Scalable kernel-based SVM classification algorithm on imbalance air quality data for proficient healthcare

Complex & Intelligent Systems ◽

10.1007/s40747-021-00435-5 ◽

2021 ◽

Author(s):

Shwet Ketu ◽

Pramod Kumar Mishra

Keyword(s):

Air Pollution ◽

Air Quality ◽

Class Imbalance ◽

Imbalanced Data ◽

Classification Algorithm ◽

Quality Data ◽

Pollution Level ◽

Classification Problems ◽

Chi Square ◽

The Impact

AbstractIn the last decade, we have seen drastic changes in the air pollution level, which has become a critical environmental issue. It should be handled carefully towards making the solutions for proficient healthcare. Reducing the impact of air pollution on human health is possible only if the data is correctly classified. In numerous classification problems, we are facing the class imbalance issue. Learning from imbalanced data is always a challenging task for researchers, and from time to time, possible solutions have been developed by researchers. In this paper, we are focused on dealing with the imbalanced class distribution in a way that the classification algorithm will not compromise its performance. The proposed algorithm is based on the concept of the adjusting kernel scaling (AKS) method to deal with the multi-class imbalanced dataset. The kernel function's selection has been evaluated with the help of weighting criteria and the chi-square test. All the experimental evaluation has been performed on sensor-based Indian Central Pollution Control Board (CPCB) dataset. The proposed algorithm with the highest accuracy of 99.66% wins the race among all the classification algorithms i.e. Adaboost (59.72%), Multi-Layer Perceptron (95.71%), GaussianNB (80.87%), and SVM (96.92). The results of the proposed algorithm are also better than the existing literature methods. It is also clear from these results that our proposed algorithm is efficient for dealing with class imbalance problems along with enhanced performance. Thus, accurate classification of air quality through our proposed algorithm will be useful for improving the existing preventive policies and will also help in enhancing the capabilities of effective emergency response in the worst pollution situation.

Download Full-text

Investigating the impacts of air quality and weather indicators on the spread of SARS-COV-2 in Istanbul, Turkey

Thermal Science ◽

10.2298/tsci201126071t ◽

2021 ◽

pp. 71-71

Author(s):

Caner Taniş ◽

Kadir Karakaya

Keyword(s):

Air Pollution ◽

Air Quality ◽

Meteorological Parameters ◽

Positive Impact ◽

Pearson Correlation ◽

Quality Data ◽

Hospital Discharges ◽

Weather Parameters ◽

The Impact ◽

Quality Indexes

Background/aim: Air pollution is having a positive impact on the spread of the SARS-COV-2 virus. The effects of meteorological parameters on the spread of SARS-COV-2 are a matter of curiosity. The main purpose of this paper is to determine the association between air quality indexes (PM2.5, PM10, NO2, SO2, CO, and O3) and weather parameters (temperature, humidity, pressure, dew, wind speed) with the number of SARS-COV-2 cases, hospitalizations, hospital discharges. In this paper, we also focused on determining the impact of air pollution and weather parameters on the number of daily hospitalizations and daily discharges. Materials and methods: It is gleaned daily cases, hospitalizations, hospital discharges, meteorological, and air quality data in Istanbul from Turkey between July 15, 2020, and September 30, 2020. We performed the Pearson correlation analysis to evaluate the effects of meteorological parameters and air quality indexes on the variables related to SARS-COV-2. Results: It is determined a statistically significant positive relationship between air quality indexes such as CO, SO2, PM2.5, PM10, NO2, and the number of daily confirmed SARS-COV-2 cases. We also observed a negative association between weather parameters such as temperature and pressure and the number of daily confirmed SARS-COV-2 cases. Conclusion: Our study proposes that high air quality could reduce the number of SARS-COV-2 cases. The empirical findings of this paper might provide key input to prevent the spread of SARS-COV-2 across Turkey.

