• Journal of Wind Energy
• /
• v.15 no.2
• /
• pp.10-22
• /
• 2024

This research is a comprehensive analysis of wind power prediction sensitivity using a Long Short-Term Memory (LSTM) deep learning neural network model, accounting for the inherent uncertainties in wind speed estimation. Utilizing a year's worth of operational data from an operational wind farm, the study forecasts the power output of both individual wind turbines and the farm collectively. Predictions were made daily at intervals of 10 minutes and 1 hour over a span of three months. The model's forecast accuracy was evaluated by comparing the root mean square error (RMSE), normalized RMSE (NRMSE), and correlation coefficients with actual power output data. Moreover, the research investigated how inaccuracies in wind speed inputs affect the power prediction sensitivity of the model. By simulating wind speed errors within a normal distribution range of 1% to 15%, the study analyzed their influence on the accuracy of power predictions. This investigation provided insights into the required wind speed prediction error rate to achieve an 8% power prediction error threshold, meeting the incentive standards for forecasting systems in renewable energy generation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.6C
• /
• pp.343-348
• /
• 2011

This paper introduces a design for real time wireless headset using ANC (active noise control) system based on NFxLMS adaptive filter algorithm. The training time of the proposed system is significantly reduced by using the RMS delay spread of a channel as an error correction parameter, and convergence rate of the FxLMS filter has been improved with updating the coefficients of the NFxLMS filter, which we have got during the training process. Our system has shorter training time and better convergence rate at the same noise reduction level than the conventional system under real noisy environment.

• Korean Journal of Remote Sensing
• /
• v.32 no.6
• /
• pp.741-746
• /
• 2016

Albedo is one of the climate variables that modulate absorption of solar energy, and its retrieval is important process for climate change study. High spatial resolution and long-term consistent periods are important considerations in order to efficiently use the retrieved albedo data. This study retrieved surface broadband albedo based on Landsat 8 as high resolution which is consistent with Landsat 7. First of all, we analyzed consistency of Landsat 7 channel and Landsat 8 channel. As a result, correlation coefficient(R) on all channels is average 0.96. Based on this analysis, we used multiple linear regression model using Landsat 7 albedo, which is being used in many studies, and Landsat 8 reflectance channel data. The regression coefficients of each channel calculated by regression analysis were used to derive a formula for converting the Landsat 8 reflectance channel data to broadband albedo. After Landsat 8 albedo calculated using the derived formula is compared with Landsat 7 albedo data, we confirmed consistency of two satellite using Root Mean Square Error (RMSE), R-square ($R^2$) and bias. As a result, $R^2$ is 0.89 and RMSE is 0.003 between Landsat 7 albedo and Landsat 8 albedo.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.121-131
• /
• 2014

Traffic speed is an important measure in transportation. It can be employed for various purposes, including traffic congestion detection, travel time estimation, and road design. Consequently, accurate speed prediction is essential in the development of intelligent transportation systems. In this paper, we present an analysis and speed prediction of a certain road section in Busan, South Korea. In previous works, only historical data of the target link are used for prediction. Here, we extract features from real traffic data by considering the neighboring links. After obtaining the candidate features, linear regression, model tree, and k-nearest neighbor (k-NN) are employed for both feature selection and speed prediction. The experiment results show that k-NN outperforms model tree and linear regression for the given dataset. Compared to the other predictors, k-NN significantly reduces the error measures that we use, including mean absolute percentage error (MAPE) and root mean square error (RMSE).

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.6 no.2
• /
• pp.1-9
• /
• 1988

The main objective of the study is to execute the simultaneous adjustment of the secondary level net on the basis of the 1st order level net adjustment carried in 1987. Moreover, the basic raw field data obtained during last 21-years(’67~’87) is to be analyzed, corrected and edited in order to carry out a reasonable adjustment of the End order level net. As the result of the study, we obtained mean random error η＝1.99$^{mm}$ /√km, mean systematic error ξ＝2.09$^{mm}$ /√km, square root of the posterior reference variance $\sigma$$_{0}$ ＝9.12$^{mm}$ /√km and concluded that the accuracy obtained is good enough for the category of precision levelling.

