IRO Journals
Journal of Electronics and Informatics

Breath Based Pneumonia Detection Using Gas Sensors and Decision Tree Classifier with Risk Analysis

Open Access
Published: 04 August, 2026
Pages: 273-286
  • Bharath P M. , Bharath P M.
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
  • Suguna S. , Suguna S.
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
  • Oviya S. , Oviya S.
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
  • Sobiya M. , Sobiya M.
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
  • Tasneem Taj H. Tasneem Taj H.
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
    Department of Biomedical Engineering, Sri Manakula Vinayagar Engineering College, Puducherry, Puducherry, India
view PDF
view PDF

How to Cite

P M., Bharath, Suguna S., Oviya S., Sobiya M., and Tasneem Taj H. 2026. “Breath Based Pneumonia Detection Using Gas Sensors and Decision Tree Classifier With Risk Analysis”. Journal of Electronics and Informatics 8 (3): 273-86. https://doi.org/10.36548/jei.2026.3.006.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Pneumonia Detection
Breath Analysis
Metal Oxide Gas Sensors
Volatile Organic Compounds (VOCs)
Decision Tree Classifier
Non-Invasive Diagnosis

Abstract

Pneumonia is a serious respiratory disease that necessitates immediate diagnosis in order to minimize the chance of complications and enhance the well-being of patients. Traditional techniques for diagnosis involve chest X-ray, laboratory testing, which are both time-intensive and costly. This article focuses on a framework for detecting pneumonia using breath analysis that utilizes multi-sensor gas sensing along with machine learning for non-invasive assessment of risks associated with it. This framework makes use of MQ-3, MQ-135, and BME680 sensors to analyze Volatile Organic Compounds (VOC) and environment. The collected data is preprocessed using Min-Max scaling technique, clustered using K-Means algorithm into different risk groups and then classified by using a Decision Tree Classifier. The experimental evaluation has resulted in 95.84% accuracy, 95.12% precision, 94.87% recall and 94.99% F1-Score. The proposed system is a cost-effective and portable approach for the early pneumonia detection.

References

  1. Arulvasan, Wisenave, Julia Greenwood, Madeleine L. Ball, Hsuan Chou, Simon Coplowe, Owen Birch, Patrick Gordon et al. "Optimized Breath Analysis: Customized Analytical Methods and Enhanced Workflow for Broader Detection of VOCs." Metabolomics, 2025, vol. 21, no. 1: 17.
  2. Abdulsattar, Nadia Shamsulddin. "Pneumonia Classification from X-ray Images with Convolutional Neural Network." 12th International Conference on Information Technology (ICIT), IEEE 2025: 444-450.
  3. Zhang, Zhaokang, Kun Li, Guangpeng Zhang, Wenjun Liu, Xinglin Chen, and Zhaocheng He. "Design and Implementation of a High-Sensitivity Exhaled Breath Analyzer." 5th International Conference on Sensors and Information Technology, IEEE 2025: 122-126.
  4. Bharath, Mr PM, P. Kiruthika, and S. Madhusnegha. "AI-Based Respiratory Tracking and Detection System for Dyspnea." High Technology Letters, 2024, vol. 30, no. 4: 700– 724.
  5. Belghiti, Mehdi Khaiaf, Mohammed El Gibari, Ahmed Rhallabi, and Amal El Fallah Serghrouchni. "Development and Optimization of Gas Sensors for Ammonia detection." 32nd Telecommunications Forum (TELFOR), IEEE 2024: 1-3.
  6. Arulvasan, Wisenave, Hsuan Chou, Julia Greenwood, Madeleine L. Ball, Owen Birch, Simon Coplowe, Patrick Gordon et al. "High-Quality Identification of Volatile Organic Compounds (VOCs) Originating from Breath." Metabolomics, 2024, vol. 20, no. 5: 102.
  7. Bekh, Igor, Serge Mamilov, Dmytro Velyhotskyi, Illya Porozinski, and Igor Yashan. "Prototype Device for Measuring Carbon Monoxide Levels in Human Exhalation." IEEE 42nd International Conference on Electronics and Nanotechnology (ELNANO), IEEE 2024: 364-368.
  8. Gupta, Rahul, Anil Kumar, Mukesh Kumar, Pradeep Kumar, and Dinesh Kumar. "Numerical Modelling of Cu2O-Based Gas Sensor for Detection of Volatile Organic Compounds in Human Breath." In International Conference on Emergent Converging Technologies and Biomedical Systems, Springer Nature Singapore 2022: 297-304.
  9. Sayo, Kevin, and Winncy Y. Du. "Portable Diabetic Ketoacidosis Detector via the Human Exhaled Breath Analysis." IEEE 6th International Conference on Electronic Information and Communication Technology (ICEICT), IEEE 2023: 1212-1217.
  10. Massey, Roslyn S., Bruno Gamero, and Ravi Prakash. "A System-on-Board Integrated Multi-Analyte PoC biosensor for Combined Analysis of Saliva and Exhaled Breath." 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE 2022: 904-909.
  11. Xiong, Hangming, Jiaying Sun, Yingying Xue, Weijei Yu, Yong Zhou, Hao Wan, and Ping Wang. "Design of Breath Sampling Device and Procedure for Volatile Organic Compounds and Exhaled Breath Condensate." IEEE International Symposium on Olfaction and Electronic Nose (ISOEN), IEEE 2022: 1-3.
  12. Human Breathomics Database (HBDB). A Comprehensive Database of Volatile Organic Compounds (VOCs) in Human Exhaled Breath. National Yang Ming Chiao Tung University. Available: https://hbdb.cmdm.tw/