GRAPH NEURAL NETWORK-ENHANCED CMOS-BASED LOW-COST AIR POLLUTION MONITORING FOR SCALABLE ENVIRONMENTAL SENSING SYSTEMS

Air pollution in urban areas is a huge concern that demands an efficient air quality control to ensure health quality standards. The hotspots can be located by increasing spatial distribution of ambient air quality monitoring for which the low-cost sensors can be used. However, it is well-known that many factors influence their results. For low-cost Particulate Matter (PM) sensors, high relative humidity can have a significant impact on data quality. In order to eliminate or reduce the impact of high relative humidity on the results obtained from low-cost PM sensors, a low-cost dryer was developed and its effectiveness was investigated. For this purpose, a test chamber was designed, and low-cost PM sensors as well as professional reference devices were installed. A vaporizer regulated the humid conditions in the test chamber. The low-cost dryer heated the sample air with a manually adjustable intensity depending on the voltage. Different voltages were tested to find the optimum one with least energy consumption and maximum drying efficiency. The low-cost PM sensors with and without the low-cost dryer were compared. The experimental results verified that using the low-cost dryer reduced the influence of relative humidity on the low-cost PM sensor results.

Many low-cost particle sensors are available for routine air quality monitoring of PM2.5, but there are concerns about the accuracy and precision of the reported data, particularly in humid conditions. The objectives of this study are to evaluate the Sensirion SPS30 particulate matter (PM) sensor against regulatory methods for measurement of real-time particulate matter concentrations and to evaluate the effectiveness of the Intelligent AirTM sensor pack for remote deployment and monitoring. To achieve this, we co-located the Intelligent AirTM sensor pack, developed at Clemson University and built around the Sensirion SPS30, to collect data from July 29, 2019, to December 12, 2019, at a regulatory site in Columbia, South Carolina. When compared to the Federal Equivalent Methods, the SPS30 showed an average bias adjusted R2 = 0.75, mean bias error of −1.59, and a root mean square error of 2.10 for 24-hour average trimmed measurements over 93 days, and R2 = 0.57, mean bias error of −1.61, and a root mean square error of 3.029, for 1-hr average trimmed measurements over 2300 hours when the central 99% of data was retained with a data completeness of 75% or greater. The Intelligent AirTM sensor pack is designed to promote long-term deployment and includes a solar panel and battery backup, protection from the elements, and the ability to upload data via a cellular network. Overall, we conclude that the SPS30 PM sensor and the Intelligent AirTM sensor pack have the potential for greatly increasing the spatial density of particulate matter measurements, but more work is needed to understand and calibrate sensor measurements. Implications: This work adds to the growing body of research that indicates that low-cost sensors of particulate matter (PM) for air quality monitoring has a promising future, and yet much work is left to be done. This work shows that the level of data processing and filtering effects how the low-cost sensors compare to existing federal reference and equivalence methods: more data filtering at low PM levels worsens the data comparison, while longer time averaging improves the measurement comparisons. Improvements must be made to how we handle, calibrate, and correct PM data from low-cost sensors before the data can be reliably used for air quality monitoring and attainment.

These data were collected during a study on the performance of low-cost particulate matter (PM) sensors. All data were collected in an indoor laboratory at Colorado State University in Fort Collins, Colorado, USA between 2019-07-02 and 2019-10-06. The files associated with this dataset include: (1) time-averaged PM mass concentrations reported by the low-cost sensors during each steady-state test point included in the study, (2) time-averaged particle number concentrations reported by the low-cost sensors during each steady-state test point included in the study, (3) time-averaged particle size distribution data measured using an Scanning Mobility Particle Sizer (SMPS) during each steady-state test point included in the study, (4) time-averaged particle size distribution data measured using an Aerodynamic Particle Sizer (APS) Spectrometer during each steady-state test point included in the study, (5) real-time particle size distribution data measured using an APS during an experiment in which the low-cost sensors were exposed to very high Arizona road dust concentrations for 18 hours, (6) PM2.5 concentrations recorded at one-minute intervals by a Tapered Element Oscillating Microbalance (TEOM) during all experiments conducted during the study, (7) PM concentrations recorded at one-minute intervals by a DustTrak during an experiment in which the low-cost sensors were exposed to very high Arizona road dust concentrations for 18 hours, (8) data associated with all gravimetric filter samples of PM collected during the study, (9) real-time data recorded by the low-cost PM sensors during an experiment in which the sensors were exposed to very high Arizona road dust concentrations for 18 hours, (10) all of the raw data recorded by the low-cost PM sensors during the study, and (11) all of the raw data recorded by a DustTrak DRX 8533 during the study.

