Application of Photo Texture Analysis and Weather Data in Assessment of Air Quality in Terms of Airborne PM10 and PM2.5 Particulate Matter

The study was undertaken in Krakow, which is situated in Lesser Poland Voivodeship, where bad PM10 air-quality indicators occurred on more than 100 days in the years 2010–2019. Krakow has continuous air quality measurement in seven locations that are run by the Province Environmental Protection Inspectorate. The research aimed to create regression and classification models for PM10 and PM2.5 estimation based on sky photos and basic weather data. For this research, one short video with a resolution of 1920 × 1080 px was captured each day. From each film, only five frames were used, the information from which was averaged. Then, texture analysis was performed on each averaged photo frame. The results of the texture analysis were used in the regression and classification models. The regression models’ quality for the test datasets equals 0.85 and 0.73 for PM10 and 0.63 for PM2.5. The quality of each classification model differs (0.86 and 0.73 for PM10, and 0.80 for PM2.5). The obtained results show that the created classification models could be used in PM10 and PM2.5 air quality assessment. Moreover, the character of the obtained regression models indicates that their quality could be enhanced; thus, improved results could be obtained.

Download Full-text

Comparison of Regression and Classification Models for User-Independent and Personal Stress Detection

Sensors ◽

10.3390/s20164402 ◽

2020 ◽

Vol 20 (16) ◽

pp. 4402

Author(s):

Pekka Siirtola ◽

Juha Röning

Keyword(s):

Feature Selection ◽

Regression Model ◽

Regression Models ◽

Personal Data ◽

The Other ◽

Training Data ◽

Classification Model ◽

Classification Models ◽

Stress Detection ◽

Personal Training

In this article, regression and classification models are compared for stress detection. Both personal and user-independent models are experimented. The article is based on publicly open dataset called AffectiveROAD, which contains data gathered using Empatica E4 sensor and unlike most of the other stress detection datasets, it contains continuous target variables. The used classification model is Random Forest and the regression model is Bagged tree based ensemble. Based on experiments, regression models outperform classification models, when classifying observations as stressed or not-stressed. The best user-independent results are obtained using a combination of blood volume pulse and skin temperature features, and using these the average balanced accuracy was 74.1% with classification model and 82.3% using regression model. In addition, regression models can be used to estimate the level of the stress. Moreover, the results based on models trained using personal data are not encouraging showing that biosignals have a lot of variation not only between the study subjects but also between the session gathered from the same person. On the other hand, it is shown that with subject-wise feature selection for user-independent model, it is possible to improve recognition models more than by using personal training data to build personal models. In fact, it is shown that with subject-wise feature selection, the average detection rate can be improved as much as 4%-units, and it is especially useful to reduce the variance in the recognition rates between the study subjects.

Download Full-text

A consistent method for modelling PM10 and PM2.5 concentrations across the United Kingdom in 2004 for air quality assessment

Atmospheric Environment ◽

10.1016/j.atmosenv.2006.07.048 ◽

2007 ◽

Vol 41 (1) ◽

pp. 161-172 ◽

Cited By ~ 20

Author(s):

John R. Stedman ◽

Andrew J. Kent ◽

Susannah Grice ◽

Tony J. Bush ◽

Richard G. Derwent

Keyword(s):

United Kingdom ◽

Air Quality ◽

Quality Assessment ◽

The United Kingdom ◽

Pm10 And Pm2.5 ◽

Air Quality Assessment ◽

Consistent Method

Download Full-text

Gradient gas sensor microarrays for on-line process control — a new dynamic classification model for fast and reliable air quality assessment

Sensors and Actuators B Chemical ◽

10.1016/s0925-4005(00)00470-6 ◽

2000 ◽

Vol 68 (1-3) ◽

pp. 115-122 ◽

Cited By ~ 14

Author(s):

R Menzel ◽

J Goschnick

Keyword(s):

Air Quality ◽

Process Control ◽

Quality Assessment ◽

Gas Sensor ◽

Classification Model ◽

Air Quality Assessment ◽

On Line ◽

Line Process

Download Full-text

Using A Low-Cost Sensor Array and Machine Learning Techniques to Detect Complex Pollutant Mixtures and Identify Likely Sources

Sensors ◽

10.3390/s19173723 ◽

2019 ◽

Vol 19 (17) ◽

pp. 3723 ◽

Cited By ~ 4

Author(s):

Jacob Thorson ◽

Ashley Collier-Oxandale ◽

Michael Hannigan

Keyword(s):

