A new approach to UVAPS data analysis towards detection of biological aerosol

Kaliszewski, Miron; Trafny, Elżbieta Anna; Lewandowski, Rafał; Włodarski, Maksymilian; Bombalska, Aneta; Kopczyński, Krzysztof; Antos-Bielska, Małgorzata; Szpakowska, Małgorzata; Młyńczak, Jarosław; Mularczyk-Oliwa, Monika; Kwaśny, M.

doi:10.1016/j.jaerosci.2013.01.007

Cited by 14 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This performance makes the neural network a great tool as a splitting node in the classification tree. Compared to our previous results, for which principal component analysis was applied to analyze data from BARDet (Kaliszewski et al, 2016), the ANNs allowed much better discrimination between various bio-aerosols.…”

Section: Classification Treecontrasting

confidence: 61%

“…We demonstrate a new approach to data analysis using ANNs which allows automation of data preparation procedures and minimum user involvement. Detailed information concerning the construction and parameters of the instrument used for the experiments was presented in our previous work (Kaliszewski et al, 2016). In general, the ambient air is continuously drawn through the nozzle.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved real-time bio-aerosol classification using artificial neural networks

et al. 2018

Self Cite

View full text Add to dashboard Cite

Abstract. Air pollution has had an increasingly powerful impact on the everyday life of humans. More and more people are aware of the health problems that may result from inhaling air which contains dust, bacteria, pollens or fungi. There is a need for real-time information about ambient particulate matter. Devices currently available on the market can detect some particles in the air but cannot classify them according to health threats. Fortunately, a new type of technology is emerging as a promising solution. Laser-based bio-detectors are characterizing a new era in aerosol research. They are capable of characterizing a great number of individual particles in seconds by analyzing optical scattering and fluorescence characteristics. In this study we demonstrate the application of artificial neural networks (ANNs) to real-time analysis of single-particle fluorescence fingerprints acquired using BARDet (a Bio-AeRosol Detector). A total of 48 different aerosols including pollens, bacteria, fungi, spores, and nonbiological substances were characterized. An entirely new approach to data analysis using a decision tree comprising 22 independent neural networks was discussed. Applying confusion matrices and receiver operating characteristics (ROC) analysis the best sets of ANNs for each group of similar aerosols were determined. As a result, a very high accuracy of aerosol classification in real time was achieved. It was found that for some substances that have characteristic spectra, almost each particle can be properly classified. Aerosols with similar spectral characteristics can be classified as specific clouds with high probability. In both cases the system recognized aerosol type with no mistakes. In the future, it is planned that performance of the system may be determined under real environmental conditions, involving characterization of fluorescent and nonfluorescent particles.

show abstract

Section: Classification Treecontrasting

confidence: 61%

Section: Introductionmentioning

confidence: 99%

Improved real-time bio-aerosol classification using artificial neural networks

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…The PCA allows to compare objects or sets consisting of many variables and quickly find the most important properties of the data. Advanced statistical methods using graphical presentation are more and more frequently used in the processing of data obtained in the study of biological samples, such as biological aerosols [ 12 ]. Due to complex mechanisms related to final elemental content in human hair, it was reasonable to assume that multivariable statistical analysis such as PCA, which includes many input variables, can be an additional effective analytical tool for experimental data [ 13 , 14 ].…”

Section: Methodsmentioning

confidence: 99%

Relationships Between Element Contents in Polish Children’s and Adolescents’ Hair

Długaszek

Skrzeczanowski

2017

Biol Trace Elem Res

View full text Add to dashboard Cite

Environment, sex, and age are the main factors which determine the elemental composition of hair. The objective of the study is to determine the contents of calcium (Ca), magnesium (Mg), zinc (Zn), copper (Cu), iron (Fe), lead (Pb), and cadmium (Cd) in girls’ and boys’ hair in five age groups (within 1–19-year range) corresponding to successive human ontogenesis phases as well as to evaluate the relationships between these elements. Quantitative analysis has been carried out using atomic absorption spectrometry (AAS). Experimental results were analyzed using classic and principal component (PCA) statistical analyses. In particular, differences between contents of particularly Ca, Mg, and Zn in girls’ and boys’ hair were found, and substantial differences between age groups were stated. In general, larger amounts of Ca, Mg, and Zn as compared to boys’ hair have been observed for girls’ hair and higher toxic element (Pb, Cd) contents for boys were measured in some age groups. An increasing trend was found for bioelements (Ca, Mg, Zn) both for girls and boys in all age groups, while for Cu and Fe content, changes are insignificant and even decreasing for teenagers. The most frequently correlating element pairs are Ca–Mg, Ca–Zn, Mg–Zn, and Pb–Cd. Classic and PCA statistics show, in general, a satisfactory consistence. The elemental composition of hair varies depending on the gender and age of children and young people.

show abstract

“…However, it has been used for some specific applications such as the influence of aerosol fungal spores or to study the effect of airborne bacterial stress (Agranovski et al 2003b;Kanaani et al 2007). More recent work using hierarchical cluster analysis showed improved classification selectivity of UVAPS on bacteria, fungi, and pollens (Kaliszewski et al 2013). The development of an affordable and more selective technique for real-time monitoring of bioaerosols can certainly push this field of research further.…”

Section: Microorganismsmentioning

confidence: 99%

On the interpretation of bioaerosol exposure measurements and impacts on health

Mbareche

Morawska

Duchaine

2019

Journal of the Air & Waste Management Association

View full text Add to dashboard Cite

Bioaerosols are recognized as one of the main transmission routes for infectious diseases and are responsible for other various types of health effects through inhalation and potential ingestion. Associating exposure with bioaerosol and health problems is challenging, and adequate exposure monitoring is a top priority for aerosol scientists. The multiple factors affecting bioaerosol content, the variability in the focus of each bioaerosol exposure study, and the variations in experimental design and the standardization of methods make bioaerosol exposure studies very difficult. Therefore, the health impacts of bioaerosol exposure are still poorly understood. This paper presents a brief description of a state-of-the-art development in bioaerosol exposure studies supported by studies on several related subjects. The main objective of this paper is to propose new considerations for bioaerosol exposure guidelines and the development of tools and study designs to better interpret bioaerosol data. The principal observations and findings are the discrepancy of the applicable methods in bioaerosol studies that makes result comparison impossible. Furthermore, the silo mentality helps in creating a bigger gap in the knowledge accumulated about bioaerosol exposure. Innovative and original ideas are presented for aerosol scientists and health scientists to consider and discuss. Although many examples cited herein are from occupational exposure, the discussion has relevance to any human environment. This work gives concrete suggestions for how to design a full bioaerosol study that includes all of the key elements necessary to help understand the real impacts of bioaerosol exposure in the short term. The creation of the proposed bioaerosol public database could give crucial information to control the public health.Implications: How can we move toward a bioaerosol exposure guidelines? The creation of the bioaerosol public database will help accumulate information for long-term association studies and help determine specific exposure biomarkers to bioaerosols. The implementation of such work will lead to a deeper understanding and more efficient utilization of bioaerosol studies to prevent public health hazards. PAPER HISTORY

show abstract

A new approach to UVAPS data analysis towards detection of biological aerosol

Cited by 14 publications

References 22 publications

Improved real-time bio-aerosol classification using artificial neural networks

Improved real-time bio-aerosol classification using artificial neural networks

Relationships Between Element Contents in Polish Children’s and Adolescents’ Hair

On the interpretation of bioaerosol exposure measurements and impacts on health

Contact Info

Product

Resources

About