Wearable Low-Cost and Low-Energy Consumption Gas Sensor with Machine Learning to Recognise Outdoor Areas

Aug 4, 2026

Upload by Riley

Urban air pollution from human activity degrades air quality and directly affects health, creating the need for continuous monitoring. MQ gas sensors are attractive for their low cost but consume substantial energy, so machine learning is used to distinguish air types. The proposed solution combines edge and fog computing with a single MQ sensor: edge extracts features in the node, while fog-classification runs on a smartphone. Sensor and buffer configurations are compared, reaching 100% accuracy with MQ2 and 45–60 measurements. Energy for data collection drops to 25%, and data forwarding energy decreases by about 97% through buffering.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Introduction

Motivation and health impact

Limitations of existing monitoring solutions

Role of gas sensors

System approach and evaluation (as described in abstract)

Low-cost single-sensor architecture with edge and fog computing

Feature extraction and classification pipeline

Sensor and time buffer comparisons

Reported accuracy and energy savings

This article has been accepted for publication in IEEE Sensors Journal. This is the author's version which has not been fully edited and content may change prior to final publication. Citation information: DOI 10. 1109/JSEN.2024.3442874 IEEE SENSORS JOURNAL, VOL. XX, NO. XX, MONTH X , XXXX 1 Wearable Low-Cost and Low-Energy Consumption Gas Sensor with Machine Learning to Recognise Outdoor Areas Jianchen Wang , Lorena Parra, Raquel Lacuesta, Jaime Lloret, IEEE Senior Member, Pascal Lorenz, IEEE Senior Member Abstract— Urban air quality, impacted by human-made pollution, impacts health and requires continuous monitoring. MQ sensors are the preferred air quality sensors despite their high energy consumption due to their cost, requiring the use machine learning to classify different types of air. The aim of this paper is to evaluate a monitoring solution with low-cost and lowenergy consumption to classify urban and rural air. A single MQ sensor will be used with a network with edge and fog computing to balance the energy consumption. Edge computing was included in the node for feature extraction, and fog computing was applied in the smartphone to classify the data using machine learning. Different sensors and time buffers are compared in order to find the adequate sensor for data generation and time buffer for feature extraction. The results indicate that it has been possible to achieve accuracies of 100% using a single sensor, the MQ2, with time buffers of 45 to 60 measures. With this proposal, it is possible to reduce the energy consumed by data gathering to 25% of the original consumption due to the use of a single sensor, thanks to the reduction in the sensors used in the previous prototype. Moreover, it has been possible to reduce the energy linked to data forwarding by almost 97 % due to using a time buffer. Index Terms—Air pollution; MQ sensor; Edge Computing; Fog Computing; Urban area; Rural area. I. INTRODUCTION AIR quality is pollution, and in strongly affected by anthropogenic the last decades, the air quality in the cities due to traffic has become a health issue [1] . Several countries are boosting policies to regulate the use of vehicles in the inner parts of the cities to reduce pollution and restore urban air quality. Besides traffic, the industry is another important component in air pollution sources [2] . Meteorological conditions might play a positive or negative Manuscript received March 5 , 2024; accepted month day, year. Date of publication month day, year. This was partially supported by by the Spanish Science and Innovation Ministry through the contract PID2022-136779OB-C31 and by “Conselleria de Educación, Universidades y Empleo” through the “Subvenciones para estancias de personal investigador doctor en c entros de investigación radicados fuera de la Comunitat Valenciana (Convocatoria 2023)” Grant number CIBEST/2022/40 . Lorena Parra, and Jaime Lloret was with Instituto de Investigación para la Gestión Integrada de Zonas Costeras, Universitat Politècnica de València, C/ Paranimf, 1, 46730 Grao de Gandia, Gandia, Valencia, Spain. (e-mail: [svictud@upv.es](svictud@upv.es) , [loparbo@doctor.upv.es](loparbo@doctor.upv.es) , [jlloret@dcom.upv.es](jlloret@dcom.upv.es)) . Raquel Lacuesta y Jianchen Wang was with Department of Computer Science and Engineering of Systems, University of Zaragoza, 50009, Zaragoza, Spain. (e-mail: [802610@unizar.es](802610@unizar.es) , lacuesta@unizar.es) . Pascal Lorenz was with 2Network and Telecommunication Research Group, University of Haute Alsace, 34 rue du Grillenbreit, 68008 Colmar, France (e-mail [lorenz@ieee.org](lorenz@ieee.org)) role in air quality according to multiple factors [3] . Air quality has a direct impact on human health [4], and therefore, it should be monitored in particular cases. Some of these cases include people with diseases or those in highpopulation-density areas. In comparison with rural areas, urban areas usua

FAQs

Why are wearable gas sensors needed for air quality monitoring?

Urban air pollution affects human health and requires continuous monitoring. Wearable sensing enables ongoing measurement in different outdoor conditions.

How does the proposed system reduce energy consumption while using an MQ gas sensor?

A single MQ sensor is combined with edge and fog computing. Edge performs feature extraction at the node, and buffering reduces energy for data forwarding, leading to about 25% collection energy and nearly 97% forwarding energy reduction.

What results are reported for classification accuracy and time buffer settings?

The approach achieves 100% accuracy using a single MQ2 sensor with time buffers of 45 to 60 measurements.

Aug 4, 2026

Upload by Riley