Assessment of urban air quality from Twitter communication using self-attention network and a multilayer classification model.
Ontology highlight
ABSTRACT:
SUBMITTER: Kumbalaparambi TS
PROVIDER: S-EPMC9453714 | biostudies-literature | 2022 Sep
REPOSITORIES: biostudies-literature
Publications
Assessment of urban air quality from Twitter communication using self-attention network and a multilayer classification model.
Kumbalaparambi Thushara Sudheish TS Menon Ratish R Radhakrishnan Vishnu P VP Nair Vinod P VP
Environmental science and pollution research international 20220908 4
Social media platforms are one of the prominent new-age methods used by public for spreading awareness or drawing attention on an issue or concern. This study demonstrates how the twitter responses of public can be used for qualitative monitoring of air pollution in an urban area. Tweets discussing about air quality in Delhi, India, were extracted during 2019-2020 using a machine learning technique based on self-attention network. These tweets were cleaned, sorted, and classified into 3-class qu ...[more]
Similar Datasets
Project description:Low-cost urban air quality sensor networks are increasingly used to study the spatio-temporal variability in air pollutant concentrations. Recently installed low-cost urban sensors, however, are more prone to result in erroneous data than conventional monitors, e.g., leading to outliers. Commonly applied outlier detection methods are unsuitable for air pollutant measurements that have large spatial and temporal variations as occur in urban areas. We present a novel outlier detection method based upon a spatio-temporal classification, focusing on hourly NO2 concentrations. We divide a full year's observations into 16 spatio-temporal classes, reflecting urban background vs. urban traffic stations, weekdays vs. weekends, and four periods per day. For each spatio-temporal class, we detect outliers using the mean and standard deviation of the normal distribution underlying the truncated normal distribution of the NO2 observations. Applying this method to a low-cost air quality sensor network in the city of Eindhoven, the Netherlands, we found 0.1-0.5% of outliers. Outliers could reflect measurement errors or unusual high air pollution events. Additional evaluation using expert knowledge is needed to decide on treatment of the identified outliers. We conclude that our method is able to detect outliers while maintaining the spatio-temporal variability of air pollutant concentrations in urban areas.
| S-EPMC5843703 | biostudies-literature
Project description:Urban environments represent the most intense human-environment interaction. This interaction can result in negative outcomes like air pollution and its health implications. There is a significant data deficit in air quality monitoring across many developing nations, which prevents effective policies and measures from being taken to promote the accomplishment of sustainable development. Around the world, lichens have been used to track environmental changes due to their sensitivity to changes and concentration of atmospheric pollutants. This study investigated the relationships between lichen and air quality across some Nigerian cities. Lichen surveys were conducted in four cities. At various periods during the day, NO2, SO2, PM2.5, and PM10 levels were measured. Association rule mining was carried out to investigate the relationship between lichen found and air quality categories. Results showed that the most prevalent lichen Genera are Pyxine in Abuja and Kano, Diorygma in Lagos, and Dirinaria in Port Harcourt. Out of the 40 rules found from the rule mining, 17 are important (lift values ≥ 1.1), capturing six of the fourteen lichen genera identified in the field. The findings indicated that there are important relationships between lichens and air quality indices, suggesting that some lichen species in Nigeria may serve as indicators of long-term air quality. To develop a network of urban environmental quality bioindicators across Nigerian cities, surveying and transplanting are advised. The use of lichen for air quality monitoring can provide information for sustainable management of air quality and environmental quality in Nigeria.