Download Full-text

Basin-scale wind transport during the MILAGRO field campaign and comparison to climatology using cluster analysis

Atmospheric Chemistry and Physics Discussions ◽

10.5194/acpd-7-13035-2007 ◽

2007 ◽

Vol 7 (5) ◽

pp. 13035-13076 ◽

Cited By ~ 1

Author(s):

B. de Foy ◽

J. D. Fast ◽

S. J. Paech ◽

D. Phillips ◽

J. T. Walters ◽

...

Keyword(s):

Air Pollution ◽

Cluster Analysis ◽

Air Quality ◽

Mexico City ◽

Atmospheric Chemistry ◽

Quality Data ◽

Field Campaign ◽

Urban Impacts ◽

Basin Scale ◽

The Impact

Abstract. The MILAGRO field campaign was a multi-agency international collaborative project to evaluate the regional impacts of the Mexico City air pollution plume as a means of understanding urban impacts on the global climate. Mexico City lies on an elevated plateau with mountains on three sides and has complex mountain and surface-driven wind flows. This paper asks what the wind transport was in the basin during the field campaign and how representative it was of the climatology. Surface meteorology and air quality data, radiosoundings and radar wind profiler data were collected at sites in the basin and its vicinity. Cluster analysis is used to identify the dominant wind patterns both during the campaign and within the past 10 years of operational data from the warm dry season. Our analysis shows that March 2006 was representative of typical flow patterns experienced in the basin. Six episode types were identified for the basin scale circulation providing a way of interpreting atmospheric chemistry and particulate data collected during the campaign. Decoupling between surface winds and those aloft had a strong influence in leading to convection and poor air quality episodes. Hourly characterisation of wind circulation during the MILAGRO, MCMA-2003 and IMADA field campaigns will enable the comparisons of similar air pollution episodes and the evaluation of the impact of wind transport on measurements of the atmospheric chemistry taking place in the basin.

Download Full-text

Contribution of Subway Expansions to Air Quality Improvement and the Corresponding Health Implications in Nanjing, China

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18030969 ◽

2021 ◽

Vol 18 (3) ◽

pp. 969

Author(s):

Meina Zheng ◽

Xiucheng Guo ◽

Feng Liu ◽

Jiayan Shen

Keyword(s):

Air Pollution ◽

Air Quality ◽

Cost Benefit Analysis ◽

Strong Support ◽

Cost Benefit ◽

Quality Data ◽

Pollution Level ◽

Health Implications ◽

Premature Deaths ◽

Reduction Effect

With China’s rapid economic development, particularly its accelerated urbanization, air pollution has been one of the serious environmental issues across China. Most major cities in China expand their subway systems to handle this problem. This study takes both long- and short-term effects of subway expansions on air quality and its corresponding health implications into account based on a network density-based time series analysis and a distance-based difference-in-differences analysis. The daily and hourly monitor-level air quality data on Nanjing from 13 May 2014 to 31 December 2018, combining with corresponding weather variables, are used to quantify the effect of subway expansions on local air pollution caused by eight new subway lines in Nanjing. The results reveal that subway expansions result in a statistically significant decrease in the air pollution level; specifically, the air pollution level experiences a 3.93% larger reduction in the areas close to subway lines. Heterogeneous analysis of different air pollutants indicates that the air pollution reduction effect of subway expansions is more significant in terms of Particulate Matter (PM2.5) and CO. A back-of-the-envelope analysis of the health benefits from this air improvement shows that the total number of yearly averted premature deaths is around 300,214 to 443,498. A set of alternative specifications confirm the robustness of our results. These results provide strong support for putting more emphasis on the environmental effect of subway expansions in the cost-benefit analysis of subway planning.

