• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.623-625
• /
• 2018

As the issue of particulate matter spreads, services for providing particulate matter information in real time are increasing. However, when a sensor node for collecting particulate matter is defective, a corresponding service may not be provided. To solve these problems, it is necessary to predict and deduce particulate matter. In this paper, a particulate matter prediction model is designed using artificial neural network algorithm based on past particulate matter and meteorological data to predict particulate matter. Also, the prediction results are compared by learning the input data of the model in the design stage.

• Journal of Korean Elementary Science Education
• /
• v.23 no.2
• /
• pp.116-122
• /
• 2004

The purpose of this study is to investigate effects of computer animations using particulate model in elementary science classes related to air pressure. To do those, four classes of 5th grade in an elementary school located in a city were selected. As an experiment group, two classes were applied the teaching materials of computer animations developed for this study based on particulate model. The other classes as a control group were not applied these materials in science classes. The total scores of experiment group in which computer animation using particulate model was applied in science classes are higher than those of the control group in the conception test. Only in one conception related to high and low atmospheric air pressure, the scores of the two groups are not significantly different at 0.05 significance level.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.3 no.6
• /
• pp.41-54
• /
• 1995

A mathematical model for wall-flow monolith ceramic diesel particulate filter was developed in order to describe the processes which take place in the filter during regeneration. The major output of the model comprises ceramic wall temperature and regeneration time(soot reduction). Various numerical tests were performed to demonstrate how the gas oxygen concentration, flow rate and the initial particulate trap loading affect the regeneration time and peak trap temperature. The model is shown to b in reasonable agreement with the published experimental results. This model can be applied to predict the thermal shock failure due to high temperature during combustion regeneration process.

• Structural Engineering and Mechanics
• /
• v.8 no.3
• /
• pp.273-283
• /
• 1999

Two physical experiments are performed to verify the effectiveness of beam-particle model for simulating the progressive failure of particulate composites such as sandstone and concrete. In the numerical model, the material is schematized at the meso-level as an assembly of discrete, interacting particles which are linked through a network of brittle breaking beams. The uniaxial compressive tests of cubic and parallelepipedal specimens made of carbon steel rod assembly which are glued together by a mixture are represented. The crack patterns and load-displacement response observed in the experiments are in good agreement with the numerical results. In the application respect of beam-particle model to the particulate composites, the influence of defects, particle arrangement and boundary conditions on crack propagation is approached, and the correlation existing between the cracking evolution and the level of loads imposed on the specimen is characterized by fractal dimensions.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.17 no.3
• /
• pp.29-34
• /
• 2009

Diesel particulate filter (DPF) has been developed to optimize engine out emission, especially particulate matter (PM). One of the main important factors for developing the DPF is estimation of soot mass being accumulated inside the DPF. Evaluation of pressure drop over the DPF is a simple way to estimate the accumulated soot mass but its accuracy is known to be limited to certain vehicle operating conditions. The method to compensate drawback is adoption of integrating time history of the engine out PM and burning soot. Present study demonstrates current status of the soot estimation methods including the results from the engine test benches and vehicles.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.20-26
• /
• 2019

Due to the human influence of particulate matter, various studies are being conducted to predict it using past data measured in the atmospheric environment monitoring network. However, it is difficult to precisely set the measurement environment and detailed conditions of the previously designed predictive model, and it is necessary to design a new predictive model based on the existing research results because of the problems such as the missing of the weather data. In this paper, as a previous study for particulate matter prediction, the conformity of the algorithm for particulate matter prediction was evaluated by designing the prediction model through the multiple linear regression and the artificial neural network, which are machine learning algorithms. As a result of the prediction performance comparison through RMSE, 18.13 for the MLR model and 14.31 for the MLP model, and the artificial neural network model was more conformable for predicting the particulate matter concentration.

