• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.1
• /
• pp.216-238
• /
• 2023

In intelligent transportation systems, traffic management is an important task. The accurate forecasting of traffic characteristics like flow, congestion, and density is still active research because of the non-linear nature and uncertainty of the spatiotemporal data. Inclement weather, such as rain and snow, and other special events such as holidays, accidents, and road closures have a significant impact on driving and the average speed of vehicles on the road, which lowers traffic capacity and causes congestion in a widespread manner. This work designs a model for multivariate short-term traffic congestion prediction using SLSTM_AE-BiLSTM. The proposed design consists of a Bidirectional Long Short Term Memory(BiLSTM) network to predict traffic flow value and a Convolutional Neural network (CNN) model for detecting the congestion status. This model uses spatial static temporal dynamic data. The stacked Long Short Term Memory Autoencoder (SLSTM AE) is used to encode the weather features into a reduced and more informative feature space. BiLSTM model is used to capture the features from the past and present traffic data simultaneously and also to identify the long-term dependencies. It uses the traffic data and encoded weather data to perform the traffic flow prediction. The CNN model is used to predict the recurring congestion status based on the predicted traffic flow value at a particular urban traffic network. In this work, a publicly available Caltrans PEMS dataset with traffic parameters is used. The proposed model generates the congestion prediction with an accuracy rate of 92.74% which is slightly better when compared with other deep learning models for congestion prediction.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2000.04a
• /
• pp.297-302
• /
• 2000

Pipe cooling method is widely used for reduction of hydration heat and control of cracking in mass concrete structures. However, in order to effectively apply pipe cooling systems to concrete structure, the coefficient of flow convection relating the thermal transfer between inner stream of pipe and concrete must be estimated. In this study, a device measuring the coefficient of flow convection is developed. Since a variation of thermal distribution caused by pipe cooling has a direct effect in internal forced flows, the developed testing device is based on the internal forced flow concept. Influencing factors on the coefficient of flow convection are mainly flow velocity, pipe diameter and thickness, and pipe material. finally a prediction model of the coefficient of flow convection is proposed using experimental results from the developed device. According to the proposed prediction model, the coefficient of flow convection increases with increase in flow velocity and decreases with increase in pipe diameter and thickness. Also, the coefficient of flow convection is largely affected by the type of pipe materials.

• The KSFM Journal of Fluid Machinery
• /
• v.2 no.1 s.2
• /
• pp.56-63
• /
• 1999

In this study, the performance prediction programs for centrifugal pumps are developed. To estimate the losses in the centrifugal pump impellers, a two-zone model and TEIS(two elements in series) model are applied to the program. The basic concept of a two zone model considers the primary zone that is an isentropic core flow and the secondary zone that has a non-isentropic region at the impeller exit. The flow goes through two different zones and is mixed out at the impeller exit and the mixing process occurs with an increase in entropy, a decrease in total pressure. The level of the core flow diffusion in an impeller was calculated using TEIS(two elements in series) model. The effects of various parameters which are used in this program on the prediction of head and efficiency are discussed. The correlation curves used to select the effectiveness of the primitive TEIS model were suggested according to the specific speed of the centrifugal pumps.

• Journal of Korea Water Resources Association
• /
• v.51 no.7
• /
• pp.607-616
• /
• 2018

Flow regime-based ANFIS Dam Inflow Prediction (FADIP) model is developed and compared with ANFIS Dam Inflow Prediction (ADIP) model in this study. The selected study area is the Chungju and Soyang multi-purpose dam watersheds in South Korea. The dam inflow, precipitation and monthly weather forecast information are used as input variables of the models. The training and validation periods of the models are 1987~2010 for Chungju and 1984~2010 for Soyang dam watershed. The testing periods for both watersheds are 2011~2016. The results of training and validation indicate that FADIP has better training ability than ADIP for predicting dam inflow in normal and low flow regimes. In the result of testing, ADIP shows low predictability of dam inflow in the low flow regime due to the model tuning on all flow regime together. However, FADIP demonstrates the improved accuracy over the entire period compared to ADIP, especially during the normal and low flow seasons. It is concluded that FADIP is valuable for the prediction of dam inflow in the case of drought years, and useful for water supply management of the multi-purpose dam.

