• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1975-1988
• /
• 2019

Short-term traffic flow prediction plays an important role in intelligent transportation systems (ITS) in areas such as transportation management, traffic control and guidance. For short-term traffic flow regression predictions, the main challenge stems from the non-stationary property of traffic flow data. In this paper, we design an ensemble cascading prediction framework based on extremely randomized trees (extra-trees) using a boosting technique called EET to predict the short-term traffic flow under non-stationary environments. Extra-trees is a tree-based ensemble method. It essentially consists of strongly randomizing both the attribute and cut-point choices while splitting a tree node. This mechanism reduces the variance of the model and is, therefore, more suitable for traffic flow regression prediction in non-stationary environments. Moreover, the extra-trees algorithm uses boosting ensemble technique averaging to improve the predictive accuracy and control overfitting. To the best of our knowledge, this is the first time that extra-trees have been used as fundamental building blocks in boosting committee machines. The proposed approach involves predicting 5 min in advance using real-time traffic flow data in the context of inherently considering temporal and spatial correlations. Experiments demonstrate that the proposed method achieves higher accuracy and lower variance and computational complexity when compared to the existing methods.

• Computers and Concrete
• /
• v.16 no.5
• /
• pp.741-757
• /
• 2015

In the last decade, several modeling approaches have been proposed and applied to estimate the high-performance concrete (HPC) slump flow. While HPC is a highly complex material, modeling its behavior is a very difficult issue. Thus, the selection and application of proper modeling methods remain therefore a crucial task. Like many other applications, HPC slump flow prediction suffers from noise which negatively affects the prediction accuracy and increases the variance. In the recent years, ensemble learning methods have introduced to optimize the prediction accuracy and reduce the prediction error. This study investigates the potential usage of bagging (Bag), which is among the most popular ensemble learning methods, in building ensemble models. Four well-known artificial intelligence models (i.e., classification and regression trees CART, support vector machines SVM, multilayer perceptron MLP and radial basis function neural networks RBF) are deployed as base learner. As a result of this study, bagging ensemble models (i.e., Bag-SVM, Bag-RT, Bag-MLP and Bag-RBF) are found superior to their base learners (i.e., SVM, CART, MLP and RBF) and bagging could noticeable optimize prediction accuracy and reduce the prediction error of proposed predictive models.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.13 no.7
• /
• pp.595-601
• /
• 2001

We applied PIV method to obtain instantaneous and ensemble averaged velocity fields from the first row to the fifth row of a staggered tube bundle. The Reynolds number based on the tube diameter and the maximum velocity was set to be 4,000. Remarkably different natures are observed in the developing bundle flow. Such differences are depicted in the mean recirculating bubble length and the vorticity distributions. The jet-like flow seems to be a dominant feature after the second row and usually skew. However, the ensemble averaged fields show symmetric profiles and the flow characteristics between the third and fourth measuring planes are not so different. comparison between the PIV data and the RANS simulation yields severe disagreement in spite of the same Reynolds number. It can be explained that the distinct jet-like unsteady motions are not to be accounted in th steady numerical analysis.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.20 no.7
• /
• pp.2289-2297
• /
• 1996

Flows in the combustion chamber near the spark plug are measured using LDv.A single cylinder DOHC S.I. engine of compression ratio 9.5:1 with a transparent quartz window piston is used. Combustion chamber shape is semi-wedge type. Measured data are analyzed using the ensemble averaged analysis and the cycle resolved analysis which uses FFT Filtering. Turbulent intensity and mean velocity are studied in the main flow direction and the normal to main flow direction as a function of engine speeds. The results shows that the turbulent intensity obtained by the ensemble averaged analysis is greater than that calculated by the cycle resolved analysis. Especially, the ensemble averaged analysis shows increase in turbulence at the end of compression stroke although the cycle resolved analysis shows increase only in the cycle-by-cycle variation with no noticeable increase in turbulence. The mean velocity in the main flow direction increase as engine speed increase. But the mean velocity normal to the main flow does not show such increase. Turbulent intensity in both direction increase in proportion to engine speeds. The magnitude of turbulent intensity is about 0.3 ~ 0.4 times the mean piston speeds at the end of the compression stroke.

• The KSFM Journal of Fluid Machinery
• /
• v.10 no.4
• /
• pp.47-54
• /
• 2007

Simultaneous 3-D LDV measurements of the in-cylinder flows of three different engine setups were summarized for the quantification of the flow characteristics in each vertical or horizontal plane, and in entire cylinder volume. The ensemble averaged-velocity, tumble and swirl motions, and turbulent kinetic energy during the intake and compression strokes were examined from the measured velocity data (approximately 2,000 points for each engine setup). The better spatial resolution of the 3-D LDV allows measurements of the instantaneous flow structures, yielding more valuable information about the smaller flow structures and the cycle-to-cycle variation of these flow patterns. Tumble and swirl ratios, and turbulent kinetic energy were quantified as planar and volumetric quantities. The measurements and calculation results were animated for the visualization of the flow, and hence ease to analysis.

• Honam Mathematical Journal
• /
• v.36 no.1
• /
• pp.11-27
• /
• 2014

In this paper, we propose closures for multi-phase flow models, which satisfy boundary conditions and conservation constraints. The models governing the evolution of the fluid mixing are derived by applying an ensemble averaging procedure to the microphysical equations characterized by distinct phases. We consider compressible multi species multi-phase flow with surface tension and transport.

