scholarly journals Majority Voting Based Multi-Task Clustering of Air Quality Monitoring Network in Turkey

2019 ◽  
Vol 9 (8) ◽  
pp. 1610
Author(s):  
Goksu Tuysuzoglu ◽  
Derya Birant ◽  
Aysegul Pala
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Clustering Algorithms ◽  
Experimental Studies ◽  
Monitoring Network ◽  
Environmental Parameters ◽  
Global Scale ◽  
Majority Voting ◽  
Clustering Methods ◽  
Task Clustering

Air pollution, which is the result of the urbanization brought by modern life, has a dramatic impact on the global scale as well as local and regional scales. Since air pollution has important effects on human health and other living things, the issue of air quality is of great importance all over the world. Accordingly, many studies based on classification, clustering and association rule mining applications for air pollution have been proposed in the field of data mining and machine learning to extract hidden knowledge from environmental parameters. One approach is to model a region in a way that cities having similar characteristics are determined and placed into the same clusters. Instead of using traditional clustering algorithms, a novel algorithm, named Majority Voting based Multi-Task Clustering (MV-MTC), is proposed and utilized to consider multiple air pollutants jointly. Experimental studies showed that the proposed method is superior to five well-known clustering algorithms: K-Means, Expectation Maximization, Canopy, Farthest First and Hierarchical clustering methods.

scholarly journals Domain adaptation based deep calibration of low-cost PM2.5 sensors

2021 ◽  
Author(s):  
Sonu Kumar Jha ◽  
Mohit Kumar ◽  
Vipul Arora ◽  
Sachchida Nand Tripathi ◽  
Vidyanand Motiram Motghare ◽  
...  
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Domain Adaptation ◽  
Low Cost ◽  
Monitoring Network ◽  
Quality Monitoring ◽  
Air Quality Monitoring ◽  
Proposed Model ◽  
Temperature And Humidity ◽  
Calibration Approach

<div>Air pollution is a severe problem growing over time. A dense air-quality monitoring network is needed to update the people regarding the air pollution status in cities. A low-cost sensor device (LCSD) based dense air-quality monitoring network is more viable than continuous ambient air quality monitoring stations (CAAQMS). An in-field calibration approach is needed to improve agreements of the LCSDs to CAAQMS. The present work aims to propose a calibration method for PM2.5 using domain adaptation technique to reduce the collocation duration of LCSDs and CAAQMS. A novel calibration approach is proposed in this work for the measured PM2.5 levels of LCSDs. The dataset used for the experimentation consists of PM2.5 values and other parameters (PM10, temperature, and humidity) at hourly duration over a period of three months data. We propose new features, by combining PM2.5, PM10, temperature, and humidity, that significantly improved the performance of calibration. Further, the calibration model is adapted to the target location for a new LCSD with a collocation time of two days. The proposed model shows high correlation coefficient values (R2) and significantly low mean absolute percentage error (MAPE) than that of other baseline models. Thus, the proposed model helps in reducing the collocation time while maintaining high calibration performance.</div>

scholarly journals REAL-TIME ENVIRONMENTAL SENSORS TO IMPROVE HEALTH IN THE SENSING CITY

2016 ◽  
Vol XLI-B2 ◽  
pp. 729-733 ◽  
Author(s):  
L. Marek ◽  
M. Campbell ◽  
M. Epton ◽  
M. Storer ◽  
S. Kingham
Keyword(s):  
Quality Of Life ◽  
Air Pollution ◽  
Air Quality ◽  
Real Time ◽  
Low Cost ◽  
Monitoring Network ◽  
Environmental Data ◽  
Chronic Obstructive ◽  
Actual Usage

