Prediction of O3 in the respiratory system of children using the artificial neural network model and with selection of input based on gamma test, Ahvaz, Iran

Using water quality parameters to prediction of the ion-based trihalomethane by an artificial neural network model

Trihalomethanes (THMs) are the first disinfectant by-products in the drinking water distribution network and are classified as potential carcinogens. The presence of THMs in chlorinated water depends on the pH, water temperature, contact time between water and chlorine, type and dose of disinfection, bromide ion concentration, and type and concentration of natural organic materials (NOMs). In the present study, the formation of THMs was evaluated by six simple and easy water quality parameters and modeled by an artificial neural network (ANN) approach through five water distribution networks (WDNs) and the Karoun River in Khuzestan province. The results of this study that was conducted from October 2014 to September 2015 showed that THM concentration ranged in five WDNs, including Shoushtar, Ahvaz (2), Ahvaz (3), Mahshahr, Khorramshahr, and total WDNs through N.D.-9.39 µg/L, 7.12-28.60, 38.16-67.00, 17.15-90.46, 15.14-29.99, and N.D.-156, respectively. The concentration of THMs exceeded Iran and EPA standards in many cases in Mahshahr and Khorramshahr WDNs. Evaluation of R², MSE, and RMSE showed the appropriate correlation between measured and modeled THMs, indicating a reasonable ANN potential for estimating THM formation in water sources.

A new hybrid prediction model of air quality index based on secondary decomposition and improved kernel extreme learning machine

Air quality index (AQI) prediction is important to control air pollution. To improve its accuracy, a new hybrid prediction model of AQI based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), multivariate multiscale dispersion entropy (mvMDE), variational mode decomposition optimized by bald eagle search (BES) algorithm (BVMD) and kernel extreme learning machine optimized by rat swarm optimizer (RSO) algorithm (RSO-KELM), named CEEMDAN-mvMDE-BVMD-RSO-KELM, is proposed. Firstly, AQI series is decomposed by CEEMDAN to obtain multiple intrinsic mode function (IMF) components, and each IMF component's complexity is calculated by mvMDE. Secondly, VMD optimized by BES algorithm, named BVMD, is proposed to solve the problem of choosing the decomposition level K and penalty factor α of VMD, and BVMD is used to perform the secondary decomposition of high complexity components. Thirdly, the penalty coefficient and kernel parameter of KELM optimized by RSO algorithm, named RSO-KELM, is proposed, and all IMF components are predicted by RSO-KELM. Finally, the final prediction results are obtained by reconstructing the prediction results of all IMF components. The objective of this study is to propose a new hybrid prediction model of AQI based on secondary decomposition and improved KELM. Taking Shanghai, Beijing and Xi'an as examples, the results show that compared with the comparison models, the proposed model has the highest prediction accuracy.

Functional Kriging for Spatiotemporal Modeling of Nitrogen Dioxide in a Middle Eastern Megacity

Long-term hour-specific air pollution exposure estimates have rarely been of interest in epidemiological research. However, this can be relevant for studies that aim to estimate the residential exposure for the hours that subjects mostly spend time there, or for those hours that they may work in another location. Here, we developed a model by spatially predicting the long-term diurnal curves of nitrogen dioxide (NO2) in Tehran, Iran, one of the most polluted and populated megacities in the Middle East. We used the statistical framework of functional data analysis (FDA) including ordinary kriging for functional data (OKFD) and functional analysis of variance (fANOVA) for modeling. The long-term NO2 diurnal curves had two distinct maxima and minima. The absolute minimum value of the city average was 40.6 ppb (around 4:00 p.m.) and the absolute maximum value was 52.0 ppb (around 10:00 p.m.). The OKFD showed the concentrations, the diurnal maximum/minimum values, and their corresponding occurring times varied across the city. The fANOVA highlighted that the effect of population density on the NO2 concentrations is not constant and depends on time within the diurnal period. The provided estimation of long-term hour-specific maps can inform future epidemiological studies to use the long-term mean for specific hour(s) of the day. Moreover, the demonstrated FDA framework can be used as a set of flexible statistical methods.