Abstract. With the continuous progress of science and technology, 3D imaging technology has been widely used in many fields, such as medical imaging, virtual reality and protection of cultural heritage. It can provide more information than traditional 2D images, greatly improving the accuracy and reliability of various applications. CMOS (Complementary Metal Oxide Semiconductor) sensors, as efficient and low-cost image sensors, have been widely used in image imaging and processing technologies in recent years. However, how to realize real-time and high-precision 3D imaging with CMOS sensors is still a technical challenge to be solved. Based on this background, this paper will focus on real-time 3D imaging techniques based on CMOS sensors through three topics. This paper will first introduce how CMOS sensors work, followed by the introduction of real-time 3D imaging technology, and finally the real-time 3D imaging technology based on CMOS sensors. The research in this paper will be valuable for the research and application of real-time 3D imaging technology based on CMOS sensors.

Background: The air quality of any area depends upon the various PMs (particulate matter) and hazardous gases present in the air. Low-cost PM sensors and gas sensors are present in different target places to monitor the air quality, read the environmental data, and transmit it to local servers through the IoT device. The low-cost sensor is not reliable due to its low sensing capacity; therefore, the read data is calibrated with the meteorological data presented by the nearby meteorological Centre of that particular area. The calibrated reading data sent to the server could be analyzed through some Machine Learning [ML] models. The ML models help to predict the risk of asthma in a particular area. The risk of asthma is directly related to the air quality of the surroundings. It is observed that the air quality of the industrial area is much worse than the non-industrial belt. Air quality monitoring of industrial areas is always a challenging task due to the ununiformed pollution in some segregated places around the industry, emitting pollutants mostly from chimneys. The air quality of any area depends upon the PM (PM), i.e., PM2.5 and PM10.0, as well as the gasses like NO2(Nitrogen Dioxide), NH3 (Ammonia), SO2(Sulfur dioxide), CO(Carbon monoxide), O3(Ozone) and Benzene. These are the most hazardous gases generally emitted by common heavy industries like iron and steel. In this article, the researchers considered the industrial belt of the Asansol- Durgapur region of West Bengal, India, and predicted the risk of asthma attacks for the test dataset. The experiment was carried out on 10 different supervised machine learning [SML] models as well as semi-supervised machine learning (SSML) models. The SML models have been further refined through hyper-parameter tuning, and better results have been obtained in the case of some ML models. The result has been compared with the existing literature considering the same external environment from where the meteorological data was collected, and similar ML models have been used. The research outperformed the existing literature, which is depicted in the result and analysis section of the article. Methods: The study evaluated ML models, both supervised and semi-supervised, to assess pollution levels. Relevant features were selected while less relevant ones were discarded. Accuracy levels of different ML algorithms werecompared in the results. The most effective model for an IoT system was chosen to maximize accuracy. In semi-supervised learning, feature selection followed supervised learning, but testing was akin to unsupervised learning. Results were compared with supervised learning data, enhancing reliability. Results: The result employing various classifiers werepresented across tables after the independent parameter Ozone was removed. Following the output of several classifiers, the results were verified using the k-fold validation method, with k being set to 5 or 10, accordingly. Tables display the best outcome, which is indicated in bold characters. method: In this research work the researcher considered 9 different ML models and used them as supervised as well as semi supervised model to determine the pollution level of the certain area. In this research work the researcher also selected the most relevant features and discarded the less relevant features. In case of SML algorithm, the accuracy level of the different ML algorithm has been determined and depicted in the result analysis section. The most effective ML model has been chosen for the proposed embedded system so that accuracy could be achieved at most. In case of semi supervised algorithm the feature selection is done as per the supervised algorithm. In this case the training is done same as the SML algorithm, but the testing phase is done like unsupervised machine learning algorithm where the decision parameter is predicted and ultimately matched with the previously achieved data of SML algorithm. The reliability of this approach is much more effective than simple SML algorithm. Conclusion: This study focused on predicting asthma risk in the Asansol-Durgapur industrial belt, India, using low-cost PM and gas sensors. Data calibration with meteorological inputs enhanced accuracy. ML models predicted risk and were refined through hyper-parameter tuning. Comparative analysis showed superior performance, emphasizing the importance of precise air quality monitoring. While offering a robust framework for future research, the study’s limitation lies in its area-specific dataset.

