• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.440-449
• /
• 2022

In recent years, the air pollution and Air Quality Index (AQI) has been a pivotal point for researchers due to its effect on human health. Various research has been done in predicting the AQI but most of these studies, either lack dense temporal data or cover one or two air pollutant elements. In this paper, a hybrid Convolutional Neural approach integrated with recurrent neural network architecture (CNN-LSTM), is presented to find air pollution inference using a multivariate air pollutant elements dataset. The aim of this research is to design a robust and real-time air pollutant forecasting system by exploiting a neural network. The proposed approach is implemented on a 24-month dataset from Seoul, Republic of Korea. The predicted results are cross-validated with the real dataset and compared with the state-of-the-art techniques to evaluate its robustness and performance. The proposed model outperforms SVM, SVM-Polynomial, ANN, and RF models with 60.17%, 68.99%, 14.6%, and 6.29%, respectively. The model performs SVM and SVM-Polynomial in predicting O3 by 78.04% and 83.79%, respectively. Overall performance of the model is measured in terms of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and the Root Mean Square Error (RMSE).

• Proceedings of the SAREK Conference
• /
• 2005.11a
• /
• pp.21-26
• /
• 2005

We performed the numerical analysis on the characteristics of indoor air quality and local supply index with a variation of supply · exhaust airflow rate. We analyzed the local supply index and carbon dioxide concentration at the room and breathing zone with respect to the variation of the supply · exhaust airflow rate. From the numerical results, we found that local supply index was affected but carbon dioxide concentration was hardly affected by the variation of the airflow rate in the room. And we also knew that carbon dioxide concentration was raised in despite of the increment of the supply airflow rate in the breathing zone. After this study it is necessary to analyze the local exhaust index when we evaluate the state of the ventilation in the room.

• Journal of environmental and Sanitary engineering
• /
• v.18 no.2
• /
• pp.42-51
• /
• 2003

Public awareness of air pollution problem has increased the need for real time air pollution information system about changes in air pollution level. The purpose of this study is to construct e-AIR, a user-friendly air pollution information system for urban air quality using GIS(geographic information system) technology for windows. GIS was ideally suited featuring a geographical characteristics(e.g., road, traffics, buildings) and very effectively used in mapping and symbolization for the distribution of the spatial/periodic pollution status(e.g., pie or column chart, graduated symbols) which can be effectively applied to a information system on the web-site. And a user interface, GUI(graphic user interface) was designed very diversely and simply enabled the users connect with e-AIR and obtain a useful information of air quality. A interpretive technique, air pollution health index(e.g., PSI, AEI) was used also which transforms complex data on measured atmospheric pollutant concentrations into a single number or set of numbers in order to make the data more understandable. Eventually the final-step of this study was to construct e-AIR based on Web GIS could be assessed anywhere if internet is available and offer a very useful information services of the air pollution to the public like a weather news.

• Asian Journal of Atmospheric Environment
• /
• v.11 no.4
• /
• pp.254-269
• /
• 2017

The work describes an assessment of the major air pollutants, $NO_2$, $SO_2$, CO, $O_3$, $NH_3$, coarse and fine particulate matter ($PM_{10}$, $PM_{2.5}$) in ambient air in and around a 3 million tonne Petroleum Refinery and the possible impacts on a pristine area marked by the presence of the world-famous Kajiranga National Park, a world heritage site and habitat for the most number of one-horned rhinos in the world. The Refinery is at an aerial distance of 20-25 km from the wildlife habitat. The assessment is based on regular monitoring at four stations around the Refinery and one station near the National Park. Heavy rains during June to August influence the pollutant concentrations while at other times of the year, large traffic volume adds to the pollutant concentrations that peak during November to March, the dry months of the year. Correlation analysis by scatter technique is utilised to obtain the enhancement ratios to predict the variations in the concentrations of the pollutants and their spatial distribution. Computation of air quality index (AQI) indicates that the coarse and the fine particulates in the ambient air could be a major hazard to wildlife in the area.

• Journal of computational fluids engineering
• /
• v.10 no.1
• /
• pp.87-93
• /
• 2005

Macao, a city with three sides bounded by water, is hot and humid in weather in more than six months of a year. This uncomfortable weather induces the frequency of operating air-conditioners. Choice of location for installation of air-conditioner in a building will affect the performance of cooling effect and thermal comfort on the occupants, which in turn will affect the indoor air quality (IAQ) of the building. In the paper, investigation of distribution on carbon dioxide, room air temperature and velocity, as well as air diffusion performance index (ADPI) of a single bedroom in Macao is studied by using the computational fluid dynamics (CFD) software FLOVENT 3.2. Simulations of locating the air-conditioner at 4 different walls will be done and comparisons and analyses of the results will be performed to decide a proper location for the air-conditioner for obtaining good thermal comfort.