• 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.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.9 no.5
• /
• pp.148-156
• /
• 2001

Computational Fluid Dynamics (CFD) analysis was carried out to investigate exhaust gas flow and acoustic characteristics in the exhaust system of a passenger car. Transient 3-dimensional flow field in the front and rear mufflers was simulated by CFD and far-field sound pressure was modeled by a simple monopole source method. Engine performance simulation was also performed to obtain the boundary condition of instantaneous fluid flow variation at the inlet of the exhaust system. Detailed exhaust gas flow characteristics such as velocity and pressure distribution inside the mufflers were presented and the pulsating pressure amplitude was compared at several positions in the exhaust system to deduce sound pressure level. The present method of the acoustic analysis coupled with CFD techniques would be very effective for the prediction of sound noise from vehicle exhaust systems although the effects of the inlet boundary condition and heat transfer on the accuracy of the prediction have to be validated through further studies.

• 한국신재생에너지학회:학술대회논문집
• /
• 2005.06a
• /
• pp.448-451
• /
• 2005

This paper presents the methodology to analyze flow duration characteristics and performance prediction for small hydro power(SHP) plants and its application. The flow duration curvecan be decided by using monthly rainfall data at the most of the SHP sites with no useful hydrological data. It was proved that the monthly rainfall data can be characterized by using the cumulative density function of Weibull distribution and Thiessen method were adopted to decide flow duration curve at SHP plants. And, the performance prediction has been studied and development. One SHP plant was selected and performance characteristics was analyzed by using the developed technique. Primary design specfications such as design flowrate, plant capacity, operational rate and annual electricity production for the SHP plant were estimated. It was found that the methodology developed in this study can be a useful tool to predict the performance of SHP plants and candidate sites in Korea.

• 유체기계공업학회:학술대회논문집
• /
• 1998.12a
• /
• pp.223-232
• /
• 1998

To investigate the flow inside the centrifugal impeller, computer program which can solve Three-dimensional compressible turbulent flow has been developed. The Navier-Stokes equations were chosen as the governing equation for viscous flow while Euler equations for inviscid case. Time marching method was incorporated with the Flux Difference Splitting method suggested by Roe to capture the steep gradients such as a shock. For high order of accuracy, MUSCL approach was adopted while differentiable limiter to ensure TVD property. For turbulence closure, Baldwin- Lomax model was applied due to its simplicity. To demonstrate the capabilities of present program, several validation problems have been solved and compared with experiments and other available data. From the above calculations generally good agreements were obtained. Finally, the developed code was applied to Eckardt's impeller and the performance prediction was carried out. Some important aspects on boundary condition for successful simulation were discussed and the remedy was also introduced.

• Proceedings of the KSME Conference
• /
• 2000.04b
• /
• pp.574-579
• /
• 2000

In this study. an off-design performance prediction program for centrifugal pumps is developed. To estimate the losses in an impeller flow passage, two-zone model and two-element in series(TEIS) model are used. At impeller exit. the mixing process occurs with an increase in entropy. In two-zone model. there are both primary zone and secondary zone for an isentropic core flow and an average of all non-isentropic streamtubes respectively. The level of the core flow diffusion in an impeller was calculated by using TEIS model. While internal losses in an impeller an automatically estimated by using the above models, some empirical correlations far estimating external losses. far example, disk friction loss, recirculation loss and leakage loss are used. In order to analyze the vaneless diffuser flow. the momentum equations for the radial and tangential directions are used and solved together with continuity and energy equations.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.130-138
• /
• 2023

The traffic flow in an urban area is affected by the date, weather, and regional traffic flow. The existing methods are weak to model the dynamic road network features, which results in inadequate long-term prediction performance. To solve the problems regarding insufficient capacity for dynamic modeling of road network structures and insufficient mining of dynamic spatio-temporal features. In this study, we propose a novel traffic flow prediction framework called shared spatio-temporal attention convolution optimization network (SSTACON). The shared spatio-temporal attention convolution layer shares a spatio-temporal attention structure, that is designed to extract dynamic spatio-temporal features from historical traffic conditions. Subsequently, the graph optimization module is used to model the dynamic road network structure. The experimental evaluation conducted on two datasets shows that the proposed method outperforms state-of-the-art methods at all time intervals.