Recent advances in wireless communication technology and the Internet of Things (IoT) have provided an opportunity for mass deployment of low cost sensor nodes to measure air pollution in real-time over a large geographical area. This article presents the design of a low cost, innovative Air Pollution Monitoring Device (APMD) along with the evaluation of its advanced features. An on-board Particulate Matter (PM) sensor is designed to measure PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> and PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">10</sub> . APMD additionally has electrochemical sensors to measure carbon monoxide, sulphur dioxide, nitrogen dioxide, ozone, besides temperature and humidity sensors. The node is equipped with a solar energy harvesting unit and a rechargeable battery as a backup to power up the module. By utilizing an on-board GPS subsystem, APMD packs all these gathered air quality data in a frame with physical location, time, and date, and sends them to a cloud server. The node can communicate through WiFi and NB-IoT connectivity. For validating the quality of sensing, the developed APMD was co-located with an accurate reference sensor node and a series of field data were collected over seven days. In a fully ON state, the on-board PM sensor saves up to 94% energy while maintaining root mean square error (RMSE) of 0.58 for PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> and 2.5 for PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">10</sub> . A power control mechanism is also applied on the PM sensor to control the speed of the fan by applying a pulse width modulated (PWM) signal at the switch connected to the power supply of fan. At 100 ms switching period with 30% duty cycle, the on-board PM sensor is 97% energy efficient compared to the commercial sensor, while maintaining sensing error (RMSE) as low as 0.7 for PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> and 2.7 for PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">10</sub> . Our outdoor deployment studies demonstrate that the designed APMD is 90.8% more power efficient than the reference setup with significantly higher coverage range, while maintaining an acceptable range of sensing error.

Exposure Monitoring Strategies for Applying Low-Cost PM Sensors to Assess Flour Dust in Industrial Bakeries.

Attention has been paid to low-cost, light-scattering-based particulate matter (PM) sensors, which provide PM measurements in order to supplement a small number of expensive air quality monitoring stations. However, low-cost PM sensors produce measurement data of questionable quality. In this paper, we evaluate the performance of low-cost PM sensors, specifically PurpleAir PA-II units. To evaluate the PurpleAir PA-II units, we use accurate air quality data measured from monitoring stations within close proximity to the PA-II units as reference. By means of linear regression, we compare PurpleAir PA-II units with air quality monitors. From the result, PurpleAir PA-II units have high correlations (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ≥ 0.84) with nephelometers, which are based on the principle of light-scattering, and thus the PurpleAir PA-II is a sufficient substitute for nephelometers. PurpleAir PA-II units have a good agreement (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.72 and 0.89) with MetOne BAM 1020 monitors based on beta ray attenuation but show a non-linear behavior. Furthermore, there is an essential observation that the PurpleAir PA-II unit needs to have significantly high precision in order to have a high correlation with an expensive reference monitor and thus be used supplementally. The considered PurpleAir PA-II units overestimate PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> concentrations compared with air quality reference monitors. Therefore, a calibration algorithm for PurpleAir PA-II units should be considered to give a correct air quality index at sites considered in this paper. However, our results show the PurpleAir PA-II to be a promising low-cost air quality sensor for supplementing a conventional air quality sensing network with expensive monitors.