Assessment of types of bacterial bio-aerosols and concentrations in the indoor air of gyms

The presence of airborne microorganisms in indoor air (home and work) is a serious public health concern. Bio-aerosols have a significant role in indoor air pollution as they can be pathogenic or cause an allergic reaction following inhalation, ingestion or skin absorption. This study aimed to assess bacterial bio-aerosols in the indoor air concentration of gyms, and its relationship with gym area per person, temperature, and relative humidity. Sampling was performed by the National Institute for Occupational Safety and Health (NIOSH) method 0800-0999 and using an Anderson single-step sampler. Fifty-five gyms were selected with simple random sampling method and 165 samples collected for evaluation of bacterial bio-aerosols. The concentrations of airborne bacteria were measured as colony-forming units per cubic meter of air (CFU/m³) collected by impaction on to tryptic soy agar plates. The maximum and minimum densities of bacteria in the air of gyms were 877 and 117 CFU/m³, respectively. Pseudomonas, Staphylococcus and Escherichia Coli had an order of the highest to lowest frequency among the microorganisms, respectively. Generally, with increasing temperature and humidity, the density of bacteria was increased. The higher amount of the microorganisms was observed in the air of gyms in the lower available area per person. Athletes are at risk of high exposure to the bacterial bio-aerosol that can affect their health.

Machine Learning Within Studies of Early-Life Environmental Exposures and Child Health: Review of the Current Literature and Discussion of Next Steps

PURPOSE OF REVIEW

The goal of this article is to review the use of machine learning (ML) within studies of environmental exposures and children's health, identify common themes across studies, and provide recommendations to advance their use in research and practice.

RECENT FINDINGS

We identified 42 articles reporting upon the use of ML within studies of environmental exposures and children's health between 2017 and 2019. The common themes among the articles were analysis of mixture data, exposure prediction, disease prediction and forecasting, analysis of complex data, and causal inference. With the increasing complexity of environmental health data, we anticipate greater use of ML to address the challenges that cannot be handled by traditional analytics. In order for these methods to beneficially impact public health, the ML techniques we use need to be appropriate for our study questions, rigorously evaluated and reported in a way that can be critically assessed by the scientific community.

High throughput mathematical modeling and multi-objective evolutionary algorithms for plant tissue culture media formulation: Case study of pear rootstocks

Simplified prediction of the interactions of plant tissue culture media components is of critical importance to efficient development and optimization of new media. We applied two algorithms, gene expression programming (GEP) and M5' model tree, to predict the effects of media components on in vitro proliferation rate (PR), shoot length (SL), shoot tip necrosis (STN), vitrification (Vitri) and quality index (QI) in pear rootstocks (Pyrodwarf and OHF 69). In order to optimize the selected prediction models, as well as achieving a precise multi-optimization method, multi-objective evolutionary optimization algorithms using genetic algorithm (GA) and particle swarm optimization (PSO) techniques were compared to the mono-objective GA optimization technique. A Gamma test (GT) was used to find the most important determinant input for optimizing each output factor. GEP had a higher prediction accuracy than M5' model tree. GT results showed that BA (Γ = 4.0178), Mesos (Γ = 0.5482), Mesos (Γ = 184.0100), Micros (Γ = 136.6100) and Mesos (Γ = 1.1146), for PR, SL, STN, Vitri and QI respectively, were the most important factors in culturing OHF 69, while for Pyrodwarf culture, BA (Γ = 10.2920), Micros (Γ = 0.7874), NH4NO3 (Γ = 166.410), KNO3 (Γ = 168.4400), and Mesos (Γ = 1.4860) were the most important influences on PR, SL, STN, Vitri and QI respectively. The PSO optimized GEP models produced the best outputs for both rootstocks.

Influence of urban forest on traffic air pollution and children respiratory health

This study aimed to assess the air quality, the prevalence of child respiratory morbidity, and the association between them, in urban areas where concentrations of pollutants are expected to be below national limits. The monitoring of PM_10, NO₂ and O₃ was performed in five schools, during 9 months. Information about respiratory diseases and associated symptoms were collected from each student using a questionnaire based on the International Study of Asthma and Allergies in Childhood. The PM₁₀ and NO₂ concentrations were higher at points closer to roads and avenues with intense vehicle flow and lower at the point closer to a park, with dense vegetation. All sampling points exceeded the annual limit established by WHO for PM₁₀. Some maximum PM₁₀ concentrations recorded close to the road was six times higher than the international limit. In total, 340 answered questionnaires were collected (68% response rate). Respiratory symptoms such as wheezing, sneezing, running nose, tearing, and itchy eyes had positive and strong correlation to the primary pollutants (0.70 to 0.87), but the frequency of some symptoms was lower close to the urban forest. Therefore, our results confirm the importance of creating and maintaining green areas in urban space, considering all ecosystem services provided by them, especially the improvement of air quality. In addition, a continuous program to monitor and control atmospheric pollution is required in mid-sized counties located nearby important roads, with growing fleets of vehicles.