The opportunity of an emerging smart city in post-disaster Christchurch has been explored as a way to improve the quality of life of people suffering Chronic Obstructive Pulmonary Disease (COPD), which is a progressive disease that affects respiratory function. It affects 1 in 15 New Zealanders and is the 4th largest cause of death, with significant costs to the health system. While, cigarette smoking is the leading cause of COPD, long-term exposure to other lung irritants, such as air pollution, chemical fumes, or dust can also cause and exacerbate it. Currently, we do know little what happens to the patients with COPD after they leave a doctor’s care. By learning more about patients’ movements in space and time, we can better understand the impacts of both the environment and personal mobility on the disease. This research is studying patients with COPD by using GPS-enabled smartphones, combined with the data about their spatiotemporal movements and information about their actual usage of medication in near real-time. We measure environmental data in the city, including air pollution, humidity and temperature and how this may subsequently be associated with COPD symptoms. In addition to the existing air quality monitoring network, to improve the spatial scale of our analysis, we deployed a series of low-cost Internet of Things (IoT) air quality sensors as well. The study demonstrates how health devices, smartphones and IoT sensors are becoming a part of a new health data ecosystem and how their usage could provide information about high-risk health hotspots, which, in the longer term, could lead to improvement in the quality of life for patients with COPD.

scholarly journals One-Year Simulation of Ozone and Particulate Matter in China Using WRF/CMAQ Modeling System

2016 ◽  
Author(s):  
Jianlin Hu ◽  
Jianjun Chen ◽  
Qi Ying ◽  
Hongliang Zhang
Keyword(s):  
Air Pollution ◽  
Particulate Matter ◽  
Air Quality ◽  
Model Performance ◽  
Monitoring Network ◽  
Organic Aerosol ◽  
Quality Monitoring ◽  
Air Quality Monitoring ◽  
Low Concentration ◽  
Temporal And Spatial

Abstract. China has been experiencing severe air pollution in recent decades. Although ambient air quality monitoring network for criteria pollutants has been constructed in over 100 cities since 2013 in China, the temporal and spatial characteristics of some important pollutants, such as particulate matter (PM) components, remain unknown, limiting further studies investigating potential air pollution control strategies to improve air quality and associating human health outcomes with air pollution exposure. In this study, a yearlong (2013) air quality simulation using the Weather Research &amp; Forecasting model (WRF) and the Community Multi-scale Air Quality model (CMAQ) was conducted to provide detailed temporal and spatial information of ozone (O3), PM2.5 total and chemical components. Multi-resolution Emission Inventory for China (MEIC) was used for anthropogenic emissions and observation data obtained from the national air quality monitoring network were collected to validate model performance. The model successfully reproduces the O3 and PM2.5 concentrations at most cities for most months, with model performance statistics meeting the performance criteria. However, over-prediction of O3 generally occurs at low concentration range while under-prediction of PM2.5 happens at low concentration range in summer. Spatially, the model has better performance in Southern China than in Northern, Central and Sichuan basin. Strong seasonal variations of PM2.5 exist and wind speed and direction play important roles in high PM2.5 events. Secondary components have more boarder distribution than primary components. Sulfate (SO42−), nitrate (NO3−), ammonium (NH4+), and primary organic aerosol (POA) are the most important PM2.5 components. All components have the highest concentrations in winter except secondary organic aerosol (SOA). This study proves the ability of CMAQ model in reproducing severe air pollution in China, identifies the directions where improvements are needed, and provides information for human exposure to multiple pollutants for assessing health effects.

A Cluster Analysis of PM2.5 Using CMAQ Model Results for Representativeness of Air Quality Monitoring Networks in Busan, Korea

2020 ◽  
Author(s):  
Woo-Sik Jung ◽  
Woo-Gon Do
Keyword(s):  
Air Pollution ◽  
Cluster Analysis ◽  
Air Quality ◽  
Monitoring Network ◽  
Hierarchical Cluster ◽  
Quality Monitoring ◽  
Quality Data ◽  
Air Quality Monitoring ◽  
Monitoring Networks ◽  
Monitoring Stations