• Journal of Environmental Impact Assessment
• /
• v.20 no.6
• /
• pp.879-890
• /
• 2011

The GOSAT (Greenhouse gases Observing SATellite) data provide new opportunities the most regionally complete and up-to-date assessment of $CO_2$. However, in practice, GOSAT records often suffer from missing data values mainly due to unfavorable meteorological condition in specific time periods of data acquisition. The aim of this research was to identify optimal spatial interpolation techniques to ensure the continuity of $CO_2$ from samples taken in the North East Asia. The accuracy among ordinary kriging (OK), universal kriging (UK) and simple kriging (SK) was compared based on the combined consideration of $R^2$ values, Root Mean Square Error (RMSE), Mean Error (ME) for variogram models. Cross validation for 1312 random sampling points indicate that the (UK) kriging is the best geostatistical method for spatial predictions of $CO_2$ in the East Asia region. The results from this study can be useful for selecting optimal kriging algorithm to produce $CO_2$ map of various landscapes. Also, data users may benefit from a statistical approach that would allow them to better understand the uncertainty and limitations of the GOSAT sample data.

• Structural Engineering and Mechanics
• /
• v.60 no.3
• /
• pp.471-488
• /
• 2016

This study predicts the strength of rotary brace damper by analyzing a new set of probabilistic models using the usual method of multiple linear regressions (MLR) and advanced machine-learning methods of multivariate adaptive regression splines (MARS), Rotary brace damper can be easily assembled with high energy-dissipation capability. To investigate the behavior of this damper in structures, a steel frame is modeled with this device subjected to monotonic and cyclic loading. Several response parameters are considered, and the performance of damper in reducing each response is evaluated. MLR and MARS methods were used to predict the strength of this damper. Displacement was determined to be the most effective parameter of damper strength, whereas the thickness did not exhibit any effect. Adding thickness parameter as inputs to MARS and MLR models did not increase the accuracies of the models in predicting the strength of this damper. The MARS model with a root mean square error (RMSE) of 0.127 and mean absolute error (MAE) of 0.090 performed better than the MLR model with an RMSE of 0.221 and MAE of 0.181.

• Proceedings of the KSME Conference
• /
• 2001.06d
• /
• pp.201-207
• /
• 2001

We modeled the liquid film dryout(LFD) process for both tube and annulus which have uniformly heated vertical channels. We set phenomenological initial conditions in the model. The initial void fraction on the onset of the annular flow location is derived from the physical chum-to-annular flow criterion with the help of the drift-flux-model. The initial thermodynamic-equilibrium-quality is calculated by iteration with the flow quality to find the onset of the annular-flow location. Present model tends to predict very well at the lower exit quality but under-estimates at the higher exit quality. We found that the prediction error of the present model is gradually bigger as the inlet subcooling approaches near the saturation. We obtained excellent results for both tube and annulus channels as the mean of 0.97 and root-mean-square error of 11% for the number of 3883 experimental data on tubes, and of 0.96 and of 12% for 593 on annuli. The present model extended the applicable range to the relatively low exit quality region than previous LFD models.

• International Journal of Highway Engineering
• /
• v.15 no.3
• /
• pp.53-63
• /
• 2013

PURPOSES : This study is to evaluate moisture susceptibility of asphalt mixtures by using non-destructive impact wave and to determine durability so as to decrease the gap between before and after freezing in the future. METHODS : Using non-destructive impact wave, this study is to determine the dynamic modulus of asphalt specimen. Furthermore, the results obtained from two experiment accelerometers are used for the dynamic modulus determination. The dynamic moduli of specimens are compared with those of the freezing-thawing specimens. RESULTS : Test results showed that the dynamic modulus before freezing and thawing environment loads at each temperature dropped about 3.7% after the environmental loads. Furthermore, correlation analysis indicates that transition of dynamic modulus at each point is about 89.59%. CONCLUSIONS: Evaluation of asphalt mixtures using non-destructive impact wave has excellent repeatability and simple equipment for the test. Consequently, the method in the study will be useful for evaluating the characteristics of a various asphalt mixtures.

• Journal of Astronomy and Space Sciences
• /
• v.27 no.4
• /
• pp.367-375
• /
• 2010

In this study, we compared the precipitable water vapor (PWV) data derived from the radiosonde observation data at Sokcho Observatory and the PWV data at Sokcho Global Positioning System (GPS) Observatory provided by Korea Astronomy and Space Science Institute, from 0000 UTC, June 1, 2007 to 1200 UTC, May 31, 2009, and analyzed the radiosonde bias between the day and the night. In the scatter diagram of the daytime and nighttime radiosonde PWV data and the GPS PWV data, dry bias was found in the daytime radiosonde observation as known in the previous study. In addition, for all the rainfall events, the tendency that the wet bias of the radiosonde PWV increased as the GPS PWV decreased and the dry bias of the radiosonde PWV increased as the GPS PWV increased was significantly less distinctive in nighttime than in daytime. The quantitative analysis of the bias and error of the radiosonde PWV data showed that the mean bias decreased in the second year, regardless of nighttime or daytime rainfall, and the non-rainfall root mean square error (RMSE) was similar to that of the previous studies, while the rainfall RMSE was larger to a certain extent.