• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.870-871
• /
• 2023

미세먼지 단계를 예측하는 딥러닝 기반 시스템을 개발하고 그 성능을 평가하는 연구를 진행했다. 연구에서 320개의 풍경 사진 데이터를 수집하고, 해당 시점의 미세먼지 농도를 측정하여 "좋음" 또는 "나쁨"으로 분류했다. 데이터 전처리 단계에서는 특히 하늘 이미지의 특성을 고려하여 다양한 전처리 기법을 적용하였다. 다섯 가지 이미지 데이터 모델을 사용하여 이미지를 분류하고 미세먼지 단계를 예측하는 모델을 개발하였으며, 또 이 모델들을 다양한 기법으로 앙상블 해보며 성능을 비교했다. 그 결과, Random Forest를 이용한 앙상블 모델이 제일 뛰어난 예측 성능을 보였다. 이러한 연구 결과는 미세먼지 모니터링 및 예측에 유용한 시스템 개발의 가능성을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.136-137
• /
• 2023

비닐하우스 외부 미세먼지로 인해 일사량이 감소하여 작물 품질 및 생산량의 감소가 지속적으로 발생하고 있으며 이를 예방하기 위한 외부 미세먼지 관리가 가능한 시스템이 요구된다. 본 연구는 라즈베리파이를 활용하여 미세먼지 관리 및 모니터링 시스템을 연구하고, 이를 농업 및 환경 연구 분야에 활용함으로써 미세먼지 관리에 새로운 가능성을 제시한다. 이는 관리자가 애플리케이션을 통해 비닐하우스 외부를 효율적으로 관리하여 품질 및 생산성 향상에 기여한다.

• Journal of the Korean Society of Radiology
• /
• v.14 no.4
• /
• pp.385-390
• /
• 2020

In the present, external environmental factors affect human health. In particular, the most important issue is fine dust in these days. Because fine dust is inhaled through the human respiratory system is known to be harmful to health. Tunnels for cars and people can also be easily seen around us. This study, the amount of scattering radiation was measured for walkable tunnels about dust. For the measurement method, dust and radiation dose in the tunnel were measured on good weather (fine dust level: 0 ~ 30 ㎍/㎥) and normal day (fine dust level: 0 ~ 80 ㎍/㎥). The measurement resulted in an increase of 10~20 % of dust in the center of the tunnel on a good weather day and an increase of 20~30 % of dust in the center of the tunnel on normal weather. On the other hand, the results of tunnel measurement of radiation dose increased by 10~20 % at the center of the tunnel non-depending on the weather. As a result, pedestrians should pay attention to scattering dust and scattered radiation while moving through the tunnel. Therefore, it is recommended to wear a filter mask of PM2.5 or less during frequent tunnel walking.

• Applied Chemistry for Engineering
• /
• v.26 no.2
• /
• pp.229-233
• /
• 2015

In this study, we examined the removal characteristics of suspended particulate matters which are one of carcinogens to cause lung cancer. The fine dust capture by a pilot scale filtration system depends on several important variables such as humidity, initial fine dust injection volume, and flow rate. The average concentration of particulate matters in the test chamber decreased, but the ultimate collection efficiency did not change during the filtration under high humidity, compared to those of using ambient conditions The initial injection amount of fine dust did not influence the particle capturing efficiency. When the flow rate reduced from 0.6 m/s to 0.3 m/s, the dust collection time increased approximately 1.4 times. Among all variables tested, the flow rate showed the most significant effect on the removal efficiency of fine particulate matter.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.6
• /
• pp.1117-1124
• /
• 2010

The PM10 (Promethium 10) data is one of the important environmental data for measurement of the atmospheric condition of the country. In this article, the Autoregressive Error (ARE) model has been considered for analyzing the monthly PM10 data at the southern part of the Gyeonggi-Do, Suwon monitoring site in Korea. In the ARE model, six meteorological variables and four pollution variables are used as the explanatory variables for the PM10 data set. The six meteorological variables are daily maximum temperature, wind speed, relative humidity, rainfall, radiation, and amount of cloud. The four air pollution explanatory variables are sulfur dioxide ($SO_2$), nitrogen dioxide ($NO_2$), carbon monoxide (CO), and ozone ($O_3$). The result showed that the monthly ARE models explained about 13-49% for describing the PM10 concentration.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.277-280
• /
• 2018

