Real-time Air Quality Research Articles

Facile Synthesis of ZnO/WO3 Nanocomposite Porous Films for High-Performance Gas Sensing of Multiple VOCs.

Volatile organic compounds (VOCs) in indoor environments have typical features of multiple components, high concentration, and long duration. The development of gas sensors with high sensitivity to multiple VOCs is of great significance to protect human health. Herein, we proposed a sensitive ZnO/WO3 composite chemi-resistive sensor facilely fabricated via a sacrificial template approach. Based on the transferable properties of self-assembled monolayer colloidal crystal (MCC) templates, two-dimensional honeycomb-like ordered porous ZnO/WO3 sensing matrixes were constructed in situ on commercial ceramic tube substrates with curved and rough surfaces. The nanocomposite thin films are about 250 nm in thickness with large-scale structural consistency and integrity, which facilitates characteristic responses with highly sensitivity and reliability. Furthermore, the nanocomposite sensor shows simultaneous responses to multiple VOCs that commonly exist in daily life with an obvious suppression sensing for traditional flammable gases. Particularly, a detection limit of 0.1 ppm with a second-level response/recovery time can be achieved, which is beneficial for real-time air quality assessments. We proposed a heterojunction-induced sensing enhancement mechanism for the ZnO/WO3 nanocomposite film in which the formation of abundant heterojunctions between ZnO and WO3 NPs significantly increases the thickness of the electron depletion layer in the bulk film and improves the formation of active oxygen species on the surface, which is conducive to enhanced responses for reducing VOC gases. This work not only provides a simple approach for the fabrication of high-performance gas sensors but also opens an achievable avenue for air quality assessment based on VOC concentration detection.

Framework for implementing air quality monitoring system using LPWA-based IoT technique

More attention is being paid to air quality monitoring in today's society because of the rapid rise of industrial and transportation uses. Conventional air quality monitoring systems, on the other hand, are unable to provide real-time air quality data with acceptable spatial and temporal resolutions at a low cost. Using cutting-edge Internet-of-things (IoT) technology, we propose a unique approach to building an air quality monitoring system. A low-power wide area network transmits the data collected by portable sensors in real time. Any and all data pertaining to air quality are analysed and assessed through the Internet of Things (IoT). Cities around the country have successfully deployed an air quality monitoring system that combines both hardware and software. Results from the experiments show that the proposed method is capable of monitoring air quality accurately, exposing some of the patterns in air quality change.

Investigating Use of Low-Cost Sensors to Increase Accuracy and Equity of Real-Time Air Quality Information.

U.S. Environmental Protection Agency (EPA) air quality (AQ) monitors, the "gold standard" for measuring air pollutants, are sparsely positioned across the U.S. Low-cost sensors (LCS) are increasingly being used by the public to fill in the gaps in AQ monitoring; however, LCS are not as accurate as EPA monitors. In this work, we investigate factors impacting the differences between an individual's true (unobserved) exposure to air pollution and the exposure reported by their nearest AQ instrument (which could be either an LCS or an EPA monitor). We use simulations based on California data to explore different combinations of hypothetical LCS placement strategies (e.g., at schools or near major roads), for different numbers of LCS, with varying plausible amounts of LCS device measurement errors. We illustrate how real-time AQ reporting could be improved (or, in some cases, worsened) by using LCS, both for the population overall and for marginalized communities specifically. This work has implications for the integration of LCS into real-time AQ reporting platforms.

Smart Air Pollution Monitoring System

<p>Air is one of the most basic and important elements for human beings to survive. Clean and Sound air is the key to a good and healthy life. But nowadays in city life it has become the most threatening factor. Pollution of air has become the most concerning and affected issue now for us. As time goes, people are finding it very difficult to cope with the growing levels of air pollution. This proposed model aims to present a smart air pollution monitoring system that calculates and predicts the air quality in real time in the environment. The proposed system measures the concentration of air pollution causing gases in the environment using sensors. The acquired data is processed using Raspberry Pi and the collected information is stored in Firebase. With the help of the training data set, the air quality in forthcoming days can be predicted using the android application and a notification feature is included to indicate very severe pollution levels. The forecasting is done using the machine learning algorithms such as Linear Regression and Random Forest Regression with accuracy of 96.52% and 99.2% respectively.</p>

DESIGN AND EVALUATION OF A SMART INDOOR AIR QUALITY MONITORING SYSTEM

This paper presents the design and development of an intelligent air quality monitoring system that utilizes the widely adopted and versatile Arduino Uno microcontroller as its foundational platform. The system underwent comprehensive testing procedures to ensure its adherence to specified requirements. Moreover, a series of experiments were conducted in diverse areas of a residential environment to generate datasets for various air quality indicators. The research findings showcase the potential of the developed system in accurately monitoring and assessing indoor air quality in real time. Enhancing indoor air quality plays a crucial role in mitigating the transmission of common airborne viruses and pollutants, thus significantly benefiting respiratory health.

