• 한국멀티미디어학회논문지
• /
• 제24권8호
• /
• pp.1122-1137
• /
• 2021

PM_2.5 concentration in Seoul could be predicted by deep neural network model. In this paper, the contribution of input factors to the model's prediction results is analyzed using the LRP(Layer-wise Relevance Propagation) technique. LRP analysis is performed by dividing the input data by time and PM concentration, respectively. As a result of the analysis by time, the contribution of the measurement factors is high in the forecast for the day, and those of the forecast factors are high in the forecast for the tomorrow and the day after tomorrow. In the case of the PM concentration analysis, the contribution of the weather factors is high in the low-concentration pattern, and that of the air quality factors is high in the high-concentration pattern. In addition, the date and the temperature factors contribute significantly regardless of time and concentration.

• 한국컴퓨터정보학회논문지
• /
• 제23권11호
• /
• pp.129-135
• /
• 2018

In this study, we designed a model that can measure the level of user's concentration by measuring and analyzing EEG data of the subjects who are performing Continuous Performance Test based on visual stimulus. This study focused on alpha and beta waves, which are closely related to concentration in various brain waves. There are a lot of research and services to enhance not only concentration but also brain activity. However, there are formidable barriers to ordinary people for using routinely because of high cost and complex procedures. Therefore, this study designed the model using the portable EEG measurement device with reasonable cost and Visual Continuous Performance Test which we developed as a simplified version of the existing CPT. This study aims to measure the concentration level of the subject objectively through simple and affordable way, EEG analysis. Concentration is also closely related to various brain diseases such as dementia, depression, and ADHD. Therefore, we believe that our proposed model can be useful not only for improving concentration but also brain disease prediction and monitoring research. In addition, the combination of this model and the Brain Computer Interface technology can create greater synergy in various fields.

• 한국멀티미디어학회논문지
• /
• 제22권9호
• /
• pp.1069-1079
• /
• 2019

In this study, we developed a $PM_{10}$ forecasting model using DNN and Membership Function, and improved the forecasting performance. The model predicts the $PM_{10}$ concentrations of the next 3 days in the Seoul area by using the weather and air quality observation data and forecast data. The best model(RM14)'s accuracy (82%, 76%, 69%) and false alarm rate(FAR:14%,33%,44%) are good. Probability of detection (POD: 79%, 50%, 53%), however, are not good performance. These are due to the lack of training data for high concentration $PM_{10}$ compared to low concentration. In addition, the model dose not reflect seasonal factors closely related to the generation of high concentration $PM_{10}$. To improve this, we propose Julian date membership function as inputs of the $PM_{10}$ forecasting model. The function express a given date in 12 factors to reflect seasonal characteristics closely related to high concentration $PM_{10}$. As a result, the accuracy (79%, 70%, 66%) and FAR (24%, 48%, 46%) are slightly reduced in performance, but the POD (79%, 75%, 71%) are up to 25% improved compared with those of the RM14 model. Hence, this shows that the proposed Julian forecast model is effective for high concentration $PM_{10}$ forecasts.

• 한국대기환경학회지
• /
• 제10권4호
• /
• pp.224-232
• /
• 1994

A new neural network model has been developed to predict short-term air pollution concentration. In addition, a multiple regression model widely used in statistical analysis was tested. These models were applied for prediction of daily maximum ozone concentration in Seoul during the summer season of 1991. The time periods between May and September 1989 and 1990 were utilized to train set of learning patterns in neural network model, and to estimate multiple regression model. To evaluate the results of the different models, several Performance indices were used. The results indicated that the multiple regression model tended to underpredict the daily maximum ozone concentration with small r$^{2}$(0.38). Also, large errors were found in this model; 21.1 ppb for RMSE, 0.324 for NMSE, and -0.164 for MRE. On the other hand, the results obtained from the neural network model were very promising. Thus, we can know that this model has a prominent efficiency in the adaptive control for the non-linear multi- variable systems such as photochemical oxidants. Also, when the recent new information was added in the neural network model, prediction accuracy was increased. From the new model, the values of RMSE, NMSE and r$^{2}$ were 13.2ppb, 0.089, 0.003 and 0.55 respectively.