최근 서울시에서는 '미세먼지 비상저감조치'로 '대중교통 무료' 정책을 시행하고 후속 조치로 '시민 참여형 차량 2 부제'를 제안하였다. 본 논문에서는 먼저, 위 두 교통 정책의 실효성을 파악하기 위해 '교통'을 중심으로 각 산업이 미세먼지에 미치는 영향을 알아보고, 위 정책들에 대한 시민들의 반응을 분석한다. 각 산업이 미세먼지에 미치는 영향은 회귀분석으로, 두 정책에 대한 시민들의 반응은 텍스트 마이닝 기법을 통해 알아보았다. 그 결과, 교통수단의 도로 이용 여부에 따라 미세먼지에 미치는 영향력의 정도와 방향이 다름을 알 수 있었고 정책에 대한 관심과 부정적인 의견이 크게 증가함을 알 수 있었다. 또 국외 요인에 대한 해결책도 필요로 함을 알 수 있었다. 마지막으로 위 결과를 토대로 향후 미세먼지 문제와 관련된 정책이 나아갈 방향을 제시한다.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1136-1140
• /
• 2020

As air pollution caused by fine dust becomes serious, interest in the spread of fine dust and prediction of air quality is increasing. The causes of fine dust are very diverse, and some fine dust naturally occurs through forest fires and yellow dust, but most of them are known to be caused by air pollutants from burning fossil fuels such as petroleum and coal or from automobile exhaust gas. In this paper, the CALPUFF model recommended by the US EPA is used, and CALPUFF diffusion modeling is performed by generating a wind field through the CALMET model as a meteorological preprocessing program that generates a three-dimensional wind field, which is a meteorological element required by CALPUFF. Through this, we propose a fine dust diffusion modeling and air quality prediction system that reflects complex topography.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.7
• /
• pp.40-48
• /
• 2019

New concept of fine dust measurement method is suggested based on ultrasonic scattering. These days, fine dust has been social problem in Korea, and many researches has been conducted including the area structural maintenance. Conventional measurement system such as optical scattering and semiconductor has a limit from environmental factors like relative humidity. However, ultrasound is based on mechanical waves, which perturb mechanical properties of medium such as density and elastic constants. Using the advantage, the algorithm for fine dust measurement is derived and evaluated using 2-D finite difference method. The numerical analysis simulates ultrasonic wave propagation inside multiple scattering medium like fine dust in air. Signal processing scheme is also suggested and the results show that the error of the algorithm is around minimum of 0.7 and maximum of 24.9 in the number density unit. It is shown that cross-section of fine dust is a key parameter to improve the accuracy of algorithm.

• Journal of Korea Game Society
• /
• v.16 no.6
• /
• pp.101-110
• /
• 2016

Currently, fires caused by fine dust particles are attracting people's attention increasingly. Fine dust particles are $2.5{\mu}m$ (micrometer) in diameter which cannot be seen by the naked eyes could penetrate deeply into the lungs and cause health problems. Although people are aware of the precautions against fine dust particles, they do not take actions because they are less aware of the hazards that fine dust particles can do. This study aims to investigate the effects of artificial and natural causes of fine dust particles. In order to improve awareness of fine dust particle prevention, the <우마이() Escape> board game was developed and tests were carried out to 20 children to find out the educational effects of the board game.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.140-145
• /
• 2022

In an advanced modern society, among air pollutants caused by urban industrialization and public transportation, fine dust flows into indoors from the outdoors. The fine dust meter used indoors provides limited information and measures the pollution level differently, so there is a problem that users cannot monitor and monitor the data they want. To solve this problem, in this paper, indoor air quality data fine dust and ultra-fine dust (PM1.0, PM2.5, PM10), VOC (Volatile Organic Compounds) and PIR (Passive Infrared Sensor) are used to measure fine dust. and a monitoring system were designed and implemented. We propose a fine dust meter and monitoring system that is installed in a designated area to measure fine dust in real time, collects, stores, and visualizes data through App Engine of Google Cloud Platform and provides it to users.