• Environmental Engineering Research
• /
• v.23 no.2
• /
• pp.143-149
• /
• 2018

Air quality conditions and pollution status have been evaluated in the industrial area between Sharjah and Ajman border in UAE. Daily concentrations of $O_3$, CO, $NO_2$, $SO_2$, $PM_{2.5}$, $PM_{10}$, Total Volatile Organic Compounds (TVOC) and Total Suspended Particulate (TSP) have been monitored from Sept. 2015 to April 2016. The monthly average concentrations of $O_3$, CO, $NO_2$, $SO_2$, TVOC were within the UAE ambient air quality standards during the survey period. However, $PM_{10}$ and TSP levels exceeded the recommended limits in Sept. 2015, Oct. 2015 and March 2016. Temporal variations in air quality parameters showed highest levels in March 2016 for $PM_{2.5}$, $PM_{10}$, $NO_2$, TVOC and TSP, whereas $O_3$, $SO_2$ and CO showed relatively low values in this month. $PM_{2.5}$ levels in ambient air were above the EPA guideline of $35{\mu}g/m^3$ in all months. $PM_{2.5}$ was the critical ambient air pollutant with Index for Pollutant ($I_p$) values varying from 103-209, indicating Air Quality Index categories of unhealthy for sensitive groups (62.5%) to unhealthy (25%) to very unhealthy (12.5%). The $I_p$ average values of $PM_{2.5}$ decreased from Sept. 2015 to reach lowest value in Dec. 2015 before increasing gradually, peaking in March 2016. These results suggest the potential health risks associated with $PM_{2.5}$ is low in winter, where the prevailing meteorological conditions of lower temperatures, higher humidity, higher wind speed reduced particulate matter. The results revealed the industrial area is impacted by anthropogenic and natural sources of particulate matter.

• Journal of Korean Society for Quality Management
• /
• v.44 no.3
• /
• pp.677-688
• /
• 2016

Purpose: In this study, we examine the effects of circulatory diseases mortality in South Korea 2005-2013 using the air pollution index, Methods: We cluster the region of high risk mortality by SaTScan$^{TM}$9.3.1 and compare this result with the regional distribution of air pollution. We use the Geographically Weighted Regression (GWR) to consider the spatial heterogeneity of data collected by administrative district in order to estimate the model. As GWR is spatial analysis techniques utilizing the spatial information, regression model estimated for each region on the assumption that regression coefficients are different by region. Results: As a result of estimating model of the collected air pollution index, circulatory diseases mortality data combined with the spatial information, GWR was found to solve the problem of spatial autocorrelation and increase the fit of the model than OLS regression model. Conclusion: GWR is used to select the air pollution affecting the disease each year, the K-means cluster analysis discover the characteristics of the distribution of air pollution by region.

• Journal of Korean Society for Atmospheric Environment
• /
• v.26 no.6
• /
• pp.666-682
• /
• 2010

The forecasting system for Today's and Tomorrow's PM10 was developed based on the statistical model and the forecasting was performed at 9 AM to predict Today's 24 hour average PM10 concentration and at 5 PM to predict Tomorrow's 24 hour average PM10. The Today's forecasting model was operated based on measured air quality and meteorological data while Tomorrow's model was run by monitored data as well as the meteorological data calculated from the weather forecasting model such as MM5 (Mesoscale Meteorological Model version 5). The observed air quality data at ambient air quality monitoring stations as well as measured and forecasted meteorological data were reviewed to find the relationship with target PM10 concentrations by the regression analysis. The PM concentration, wind speed, precipitation rate, mixing height and dew-point deficit temperature were major variables to determine the level of PM10 and the wind direction at 500 hpa height was also a good indicator to identify the influence of long-range transport from other countries. The neural network, regression model, and decision tree method were used as the forecasting models to predict the class of a comprehensive air quality index and the final forecasting index was determined by the most frequent index among the three model's predicted indexes. The accuracy, false alarm rate, and probability of detection in Tomorrow's model were 72.4%, 0.0%, and 42.9% while those in Today's model were 80.8%, 12.5%, and 77.8%, respectively. The statistical model had the limitation to predict the rapid changing PM10 concentration by long-range transport from the outside of Korea and in this case the chemical transport model would be an alternative method.

• Analytical Science and Technology
• /
• v.8 no.4
• /
• pp.807-814
• /
• 1995

Accurate measurements of ozone precursors are required to understand the process and extent of ozone formation in rural and urban areas. Nonmethane hydrocarbons (NMHCs) have been identified as important ozone precursors. Identification and quantification of NMHCs are difficult because of the large number present and the wide molecular weight range encountered in typical air samples. A major plan of the research team of the Climate and Air Quality Taiwan Station (CATs) was the measurement of atmospheric nonmethane hydrocarbons. An analytical method has been development for the analysis of the individual nonmethane hydrocarbons in ambient air at ppb (v) and subppb(v) levels. The whole ambient air samples were collected in canisters and analyzed by GC-FID with $Al_2O_3$/KCl PLOT column. Our targeted for quantitative analysis 43 compounds that may be substantial contributors to ozone formation. The retention indices and molar response factors of some commercially available $C_2{\sim}C_{10}$ hydrocarbons were determined and used to identify and quantify air samples. A quality assurance program was instituted to ensure that good measurements were made by participating in the International Nonmethane Hydrocarbon Intercomparison Experiments (NOMHICE).

• Journal of the Korean Society of Food Culture
• /
• v.38 no.5
• /
• pp.356-364
• /
• 2023

This study compared the physicochemical properties of soybean curd residue and black soybean curd residue produced by hot air-drying and freeze-drying. Regardless of drying method, the crude protein, crude ash, crude fiber contents, pH, L, a, b color values and water soluble index were higher in soybean curd residue, whereas total polyphenol contents and antioxidant activity were higher in black soybean curd residue. Significant differences in water absorption index, oil absorption capacity and emulsion activity were observed between soybean curd residue and black soybean curd residue in freeze-drying. On the other hand, the emulsion stability was not significant difference in both hot-air drying and freeze-drying. The crude protein and crude fiber contents of soybean curd residue were not significant difference between hot-air drying and freeze-drying. Freeze-drying resulted in higher crude ash contents, pH, water absorption index, water soluble index, oil absorption capacity, emulsion activity and emulsion stability than hot-air drying. Hot-air drying have caused significantly higher water contents, water activity, total polyphenol contents and antioxidant activity in soybean curd residue than freeze-drying. In conclusion, soybean type and drying methods affect the physicochemical and quality characteristics of soybean curd residue, which could be important factors in the manufacture of processed foods.