determine an optimal time series model for forecasting price trends, comparative analysis of predictability of tentative autoregressive integrated moving average (ARIMA) models is conducted. The proposed BIM-based time series forecasting model can help to deal with sudden changes in economic conditions by estimating material prices that correspond to resource injection times.