Development of Ambiance Air Recirculation Unit for Air Quality Monitoring in Lecture & Laboratory Rooms

This study focuses on the purification and monitoring of indoor air pollution aided with UV light radiation intended for laboratory and lecture rooms in Bataan Peninsula State University. The developed air recirculation prototype utilizes Arduino integrated development environment (IDE) software with two air quality sensors namely, BME680 and PMS5003, which send signals to relay to control the purification and monitoring operations. As a monitoring device, the prototype is capable of displaying real time air quality measurements as well as pollutant concentrations. The measured data control the purification process which activates only at acceptable range of indoor air quality (IAQ) allowing the prototype to conserve energy. Two approaches on monitoring accuracy were done with respect to the distance of prototype sensors to the air quality tester. While for the effectiveness of purification process, a five-minute recalibration speed on smoke tests were conducted. This study aimed to help in reducing the intake of harmful air on the human body that causes cardiovascular diseases, respiratory problems and even viruses, more particularly in indoor environments like laboratory and lecture rooms.

Design & development of a air pollution monitoring using smartphone

In this paper, the design & development of a Air Pollution Monitoring Using Smartphone is presented. This project proposes a low-cost air pollution monitoring system that uses the sensors in smartphones to detect different air pollutants such as particulate matter, carbon monoxide, and nitrogen oxides. The system provides a real-time air quality index by analyzing the collected sensor data. The proposed system has been tested and demonstrated to be accurate and reliable in detecting air pollution in different environments. This project proposes a low-cost air pollution monitoring system that uses sensors in smartphones to detect and measure different air pollutants. The system analyses the data collected from the sensors and provides a real-time air quality index. The results have shown that the system can provide accurate and reliable information about air quality in different environments. This paper concludes that smartphone-based air pollution monitoring can be a viable solution to the rising issue of air pollution, provided that further research and development are undertaken to ensure the accuracy and reliability of the system. Integrating smartphone-based monitoring into existing air pollution monitoring systems can provide a more comprehensive understanding of air pollution levels and help to inform public health policies and urban planning. The work done & presented in this paper is the result of the mini-project work that has been done by the first sem engineering students of the college and as such there is little novelty in it and the references are being taken from various sources from the internet, the paper is being written by the students to test their writing skills in the starting of their engineering career and also to test the presentation skills during their mini-project presentation. The work done & presented in this paper is the report of the assignment / alternate assessment tool as a part and parcel of the academic assignment of the first year subject on nanotechnology & IoT.

Evaluating the Performance of Low-cost PM Sensors over Multiple COALESCE Network Sites

Air quality is a global concern, with particulate matter receiving considerable attention due to its impact on human health and climate change. Recent advances in low-cost sensors allow their deployment in large number to measure spatio-temporal and real-time air quality data. Low-cost sensors need careful evaluation with both regulatory approved methods and other data sets to understand their efficacy. In this work, PM concentrations measured by deploying low-cost sensors at four regional sites are evaluated through comparison with satellite-based model MERRA-2 and the SASS reference instrument. Daily PM2.5 mass concentration variation was analyzed at four regional sites of India from January 2020 to July 2020, including pre-lockdown and six different lockdown periods. Higher PM2.5 concentration was observed at Rohtak (119 µg/m3) compared to Mahabaleshwar (33 µg/m3), Bhopal (45 µg/m3) and Kashmir sites during the pre-lock down period. During the lockdown period, the PM2.5 mass concentration was reduced significantly compared to the pre-lockdown period at every location, although the PM2.5 concentration was different at each location. The air quality trend was quite similar in both the measurements, however, MERRA-2 reconstructed PM2.5 was significantly lower in the pre-lockdown period compared to the lockdown periods. Significant differences were observed between low-cost sensor measurements and MERRA-2 reanalysis data. These are attributed to the MERRA-2 modelling analysis that measures less PM2.5 concentration as compared to ground-based measurements, whereas low-cost sensor are ground-based measurements but needs corrections as it is subject to the calibration dependencies and biases.

