• Journal of Korean Society for Atmospheric Environment
• /
• v.22 no.4
• /
• pp.518-528
• /
• 2006

The air quality index (AQI) is an index for reporting daily or hourly air quality to the general public. The AQI focuses on health effects that can happen within a few hours or days after breathing polluted air. Many countries have their own AQI reporting systems, and the HAEI (hourly air environment index) method is now being used in Korea. In this study, in order to compare the AQI results from different methods, we applied three methods. i.e. US AQI, Canadian AQI, and Korean HAEI, to the same air quality data-base. The data-base was constructed from 10 monitoring sites in Gyeong-buk province for the last four years since 2000. Based on the results, a critical evaluation of the Korean HAEI method was made, and a number of suggestions and recommendations were presented to improve the AQI reporting system in Korea.

• Communications for Statistical Applications and Methods
• /
• v.30 no.2
• /
• pp.119-133
• /
• 2023

With the rapid growth of the economy and fossil fuel consumption, the concentration of air pollutants has increased significantly and the air pollution problem is no longer limited to small areas. We conduct statistical analysis with the actual data related to air quality that covers the entire of South Korea using R and Python. Some factors such as SO₂, CO, O₃, NO₂, PM₁₀, precipitation, wind speed, wind direction, vapor pressure, local pressure, sea level pressure, temperature, humidity, and others are used as covariates. The main goal of this paper is to predict air quality index (AQI) spatio-temporal data. The observations of spatio-temporal big datasets like AQI data are correlated both spatially and temporally, and computation of the prediction or forecasting with dependence structure is often infeasible. As such, the likelihood function based on the spatio-temporal model may be complicated and some special modelings are useful for statistically reliable predictions. In this paper, we propose several methods for this big spatio-temporal AQI data. First, random effects with spatio-temporal basis functions model, a classical statistical analysis, is proposed. Next, neural networks model, a deep learning method based on artificial neural networks, is applied. Finally, random forest model, a machine learning method that is closer to computational science, will be introduced. Then we compare the forecasting performance of each other in terms of predictive diagnostics. As a result of the analysis, all three methods predicted the normal level of PM_2.5 well, but the performance seems to be poor at the extreme value.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.49 no.5
• /
• pp.1-11
• /
• 2021

The purpose of this study is to find out the main factors affecting air quality in urban physical space factors, and provide clues for environmental improvement. Nine monitoring stations in China's industrial city, Changchun, collected AQI concentration data from January 1, 2018 to December 31, 2019. This paper analyzes the types and distribution characteristics of urban physical facilities within a radius of 300m with the detection station as the center. The monitoring station is divided into three groups, and the difference in floating dust concentration among the three groups in different seasons is analyzed. The results show that AQI concentration is the highest in spring and winter, followed by summer, and the lowest in autumn. The place with the highest concentrations of AQI in spring are F (93.00), D (91.10), I (89.20), in summer are D (69.05), A (67.89), B (84.44), in autumn are I (62.80), G (60.84), D (53.27), D (53.27), in winter are I (95.82), H (95.60), f (94.04). Through SPSS analysis, it shows that the air index in a space with a diameter of 600 meters is related to forest land, grassland, bare land, water space, tree height, building area (average value), and building volume (average value). According to the statistical analysis results of spring and winter with the most serious pollution, forest land area (43,637m², 15.44%) and water surface area (18,736m², 6.63%) accounted for the majority, and group 1 (A, B, C) with the least average building area (448m², 0.17%) and average building volume (10,201m²) had the lowest pollution concentration. On the contrary, group 2 (D, E, F) had the highest AQI concentration, with less or no woodland (1,917m², 0.68%) and water surface area (0m², 0%), and the highest average building area (1,056m², 0.37%) and average building volume (17,470m³). It is confirmed that the characteristics of the area with the highest AQI concentration are that the more the site ratio of tree height above 12m, the smaller the site ratio of bare land, and the lower the pollution degree. On the contrary, the larger the area of bare land, the higher the pollution degree. By analyzing the characteristics of nine monitoring stations in Changchun, it can be seen that the air quality brought by the physical characteristics of urban space is closely related to the above factors.

• 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).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.8-14
• /
• 2020

The human impact of particulate matter are revealed and demand for improved forecast accuracy is increasing. Recently, efforts is made to improve the accuracy of PM10 predictions by using machine learning, but prediction performance is decreasing due to the particulate matter data with a large rate of low concentration occurrence. In this paper, separation prediction model by concentration is proposed to improve the accuracy of PM10 particulate matter forecast. The low and high concentration prediction model was designed using the weather and air pollution factors in Cheonan, and the performance comparison with the prediction models was performed. As a result of experiments with RMSE, MAPE, correlation coefficient, and AQI accuracy, it was confirmed that the predictive performance was improved, and that 20.62% of the AQI high-concentration prediction performance was improved.

• Asian Journal of Business Environment
• /
• v.10 no.4
• /
• pp.15-19
• /
• 2020

Purpose: This research aims to explore the level of air pollution in Jakarta, the epicenter of COVID-19 Pandemic in Indonesia and its surrounding provinces during the first month of the Pandemic. Research design, data and methodology: This study uses data, which have been obtained real time from API (Application Programming Interfaces) of air quality website. The measurements of Air Quality Index (AQI), temperature, humidity, and other factors from several cities and regencies in Indonesia were obtained eight times a day. The data collected have been analyzed using descriptive statistics and mapped using QGIS. Results: The finding of this study indicates that The Greater Jakarta Area experienced a decrease in pollutant levels, especially in the Bogor area. Nevertheless, some areas, such as the north Jakarta, have exhibited slow reduction. Furthermore, the regions with high COVID-19 confirmed cases have experienced a decline in AQI. Conclusions: The study concludes that the air quality of three provinces, Jakarta, Banten, and West Java, especially in cities located in the Jakarta Metropolitan Area during COVID-19 pandemic and large-scale social restrictions, is getting better. However, in some regions, the reduction of pollutant concentrations requires a longer time, as it was very high before the pandemic.