Download Full-text

Monitoring of ambient air quality in relation to traffic density in Bareilly City (U.P.), India

Journal of Applied and Natural Science ◽

10.31018/jans.v5i2.359 ◽

2013 ◽

Vol 5 (2) ◽

pp. 497-502

Author(s):

D. R. Khanna ◽

N. S. Nigam ◽

R. Bhutiani

Keyword(s):

Air Pollution ◽

Air Quality ◽

Sampling Site ◽

Ambient Air ◽

Quality Data ◽

Traffic Density ◽

Pollution Level ◽

Ambient Air Quality ◽

Oak Ridge ◽

The City

An ambient air quality study was undertaken in Bareilly city, U.P., India during the year 2010 and 2011. The seasonal air quality data was obtained from ten monitoring sites across the city considering sampling site of Cantt as control site. The maximum (713.06±55.64 µg/m3) suspended particulate matter (SPM), sulphur dioxide (SO2) (80.08±4.77 µg/m3) and nitrogen oxides (NOx) (64.98±3.53 µg/m3) level was found at Choupla during the winter 2011. Among the annual mean values of air pollutants were analyzed, SPM level was found to be above the National Ambient Air Quality Standards (NAAQS) (200 µg/m3) at all the polluted sites. SO2 and NOx levels were below the threshold limits (80 µg/m3) as per NAAQS. The ambient air quality was correlated with the traffic density in the city. The pollution level was observed to be positively correlated with traffic density which is the major source of air pollution in the city. The ambient air quality at different monitoring sites was categorized into different pollution level on the basis of Oak ridge air quality index (ORAQI). Light to moderate air pollution conditions were present at different sites. Sampling site of Choupla (SVII) observe maximum ORAQI of 64.48 and 70.81 and falls under category of moderate pollution.

Download Full-text

Basin-scale wind transport during the MILAGRO field campaign and comparison to climatology using cluster analysis

Atmospheric Chemistry and Physics ◽

10.5194/acp-8-1209-2008 ◽

2008 ◽

Vol 8 (5) ◽

pp. 1209-1224 ◽

Cited By ~ 114

Author(s):

B. de Foy ◽

J. D. Fast ◽

S. J. Paech ◽

D. Phillips ◽

J. T. Walters ◽

...

Keyword(s):

Air Pollution ◽

Cluster Analysis ◽

Air Quality ◽

Mexico City ◽

Atmospheric Chemistry ◽

Quality Data ◽

Field Campaign ◽

Urban Impacts ◽

Basin Scale ◽

The Impact

Abstract. The MILAGRO field campaign was a multi-agency international collaborative project to evaluate the regional impacts of the Mexico City air pollution plume as a means of understanding urban impacts on the global climate. Mexico City lies on an elevated plateau with mountains on three sides and has complex mountain and surface-driven wind flows. This paper asks what the wind transport was in the basin during the field campaign and how representative it was of the climatology. Surface meteorology and air quality data, radiosondes and radar wind profiler data were collected at sites in the basin and its vicinity. Cluster analysis was used to identify the dominant wind patterns both during the campaign and within the past 10 years of operational data from the warm dry season. Our analysis shows that March 2006 was representative of typical flow patterns experienced in the basin. Six episode types were identified for the basin-scale circulation providing a way of interpreting atmospheric chemistry and particulate data collected during the campaign. Decoupling between surface winds and those aloft had a strong influence in leading to convection and poor air quality episodes. Hourly characterisation of wind circulation during the MILAGRO, MCMA-2003 and IMADA field campaigns enables the comparisons of similar air pollution episodes and the evaluation of the impact of wind transport on measurements of the atmospheric chemistry taking place in the basin.

Download Full-text

Kernel Based Data-Adaptive Support Vector Machines for Multi-Class Classification

Mathematics ◽

10.3390/math9090936 ◽

2021 ◽

Vol 9 (9) ◽

pp. 936

Author(s):

Jianli Shao ◽

Xin Liu ◽

Wenqing He

Keyword(s):

Machine Learning ◽

Spatial Association ◽

Class Imbalance ◽

Imbalanced Data ◽

Real Data ◽

Kernel Functions ◽

Support Vector ◽

Classification Problems ◽

Rare Class ◽

Data Adaptive

Imbalanced data exist in many classification problems. The classification of imbalanced data has remarkable challenges in machine learning. The support vector machine (SVM) and its variants are popularly used in machine learning among different classifiers thanks to their flexibility and interpretability. However, the performance of SVMs is impacted when the data are imbalanced, which is a typical data structure in the multi-category classification problem. In this paper, we employ the data-adaptive SVM with scaled kernel functions to classify instances for a multi-class population. We propose a multi-class data-dependent kernel function for the SVM by considering class imbalance and the spatial association among instances so that the classification accuracy is enhanced. Simulation studies demonstrate the superb performance of the proposed method, and a real multi-class prostate cancer image dataset is employed as an illustration. Not only does the proposed method outperform the competitor methods in terms of the commonly used accuracy measures such as the F-score and G-means, but also successfully detects more than 60% of instances from the rare class in the real data, while the competitors can only detect less than 20% of the rare class instances. The proposed method will benefit other scientific research fields, such as multiple region boundary detection.

