• Journal of the Korean Wood Science and Technology
• /
• v.47 no.6
• /
• pp.732-750
• /
• 2019

Air drying was carried out on 15 Korean red pine logs to provide a prediction model of the moisture content (MC) change in the wood during drying. The final MC was 17.4% after 880 days since the beginning of air drying in the summer for 6 Korean red pine logs with 68.7% initial MC. The final MC was 16.0% after 760 days since the beginning of air drying in the winter for 9 Korean red pine logs with 35.8% initial MC. A regression model with R-squared of 0.925 was obtained as a result of multiple regression analyses with initial MC, top diameter, temperature, relative humidity, and wind speed as independent variable and and MC change during air drying as dependent variable. The initial MC and top diameter, which is the characteristic of Korean red pine, have greater effect on the MC decrease during air drying compared to meteorological factors such as the temperature, relative humidity, and wind speed. Two-dimensional mass transfer analysis was performed to predict the MC distribution of Korean red pine logs during air drying. Two prediction models with different air drying days and different meteorological factors for the determination of the diffusion coefficient and surface emission coefficient were presented. The error between the different two methods ranged from 0.1 to 0.8% and the difference from the measured value ranged from 2.2 to 3.6%. By measuring the internal MC during air drying of Korean pine logs with various initial MC and diameter, and calculating the moisture transfer coefficient in wood for each meteorological condition, the error of the prediction model can be reduced.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.6
• /
• pp.390-395
• /
• 2005

Sunspots are dark areas that grow and decay on the lowest level of the sun that is visible from the Earth. Shot-term predictions of solar activity are essential to help plan missions and to design satellites that will survive for their useful lifetimes. This paper presents a parallel-structure fuzzy system(PSFS) for prediction of sunspot number time series. The PSFS consists of a multiple number of component fuzzy systems connected in parallel. Each component fuzzy system in the PSFS predicts future data independently based on its past time series data with different embedding dimension and time delay. An embedding dimension determines the number of inputs of each component fuzzy system and a time delay decides the interval of inputs of the time series. According to the embedding dimension and the time delay, the component fuzzy system takes various input-output pairs. The PSFS determines the final predicted value as an average of all the outputs of the component fuzzy systems in order to reduce error accumulation effect.

• The korean journal of orthodontics
• /
• v.37 no.1 s.120
• /
• pp.16-28
• /
• 2007

Objective: Evaluation of individual growth is important in orthodontics. The aim of this study was to develop a convenient software that can evaluate current growth status and predict further growth. Methods: Stature data of 2 to 20 year-old Koreans (4893 boys and 4987 girls) were extracted from a nationwide data. Age-sex-specific continuous functions describing percentile growth curves were constructed using natural cubic spline function (NCSF). Then, final stature prediction algorithm was developed and its validity was tested using longitudinal series of stature measurements on randomly selected 200 samples. Various accuracy measurements and analyses of errors between observed and predicted stature using NCSF growth curves were performed. Results: NCSF growth curves were shown to be excellent models in describing reference percentile stature growth curie over age. The prediction accuracy compared favorably with previous prediction models, even more accurate. The current prediction models gave more accurate results in girls than boys. Although the prediction accuracy was high, the error pattern of the validation data showed that in most cases, there were a lot of residuals with the same sign, suggestive of autocorrelation among them. Conclusion: More sophisticated growth prediction algorithm is warranted to enhance a more appropriate goodness of model fit for individual growth.

• Journal of Communications and Networks
• /
• v.8 no.2
• /
• pp.234-240
• /
• 2006

We study the dynamic burst assembly based on traffic prediction and offset and delay differentiation in optical burst switching network. To improve existing burst assembly mechanism and build an adaptive flexible optical burst switching network, an approach called quality of service (QoS) based adaptive dynamic assembly (QADA) is proposed in this paper. QADA method takes into account current arrival traffic in prediction time adequately and performs adaptive dynamic assembly in limited burst assembly time (BAT) range. By the simulation of burst length error, the QADA method is proved better than the existing method and can achieve the small enough predictive error for real scenarios. Then the different dynamic ranges of BAT for four traffic classes are introduced to make delay differentiation. According to the limitation of BAT range, the burst assembly is classified into one-dimension limit and two-dimension limit. We draw a comparison between one-dimension and two-dimension limit with different prediction time under QoS based offset time and find that the one-dimensional approach offers better network performance, while the two-dimensional approach provides strict inter-class differentiation. Furthermore, the final simulation results in our network condition show that QADA can execute adaptive flexible burst assembly with dynamic BAT and achieve a latency reduction, delay fairness, and offset time QoS guarantee for different traffic classes.

• The Journal of the Korea Contents Association
• /
• v.20 no.4
• /
• pp.25-37
• /
• 2020

As social costs of traffic congestion increase, various studies are underway to predict road speed. In order to improve the accuracy of road speed prediction, unexpected traffic situations need to be considered. In this paper, we propose a road speed prediction scheme considering traffic incidents affecting road speed. We use not only the speed data of the target road but also the speed data of the connected roads to reflect the impact of the connected roads. We also analyze the amount of speed change to predict the traffic congestion caused by traffic incidents. We use the speed data of connected roads and target road with input data to predict road speed in the first place. To reduce the prediction error caused by breaking the regular road flow due to traffic incidents, we predict the final road speed by applying event weights. It is shown through various performance evaluations that the proposed method outperforms the existing methods.