• Journal of Advanced Navigation Technology
• /
• v.28 no.1
• /
• pp.149-154
• /
• 2024

Research on particulate matter is advancing in real-time, and various methods are being studied to improve the accuracy of prediction models. Furthermore, studies that take into account various factors to understand the precise causes and impacts of particulate matter are actively being pursued. This paper trains an LSTM model using seasonal data and another LSTM model using concentration-based data. It compares and analyzes the PM_2.5 prediction performance of the two models. To train the model, weather data and air pollutant data were collected. The collected data was then used to confirm the correlation with PM_2.5. Based on the results of the correlation analysis, the data was structured for training and evaluation. The seasonal prediction model and the concentration-specific prediction model were designed using the LSTM algorithm. The performance of the prediction model was evaluated using accuracy, RMSE, and MAPE. As a result of the performance evaluation, the prediction model learned by concentration had an accuracy of 91.02% in the "bad" range of AQI. And overall, it performed better than the prediction model trained by season.

• Journal of the Economic Geographical Society of Korea
• /
• v.14 no.2
• /
• pp.143-156
• /
• 2011

Recently, the environmental problems become a serious social issue, there are many efforts to manage it efficiently. As one of the ways to measure the environment in quantitative index, the environmental indicators are used in decision-making process. Air Environmental Index(AEI), which is derived from the U.S. Air Quality Index(AQI), illustrates the degree of air pollution. In study as follows: to find the charateristics of administrative dongs in Seoul, correlation analysis is conducted based on the land-use patterns and daily traffic data that represent AEI and urban spatial structure of Seoul.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.13
• /
• pp.5299-5303
• /
• 2014

Background: To explore etiology for providing scientific clues for the prevention of lung cancer. Materials and Methods: Data for lung cancer incidence and meteorological geographic factors from 25 counties in Zhejiang province of China during 2011 were studied. Stepwise multiple regression and correlation analysis were performed to analyze the geographic distribution and epidemiology of lung cancer. Results: 8,291 new cases (5,998 in males and 2,293 females) of lung cancer during 2011 in Zhejiang province were reported in the 25 studied counties. Reported and standardized incidence rates for lung cancer were 58.0 and 47.0 per 100,000 population, respectively. The incidence of lung cancer increased with age. Geographic distribution analysis shows that the standardized incidence rates of lung cancer in northeastern Zhejiang province were higher than in the southwestern part, such as in Nanhu, Fuyang, Wuxing and Yuyao counties, where the rates were more than 50 per 100,000 population. In the southwestern Zhejiang province, for instance, in Yueqing, Xianju and Jiande counties, the standardized incidence rates of lung cancer were lower than 37 per 100,000 population. Spearman correlation tests showed that forest coverage rate, air quality index (AQI), and annual precipitation level are associated with the incidence of lung cancer. Conclusions: Lung cancer in Zhejiang province shows obvious regional differences. High incidence appears associated with low forest coverage rate, poor air quality and low annual precipitation. Therefore, increasing the forest coverage rate and controlling air pollution may play an important role in lung cancer prevention.

• Journal of Korean Academy of Nursing
• /
• v.30 no.2
• /
• pp.437-451
• /
• 2000

The purpose of this study was to estimate the forecast of bed demand for institutional long-term care for the elderly persons in Taegu Metropolitan City. The study subject was the total 1,877 elderly persons over age 65 living in Taegu. Among them 1,441 elderly persons were sampled from community and 436 were from the elderly admitted 5 general hospitals. Data collection was carried out by interview from 25 August to 25 December 1997. The measuring instrument of this study was the modified tool of CARE, MAI, PCTC, and ADL which were examined for validity and reliability. In order to forecast bed demand of Nursing Home, this study revised prediction techniques suggested by Robin. The results were as follows : 1. OLDi of Taegu City were 122,202 by the year 1998 and number of Low-Income Elderly Persons were 3,210. 2. The Level I : Senior Citizen Home $ADEMi=\frac{AQi * ASTAYi}{365 * AOCUi}$. AQi = OLDi * LADLi * NASi * ALONi * LIADLi * AUTILi. Predicted number of bed demand for Home Based. Elderly Persons were 4,210 and Low-Income Elderly Persons were 1,081 and Total Elderly Persons were 5,291 by the year 1998, 6,343 by the year 2000 and 8,351 by the 2005. 3. The Level II : Nursing Home $BDEMi=\frac{(BQ1i+BQ2i) * BSTAYi}{365 * BOCUi}$. BQ1i = OLDi * HADLi * ALONi * HIADLi BQ2i = OLDi * HADLi * FAMi * OBEDi Predicted number of demand for Total Elderly Persons were 668 by the year 1998, 802 by the year 2000 and 1,055 by the 2005. 4. The Level III : Nursing Home $CDEMi=\frac{COLDi * HDISi * CUTILi * CSTAYi}{365 * COCUi}+OQi/10$ Predicted number of demand for Total Elderly Persons were 1,899 by the year 1998, 2,311 by the year 2000 and 3,003 by the 2005. 5. Predicted number of bed demand of long-term care facilities in the year 1998 according to Levels were 4.3% among elderly persons in Taegu by Level I, 0.5% by Level II and 1.5% by Level III. Number of elderly persons in current long-term care facilities were 458 in LevelI I,284 in Level II. 6. Deficit number of bed demand of long-term care facilities were 4,833 in Level I, 384 in Level II, 1,899 in Level III for the elderly persons in Taegu Metropolitan City.