• Journal of Korean Society on Water Environment
• /
• v.36 no.5
• /
• pp.353-363
• /
• 2020

Hydrologic models can be classified into two types: those for understanding physical processes and those for predicting hydrologic quantities. This study deals with how to use the model to predict today's stream flow based on the system's knowledge of yesterday's state and the model parameters. In this regard, for the model to generate accurate predictions, the uncertainty of the parameters and appropriate estimates of the state variables are required. In this study, a relatively simple hydrologic partitioning model is proposed that can explicitly implement the hydrologic partitioning process, and the posterior distribution of the parameters of the proposed model is estimated using the Markov chain Monte Carlo approach. Further, the application method of the ensemble Kalman filter is proposed for updating the normalized soil moisture, which is the state variable of the model, by linking the information on the posterior distribution of the parameters and by assimilating the observed steam flow data. The stochastically and recursively estimated stream flows using the data assimilation technique revealed better representation of the observed data than the stream flows predicted using the deterministic model. Therefore, the ensemble Kalman filter in conjunction with the Markov chain Monte Carlo approach could be a reliable and effective method for forecasting daily stream flow, and it could also be a suitable method for routinely updating and monitoring the watershed-averaged soil moisture.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.9
• /
• pp.2423-2430
• /
• 1994

Several factors of the efficient combustion process are shape of combustion chamber, position of spark plug, turbulence flow and so on. the shape of combustion chamber and position of spark plug are constrained to geometrically, and then it could not make a change the shape easily. But the turlence flow in combustion chamber have a great influence on combustion phenomena, and which is much easier to control relatively. And since characteristics of turbulence flow would be very important to the stability of combustion and performances, This study is also essential to future engine-low emission and lean burn engine. This paper shows that the visualization of the turbulence flow of single cylinder engine by using 2way, $45^{\circ}$ inclined and 2 channel hot wire probe through the park plug hole. We also study the characteristics of turbulence flow by means of ensemble averaged mean velocity, turvulence intensity and integral length scale.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.24 no.3
• /
• pp.382-389
• /
• 2000

The instantaneous and ensemble averaged flow characteristics of a round jet issuing normally into a crossflow was studied using a flow visualization technique and Particle Image Velocimetry measurements. Experiments were performed at a jet-to-crossflow velocity ratio, 3.3, and two Reynolds numbers, 1050 and 2100, based on crossflow velocity and jet diameter. Instantaneous laser tomographic images of the vertical center plane of the crossflow jet showed that there exist very different natures in the flow structures of the near field jet even though the velocity ratio is the same. It was found that the shear layer becomes much thicker when the Reynolds number is 2100 due to the strong entrainment of the inviscid fluid by turbulent interaction between the jet and crossflow. The mean and second order statistics were calculated by ensemble averaging over 1000 realizations of instantaneous velocity fields. The detail characteristics of mean flow field, stream wise and vertical r.m.s. velocity fluctuations, and Reynolds shear stress distributions were presented. The new PlV results were compared with those from previous experimental and LES studies.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.6
• /
• pp.486-491
• /
• 2004

Purpose: factor analysis and independent component analysis (ICA) has been used for handling dynamic image sequences. Theoretical advantages of a newly suggested ICA method, ensemble ICA, leaded us to consider applying this method to the analysis of dynamic myocardial $H_2^{15}O$ PET data. In this study, we quantified patients' blood flow using the ensemble ICA method. Materials and Methods: Twenty subjects underwent $H_2^{15}O$ PET scans using ECAT EXACT 47 scanner and myocardial perfusion SPECT using Vertex scanner. After transmission scanning, dynamic emission scans were initiated simultaneously with the injection of $555{\sim}740$ MBq $H_2^{15}O$. Hidden independent components can be extracted from the observed mixed data (PET image) by means of ICA algorithms. Ensemble learning is a variational Bayesian method that provides an analytical approximation to the parameter posterior using a tractable distribution. Variational approximation forms a lower bound on the ensemble likelihood and the maximization of the lower bound is achieved through minimizing the Kullback-Leibler divergence between the true posterior and the variational posterior. In this study, posterior pdf was approximated by a rectified Gaussian distribution to incorporate non-negativity constraint, which is suitable to dynamic images in nuclear medicine. Blood flow was measured in 9 regions - apex, four areas in mid wall, and four areas in base wall. Myocardial perfusion SPECT score and angiography results were compared with the regional blood flow. Results: Major cardiac components were separated successfully by the ensemble ICA method and blood flow could be estimated in 15 among 20 patients. Mean myocardial blood flow was $1.2{\pm}0.40$ ml/min/g in rest, $1.85{\pm}1.12$ ml/min/g in stress state. Blood flow values obtained by an operator in two different occasion were highly correlated (r=0.99). In myocardium component image, the image contrast between left ventricle and myocardium was 1:2.7 in average. Perfusion reserve was significantly different between the regions with and without stenosis detected by the coronary angiography (P<0.01). In 66 segment with stenosis confirmed by angiography, the segments with reversible perfusion decrease in perfusion SPECT showed lower perfusion reserve values in $H_2^{15}O$ PET. Conclusions: Myocardial blood flow could be estimated using an ICA method with ensemble learning. We suggest that the ensemble ICA incorporating non-negative constraint is a feasible method to handle dynamic image sequence obtained by the nuclear medicine techniques.