• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.1
• /
• pp.83-91
• /
• 2021

The increased turbidity in rivers during flood events has various effects on water environmental management, including drinking water supply systems. Thus, prediction of turbid water is essential for water environmental management. Recently, various advanced machine learning algorithms have been increasingly used in water environmental management. Ensemble machine learning algorithms such as random forest (RF) and gradient boosting decision tree (GBDT) are some of the most popular machine learning algorithms used for water environmental management, along with deep learning algorithms such as recurrent neural networks. In this study GBDT, an ensemble machine learning algorithm, and gated recurrent unit (GRU), a recurrent neural networks algorithm, are used for model development to predict turbidity in a river. The observation frequencies of input data used for the model were 2, 4, 8, 24, 48, 120 and 168 h. The root-mean-square error-observations standard deviation ratio (RSR) of GRU and GBDT ranges between 0.182~0.766 and 0.400~0.683, respectively. Both models show similar prediction accuracy with RSR of 0.682 for GRU and 0.683 for GBDT. The GRU shows better prediction accuracy when the observation frequency is relatively short (i.e., 2, 4, and 8 h) where GBDT shows better prediction accuracy when the observation frequency is relatively long (i.e. 48, 120, 160 h). The results suggest that the characteristics of input data should be considered to develop an appropriate model to predict turbidity.

• Structural Engineering and Mechanics
• /
• v.80 no.6
• /
• pp.749-765
• /
• 2021

Suspension bridges bear large eccentric live loads in rush hours when most vehicles travel in one direction on the left or right side of the bridge. With the increasing number and weight of vehicles and the girder widening, the eccentric live load effect on the bridge behavior, including bending and distortion of the main girder, gets more pronounced, even jeopardizing bridge safety. This study proposes an analytical algorithm based on multi-catenary theory for predicting the suspension bridge responses to eccentric live load via the nonlinear generalized reduced gradient method. A set of governing equations is derived to solve the following unknown values: the girder rigid-body displacement in the longitudinal direction; the horizontal projection lengths of main cable's segments; the parameters of catenary equations and horizontal forces of the side span cable segments and the leftmost segments of middle span cables; the suspender tensions and the bearing reactions. Then girder's responses, including rigid-body displacement in the longitudinal direction, deflections, and torsion angles; suspenders' responses, including the suspender tensions and the hanging point displacements; main cables' responses, including the horizontal forces of each segment; and the longitudinal displacement of the pylons' tower top under eccentric load can be calculated. The response of an exemplar suspension bridge with three spans of 168, 548, and 168 m is calculated by the proposed analytical method and the finite element method in two eccentric live load cases, and their results prove the former's feasibility. The nonuniform distribution of the live load in the lateral direction is shown to impose a greater threat to suspension bridge safety than that in the longitudinal direction, while some other specific features revealed by the proposed method are discussed in detail.

• Progress in Medical Physics
• /
• v.20 no.3
• /
• pp.132-138
• /
• 2009

Studies on target motion in 4-dimensional radiotherapy are being world-widely conducted to enhance treatment record and protection of normal organs. Prediction of tumor motion might be very useful and/or essential for especially free-breathing system during radiation delivery such as respiratory gating system and tumor tracking system. Neural network is powerful to express a time series with nonlinearity because its prediction algorithm is not governed by statistic formula but finds a rule of data expression. This study intended to assess applicability of neural network method to predict tumor motion in 4-dimensional radiotherapy. Scaled Conjugate Gradient algorithm was employed as a learning algorithm. Considering reparation data for 10 patients, prediction by the neural network algorithms was compared with the measurement by the real-time position management (RPM) system. The results showed that the neural network algorithm has the excellent accuracy of maximum absolute error smaller than 3 mm, except for the cases in which the maximum amplitude of respiration is over the range of respiration used in the learning process of neural network. It indicates the insufficient learning of the neural network for extrapolation. The problem could be solved by acquiring a full range of respiration before learning procedure. Further works are programmed to verify a feasibility of practical application for 4-dimensional treatment system, including prediction performance according to various system latency and irregular patterns of respiration.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.1-8
• /
• 2005

In this paper, we propose a two-stage head tracking algorithm adequate for real-time active camera system having pan-tilt-zoom functions. In the color convergence stage, we first assume that the shape of a head is an ellipse and its model color histogram is acquired in advance. Then, the min-shift method is applied to roughly estimate a target position by examining the histogram similarity of the model and a candidate ellipse. To reflect the temporal change of object color and enhance the reliability of mean-shift based tracking, the target histogram obtained in the previous frame is considered to update the model histogram. In the updating process, to alleviate error-accumulation due to outliers in the target ellipse of the previous frame, the target histogram in the previous frame is obtained within an ellipse adaptively shrunken on the basis of the model histogram. In addition, to enhance tracking reliability further, we set the initial position closer to the true position by compensating the global motion, which is rapidly estimated on the basis of two 1-D projection datasets. In the subsequent stage, we refine the position and size of the ellipse obtained in the first stage by using shape information. Here, we define a robust shape-similarity function based on the gradient direction. Extensive experimental results proved that the proposed algorithm performs head hacking well, even when a person moves fast, the head size changes drastically, or the background has many clusters and distracting colors. Also, the propose algorithm can perform tracking with the processing speed of about 30 fps on a standard PC.