AIRO: Development of an Intelligent IoT-based Air Quality Monitoring Solution for Urban Areas

Air pollution is the contamination of the atmosphere by any biological, physical, or chemical means. Bengaluru, the Silicon Valley of India, has air pollution levels that exceed WHO standards. Its air has high PM10, PM2.5, SO2, NO2, and CO2 levels, exposing residents to an increased risk of respiratory diseases. AIRO, a decentralised IoT-based air quality monitoring solution, is proposed to calculate the (Air Quality Index) AQI in real-time and notify the users of dangerous AQI levels. Unlike the city's fixed air quality monitoring stations, this portable system can easily be integrated into everyday items for computing real-time air quality at any given place. The proposed solution is then validated using a physical prototype incorporated into a water bottle. Using the Intel Edison development platform, this prototype is equipped with a GPS module, Wi-Fi module, PMS5003, MQ131, MQ135, MQ136, MQ7 sensors, and an LCD Display. The prototype records the air quality indicators, calculates the AQI, and sends the data to the AWS Cloud Server. After an in-depth analysis of the cloud data, the daily and weekly AQI is predicted for multiple locations in the city. A hybrid CNN-Bi-LSTM model is proposed for predicting AQI, which needs to be evaluated at the city scale for dependable results. Finally, a smartphone app is developed using Android Studio and Python to monitor the air quality and notify the users. The users also have an option to select a location and get the real-time and predicted AQI. In the future, this hybrid deep-learning model can be extended to other cities using the transfer learning approach.

FVM-RANS Modeling of Air Pollutants Dispersion and Traffic Emission in Dhaka City on a Suburb Scale

The present study aims to investigate the impact of air pollutants dispersion from traffic emission under the influence of wind velocity and direction considering the seasonal cycle in two major areas of Dhaka city: namely, Tejgaon and Gazipur. Carbon monoxide (CO) mass fraction has been considered as a representative element of traffic-exhausted pollutants, and the distribution of pollutants has been investigated in five different street geometries: namely, single regular and irregular, double regular and irregular, and finally, multiple irregular streets. After the grid independence test confirmation as well as numerical validation, a series of case studies has been presented to analyze the air pollutants dispersion, which mostly exists due to the traffic emission. The popular Reynolds-averaged Navier–Stokes (RANS) approach has been considered, and the finite volume method (FVM) has been applied by ANSYS FluentTM. The k−ϵ turbulence model has been integrated from the RANS approach. It was found that the wind velocity as well as wind direction and the fluid flow fields can play a potential role on pollution dispersion in the Dhaka city street canyons and suburbs. Inhabitants residing near the single regular streets are exposed to more traffic emission than those of single irregular streets due to fewer obstacles being created by the buildings. Double regular streets have been found to be a better solution to disperse pollutants, but city dwellers in the east region of double irregular streets are exposed to a greater concentration of pollutants due to the change of wind directions and seasonal cycles. Multiple irregular streets limit the mobility of the pollutants due to the increased number of buildings, yet the inhabitants near the multi-irregular streets are likely to experience approximately 11.25% more pollutants than other dwellers living far from the main street. The key findings of this study will provide insights on improving the urbanization plan where different geometries of streets are present and city dwellers could have less exposure to traffic-exhausted pollutants. The case studies will also provide a template layout to map pollutant exposure to identify the alarming zone and stop incessant building construction within those regions by creating real-time air quality monitoring to safeguard public safety.

A modular IOT sensing platform using hybrid learning ability for air quality prediction

The world's underdeveloped countries, who have been affected the worst, are experiencing an increase in climatic issues. Today more than ever, the requirement for precise measurements and predictions of pollutants with low-cost installation is essential. Low-cost air quality sensors are susceptible to inaccurate readings, frequent outages, and erratic operating circumstances. To provide an efficient and adaptable calibration method in such a setting, a cautious approach is required. There are several commercially available monitoring options; a typical system uses particle sensor and gas to keep track of the air quality. These sensor values are compared to established criteria, and alerts are then generated when those thresholds are exceeded. An IoT node with many sensors for a few pollutants, including NH3, NO2, CO, and PM 2.5 as well as air humidity & the ambient temperature, is designed for this purpose. The Internet of Things node is installed inside a research facility to gather indoor air data for research purposes and proof of concept. The suggested system may use GSM/WiFi technology to transmit real-time air quality reports to a web site and web/mobile app, and it can also produce alarms when it notices abnormalities in the air quality. The platform is appropriate for Big Information analysis applications including weather forecasts, and traffic predictions since it can capture sensor readings as fast as one sample per second. Normalized to the average CO, O3, and NO2 sensor readings and association of sensor information are optimal in range. The goal of the study is to advance the field of distributed, low-cost sensing devices for environment intelligence applications.