PM sensors as an indicator of overall air quality: Pre-COVID and COVID periods

A land use regression model using machine learning and locally developed low cost particulate matter sensors in Uganda

Low-cost light scattering particulate matter (PM) sensors have been widely researched and deployed in order to overcome the limitations of low spatio-temporal resolution of government-operated beta attenuation monitor (BAM). However, the accuracy of low-cost sensors has been questioned, thus impeding their wide adoption in practice. To evaluate the accuracy of low-cost PM sensors in the field, a multi-sensor platform has been developed and co-located with BAM in Dongjak-gu, Seoul, Korea from 15 January 2019 to 4 September 2019. In this paper, a sample variation of low-cost sensors has been analyzed while using three commercial low-cost PM sensors. Influences on PM sensor by environmental conditions, such as humidity, temperature, and ambient light, have also been described. Based on this information, we developed a novel combined calibration algorithm, which selectively applies multiple calibration models and statistically reduces residuals, while using a prebuilt parameter lookup table where each cell records statistical parameters of each calibration model at current input parameters. As our proposed framework significantly improves the accuracy of the low-cost PM sensors (e.g., RMSE: 23.94 → 4.70 g/m) and increases the correlation (e.g., R: 0.41 → 0.89), this calibration model can be transferred to all sensor nodes through the sensor network.

Particulates from diesel generator operation are a known air pollutant with adverse health effects. In this study, we used low-cost particulate matter (PM) sensors to monitor PM2.5 in a diesel generator plant. We compared the measurement results from a PM sensor and a reference instrument (DustTrak), and we found a high correlation between them. The data overestimation or underestimation of PM sensors implied the need for data calibration. Hence, we proposed a data calibration algorithm based on a nonlinear support vector machines(SVM )model, and we investigated the effect of three calibration factors on the model: humidity, temperature, and total volatile organic compounds (TVOC). It was found that the TVOC correction coefficient has great influence on the model, which should be considered when calibrating the low-cost PM sensor in diesel generator operation sites. A monitoring network with six low-cost sensors was installed in the diesel generator plant to monitor PM2.5 concentration. It was found that normal diesel generator work, diesel generator set handling work, and human activity are the most dominant ways of producing particulate matter at the site, and dispersion is the main cause of increased PM2.5 concentrations in nonworking areas. In this study, PM2.5 emissions from two different diesel generators were tested, and PM2.5 concentrations at monitoring points reached 220 μg/m3 and 120 μg/m3, respectively. This further confirms that diesel generators produce many respirable particles when working.

Integrating low-cost air quality sensor networks with fixed and satellite monitoring systems to study ground-level PM2.5

Numerical and experimental investigation on the performance of a ventilated chamber for low-cost PM sensor calibration

Abstract. Particle sensing technology has shown great potential for monitoring particulate matter (PM) with very few temporal and spatial restrictions because of its low cost, compact size, and easy operation. However, the performance of low-cost sensors for PM monitoring in ambient conditions has not been thoroughly evaluated. Monitoring results by low-cost sensors are often questionable. In this study, a low-cost fine particle monitor (Plantower PMS 5003) was colocated with a reference instrument, the Synchronized Hybrid Ambient Real-time Particulate (SHARP) monitor, at the Calgary Varsity air monitoring station from December 2018 to April 2019. The study evaluated the performance of this low-cost PM sensor in ambient conditions and calibrated its readings using simple linear regression (SLR), multiple linear regression (MLR), and two more powerful machine-learning algorithms using random search techniques for the best model architectures. The two machine-learning algorithms are XGBoost and a feedforward neural network (NN). Field evaluation showed that the Pearson correlation (r) between the low-cost sensor and the SHARP instrument was 0.78. The Fligner and Killeen (F–K) test indicated a statistically significant difference between the variances of the PM2.5 values by the low-cost sensor and the SHARP instrument. Large overestimations by the low-cost sensor before calibration were observed in the field and were believed to be caused by the variation of ambient relative humidity. The root mean square error (RMSE) was 9.93 when comparing the low-cost sensor with the SHARP instrument. The calibration by the feedforward NN had the smallest RMSE of 3.91 in the test dataset compared to the calibrations by SLR (4.91), MLR (4.65), and XGBoost (4.19). After calibrations, the F–K test using the test dataset showed that the variances of the PM2.5 values by the NN, XGBoost, and the reference method were not statistically significantly different. From this study, we conclude that a feedforward NN is a promising method to address the poor performance of low-cost sensors for PM2.5 monitoring. In addition, the random search method for hyperparameters was demonstrated to be an efficient approach for selecting the best model structure.