• Economic and Environmental Geology
• /
• v.30 no.6
• /
• pp.625-635
• /
• 1997

A back projection algorithm is applied to 216 Pn travel time measurements to image lateral variations of compressional velocity in the uppermost mantle in the Korean Peninsula. We obtained an average P-velocity value for the uppermost mantle of $7.90{\pm}0.18km/sec$, and an average mantle P-velocity gradient of $5.3{\times}10^{-3}s^{-1}$ for the Korean Peninsula. The final 3-D velocity image in the uppermost mantle is characterized by a low-velocity (about $7.77{\pm}0.12km/sec$) region in the southeast area of the Korean peninsula, which is called 'Kyongsang Basin' and by high-velocity(${\geq}8.08km/sec$) region in the northern area of the Korean Peninsula(Hamkyong and Pyongan provinces). The crustal thicknesses are calculated for the 10 subregions. The crustal thickness of the northern part(${\geq}39^{\circ}N$) of the Korean Peninsula is 33.0-36.0 km, on the contrary, that of the southern part(< $39^{\circ}N$) is 30.7~33.7 km. The velocity image obtained in this study is somewhat consistent with previous S-P travel time studies and gravity studies.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.3
• /
• pp.775-787
• /
• 1996

An optimization procedure is proposed for the design of cylindrically laminated composite shell having midplane symmetry and subjected to axial force, torsion and internal pressure. Tsai-Wu and Tsai-Hill failure criteria are taken as objective functions. The stacking sequence represents the design variable. The optimal design formulation based on state space method is adopted and solution proccedure is described with the emphasis on the method of calculations of the design sensitivities. A gradient projection algorithm is employed for the optimization process. Numerical results are presented for the several test problems.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.10
• /
• pp.1566-1573
• /
• 2004

When a projectile travels at high speed underwater, supercavitating flow arises, in which a huge cavity is generated behind the projectile so that only the nose, i.e., the cavitator, of the projectile is wetted, while the rest of it should be surrounded by the cavity. In that case, the projectile can achieve very high speed due to the reduced drag. Furthermore if the nose of the body is shaped properly, the attendant pressure drag can be maintained at a very low value, so that the overall drag is also reduced dramatically. In this study, shape optimization technique is employed to determine the optimum cavitator shape for minimum drag, given certain operating conditions. Shape optimization technique is also used to solve the potential flow problem fur any given cavitator, which is a free boundary value problem having the cavity shape as unknown a priori. Analytical sensitivities are derived for various shape parameters in order to implement a gradient-based optimization algorithm. Simultaneous optimization technique is proposed for efficient cavitator shape optimization, in which the cavity and cavitator shape are determined in a single optimization routine.

• The KSFM Journal of Fluid Machinery
• /
• v.16 no.1
• /
• pp.11-16
• /
• 2013

A numerical study was conducted to improve the performance of an impeller of centrifugal compressor. Nine design variables were chosen with constraints. Only meridional contours and blade profile were adjusted. ANN (Artificial Neural Net) was adopted as a main optimization algorithm with PSO (Particle Swarm Optimization) in order to reduce the optimization time. At first, ANN was learned and trained with the design variable sets which were obtained using DOE (Design of Experiment). This ANN was continuously improved its accuracy for each generation of which population was one hundred. New design variable set in each generation was selected using a non-gradient based method of PSO in order to obtain the global optimized result. After $7^{th}$ generation, the prediction difference of efficiency and pressure ratio between ANN and CFD was less than 0.6%. From more than 1,200 design variable sets, a pareto of efficiency versus pressure ratio was obtained and an optimized result was selected based on the multi-objective function. On this optimized impeller, the efficiency and pressure ratio were improved by 1% and 9.3%, respectively.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.29 no.9 s.240
• /
• pp.1049-1056
• /
• 2005

A conservative pressure-based finite-volume numerical method has been developed for computing flow and heat transfer by using an unstructured grid system. The method admits arbitrary convex polyhedra. Care is taken in the discretization and solution procedures to avoid formulations that are cell-shape-specific. A collocated variable arrangement formulation is developed, i.e. all dependent variables such as pressure and velocity are stored at cell centers. Gradients required for the evaluation of diffusion fluxes and for second-order-accurate convective operators are found by a novel second-order accurate spatial discretization. Momentum interpolation is used to prevent pressure checkerboarding and the SIMPLE algorithm is used for pressure-velocity coupling. The resulting set of coupled nonlinear algebraic equations is solved by employing a segregated approach, leading to a decoupled set of linear algebraic equations fer each dependent variable, with a sparse diagonally dominant coefficient matrix. These equations are solved by an iterative preconditioned conjugate gradient solver which retains the sparsity of the coefficient matrix, thus achieving a very efficient use of computer resources.

• International Journal of Aeronautical and Space Sciences
• /
• v.13 no.4
• /
• pp.484-490
• /
• 2012

This paper is devoted to investigate the feasibility of using a medium power ground-based laser to produce a torque on LEO satellites of various shapes. The laser intensity delivered to a satellite is calculated using a simple model of laser propagation in which a standard atmospheric condition and linear atmospheric interaction mechanism is assumed. The laser force is formulated using a geocentric equatorial system in which the Earth is an oblate spheroid. The torque is formulated for a cylindrical satellite, spherical satellites and for satellites of complex shape. The torque algorithm is implemented for some sun synchronous low Earth orbit cubesats. Based on satellites perigee height, the results demonstrate that laser torque affecting on a cubesat has a maximum value in the order of $10^{-9}$ which is comparable with that of solar radiation. However, it has a minimum value in the order of $10^{-10}$ which is comparable with that of gravity gradient. Moreover, the results clarify the dependency of the laser torque on the orbital eccentricity. As the orbit becomes more circular it will experience less torque. So, we can conclude that the ground based laser torque has a significant contribution on the low Earth orbit cubesats. It can be adjusted to obtain the required control torque and it can be used as an active attitude control system for cubesats.