Correction and Accuracy of PurpleAir PM2.5 Measurements for Extreme Wildfire Smoke.

PurpleAir particulate matter (PM) sensors are increasingly used in the United States and other countries for real-time air quality information, particularly during wildfire smoke episodes. Uncorrected PurpleAir data can be biased and may exhibit a nonlinear response at extreme smoke concentrations (>300 µg/m3). This bias and nonlinearity result in a disagreement with the traditional ambient monitoring network, leading to the public’s confusion during smoke episodes. These sensors must be evaluated during smoke-impacted times and then corrected for bias, to ensure that accurate data are reported. The nearby public PurpleAir sensor and monitor pairs were identified during the summer of 2020 and were used to supplement the data from collocated pairs to develop an extended U.S.-wide correction for high concentrations. We evaluated several correction schemes to identify an optimal correction, using the previously developed U.S.-wide correction, up to 300 µg/m3, transitioning to a quadradic fit above 400 µg/m3. The correction reduces the bias at each air quality index (AQI) breakpoint; most ambient collocations that were studied met the Environmental Protection Agency’s (EPA) performance targets (twelve of the thirteen ambient sensors met the EPA’s targets) and some smoke-impacted sites (5 out of 15 met the EPA’s performance targets in terms of the 1-h averages). This correction can also be used to improve the comparability of PurpleAir sensor data with regulatory-grade monitors when they are collectively analyzed or shown together on public information websites; the methods developed in this paper can also be used to correct future air-sensor types. The PurpleAir network is already filling in spatial and temporal gaps in the regulatory monitoring network and providing valuable air-quality information during smoke episodes.

PLUME Dashboard: A free and open-source mobile air quality monitoring dashboard

The deployment of a mobile air quality monitoring laboratory requires advanced real-time instrument monitoring and data management software, which can be prohibitively expensive. In this work we present the PLUME Dashboard: a software package built in Python designed specifically for mobile air quality monitoring purposes. It aims to provide a free and open-source alternative to comparable commercial packages, thus reducing the barrier to entry of conducting such research. This paper outlines the development of the PLUME Dashboard and justifies the design choices that were made while also providing thorough documentation and explanation for how the software works. Functionality includes real-time data display, real-time peak identification, baseline subtraction, real-time air quality and self-sampling alerts (based on wind direction and vehicle speed), and post-processing tools such as peak identification and map merging with GPS data. The functionality of PLUME Dashboard is tested using real-world data collected in Toronto and Vancouver Canada.

IoT monitoring system for air quality assessment and collecting data

The composition of the air has been visibly altered as a result of human activity, resulting in what we term air pollution. It is no longer necessary to prove the effects on ecosystems and human health. Under these conditions, governments all around the world are working to address this issue, notably in the area of real-time air quality monitoring. The implementation of a data provider is a necessary step in achieving this goal. In that case, this study presents a hardware and software solution to provide a low-cost deployable device to acquire environmental data related to AP such as CO, CO<sub>2</sub>, NH<sub>3</sub>, and NO<sub>2</sub>, along with temperature and humidity. In addition to an user interface development, a complete circuit layout and a set of software criteria are set up to ensure a reliable implementation, data collection, and network communications. The results demonstrated that the device is capable of effectively obtaining real-time data. The analysis results indicate a link between environmental conditions and parameter values. This system deployment will ultimately contribute to providing a more elaborate mapped data distribution, according to a better understanding of our environment.<br /><br />

A PEER-TO-PEER AIR QUALITY MONITORING SYSTEM USING IOT SENSORS AND CLOUD PLATFORMS

This paper presents the design and implementation of an air quality monitoring system that combines Internet of Things (IoT) sensors, cloud computing platforms, and peer-to-peer (P2P) networking. The system uses IoT sensors to collect real-time air quality data from multiple geographic areas. This data is sent to cloud platforms, including AWS IoT Core, for processing and storage. A P2P network of servers, with each server responsible for a specific area, enables distributed access to the air quality data. The system also incorporates machine learning models deployed on the Google Cloud Platform to provide air quality predictions. The proposed architecture for wide-area air quality monitoring is feasible and scalable based on experimental results.