Download Full-text

Functional ANOVA approaches for detecting changes in air pollution during the COVID-19 pandemic

Stochastic Environmental Research and Risk Assessment ◽

10.1007/s00477-021-02071-4 ◽

2021 ◽

Author(s):

Christian Acal ◽

Ana M. Aguilera ◽

Annalina Sarra ◽

Adelia Evangelista ◽

Tonio Di Battista ◽

...

Keyword(s):

Air Pollution ◽

Air Quality ◽

Functional Data ◽

Central Italy ◽

Principal Component ◽

Functional Principal Component Analysis ◽

Area Of Interest ◽

Pm 10 ◽

The Impact ◽

Monitoring Stations

AbstractFaced with novel coronavirus outbreak, the most hard-hit countries adopted a lockdown strategy to contrast the spread of virus. Many studies have already documented that the COVID-19 control actions have resulted in improved air quality locally and around the world. Following these lines of research, we focus on air quality changes in the urban territory of Chieti-Pescara (Central Italy), identified as an area of criticality in terms of air pollution. Concentrations of $$\hbox {NO}_{{2}}$$ NO 2 , $$\hbox {PM}_{{10}}$$ PM 10 , $$\hbox {PM}_{2.5}$$ PM 2.5 and benzene are used to evaluate air pollution changes in this Region. Data were measured by several monitoring stations over two specific periods: from 1st February to 10 th March 2020 (before lockdown period) and from 11st March 2020 to 18 th April 2020 (during lockdown period). The impact of lockdown on air quality is assessed through functional data analysis. Our work makes an important contribution to the analysis of variance for functional data (FANOVA). Specifically, a novel approach based on multivariate functional principal component analysis is introduced to tackle the multivariate FANOVA problem for independent measures, which is reduced to test multivariate homogeneity on the vectors of the most explicative principal components scores. Results of the present study suggest that the level of each pollutant changed during the confinement. Additionally, the differences in the mean functions of all pollutants according to the location and type of monitoring stations (background vs traffic), are ascribable to the $$\hbox {PM}_{{10}}$$ PM 10 and benzene concentrations for pre-lockdown and during-lockdown tenure, respectively. FANOVA has proven to be beneficial to monitoring the evolution of air quality in both periods of time. This can help environmental protection agencies in drawing a more holistic picture of air quality status in the area of interest.

Download Full-text

The interplay between environmental exposures and COVID-19 risks in the health of children

Environmental Health ◽

10.1186/s12940-021-00716-z ◽

2021 ◽

Vol 20 (1) ◽

Author(s):

Peter D. Sly ◽

Brittany A. Trottier ◽

Catherine M. Bulka ◽

Stephania A. Cormier ◽

Julius Fobil ◽

...

Keyword(s):