| S-EPMC9898642 | biostudies-literature
Project description:Air quality in European cities is still a challenge, with various urban areas frequently exceeding the PM2.5 and NO2 concentration levels allowed by the European Union Air Quality Standards. This is a problem both in terms of legislation compliance, but also in terms of health of citizens, as it has been recently estimated that 400 to 450 thousand people die prematurely every year due to poor air quality. Air quality in cities can be improved with a number of interventions, at different sectoral (industry, traffic, residential, etc …) and geographical (international, European, national, local, etc.) levels. In this paper we explore the potential of city level plans to improve mobility and air quality (excluding electro-mobility options, not considered in this study). We applied the "Sustainable Urban Mobility Plans" (SUMPs) framework to 642 cities in Europe and modelled how the measures they include may impact at first on mobility and emissions at urban level, and then on urban background concentrations of PM2.5 and NO2. Results show that annual averages moderately improve for both pollutants, with reductions of urban background concentrations up to 2% for PM2.5 and close to 4% for NO2. The impact on NO2 at street level (that will be higher than on urban background) is not evaluated in this work. The air quality improvement of the simulated SUMP would only partially alleviate air quality problems in urban areas, but such a reduction in the emissions of air pollutants should still be considered as a positive result of SUMPs, given that they correspond to a set of low-cost measures that can be implemented at local level. Furthermore, the introduction of electro-mobility options (not considered here) would increase the impact on air quality. Other types of benefits, such as reduced fuel consumption, greenhouse gas emissions, higher impact at street level or accident rates reduction further add to the overall positive impact.
| S-EPMC6331659 | biostudies-literature
Project description:Atmospheric particulate matter (PM) is a recognized risk factor for the global burden of disease in human populations. We are presenting here the application of toxicogenomics in the evaluation of the toxic effects of organic content of atmospheric particle matter (PM), from urban and rural environments (city of Barcelona and village of La Pobla, NE Spain), using the developing zebrafish embryo. The main goal is to identify the metabolic pathways involved in the adverse effects observed in zebrafish embryos exposed to PM organic content from urban and rural environments, also allowing the selection of genes of interest that are differentially expressed. The relevance of particle size to the PM toxicity is also addressed. Indeed, the zebrafish embryos were exposed to PM of aerodynamic diameter larger than 7.2 μm and smaller than 0.5 μm (PM10 and PM0.5, respectively). PM0.5 concentrated biological and toxic activities linked to organic substances. Transcriptomic analyses showed strong induction of the AhR signalling pathway (a.k.a. dioxin-like activity) for embryos exposed to both rural and urban extracts, correlating with the concentrations of PAHs. Urban extracts, with strong contribution of traffic emissions, specifically de-regulated oxidative stress-related genes, as well as pancreatic and eye-lens specific genes, two organs known to be affected by air pollution in humans. Exposure to rural extracts, with high contribution of wood burning emissions, affected genes implicated in basic cellular functions, in agreement with their strong embryotoxicity. Extracts from rural and urban samples elicited both common and specific transcriptome responses, suggesting different potentially adverse outcomes depending on PM source and composition. The authors thank the financial support of the Spanish Ministry (project TEA-PARTICLE, grant number CGL2011-29621) and the Portuguese Foundation for Science and Technology for the doctoral grant of Sofia R. Mesquita (SFRH/BD/80710/2011) funded by the Program POPH-QREN through the Portuguese Ministry of Education and Science and the European Social Fund, and support through project PEst-C/MAR/LA0015/2013.
2015-10-26 | GSE53522 | GEO
Project description:Deep learning has emerged as a paradigm that revolutionizes numerous domains of scientific research. Transformers have been utilized in language modeling outperforming previous approaches. Therefore, the utilization of deep learning as a tool for analyzing the genomic sequences is promising, yielding convincing results in fields such as motif identification and variant calling. DeepMicrobes, a machine learning-based classifier, has recently been introduced for taxonomic prediction at species and genus level. However, it relies on complex models based on bidirectional long short-term memory cells resulting in slow runtimes and excessive memory requirements, hampering its effective usability. We present MetaTransformer, a self-attention-based deep learning metagenomic analysis tool. Our transformer-encoder-based models enable efficient parallelization while outperforming DeepMicrobes in terms of species and genus classification abilities. Furthermore, we investigate approaches to reduce memory consumption and boost performance using different embedding schemes. As a result, we are able to achieve 2× to 5× speedup for inference compared to DeepMicrobes while keeping a significantly smaller memory footprint. MetaTransformer can be trained in 9 hours for genus and 16 hours for species prediction. Our results demonstrate performance improvements due to self-attention models and the impact of embedding schemes in deep learning on metagenomic sequencing data.