Public health in Global South: effect of environmental pollutant PM2.5 on the incidence and mortality of SARS-CoV-2 in Karachi, Lahore, and Islamabad.

Environmental pollution has undoubtedly been established as a planetary, intergenerational, and existential threat to global human health and safety. Environmental pollution is adversely affecting the world, mainly the countries where human health is not a priority aspect, and this has been exacerbated due to the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2), and pandemic is known as "COVID pandemic". This study investigates the association of environmental pollutants, particulate matter (PM2.5), with SARS-CoV-2 daily cases and deaths in Karachi, Lahore, and Islamabad, Pakistan, presenting the perspectives from the Global South. The day-to-day PM2.5 levels were recorded from the metrological website, Real-Time Air Quality Index-AQI. The corresponding data on the COVID cases and deaths in Karachi, Lahore, and Islamabad were obtained from August 1, 2020, to September 30, 2021, from the Health Ministry and National Command Operations Centre Pakistan. The mean values for PM2.5 in Karachi were 110.4±46.2; in Lahore 174.0±83.2; and in Islamabad 107.1±40.0. The COVID-19 mean daily cases in Karachi were 538.9±446.6; Lahore 398.3±403.1; and Islamabad 212.2±187.6; and mean daily deaths in Karachi were 9.2±8.3; Lahore 9.3±9.7; and Islamabad 1.8±1.8. The results further depicted that the SARS-CoV-2 cases were 2.86 times higher in Karachi and 1.4 times higher in Lahore than in Islamabad. Similarly, the SARS-CoV-2 deaths were 3.6 and 2.8 times higher in Karachi and Lahore, respectively, compared to Islamabad. The findings claim that cases and deaths augmented significantly along with PM2.5 levels. These empirical estimates demonstrate an association between PM2.5 and SARS-CoV-2 daily cases and deaths in the cities of the Global South. These findings can contribute to policy-making decisions about addressing air pollutants and climate concerns in developing countries and create an urgency to develop a strategy for minimizing environmental pollution. This study can also steer the actions needed to address the environmental problems in developing countries to improve public health and safety.

INVESTIGATING THE ANNUAL ATMOSPHERIC POLLUTION AND ITS ANALYSIS

In the new global health report, air pollution has been regarded as one of the leading causes of deadly diseases in both rural and urban area. The major causes of Air Pollution are the particulate matters (PM). Several researches have been carried out on air quality and concentration of PM in different states of Nigeria. So far, however, there has been little discussion about the annual concentration of particulate matters (PM) in Nigeria. The aim of this paper is to analyze the annual concentration of PM from January2021 – December2021 in some states in Nigeria using real-time air quality data obtained from PurpleAir.com. Results obtained from this study have shown that the annual concentration of PM2.5 in the study locations in Abuja, Kogi, Edo and Port Harcourt is greater than 20 µg/m3 which is beyond the annual Air quality standards regulation while for PM10.0, Abuja and Port Harcourt exceeded 40µg/m3 (recommended value for PM10.0) and therefore can be said to be highly polluted

Impact of environmental pollutants Particulate Matter PM2.5, carbon monoxide, nitrogen dioxide and ozone on the incidence of Monkeypox cases. [corrected