&lt;p&gt;&lt;strong&gt;With increasing interest in air pollution, the installation of air quality monitoring networks for regular measurement is considered a very important task in many countries. However, operation of air quality monitoring networks requires much time and money. Therefore, the representativeness of the locations of air quality monitoring networks is an important issue that has been studied by many groups worldwide. Most such studies are based on statistical analysis or the use of geographic information systems (GIS) in existing air quality monitoring network data. These methods are useful for identifying the representativeness of existing measuring networks, but they cannot verify the need to add new monitoring stations. With the development of computer technology, numerical air quality models such as CMAQ have become increasingly important in analyzing and diagnosing air pollution. In this study, PM2.5 distributions in Busan were reproduced with 1-km grid spacing by the CMAQ model. The model results reflected actual PM2.5 changes relatively well. A cluster analysis, which is a statistical method that groups similar objects together, was then applied to the hourly PM2.5 concentration for all grids in the model domain. Similarities and differences between objects can be measured in several ways. K-means clustering uses a non-hierarchical cluster analysis method featuring an advantageously low calculation time for the fast processing of large amounts of data. K-means clustering was highly prevalent in existing studies that grouped air quality data according to the same characteristics. As a result of the cluster analysis, PM2.5 pollution in Busan was successfully divided into groups with the same concentration change characteristics. Finally, the redundancy of the monitoring stations and the need for additional sites were analyzed by comparing the clusters of PM2.5 with the locations of the air quality monitoring networks currently in operation.&lt;/strong&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(2017R1D1A3B03036152).&lt;/strong&gt;&lt;/p&gt;

scholarly journals Development of an Air Quality Learning and Demonstration Center at the Arboretum at Penn State

HortScience ◽  
2004 ◽  
Vol 39 (4) ◽  
pp. 810B-810
Author(s):  
John M. Skelly ◽  
Don D. Davis ◽  
Dennis R. Decoteau*
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Pollution Abatement ◽  
Environmental Parameters ◽  
Quality Monitoring ◽  
Air Quality Monitoring ◽  
Monitoring Methods ◽  
Penn State ◽  
Internet Connections ◽  
Quality Learning

An Air Quality Learning and Demonstration Center has been developed within the Arboretum at Penn State Univ.. The Center provides opportunities where students (of all ages) and teachers (grade-school through to classes within the Univ.) can learn about air quality as one of our most important natural resources. A seasonally interactive display of air quality monitoring instrumentation, self guided walkways through gardens of air pollution sensitive plant species, innovative techniques for demonstrating the effects of air pollutants on plants, displays of recent research findings, industry supported displays of pollution abatement technologies, and a teaching pavilion are within the Center. A Pennsylvania Dept. of Environmental Protection air quality monitoring station with ozone, sulfur dioxide, nitrogen oxides, carbon dioxide, PM < 2.5 u mass and speciation samplers, and a complete meteorological station provide data on the immediate environmental parameters. These data are relayed to an LCD crystal display board that has been mounted on the outside of the monitoring building; visitors are able to see the various measures of the air quality on a real time basis. Pannier type fiberglass display panels provide understandings of the various facets of air pollution formation and transport phenomena, air quality monitoring methods, the functions of open-top chambers, foliar symptoms expressed by pollution sensitive plants within the bioindicator gardens, and the impacts of pollution on agricultural and forested ecosystems. Handicapped accessible walkways lead visitors throughout the Center to the Teaching Pavilion that easily accommodates 80 persons. The pavilion is equipped with drop down curtains, electric power, and internet connections.

scholarly journals Street-scale air quality modelling for Beijing during a winter 2016 measurement campaign

2020 ◽  
Vol 20 (5) ◽  
pp. 2755-2780 ◽  
Author(s):  
Michael Biggart ◽  
Jenny Stocker ◽  
Ruth M. Doherty ◽  
Oliver Wild ◽  
Michael Hollaway ◽  
...  
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Urban Heat Island ◽  
Monitoring Network ◽  
Ambient Air ◽  
Traffic Emissions ◽  
Heat Island ◽  
Emissions Inventory ◽  
Measurement Campaign ◽  
Urban Heat