• Nuclear Engineering and Technology
• /
• 제24권1호
• /
• pp.30-39
• /
• 1992

본 연구에서는 붕산주입 및 회석운전동안에 노심의 붕산농도를 변화시키기 위한 보충수 유량을 예측하고 화학 및 체적제어계통을 포함한 원자로 냉각재계통내에 있는 각종 계통에서 붕산농도 거동분석을 위한 종합적 붕산주입 및 희석모델(INBAD)이 제안되었다. 이 모델은 기존의 노심코드와 새로 개발된 붕산주입 및 희석모델로 구성되어 있으며 붕산주입 및 희석모델은 단일 cell 모델 및 다중 cell모델을 이용하여 본 연구목적에 맞게 개발되었다. 또한, 본 모델에서는 보다 실제적인 붕산농도 거동분석을 위하여 가변적 가압기 가열기 출력 및 선택적인 보충수 운전형태 (직접주입 또는 간접주입)가 모사되었다. 이 모델의 유용성을 증명하기 위하여 영광 3,4호기 설계자료를 이용하여 각종 계통에서 직접주입 및 간접주입운전에 대한 붕산농도 거동분석을 수행하였고, 노심의 붕산농도에 대한 가압기 가열기의 영향을 검토하였다. 그 결과 본 모델은 붕산주입 및 희석운전시에 각종 계통에서 붕산농도 변화를 정확히 예측할 수 있음을 보여 주었다.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• 한국대기환경학회지
• /
• 제19권1호
• /
• pp.13-23
• /
• 2003

A local wind model and a three dimensional local environmental model including advection, diffusion, deposition. and photochemical reactions were performed at Gwangyang Bay, Korea, to predict air flow and air pollutants concentrations. A large grid was used, and nesting method was employed for small grid calculation. From the meterological module simulation, we were able to reproduce local wind characteristics such as sea/land winds and mountain/valley winds simulation at Gwangyang Bay. In addition, the concentration module showed high concentration regions at Yosu industrial complex, Gwangyang steel company. and Container anchor. It was also seen that air pollutants were dispersed by sea/land winds. A comparison between the measurement and the prediction of sulfur dioxide and nitric oxide, which are relatively low-reacted pollutants, was performed. However, the measured nitrogen dioxide and ozone concentrations were higher than the simulated ones. Particularly, ozone concentration between 8 a..m. and 8 p.m. agreed well, but the measured ozone during the rest of time were generally higher.

• Biomolecules & Therapeutics
• /
• 제2권4호
• /
• pp.343-346
• /
• 1994

In vivo activity of recombinant human erythropoietin (rh-EPO) has been examined using polycythemic model in mice and acute hemorrhage model in rats. The number of reticulocytes in blood stream was increased after a single injection of rh-EPO depending on the dosage of rh-EPO in polycythemy model. It seemed that optimal dose of rh-EPO for polycythemic mice was around 1-10 U/kg. Rh-EPO also showed the effectiveness for increase of reticulocyte numbers both in male and female rats after bleeding. The number of reticulocytes and the change of hemoglobin concentration in the blood stream of normal rats has been examined after injection of rh-EPO. The maximum value of reticulocyte was observed on the 6th day of the injection in these normal rats. In addition, the increase of reticulocyte and the concentration of hemoglobin were dependent on the dosage of rh-EPO. The increase of hemoglobin concentration was continued to the 9th day after injection. In this study, the efficacy of rh-EPO was confirmed in both mice and rats.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.137-150
• /
• 2019

Although the research of immune-based anomaly detection technology has made some progress, there are still some defects which have not been solved, such as the loophole problem which leads to low detection rate and high false alarm rate, the exponential relationship between training cost of mature detectors and size of self-antigens. This paper proposed an intrusion detection method based on changes of antibody concentration in immune response to improve and solve existing problems of immune based anomaly detection technology. The method introduces blood relative and blood family to classify antibodies and antigens and simulate correlations between antibodies and antigens. Then, the method establishes dynamic evolution models of antigens and antibodies in intrusion detection. In addition, the method determines concentration changes of antibodies in the immune system drawing the experience of cloud model, and divides the risk levels to guide immune responses. Experimental results show that the method has better detection performance and adaptability than traditional methods.

• 통합자연과학논문집
• /
• 제11권1호
• /
• pp.30-38
• /
• 2018

CALPUFF is one of the recommended air pollution models by EPA with AERMOD. It has been used to simulate the ambient concentration of critical air pollutants as well as non-critical pollutants such as persistent organic matters and the organic materials causing odor. In this model, the air pollutants go through dispersion, transportation, chemical reaction, and deposition process. These mechanisms are significantly influenced by meteorological condition. This study produces the meteorological field in three different methods for the simulation of $SO_2$ using CALPUFF: 1) CALMET model by using both ground-level and aerological observation, 2) CALMET model by using MM5 results with NCEP/NCAR reanalyzed data, 3) CALMET model by using MM5 results in which FDDA is applied with NCEP/NCAR reanalyzed data as well as the meteorological data of Korea Meteorological Administration. As a result of CALPUFF model, the resolved concentration of $SO_2$ showed different behaviors in three cases. For the first case, the fluctuation of SO2 concentration was frequently observed while the fluctuation is reduced in the second and third cases. In addition, the maximum concentration of $SO_2$ in the first case was about 2~3 times higher than the second case, and about 4~6 times higher than the third case. These results can be caused by the accuracy of the resolved meteorological field. It is inferred that the meteorological field of the first case could be less accurate than other two cases. These results show that the use of correct meteorological data can improve the result of dispersion model. Moreover, the contribution of various sources such as point, line, and area sources on the ambient concentration of air pollutant can be roughly estimated from the sensitivity analysis.