Mid Sweden University

miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Deep Learning Approach for Classification and Measurement of Hazardous Gases Using Multi-Sensor Data Fusion
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). (STC)ORCID iD: 0000-0002-8776-2985
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). (STC)
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). (STC)
Mid Sweden University, Faculty of Science, Technology and Media, Department of Engineering, Mathematics, and Science Education (2023-).
Show others and affiliations
2023 (English)In: 2023 IEEE Sensors Applications Symposium (SAS), IEEE conference proceedings, 2023, article id 10254191Conference paper, Published paper (Refereed)
Sustainable development
Hållbar utveckling
Abstract [en]

Significant risks to public health and the environment are posed by the release of hazardous gases from industries such as pulp and paper. In this study, the aim was to develop a multi-sensor system with a minimal number of sensors to detect and identify hazardous gases. Training and test data for two gases, hydrogen sulfide and methyl mercaptan, which are known to contribute significantly to odors, were generated in a controlled laboratory environment. The performance of two deep learning models, a 1d-CNN and a stacked LSTM, for data fusion with different sensor configurations was evaluated. The performance of these models was compared with a baseline machine learning model. It was observed that the baseline model was outperformed by the deep learning models and achieved good accuracy with a four-sensor configuration. The potential of a cost-effective multi-sensor system and deep learning models in detecting and identifying hazardous gases is demonstrated by this study, which can be used to collect data from multiple locations and help guide the development of in-situ measurement systems for real-time detection and identification of hazardous gases at industrial sites. The proposed system has important implications for reducing pollution and protecting public health.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2023. article id 10254191
Keywords [en]
Gas measurement, Pulp & Paper, Multi-sensor, Data fusion, Machine learning, Deep learning, CNN, 1D-CNN, SVM, LSTM, Gas classification
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:miun:diva-49384DOI: 10.1109/SAS58821.2023.10254191ISI: 001086399500100Scopus ID: 2-s2.0-85174035432OAI: oai:DiVA.org:miun-49384DiVA, id: diva2:1800455
Conference
2023 IEEE Sensors Applications Symposium (SAS) Ottawa, ON, Canada
Available from: 2023-09-26 Created: 2023-09-26 Last updated: 2024-12-11Bibliographically approved
In thesis
1. Advanced Nanomaterials for Gas Sensing
Open this publication in new window or tab >>Advanced Nanomaterials for Gas Sensing
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This thesis explores the development and performance of semiconducting metal oxide (SMOX)-based gas sensors prepared by different methods, specifically targeting hazardous gases like hydrogen sulfide (H₂S) and in some cases methyl mercaptan (CH₃SH). These gases pose significant risks to human health and the environment, even at low concentrations. Therefore, developing sensitive, reliable, and cost-effective sensors is crucial for industrial safety, environmental monitoring, and healthcare. 

The compact SnO₂ layers prepared by Ultrasonic Spray Pyrolysis (USP) demonstrated effective H₂S detection at an optimal operating temperature of 450°C. This method resulted in uniform, dense layers with high crystallinity and minimal impurities, ensuring a reliable sensor response. However, the sensor’s selectivity was limited by the presence of other interference gases, especially in humid environments. To enhance performance, ZnO/SnO₂ heterostructures were incorporated, fabricated by controlling precursor ratios during the USP process. These heterostructures showed improved sensor response and selectivity for detecting H₂S compared to pure SnO₂. 

The Flame Spray Pyrolysis (FSP) method successfully produced porous SnO₂ structures, which excelled in detecting low concentrations of H₂S and CH₃SH at an optimal operating temperature of 250°C. The highly porous morphology increased the surface area, yielding a remarkable gas response down to 20 ppb and enabling efficient gas diffusion, making it suitable for detecting sub-ppb levels of toxic gases.

Additionally, screen printing was employed to create ZnO/SnO₂ porous heterostructure sensors. The sensor with a 3:4 SnO₂/ZnO ratio achieved a limit of detection (LOD) of 140 ppt at an optimal operating temperature of 325°C, outperforming single-component sensors and demonstrating the effectiveness of the simple screen-printing method in producing scalable, high-performance gas sensors.

In summary, this thesis underscores the significance of material design and fabrication techniques in enhancing the performance of SMOX-based gas sensors. The findings highlight that utilizing porous structures and heterojunction engineering offers substantial advantages in sensor response and selectivity, making these sensors well-suited for real-world applications in hazardous gas detection.

Place, publisher, year, edition, pages
Sundsvall: Mid Sweden University, 2025. p. 60
Series
Mid Sweden University doctoral thesis, ISSN 1652-893X ; 417
Keywords
gas sensor
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-53331 (URN)978-91-89786-88-2 (ISBN)
Public defence
2025-01-24, C312, Holmgatan 10, Sundsvall, 08:00 (English)
Opponent
Supervisors
Available from: 2024-12-12 Created: 2024-12-11 Last updated: 2024-12-12Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Hussain, MazharO'Nils, MattiasLundgren, JanAkbari-Saatlu, MehdiHamrin, RikardMattsson, Claes

Search in DiVA

By author/editor
Hussain, MazharO'Nils, MattiasLundgren, JanAkbari-Saatlu, MehdiHamrin, RikardMattsson, Claes
By organisation
Department of Computer and Electrical Engineering (2023-)Department of Engineering, Mathematics, and Science Education (2023-)
Other Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 234 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf