• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.4
• /
• pp.79-86
• /
• 2007

The shape of excessive penetration mainly depends on welding conditions(welding current and welding voltage), and welding process(groove gap and welding speed). These conditions are the major affecting factors to width and height of back bead. In this paper, back-bead prediction and weldability estimation using artificial neural network were investigated. Results are as follows. 1) If groove gap, welding current, welding voltage and welding speed will be previously determined as a welding condition, width and height of back bead can be predicted by artificial neural network system without experimental measurement. 2) From the result applied to three weld quality levels(ISO 5817), both experimented measurement using vision sensor and predicted mean values by artificial neural network showed good agreement. 3) The width and height of back bead are proportional to groove gap, welding current and welding voltage, but welding speed. is not.

• Journal of Wind Energy
• /
• v.14 no.3
• /
• pp.25-33
• /
• 2023

In order to secure the safety of increasing offshore activities such as offshore wind farm maintenance and fishing, IMPACT, a mid-term marine weather forecasting system, was established by predicting marine weather up to 7 days in advance. Forecast data from the Korea Hydrographic and Oceanographic Agency (KHOA), which provides the most reliable marine meteorological service in Korea, was used, but wind speed and wave height forecast errors increased as the leading forecast period increased, so improvement of the accuracy of the model results was needed. The Model Output Statistics (MOS) method, a post-correction method using statistical machine learning, was applied to improve the prediction accuracy of wave height, which is an important factor in forecasting the risk of marine activities. Compared with the observed data, the wave height prediction results by the model before correction for 6 to 7 days ahead showed an RMSE of 0.692 m and R of 0.591, and there was a tendency to underestimate high waves. After correction with the MOS technique, RMSE was 0.554 m and R was 0.732, confirming that accuracy was significantly improved.

• The Journal of Pediatrics of Korean Medicine
• /
• v.26 no.3
• /
• pp.46-54
• /
• 2012

Objectives The purpose of this study is to find out the relationship between parents' heights and predicted height of the children who had been treated in the growth clinic of oriental medical hospital. Methods The study was conducted with 253 children who visited Oriental Medical Hospital from July 2010 to June 2012. They were analyzed by reviewing the children's chart and correlation analysis to find out the relationship between the two heights. Results In distribution of the sex and the age, sex were similar, but boys who came to the clinic were averagely younger than the girls. In predicting adult height by TW3 method and mean parent's height, correlation in the girls was higher than the boys, especially the girls after their first menstruation. Parents' heights were related to both the boys and the girls, but mother's height was more closely related. Predicted heights of the boys before secondary sex characteristics were correlated with the child's height, but rather correlated with parent's both heights after secondary sexual character and found to be more relevant to father's height. The girls' predicted heights before their menstruation were not correlated with father's height, but with mother's. Their heights after their first periods were correlated with parents' both heights, but more correlated with father's height. Conclusions This study helps set proper periods and goals of growth treatment based on the correlation between parents' height and predicted adult height according to TW3 method.

• Journal of Forest and Environmental Science
• /
• v.28 no.2
• /
• pp.68-74
• /
• 2012

A total of 45 Pinus sylvestnis var. mongolica trees from 9 plots in northeast China were destructively sampled to develop aboveground prediction equations for inventory application. Sampling plots covered a range of stand ages (12-47-years-old) and densities (450-3,840/ha). The distribution of aboveground biomass of whole-trees and tree component (stems, branches and leaves) of individual trees were studied and 4 equations were developed as functions of diameter at breast height (DBH), total height (HT). All the equations have good estimation effect with high prediction precision over 90%. Forest biomass was estimated based on the individual biomass prediction equations. It was found forest biomass of all organs increased with the increasing of stand age and density. And the period of 45-50 years was the suitable harvest time for Pinus sylvesris plantation.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.5
• /
• pp.336-346
• /
• 2021

The prediction of wave conditions is crucial in the field of marine and ocean engineering. Hence, this study aims to predict the significant wave height through machine learning (ML), a soft computing method. The adopted metocean data, collected from 2012 to 2020, were obtained from the Korea Institute of Ocean Science and Technology. We adopted the feedforward neural network (FNN) and long-short term memory (LSTM) models to predict significant wave height. Input parameters for the input layer were selected by Pearson correlation coefficients. To obtain the optimized hyperparameter, we conducted a sensitivity study on the window size, node, layer, and activation function. Finally, the significant wave height was predicted using the FNN and LSTM models, by varying the three input parameters and three window sizes. Accordingly, FNN (W48) (i.e., FNN with window size 48) and LSTM (W48) (i.e., LSTM with window size 48) were superior outcomes. The most suitable model for predicting the significant wave height was FNN(W48) owing to its accuracy and calculation time. If the metocean data were further accumulated, the accuracy of the ML model would have improved, and it will be beneficial to predict added resistance by waves when conducting a sea trial test.

