• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.6
• /
• pp.616-628
• /
• 2000

In this paper, we present the modeling of the ozone prediction system using Neuro-Fuzzy approaches. The mechanism of ozone concentration is highly complex, nonlinear, and nonstationary, the modeling of ozone prediction system has many problems and the results of prediction is not a good performance so far. The Dynamic Polynomial Neural Network(DPNN) which employs a typical algorithm of GMDH(Group Method of Data Handling) is a useful method for data analysis, identification of nonlinear complex system, and prediction of a dynamical system. The structure of the final model is compact and the computation speed to produce an output is faster than other modeling methods. In addition to DPNN, this paper also includes a Fuzzy Logic Method for modeling of ozone prediction system. The results of each modeling method and the performance of ozone prediction are presented. The proposed method shows that the prediction to the ozone concentration based upon Neuro-Fuzzy approaches gives us a good performance for ozone prediction in high and low ozone concentration with the ability of superior data approximation and self organization.

• 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.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.191-194
• /
• 2001

The ozone forecasting systems have many problems because the mechanism of the ozone concentration is highly complex, nonlinear, and nonstationary. Also, the results of prediction are not a good performance so far, especially in the high-level ozone concentration. This paper describes the modeling method of the ozone prediction system using neuro-fuzzy approaches and fuzzy clustering. The dynamic polynomial neural network (DPNN) based upon a typical algorithm of GMDH (group method of data handling) is a useful method for data analysis, identification of nonlinear complex system, and prediction of a dynamical system.

• Transactions of Materials Processing
• /
• v.7 no.3
• /
• pp.197-206
• /
• 1998

This paper presents the prediction of dynamic recrystallization behavior during hot forging of Inconel 718. Another experiment of pancake forging was also carried out to examine the recrystallization ration dynamically recrystallizaed grain size, and grain growth in the forging. In experiments cylindrical billets were forged by two operations with variations of forging temperature, reduction ration of deformation. and preheating process at each forging step. Also the finite element program, developed here for the prediction using the metallurgical models was used for the analysis of to Inconel 718 upsetting and the results were compared with experimental ones.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.6
• /
• pp.323-330
• /
• 2021

Visual object tracking is a challenging area of study in the field of computer vision due to many difficult problems, including a fast variation of target shape, occlusion, and arbitrary ground truth object designation. In this paper, we focus on the reinforced feature of the dynamic search area to get better performance than conventional discriminative model prediction trackers on the condition when the accuracy deteriorates since low feature discrimination. We propose a reinforced input feature method shown like the spotlight effect on the dynamic search area of the target tracking. This method can be used to improve performances for deep learning based discriminative model prediction tracker, also various types of trackers which are used to infer the center of the target based on the visual object tracking. The proposed method shows the improved tracking performance than the baseline trackers, achieving a relative gain of 38% quantitative improvement from 0.433 to 0.601 F-score at the visual object tracking evaluation.

• 한국전산유체공학회:학술대회논문집
• /
• 2011.05a
• /
• pp.428-433
• /
• 2011

In this paper, a prediction method for dynamic stability derivatives is studied using steady state simulations in rotational coordinates. The simulations require the extension of a standard CFD formulations based on inertial coordinate. A new CFD code based on the method are developed. Flows induced by steady circular motions of airfoils with a constant pitch rate are simulated with the code. From the numerical simulations, the pitch rate derivatives are obtained at various Mach numbers, and the results are compared with other numerical results. The numerical simulations show that the new code are capable of predicting dynamic stability derivatives.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.368-368
• /
• 2000

In this paper, we present forecasting ozone concentration with decision support system. Since the mechanism of ozone concentration is highly complex, nonlinear, and nonstationary, modeling of ozone prediction system has many problems and results of prediction are not good performance so far. Forecasting ozone concentration with decision support system is acquired to information from human knowledge and experiment data. Fuzzy clustering method uses the acquisition and dynamic polynomial neural network gives us a good performance for ozone prediction with ability of superior data approximation and self-organization.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.8
• /
• pp.59-66
• /
• 2010

In this study, an applicability by using the FEM was investigated for the prediction of both the depth of improvement and the vibration effect when dynamic compaction method is applied. The region was modelled by the field conditions applying dynamic compaction method and the rigid body force was applied to the dynamic load model. Predicted depth of improvement calculated by the vertical peak particle acceleration was compared and analyzed with an existing empirical equation, and the effect of groundwave by deducing the peak particle velocity from vibration sources was compared and analyzed with the results of another existing empirical equation. The results showed that the prediction of the depth of improvement has similar tendency to practice, and the vibration effect has some differences in a particular section from existing equation, but it could predict the safety distance to some degree. The analyzed results are expected to be basic data for the development of reliability of dynamic compaction design with existing empirical method.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.219-224
• /
• 2004

There have been many researches on machine tool vibration and chatter to obtain assessment procedure and more productivity. In this paper chatter limit is predicted on a universal machining center which used a parallel mechanism. The prediction method uses the combination of structural dynamic characteristics and cutting dynamics. So the dynamic characieristics were obtained by vibration experiments. We showed the unstable cutting conditions, and from them we could plot the unstable borderlines.

• 한국전산유체공학회:학술대회논문집
• /
• 2010.05a
• /
• pp.358-361
• /
• 2010

A Reynolds-Averaged Navier-Stokes (RANS) code with transition prediction model is developed and the computational results on an oscillating airfoil are compared with the experimental data for OA209 airfoil. An approximated eN method that can predict transition onset points and the length of transition region is directly applied to the RANS code. The hysteresis loop in dynamic stall is compared for the computational results using transition prediction and fully turbulent models with the experimental data. Results with transition prediction show more correlation with the experimental data than the fully turbulent computation.