Abstract. We examine the street-scale variation of NOx, NO2, O3 and PM2.5 concentrations in Beijing during the Atmospheric Pollution and Human Health in a Chinese Megacity (APHH-China) winter measurement campaign in November–December 2016. Simulations are performed using the urban air pollution dispersion and chemistry model ADMS-Urban and an explicit network of road source emissions. Two versions of the gridded Multi-resolution Emission Inventory for China (MEIC v1.3) are used: the standard MEIC v1.3 emissions and an optimised version, both at 3 km resolution. We construct a new traffic emissions inventory by apportioning the transport sector onto a detailed spatial road map. Agreement between mean simulated and measured pollutant concentrations from Beijing's air quality monitoring network and the Institute of Atmospheric Physics (IAP) field site is improved when using the optimised emissions inventory. The inclusion of fast NOx–O3 chemistry and explicit traffic emissions enables the sharp concentration gradients adjacent to major roads to be resolved with the model. However, NO2 concentrations are overestimated close to roads, likely due to the assumption of uniform traffic activity across the study domain. Differences between measured and simulated diurnal NO2 cycles suggest that an additional evening NOx emission source, likely related to heavy-duty diesel trucks, is not fully accounted for in the emissions inventory. Overestimates in simulated early evening NO2 are reduced by delaying the formation of stable boundary layer conditions in the model to replicate Beijing's urban heat island. The simulated campaign period mean PM2.5 concentration range across the monitoring network (∼15 µg m−3) is much lower than the measured range (∼40 µg m−3). This is likely a consequence of insufficient PM2.5 emissions and spatial variability, neglect of explicit point sources, and assumption of a homogeneous background PM2.5 level. Sensitivity studies highlight that the use of explicit road source emissions, modified diurnal emission profiles, and inclusion of urban heat island effects permit closer agreement between simulated and measured NO2 concentrations. This work lays the foundations for future studies of human exposure to ambient air pollution across complex urban areas, with the APHH-China campaign measurements providing a valuable means of evaluating the impact of key processes on street-scale air quality.

Air Pollution Monitoring in Intelligent Cities Using Weighted Association Rule Mining

2021 ◽  
pp. 171-197
Author(s):  
Goksu Tuysuzoglu ◽  
Derya Birant
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Association Rules ◽  
Association Rule ◽  
Association Rule Mining ◽  
Experimental Studies ◽  
Rule Mining ◽  
Air Pollution Monitoring ◽  
Real World Datasets ◽  
Monitoring Stations

Through the use of internet of things-based sensors in air quality monitoring stations, concentration of different pollutants and meteorological parameters can be regularly measured. In case of unusual conditions (e.g., increased levels of dangerous pollutants), a smart assessment system can produce warning so that appropriate air quality management process can be initiated. In this context, the objective of this study is to discover relationships and patterns among air pollution features and characteristics. In this case, determination of frequently observed association rules can trigger an appropriate background smart environment system when a critical situation is detected. In the experimental studies in the current project, traditional association rule mining and weighted association rule mining methods have been employed using real-world datasets collected from 21 monitoring stations in Turkey. In consequence, useful and outstanding association rules exceeding the user-defined support and confidence levels were obtained that can form basis for further research.

scholarly journals One-year simulation of ozone and particulate matter in China using WRF/CMAQ modeling system

2016 ◽  
Vol 16 (16) ◽  
pp. 10333-10350 ◽  
Author(s):  
Jianlin Hu ◽  
Jianjun Chen ◽  
Qi Ying ◽  
Hongliang Zhang
Keyword(s):  
Air Pollution ◽  
Particulate Matter ◽  
Air Quality ◽  
Model Performance ◽  
Monitoring Network ◽  
Organic Aerosol ◽  
Quality Monitoring ◽  
Air Quality Monitoring ◽  
Low Concentration ◽  
Temporal And Spatial