• Geomechanics and Engineering
• /
• v.37 no.2
• /
• pp.97-107
• /
• 2024

The accurate prediction of grouting upward diffusion height is crucial for estimating the bearing capacity of tip-grouted piles. Borehole construction during the installation of bored piles induces soil unloading, resulting in both radial stress loss in the surrounding soil and an impact on grouting fluid diffusion. In this study, a modified model is developed for predicting grout diffusion height. This model incorporates the classical rheological equation of power-law cement grout and the cavity reverse expansion model to account for different degrees of unloading. A series of single-pile tip grouting and static load tests are conducted with varying initial grouting pressures. The test results demonstrate a significant effect of vertical grout diffusion on improving pile lateral friction resistance and bearing capacity. Increasing the grouting pressure leads to an increase in the vertical height of the grout. A comparison between the predicted values using the proposed model and the actual measured results reveals a model error ranging from -12.3% to 8.0%. Parametric analysis shows that grout diffusion height increases with an increase in the degree of unloading, with a more pronounced effect observed at higher grouting pressures. Two case studies are presented to verify the applicability of the proposed model. Field measurements of grout diffusion height correspond to unloading ratios of 0.68 and 0.71, respectively, as predicted by the model. Neglecting the unloading effect would result in a conservative estimate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.1976-1995
• /
• 2023

The anchor-free object detector CenterNet regards the object as a center point and predicts it based on the Gaussian circle region. For each object's center point, CenterNet directly regresses the width and height of the objects and finally gets the boundary range of the objects. However, the critical range of the object's center point can not be accurately limited by using the Gaussian circle region to constrain the prediction region, resulting in many low-quality centers' predicted values. In addition, because of the large difference between the width and height of different objects, directly regressing the width and height will make the model difficult to converge and lose the intrinsic relationship between them, thereby reducing the stability and consistency of accuracy. For these problems, we proposed a center point prediction method based on the Gaussian elliptic region and a size component regression method based on the small solution space. First, we constructed a Gaussian ellipse region that can accurately predict the object's center point. Second, we recode the width and height of the objects, which significantly reduces the regression solution space and improves the convergence speed of the model. Finally, we jointly decode the predicted components, enhancing the internal relationship between the size components and improving the accuracy consistency. Experiments show that when using CenterNet as the improved baseline and Hourglass-104 as the backbone, on the MS COCO dataset, our improved model achieved 44.7%, which is 2.6% higher than the baseline.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1841-1857
• /
• 2023

CenterNet, a novel object detection algorithm without anchor based on key points, regards the object as a single center point for prediction and directly regresses the object's height and width. However, because the objects have different sizes, directly regressing their height and width will make the model difficult to converge and lose the intrinsic relationship between object's width and height, thereby reducing the stability of the model and the consistency of prediction accuracy. For this problem, we proposed an algorithm based on the regression of the diagonal half-length and the center angle, which significantly compresses the solution space of the regression components and enhances the intrinsic relationship between the decoded components. First, encode the object's width and height into the diagonal half-length and the center angle, where the center angle is the angle between the diagonal and the vertical centreline. Secondly, the predicted diagonal half-length and center angle are decoded into two length components. Finally, the position of the object bounding box can be accurately obtained by combining the corresponding center point coordinates. Experiments show that, when using CenterNet as the improved baseline and resnet50 as the Backbone, the improved model achieved 81.6% and 79.7% mAP on the VOC 2007 and 2012 test sets, respectively. When using Hourglass-104 as the Backbone, the improved model achieved 43.3% mAP on the COCO 2017 test sets. Compared with CenterNet, the improved model has a faster convergence rate and significantly improved the stability and prediction accuracy.

• Journal of the Korean Society for Railway
• /
• v.19 no.5
• /
• pp.629-637
• /
• 2016

In this paper, an investigation was conducted to evaluate the acoustic performance of low height noise barriers installed adjacent to rails; an easy-to-use approximation formula was suggested for the evaluation of insertion loss (IL), instead of using the boundary element method. At first, the acoustic performance of the low height noise barriers was measured in an anechoic chamber using a scaled down model; the overall IL according to the source location was analyzed with the equivalent IL contour line. Using the measurement results obtained from the scaled down model, an approximation formula was suggested for the IL of low height noise barriers having various shapes. Also, the prediction program was validated through a comparison between the actual measurement results in the anechoic chamber and the prediction results. Finally, using the prediction program, an approximation formula for IL was suggested for the low height noise absorption barriers. Considering the frequency characteristics of the noise sources of the train, the absorptive low height noise barriers have a 'ㄱ' type shape, a height of 1.0m, and a length of 0.5m when they are installed on the structure gauge for the train.

• Tunnel and Underground Space
• /
• v.18 no.6
• /
• pp.447-456
• /
• 2008

Open-pit mine slope design must be carried out from the economical efficiency and stability point of view. The overall slope angle is the primary design variable because of limited support or reinforce options available. In this study, the slope angle and critical slope height of large coal mine located in Pasir, Kalimantan, Indonesia were determined from safety point of view. Failure time prediction based on the monitored displacement using inverse velocity was also conducted to make up fir the uncertainty of the slope design. From the study, critical slope height was calculated as $353{\sim}438m$ under safety factor guideline (SF>1.5) and $30^{\circ}$ overall slope angle but loom is recommended as a critical slope height considering the results of sensitivity analysis of strength parameters. The results of inverse velocity analysis also showed good agreement with field slope cases. Therefore, failure of unstable slope can be roughly detected before real slope failure.