Air Pollution ◽

Air Quality ◽

Disease Severity ◽

Research Effort ◽

Severe Disease ◽

Environmental Exposures ◽

Research Strategy ◽

Lessons Learned ◽

Research Questions ◽

The Impact

Abstract Background An unusual feature of SARS-Cov-2 infection and the COVID-19 pandemic is that children are less severely affected than adults. This is especially paradoxical given the epidemiological links between poor air quality and increased COVID-19 severity in adults and that children are generally more vulnerable than adults to the adverse consequences of air pollution. Objectives To identify gaps in knowledge about the factors that protect children from severe SARS-Cov-2 infection even in the face of air pollution, and to develop a transdisciplinary research strategy to address these gaps. Methods An international group of researchers interested in children’s environmental health was invited to identify knowledge gaps and to develop research questions to close these gaps. Discussion Key research questions identified include: what are the effects of SAR-Cov-2 infection during pregnancy on the developing fetus and child; what is the impact of age at infection and genetic susceptibility on disease severity; why do some children with COVID-19 infection develop toxic shock and Kawasaki-like symptoms; what are the impacts of toxic environmental exposures including poor air quality, chemical and metal exposures on innate immunity, especially in the respiratory epithelium; what is the possible role of a “dirty” environment in conveying protection – an example of the “hygiene hypothesis”; and what are the long term health effects of SARS-Cov-2 infection in early life. Conclusion A concerted research effort by a multidisciplinary team of scientists is needed to understand the links between environmental exposures, especially air pollution and COVID-19. We call for specific research funding to encourage basic and clinical research to understand if/why exposure to environmental factors is associated with more severe disease, why children appear to be protected, and how innate immune responses may be involved. Lessons learned about SARS-Cov-2 infection in our children will help us to understand and reduce disease severity in adults, the opposite of the usual scenario.

Download Full-text

Gender Differences in Association between Air Pollution and Daily Mortality in the Capital of the Green Lungs of Poland–Population-Based Study with 2,953,000 Person-Years of Follow-Up

Journal of Clinical Medicine ◽

10.3390/jcm9082351 ◽

2020 ◽

Vol 9 (8) ◽

pp. 2351

Author(s):

Łukasz Kuźma ◽

Krzysztof Struniawski ◽

Szymon Pogorzelski ◽

Hanna Bachórzewska-Gajewska ◽

Sławomir Dobrzycki

Keyword(s):

Public Health ◽

Gender Differences ◽

Air Pollution ◽

Air Quality ◽

Air Pollutant ◽

World Health ◽

The European Union ◽

Daily Mortality ◽

Male Population ◽

The Impact

(1) Introduction: air pollution is considered to be one of the main risk factors for public health. According to the European Environment Agency (EEA), air pollution contributes to the premature deaths of approximately 500,000 citizens of the European Union (EU), including almost 5000 inhabitants of Poland every year. (2) Purpose: to assess the gender differences in the impact of air pollution on the mortality in the population of the city of Bialystok—the capital of the Green Lungs of Poland. (3) Materials and Methods: based on the data from the Central Statistical Office, the number—and causes of death—of Białystok residents in the period 2008–2017 were analyzed. The study utilized the data recorded by the Provincial Inspectorate for Environmental Protection station and the Institute of Meteorology and Water Management during the analysis period. Time series regression with Poisson distribution was used in statistical analysis. (4) Results: A total of 34,005 deaths had been recorded, in which women accounted for 47.5%. The proportion of cardiovascular-related deaths was 48% (n = 16,370). An increase of SO2 concentration by 1-µg/m3 (relative risk (RR) 1.07, 95% confidence interval (CI) 1.02–1.12; p = 0.005) and a 10 °C decrease of temperature (RR 1.03, 95% CI 1.01–1.05; p = 0.005) were related to an increase in the number of daily deaths. No gender differences in the impact of air pollution on mortality were observed. In the analysis of the subgroup of cardiovascular deaths, the main pollutant that was found to have an effect on daily mortality was particulate matter with a diameter of 2.5 μm or less (PM2.5); the RR for 10-µg/m3 increase of PM2.5 was 1.07 (95% CI 1.02–1.12; p = 0.01), and this effect was noted only in the male population. (5) Conclusions: air quality and atmospheric conditions had an impact on the mortality of Bialystok residents. The main air pollutant that influenced the mortality rate was SO2, and there were no gender differences in the impact of this pollutant. In the male population, an increased exposure to PM2.5 concentration was associated with significantly higher cardiovascular mortality. These findings suggest that improving air quality, in particular, even with lower SO2 levels than currently allowed by the World Health Organization (WHO) guidelines, may benefit public health. Further studies on this topic are needed, but our results bring questions whether the recommendations concerning acceptable concentrations of air pollutants should be stricter, or is there a safe concentration of SO2 in the air at all.

Download Full-text