Abstract. China has been experiencing severe air pollution in recent decades. Although an ambient air quality monitoring network for criteria pollutants has been constructed in over 100 cities since 2013 in China, the temporal and spatial characteristics of some important pollutants, such as particulate matter (PM) components, remain unknown, limiting further studies investigating potential air pollution control strategies to improve air quality and associating human health outcomes with air pollution exposure. In this study, a yearlong (2013) air quality simulation using the Weather Research and Forecasting (WRF) model and the Community Multi-scale Air Quality (CMAQ) model was conducted to provide detailed temporal and spatial information of ozone (O3), total PM2.5, and chemical components. Multi-resolution Emission Inventory for China (MEIC) was used for anthropogenic emissions and observation data obtained from the national air quality monitoring network were collected to validate model performance. The model successfully reproduces the O3 and PM2.5 concentrations at most cities for most months, with model performance statistics meeting the performance criteria. However, overprediction of O3 generally occurs at low concentration range while underprediction of PM2.5 happens at low concentration range in summer. Spatially, the model has better performance in southern China than in northern China, central China, and Sichuan Basin. Strong seasonal variations of PM2.5 exist and wind speed and direction play important roles in high PM2.5 events. Secondary components have more boarder distribution than primary components. Sulfate (SO42−), nitrate (NO3−), ammonium (NH4+), and primary organic aerosol (POA) are the most important PM2.5 components. All components have the highest concentrations in winter except secondary organic aerosol (SOA). This study proves the ability of the CMAQ model to reproduce severe air pollution in China, identifies the directions where improvements are needed, and provides information for human exposure to multiple pollutants for assessing health effects.

Time Series Analysis for Prediction of PM2.5 Using Seasonal Autoregressive Integrated Moving Average (SARIMA) Model on Taiwan Air Quality Monitoring Network Data

2020 ◽  
Vol 17 (9) ◽  
pp. 3964-3969
Author(s):  
Doreswamy ◽  
K. S. Harish Kumar ◽  
Ibrahim Gad
Keyword(s):  
Air Pollution ◽  
Particulate Matter ◽  
Air Quality ◽  
Moving Average ◽  
Monitoring Network ◽  
Quality Monitoring ◽  
Air Quality Monitoring ◽  
Data Set ◽  
Sarima Model ◽  
Autoregressive Integrated Moving Average

Nowadays, in Taiwan, due to the increasing number of vehicles, industrialization of large energy consumption, uncontrolled constructions and urbanization, air pollution is becoming a major problem. Hence, it is necessary to control air pollution by applying air quality monitoring actions. The particulate matter (PM2.5) of the air pollution in TAQMN data is the main pollutant accountable for at least two-thirds of the severely polluted days in the major cities of Taiwan. In this work, machine learning (ML) techniques are widely used in developing models that can be used to control the air pollution. Seasonal Autoregressive Integrated Moving Average (SARIMA) model is used to predict the air pollution concentration, where the dataset chronologically from 2012 to 2016 are used to train the proposed method and testing data set from 2016 to 2017. The result of the SARIMA model shows high precision in forecasting the future values of particulate matter (P2.5) level with minimum error.

Exploring performance of clustering methods on document sentiment analysis

2016 ◽  
Vol 43 (1) ◽  
pp. 54-74 ◽  
Author(s):  
Baojun Ma ◽  
Hua Yuan ◽  
Ye Wu
Keyword(s):  
Sentiment Analysis ◽  
Clustering Algorithm ◽  
Clustering Algorithms ◽  
Experimental Studies ◽  
Experimental Results ◽  
Clustering Methods ◽  
Term Weighting ◽  
Weighting Method ◽  
Clustering Techniques ◽  
Better Than

Clustering is a powerful unsupervised tool for sentiment analysis from text. However, the clustering results may be affected by any step of the clustering process, such as data pre-processing strategy, term weighting method in Vector Space Model and clustering algorithm. This paper presents the results of an experimental study of some common clustering techniques with respect to the task of sentiment analysis. Different from previous studies, in particular, we investigate the combination effects of these factors with a series of comprehensive experimental studies. The experimental results indicate that, first, the K-means-type clustering algorithms show clear advantages on balanced review datasets, while performing rather poorly on unbalanced datasets by considering clustering accuracy. Second, the comparatively newly designed weighting models are better than the traditional weighting models for sentiment clustering on both balanced and unbalanced datasets. Furthermore, adjective and adverb words extraction strategy can offer obvious improvements on clustering performance, while strategies of adopting stemming and stopword removal will bring negative influences on sentiment clustering. The experimental results would be valuable for both the study and usage of clustering methods in online review sentiment analysis.

Sign in / Sign up

Export Citation Format

Share Document