Neural Networks ◽

Linear Regression ◽

Multiple Linear Regression ◽

Random Forests ◽

Regression Models ◽

Low Cost ◽

Classification Model ◽

Support Vector ◽

Classification Models ◽

Pollutant Mixtures

An array of low-cost sensors was assembled and tested in a chamber environment wherein several pollutant mixtures were generated. The four classes of sources that were simulated were mobile emissions, biomass burning, natural gas emissions, and gasoline vapors. A two-step regression and classification method was developed and applied to the sensor data from this array. We first applied regression models to estimate the concentrations of several compounds and then classification models trained to use those estimates to identify the presence of each of those sources. The regression models that were used included forms of multiple linear regression, random forests, Gaussian process regression, and neural networks. The regression models with human-interpretable outputs were investigated to understand the utility of each sensor signal. The classification models that were trained included logistic regression, random forests, support vector machines, and neural networks. The best combination of models was determined by maximizing the F1 score on ten-fold cross-validation data. The highest F1 score, as calculated on testing data, was 0.72 and was produced by the combination of a multiple linear regression model utilizing the full array of sensors and a random forest classification model.

Download Full-text

Atmospheric aerosols and their influence on air quality in urban areas

Facta universitatis - series Physics Chemistry and Technology ◽

10.2298/fupct0601083t ◽

2006 ◽

Vol 4 (1) ◽

pp. 83-91 ◽

Cited By ~ 8

Author(s):

Mirjana Tasic ◽

Slavica Rajsic ◽

Velibor Novakovic ◽

Zoran Mijic

Keyword(s):

Air Quality ◽

Human Health ◽

Atmospheric Aerosols ◽

Urban Areas ◽

Ground Level ◽

Urban Atmosphere ◽

Basic Knowledge ◽

Pm10 And Pm2.5 ◽

Air Quality Assessment

The quality and pollution of air and its impact on the environment and particularly on human health, is an issue of significant public and governmental concern. The emission of the main air pollutants (sulfur dioxide, nitrogen oxides) has declined significantly but the trends in concentrations of a particulate matter are less clear and this pollutant still pose a risk to human health. The studies on the quality of air in urban atmosphere related to suspended particles PM10 and PM2.5, and first measurements of their mass concentrations have been initiated in our country in 2002, and are still in progress. The results of preliminary investigations revealed the need for the continuous and long-term systematical sampling measurements and analysis of interaction of the specific pollutants ? PM10 and PM2.5 as well as ozone, heavy metals in the ground level. Survey of some basic knowledge and features of atmospheric particles will be given and the results of air quality assessment in Belgrade will be presented as well.

Download Full-text

Air quality assessment in Southeast Brazil during COVID-19 pandemic and lockdown: report of increased air pollution

Cadernos de Saúde Pública ◽

10.1590/0102-311x00242320 ◽

2021 ◽

Vol 37 (9) ◽

Author(s):

Bruno Kabke Bainy ◽

Ilma Aparecida Paschoal ◽

Ana Maria Heuminski de Avila ◽

Henrique Oliveira dos Santos

Keyword(s):

Air Pollution ◽

Air Quality ◽

Rural Areas ◽

Sao Paulo ◽

The State ◽

Weather Data ◽

São Paulo ◽

Air Quality Assessment ◽

Possible Cause

On March 24, 2020, a partial lockdown was decreed in the state of São Paulo, Brazil, as a measure to hinder the spread of COVID-19, which consisted in prohibiting crowding and advising people to stay home, except for urgent or extremely necessary matters. Based on studies performed in other countries, this study aims to assess the impacts of the lockdown on the air quality of five cities in the state of São Paulo. Our study was conducted by using particulate matter and nitrogen dioxide as air quality indicators, and by correlating the contaminants concentrations with weather data. The results showed an increase in these contaminants in all cities within the first weeks after the lockdown compared with the weeks before the decree and with the same period in previous years. This result is inconsistent with the literature. Therefore, a secondary goal was set to investigate the possible cause (or causes) of such deterioration in air quality, which led to the increased number of wildfires. The anomalous dry weather favored the burning of vegetation in agricultural rural areas and in small, vegetated areas near the municipalities, and limited pollution scavenging by rainfall, both of which contributed to higher pollution concentration. We hypothesize the possible effects of worse air quality on the aggravation of COVID-19, but further research is necessary to obtain a complete assessment.

Download Full-text