• Journal of Power System Engineering
• /
• v.10 no.4
• /
• pp.133-138
• /
• 2006

Effective thermal conductivity of particulate reinforced composite has been predicted by Eshelby's equivalent inclusion method modified with Mori-Tanaka's mean field theory. The predicted results are compared with the experimental results from the literature. The model composite is polymer matrix filled with ceramic particles such as silica, alumina, and aluminum nitride. The preliminary examination by Eshelby type model shows that the predicted results are in good agreements with the experimental results for the composite with perfect spherical filler. As the shape of filler deviates from the perfect sphere, the predicted error increases. By using the aspect ratio of the filler deduced from the fixed filler volume fraction of 30%, the predicted results coincide well with the experimental results for filler volume fraction of 40% or less. Beyond this fraction, the predicted error increases rapidly. It can be finally concluded from the study that Eshelby type model can be applied to predict the thermal conductivity of the particulate composite with filler volume fraction less than 40%.

• Journal of information and communication convergence engineering
• /
• v.19 no.4
• /
• pp.241-247
• /
• 2021

Particulate matter has emerged as a serious global problem, necessitating highly reliable information on the matter. Therefore, various algorithms have been used in studies to predict particulate matter. In this study, we compared the prediction performance of neural network models that have been actively studied for particulate matter prediction. Among the neural network algorithms, a deep neural network (DNN), a recurrent neural network, and long short-term memory were used to design the optimal prediction model using a hyper-parameter search. In the comparative analysis of the prediction performance of each model, the DNN model showed a lower root mean square error (RMSE) than the other algorithms in the performance comparison using the RMSE and the level of accuracy as metrics for evaluation. The stability of the recurrent neural network was slightly lower than that of the other algorithms, although the accuracy was higher.

• Journal of Cadastre & Land InformatiX
• /
• v.51 no.2
• /
• pp.141-150
• /
• 2021

Fine dust is a substance that greatly affects human health, and various studies have been conducted in this regard. Due to the human influence of particulate matter, various studies are being conducted to predict particulate matter grade using past data measured in the monitoring network of Seoul city. In this paper, predictive model have focused on particulate matter concentration in May, 2019, Seoul. The air pollutant variables were used to training such as SO₂, CO, NO₂, O₃. The predictive model based on Adaboost, and training model was dividing PM₁₀ and PM_2.5. As a result of the prediction performance comparison through confusion matrix, the Adaboost model was more conformable for predicting the particulate matter concentration grade. Although air pollutant variables have a higher correlation with PM2.5, training model need to train a lot of data and to use additional variables such as traffic volume to predict more effective PM₁₀ and PM_2.5 distribution grade.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.13 no.3 s.31
• /
• pp.286-294
• /
• 1989

This Study has treated the effects of fiber, surfactants, temperature, surfactant concentration, pH, electrolyte, fatty acid contents and mechanical force on the removal of particulate soil from fabric, vacuum cleaner dirt was used as model particulate soil. The fabrics were soiled with mixture of vacuum cleaner dirt and fatty soil, and washed in Terg-O-tometer. The detergency was evaluated by measuring reflectance of a fabric before and after washing. The results were as follows. 1. The fiber type showed a different pattern of soil removal with surfactants. In general, particulate soil removal increased in the following order Acetate>PET. Nylon>Cotton. Particulate soil removal, which is affected by the surfactant type, increased in the following order NPE $(EO)_{10}\leqq$Soap>SLS>DBS>Tween 80. 2. The influence of temperature on the particulate soil removal was very complex because efficiency of removal was varied with surfactant and fiber types. The washing efficiency of NPE $(EO)_{10}$ was highest at around $40^{\circ}C\;and\;60^{\circ}C$ with cotton and PET but the washing efficiency of DBS was the highest at $60^{\circ}C$ with cotton, decreased monotonously with increasing temperature with PET 3. The detergency of particulate soil increased with increasing surfactant concentration at relatively low concentration and then levelled off above some optimum concentration. 4. The removal of particulate soil increased with increasing pH and mechanical force. 5. Effect of electrolyte on the particulate soil removal was depended on the concentration of the surfactant. At low concentration of surfactant, addition of electrolytes improved soil removal but above the some concentration no effect was observed. At high concentration of surfactant, Vie., $0.6\%$ , the maximum washing effect is reached without added electrolyte. These result indicate that added electrolyte only influence the adsorption of surfactant on the soil and fiber 6. Fatty acid content in the soil did not influence on particulate soil removal without regard to surfactants.