The human monkeypox disease (MPXD), is an emerging zoonotic disease caused by the monkeypox virus. The rapid spread of human monkeypox cases has developed an alarming situation worldwide. This study evaluated the impact of day-to-day air pollutants, particulate matter PM2.5, Carbon monoxide (CO), Nitrogen dioxide (NO2), and Ozone (O3) on the daily incidence of monkeypox cases in New York City, United States of America. The daily data on air pollutants and monkeypox cases were recorded from May 1, 2022, to August 16, 2022. The everyday concentrations of "PM2.5, CO, NO2, and O3 were recorded from the metrological website "Real-Time Air Quality Index-AQI" and human monkeypox cases were documented from the official website of "NVC Health". The mean values along with correlations were performed to investigate the impact of environmental pollutants on the occurrence of monkeypox cases in New York, city USA. The mean value for the concentration of CO in the air was 25.61 ppm, NO2 38.16 ppm, O3 9.46 μg/m3 and PM2.5 was 1.82 ppm. The air pollutants, CO, and NO2 have a positive association (p=0.001) with daily monkeypox cases in New York, USA. The correlation analysis showed significant relationships between CO and NO2 and the number of monkeypox cases (r=0.298, p<0.002), (r=0.513, p<0.001), respectively. The linear regression analysis also showed that CO has a positive impact on monkeypox cases (β=0.298, p<0.001). With one unit increase in the CO levels in the air, the number of monkeypox cases increased by 0.298 units, and adjusted R-square shows a 0.08 or 8% variation in the number of monkeypox cases due to an increase in CO in the environment. Moreover, NO2 has a significant positive impact on monkeypox cases (β=0.513, p<0.001), with a one-unit increase in NO2 concentration in the air, the monkeypox cases increased by 0.513. The adjusted R-square shows that NO2 causes a 25.7% variation in the increase in monkeypox cases. However, Ozone (β=0.018. p>0.05) and PM2.5 (β=-0.122, p>0.05) does not have a significant correlation with monkeypox cases in the city of New York. Environmental pollutants NO2 and CO have a positive relationship with the number of daily monkeypox cases in New York City, USA. The air pollutants which have a high concentration in the environment have a strong relationship with the occurrence of monkeypox cases. Environmental pollution may be a risk factor for the increasing occurrence of monkeypox cases. Health officials must take priority preventive measures to curtail environmental pollution to combat the monkeypox disease.

Fast and operational gap filling in satellite-derived aerosol optical depths using statistical techniques

Satellite observations, used worldwide in the atmospheric sciences, are extremely useful for providing aerosol information within a wide spatial range. However, the coverage of aerosol data by satellite observations is sometimes of inferior quality because of the effects of surface reflectivity and clouds. To fill the gaps in aerosol optical depths (AODs) retrieved from geostationary ocean color imager observations, this study applies operational statistical techniques, including radial basis functions (RBFs) with four different weightings (i.e., linear, multiquadric, thin-plate, and inverse), Poisson, and ordinary Kriging. Based on computation time and accuracy of the individual gap-filling techniques, Poisson and the liner RBF are selected as the two best methods and then averaged with weights using one-dimensional weighted average (1D-WAVG) and two-dimensional weighted average (2D-WAVG) root mean square errors. All methods produce reliable results, yielding a correlation coefficient between 0.74 and 0.87 over the entire research domain. Out of the individual techniques, the Poisson, with an initial estimation from a zonal mean of AODs, is the most accurate with the lowest computational costs, even for a large number of missing pixels and most regions, excluding East China (EC). The Poisson’s high bias over EC is compensated in 1D- and 2D-WAVGs by taking more accurate estimations of the linear RBF than those of the Poisson over the region. If we consider 1D- and 2D-WAVGs in our analysis, the highest correlation is obtained from the 2D-WAVG over all regions. Because of its reliability and fast computation time, applying the 2D-WAVG can be a good solution to provide spatial–temporal continuous aerosol information. In addition to air pollution studies, such as real-time air quality predictions, estimation of ground-level particulate matter concentrations, and other applications, the fast and operational gap-filling technique can also be expanded to remote sensing data obtained from satellite observations to provide helpful and useful information for the public.

Optimal architecture artificial neural network model design with exploitative alpha gray wolf optimization for soft calibration of CO concentration measurements in electronic nose applications

The low-cost and small size solid-state sensor arrays are suitable to implement a wide-area electronic nose (e-nose) for real-time air quality monitoring. However, accuracy of these low-cost sensors is not adequate for precise measurements of pollutant concentrations. Artificial neural network (ANN) estimation models are used for the soft calibration of low-cost sensor array measurements and significantly improve the accuracy of low-cost multi-sensor measurements. However, optimality of neural architecture affects the performance of ANN estimation models, and optimization of the ANN architecture for a training data set is essential to improve data-driven modeling performance of ANNs to reach optimal neural complexity and improved generalization. In this study, an optimal architecture ANN estimator design scheme is suggested to improve the estimation performance of ANN models for e-nose applications. To this end, a gray wolf optimization (GWO) algorithm is modified, and an exploitative alpha gray wolf optimization (EA-GWO) algorithm is suggested. This modification enhances local exploitation skill of the best alpha gray wolf search agent, and thus allows the fine-tuning of ANN architectures by minimizing a multi-objective cost function that implements mean error search policy. Experimental study demonstrates the effectiveness of optimal architecture ANN models to estimate CO concentration from the low-cost multi-sensor data.