| S-EPMC10495543 | biostudies-literature
Project description:Bacteriophages are the viruses that infect bacterial cells. They are the most diverse biological entities on earth and play important roles in microbiome. According to the phage lifestyle, phages can be divided into the virulent phages and the temperate phages. Classifying virulent and temperate phages is crucial for further understanding of the phage-host interactions. Although there are several methods designed for phage lifestyle classification, they merely either consider sequence features or gene features, leading to low accuracy. A new computational method, DeePhafier, is proposed to improve classification performance on phage lifestyle. Built by several multilayer self-attention neural networks, a global self-attention neural network, and being combined by protein features of the Position Specific Scoring Matrix matrix, DeePhafier improves the classification accuracy and outperforms two benchmark methods. The accuracy of DeePhafier on five-fold cross-validation is as high as 87.54% for sequences with length >2000bp.
| S-EPMC11304974 | biostudies-literature
Project description:The Transformer has achieved great success in many computer vision tasks. With the in-depth exploration of it, researchers have found that Transformers can better obtain long-range features than convolutional neural networks (CNN). However, there will be a deterioration of local feature details when the Transformer extracts local features. Although CNN is adept at capturing the local feature details, it cannot easily obtain the global representation of features. In order to solve the above problems effectively, this paper proposes a hybrid model consisting of CNN and Transformer inspired by Visual Attention Net (VAN) and CoAtNet. This model optimizes its shortcomings in the difficulty of capturing the global representation of features by introducing Large Kernel Attention (LKA) in CNN while using the Transformer blocks with relative position self-attention variant to alleviate the problem of detail deterioration in local features of the Transformer. Our model effectively combines the advantages of the above two structures to obtain the details of local features more accurately and capture the relationship between features far apart more efficiently on a large receptive field. Our experiments show that in the image classification task without additional training data, the proposed model in this paper can achieve excellent results on the cifar10 dataset, the cifar100 dataset, and the birds400 dataset (a public dataset on the Kaggle platform) with fewer model parameters. Among them, SE_LKACAT achieved a Top-1 accuracy of 98.01% on the cifar10 dataset with only 7.5M parameters.
| S-EPMC10280586 | biostudies-literature
Project description:With the unprecedented urbanization during the past three decades, air quality in many Chinese cities has been a serious issue which poses great challenges for urban sustainability. This study examines the health consequences of development patterns in China by establishing the linkage between urban form, air pollution level, and cardiorespiratory mortality rate. We assembled a dataset by compiling a series of variables from multiple sources, including China's Disease Surveillance Points (DSP) system, which forms a nationally representative sample of mortality for the year 2005, Chinese census, satellite imagery, and the Chinese National Land Use Database. After controlling for local climate, demography, socioeconomics, and other pollution factors, this study finds that urban form elements (e.g., urban density, fragmentation level, forest/green space ratio) have significant influences on PM2.5 (atmospheric particulate matter with a diameter of less than 2.5 micrometers) concentration, thus influencing the incidence of cardiorespiratory mortality at the county level. These results may help explain how the type and pattern of development shape public health by influencing air quality and form an evidence-based land use policy to improve environmental quality and public health.
| S-EPMC7068322 | biostudies-literature
Project description:Protein tertiary structures are essential for studying functions of proteins at molecular level. An indispensable approach for protein structure solution is computational prediction. Most protein structure prediction methods generate candidate models first and select the best candidates by model quality assessment (QA). In many cases, good models can be produced, but the QA tools fail to select the best ones from the candidate model pool. Because of incomplete understanding of protein folding, each QA method only reflects partial facets of a structure model and thus has limited discerning power with no one consistently outperforming others. In this article, we developed a set of new QA methods, including two QA methods for evaluating target/template alignments, a molecular dynamics (MD)-based QA method, and three consensus QA methods with selected references to reveal new facets of protein structures complementary to the existing methods. Moreover, the underlying relationship among different QA methods were analyzed and then integrated into a multilayer evaluation approach to guide the model generation and model selection in prediction. All methods are integrated and implemented into an innovative and improved prediction system hereafter referred to as MUFOLD. In CASP8 and CASP9, MUFOLD has demonstrated the proof of the principles in terms of both QA discerning power and structure prediction accuracy.