• Journal of Korea Water Resources Association
• /
• v.39 no.12 s.173
• /
• pp.997-1012
• /
• 2006

We have presented a nonparametric stochastic approach for the SOI(Southern Oscillation Index) series that used nonlinear methodology called Nonlinear AutoRegressive(NAR) based on conditional kernel density function and CAFPE(Corrected Asymptotic Final Prediction Error) lag selection. The fitted linear AR model represents heteroscedasticity, and besides, a BDS(Brock - Dechert - Sheinkman) statistics is rejected. Hence, we applied NAR model to the SOI series. We can identify the lags 1, 2 and 4 are appropriate one, and estimated conditional mean function. There is no autocorrelation of residuals in the Portmanteau Test. However, the null hypothesis of normality and no heteroscedasticity is rejected in the Jarque-Bera Test and ARCH-LM Test, respectively. Moreover, the lag selection for conditional standard deviation function with CAFPE provides lags 3, 8 and 9. As the results of conditional standard deviation analysis, all I.I.D assumptions of the residuals are accepted. Particularly, the BDS statistics is accepted at the 95% and 99% significance level. Finally, we split the SOI set into a sample for estimating themodel and a sample for out-of-sample prediction, that is, we conduct the one-step ahead forecasts for the last 97 values (15%). The NAR model shows a MSEP of 0.5464 that is 7% lower than those of the linear model. Hence, the relevance of the NAR model may be proved in these results, and the nonparametric NAR model is encouraging rather than a linear one to reflect the nonlinearity of SOI series.

• Journal of ILASS-Korea
• /
• v.27 no.2
• /
• pp.57-65
• /
• 2022

The purpose of this study is to use machine learning to build a model capable of predicting the flash boiling spray characteristics. In this study, the flash boiling spray was visualized using Shadowgraph visualization technology, and then the spray image was processed with MATLAB to obtain quantitative data of spray characteristics. The experimental conditions were used as input, and the spray characteristics were used as output to train the machine learning model. For the machine learning model, the XGB (extreme gradient boosting) algorithm was used. Finally, the performance of machine learning model was evaluated using R² and RMSE (root mean square error). In order to have enough data to train the machine learning model, this study used 12 injectors with different design parameters, and set various fuel temperatures and ambient pressures, resulting in about 12,000 data. By comparing the performance of the model with different amounts of training data, it was found that the number of training data must reach at least 7,000 before the model can show optimal performance. The model showed different prediction performances for different spray characteristics. Compared with the upstream spray angle and the downstream spray angle, the model had the best prediction performance for the spray tip penetration. In addition, the prediction performance of the model showed a relatively poor trend in the initial stage of injection and the final stage of injection. The model performance is expired to be further enhanced by optimizing the hyper-parameters input into the model.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.1
• /
• pp.11-18
• /
• 2022

In order to improve the accuracy of particle tracking prediction techniques near the Korean Strait, this study compared and analyzed a particle tracking model based on a seawater flow numerical model and a machine learning based on a particle tracking model using field observation data. The data used in the study were the surface drifter buoy movement trajectory data observed in the Korea Strait, prediction data by machine learning (linear regression, decision tree) using the tide and wind data from three observation stations (Gageo Island, Geoje Island, Gyoboncho), and prediciton data by numerical models (ROMS, MOHID). The above three data were compared through three error evaluation methods (Correlation Coefficient (CC), Root Mean Square Errors (RMSE), and Normalized Cumulative Lagrangian Separation (NCLS)). As a final result, the decision tree model had the best prediction accuracy in CC and RMSE, and the MOHID model had the best prediction results in NCLS.

• Journal of information and communication convergence engineering
• /
• v.22 no.2
• /
• pp.145-152
• /
• 2024

Closed quotient (CQ) represents the time ratio for which the vocal folds remain in contact during voice production. Because analyzing CQ values serves as an important reference point in vocal training for professional singers, these values have been measured mechanically or electrically by either inverse filtering of airflows captured by a circumferentially vented mask or post-processing of electroglottography waveforms. In this study, we introduced a novel algorithm to predict the CQ values only from audio signals. This has eliminated the need for mechanical or electrical measurement techniques. Our algorithm is based on a gated recurrent unit (GRU)-type neural network. To enhance the efficiency, we pre-processed an audio signal using the pitch feature extraction algorithm. Then, GRU-type neural networks were employed to extract the features. This was followed by a dense layer for the final prediction. The Results section reports the mean square error between the predicted and real CQ. It shows the capability of the proposed algorithm to predict CQ values.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.4
• /
• pp.17-27
• /
• 2021

Streamflow prediction is a very vital disaster mitigation approach for effective flood management and water resources planning. Lately, torrential rainfall caused by climate change has been reported to have increased globally, thereby causing enormous infrastructural loss, properties and lives. This study evaluates the contribution of rainfall to streamflow prediction in normal and peak rainfall scenarios, typical of the recent flood at Piney Resort in Vernon, Hickman County, Tennessee, United States. Daily streamflow, water level, and rainfall data for 20 years (2000-2019) from two USGS gage stations (03602500 upstream and 03599500 downstream) of the Piney River watershed were obtained, preprocesssed and fitted with Long short term memory (LSTM) model. Tensorflow and Keras machine learning frameworks were used with Python to predict streamflow values with a sequence size of 14 days, to determine whether the model could have predicted the flooding event in August 21, 2021. Model skill analysis showed that LSTM model with full data (water level, streamflow and rainfall) performed better than the Naive Model except some rainfall models, indicating that only rainfall is insufficient for streamflow prediction. The final LSTM model recorded optimal NSE and RMSE values of 0.68 and 13.84 m³/s and predicted peak flow with the lowest prediction error of 11.6%, indicating that the final model could have predicted the flood on August 24, 2021 given a peak rainfall scenario. Adequate knowledge of rainfall patterns will guide hydrologists and disaster prevention managers in designing efficient early warning systems and policies aimed at mitigating flood risks.