| S-EPMC3226843 | biostudies-literature
Project description:Atmospheric particulate matter (PM) is a recognized risk factor for the global burden of disease in human populations. We are presenting here the application of toxicogenomics in the evaluation of the toxic effects of organic content of atmospheric particle matter (PM), from urban and rural environments (city of Barcelona and village of La Pobla, NE Spain), using the developing zebrafish embryo. The main goal is to identify the metabolic pathways involved in the adverse effects observed in zebrafish embryos exposed to PM organic content from urban and rural environments, also allowing the selection of genes of interest that are differentially expressed. The relevance of particle size to the PM toxicity is also addressed. Indeed, the zebrafish embryos were exposed to PM of aerodynamic diameter larger than 7.2 μm and smaller than 0.5 μm (PM10 and PM0.5, respectively). PM0.5 concentrated biological and toxic activities linked to organic substances. Transcriptomic analyses showed strong induction of the AhR signalling pathway (a.k.a. dioxin-like activity) for embryos exposed to both rural and urban extracts, correlating with the concentrations of PAHs. Urban extracts, with strong contribution of traffic emissions, specifically de-regulated oxidative stress-related genes, as well as pancreatic and eye-lens specific genes, two organs known to be affected by air pollution in humans. Exposure to rural extracts, with high contribution of wood burning emissions, affected genes implicated in basic cellular functions, in agreement with their strong embryotoxicity. Extracts from rural and urban samples elicited both common and specific transcriptome responses, suggesting different potentially adverse outcomes depending on PM source and composition. The authors thank the financial support of the Spanish Ministry (project TEA-PARTICLE, grant number CGL2011-29621) and the Portuguese Foundation for Science and Technology for the doctoral grant of Sofia R. Mesquita (SFRH/BD/80710/2011) funded by the Program POPH-QREN through the Portuguese Ministry of Education and Science and the European Social Fund, and support through project PEst-C/MAR/LA0015/2013. The PM filter samples used in the present study were PM10 and PM0.5 from the urban site - total of 4 samples from 2 sampling months; and PM0.5 from the rural site - total of 2 samples from 2 sampling months (PM10 samples from the rural site were not tested due to their very low concentration in organic compounds, and insignificant biological activity, previously measured). Sampling occurred during the cold periods of the year 2012/2013. The organic fraction of PM samples was extracted by sonication using a mixture of dichloromethane:methanol. Then, the extracts were filtered, evaporated and re-dissolved in Dimethyl sulfoxide (DMSO). Zebrafish fertilized eggs were exposed to PM organic extracts (0.2% DMSO) from the urban and rural sites from 24 to 120h post-fertilization. Total RNA was isolated from whole embryos (pools of 20 individuals), using Trizol reagent protocol (Invitrogen Life Technologies, Carlsberg, CA). The microarray study was performed using the Agilent Two-colour D. rerio Oligo Microarray v3 platform, following the Agilent Microarray â?? Based Gene Expression Analysis protocol. Three biological replicates were performed for each PM sample and controls. Biological replicates, a technical replicate and a self-to-self, were simultaneously amplified and labelled using Cyanine 3 (Cy3) and Cyanine 5 (Cy5) dye. After cRNA purification (RNeasy Kit, Quiagen GmbH, Hilden, Germany), the cRNA concentration and labelling were quantified in the NanoDrop spectrophotometer, obtaining incorporation rates in the range of 15-20pmol of cyanide dye/µl cRNA and yield values > 0.825ug, as recommended. cRNA was fragmented and hybridized in 4x44K arrays, for 17h at 65oC. After the hybridization the array slides were washed, and immediately scanned using Microarray Scanner Agilent G2505C system. Data was extracted using Agilent Feature Extraction Software v10.5.1.1, and the quality of microarray data was evaluated using the Quality Control report provided by Agilent Software. Based on the microarray data analysis, 22 primers were selected and designed using Primer Express 2.0 software (Applied Biosystems, Foster City, CA). Genes were quantified by real-time PCR to validate the microarray data, and a subset of 13 genes were further selected by their robust behaviour in the validation assays, allowing to differentiate the toxic potential of PM from urban and rural sources.
2015-10-26 | E-GEOD-53522 | biostudies-arrayexpress