Machine Learning Powered Asbestos Exposure Modeling Using Feature Extraction from IoT Based Sensor Data

Machine Learning Powered Asbestos Exposure Modeling Using Feature Extraction from IoT Based Sensor Data Banushri Annamalai Department of Computer Science and Engineering, Vels Institute of Science, Technology and Advanced Studies, Chennai, Tami Nadu, India. Kishore Kunal Business Analytics, Loyola Institute of Business Administration, Chennai, Tamil Nadu, India. Vairavel Madeshwaren Department of Agriculture Engineering, Dhanalakshmi Srinivasan College of Engineering, Coimbatore, Tamil Nadu, India. Kathiravan M Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, Tamil Nadu, India. Goli Ramkrishna Indian Naval Academy, Kannur, Kerala, India. Neha Sharma Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India.

Asbestos, a dangerous substance commonly used in buildings, continues to present serious risks in urban areas, because of outdated infrastructure and inappropriate disposal methods. The goal of this study is to help with proactive public health measures by utilizing machine learning algorithms to predict asbestos exposure levels. An IoT-based environmental sensor dataset that tracks temperature humidity and air quality is presented in this study. Random Forest, Support Vector Machines (SVM), and Neural Networks are three machine-learning techniques used to create predictive models that can estimate asbestos concentrations under different conditions. Data preprocessing includes feature extraction and normalization to improve prediction accuracy. Performance metrics such as F1 score, accuracy, sensitivity, and specificity are used to compare the models. Additionally, certain environmental factors that influence asbestos dispersion are identified by the Random Forest feature importance analysis. Moreover, the IoT-based environmental sensor dataset used in this study is derived from real-world deployed sensors installed in high-risk industrial zones. These sensors continuously monitor environmental parameters such as formaldehyde concentration, temperature, humidity, and AQI, ensuring that the data reflects authentic field conditions for reliable model training and evaluation. These findings demonstrate how real-time asbestos exposure prediction using machine learning enables timely interventions. Future studies aim to increase accuracy and computational efficiency, future enhancements may incorporate techniques such as Long Short-Term Memory (LSTM) networks for temporal modeling, CNN pruning for model optimization, and feature selection methods to reduce dimensionality and processing time.
7 5 2025 7 5 2025 1673 1684 10.53759/7669/jmc202505132 10.53759/7669/jmc202505132 https://anapub.co.ke/journals/jmc/jmc_abstract/2025/jmc_volume_05_issue_03/jmc_volume5_issue3_132.html https://anapub.co.ke/journals/jmc/jmc_pdf/2025/jmc_volume_5-issue_3/JMC202505132.pdf 10.1016/j.resconrec.2023.107253 P.-Y. Wu, C. Sandels, T. Johansson, M. Mangold, and Kristina Mjörnell, “Machine learning models for the prediction of polychlorinated biphenyls and asbestos materials in buildings,” Resources, Conservation and Recycling, vol. 199, p. 107253, Dec. 2023, doi: 10.1016/j.resconrec.2023.107253. 10.3390/app14188441 M. Saba, D. Valdelamar Martínez, L. K. Torres Gil, G. E. Chanchí Golondrino, and M. A. O. Alarcón, “Application of Supervised Learning Methods and Information Gain Methods in the Determination of Asbestos–Cement Roofs’ Deterioration State,” Applied Sciences, vol. 14, no. 18, p. 8441, Sep. 2024, doi: 10.3390/app14188441. 10.1088/1755-1315/1122/1/012050 P.-Y. Wu, M. Mangold, C. Sandels, T. Johansson, and K. Mjörnell, “Modeling Artificial Neural Networks to Predict Asbestos-containing Materials in Residential Buildings,” IOP Conference Series: Earth and Environmental Science, vol. 1122, no. 1, p. 012050, Dec. 2022, doi:10.1088/1755-1315/1122/1/012050. 10.3390/su11164355 E. Wilk, M. Krówczyńska, and B. Zagajewski, “Modelling the Spatial Distribution of Asbestos—Cement Products in Poland with the Use of the Random Forest Algorithm,” Sustainability, vol. 11, no. 16, p. 4355, Aug. 2019, doi: 10.3390/su11164355. 10.3390/su15076067 G. Kaplan, M. Gašparović, O. Kaplan, V. Adjiski, R. Comert, and M. A. Mobariz, “Machine Learning-Based Classification of Asbestos- Containing Roofs Using Airborne RGB and Thermal Imagery,” Sustainability, vol. 15, no. 7, p. 6067, Mar. 2023, doi: 10.3390/su15076067. 10.3390/su15054276 M. Hikuwai, N. Patorniti, A. Vieira, G. Frangioudakis Khatib, and R. Stewart, “Artificial Intelligence for the Detection of Asbestos Cement Roofing: An Investigation of Multi-Spectral Satellite Imagery and High-Resolution Aerial Imagery,” Sustainability, vol. 15, no. 5, p. 4276, Feb. 2023, doi: 10.3390/su15054276. 10.3390/s21134582 C. Cai, T. Nishimura, J. Hwang, X.-M. Hu, and A. Kuroda, “Asbestos Detection with Fluorescence Microscopy Images and Deep Learning,” Sensors, vol. 21, no. 13, p. 4582, Jul. 2021, doi: 10.3390/s21134582. 10.3390/rs14143418 T.-T. Yu, Y.-C. Lin, S.-C. Lan, Y.-E. Yang, P.-Y. Wu, and J.-C. Lin, “Mapping Asbestos-Cement Corrugated Roofing Tiles with Imagery Cube via Machine Learning in Taiwan,” Remote Sensing, vol. 14, no. 14, p. 3418, Jul. 2022, doi: 10.3390/rs14143418. 10.3390/app14209408 T. Matsuo, M. Takimoto, S. Tanaka, A. Futamura, H. Shimadera, and A. Kondo, “Developing an Automatic Asbestos Detection Method Based on a Convolutional Neural Network and Support Vector Machine,” Applied Sciences, vol. 14, no. 20, p. 9408, Oct. 2024, doi:10.3390/app14209408. 10.5220/0011059400003209 G. Bonifazi, G. Capobianco, R. Gasbarrone, S. Serranti, S. Bellagamba, and D. Taddei, “Data Fusion of PRISMA Satellite Imagery for Asbestos-containing Materials: An Application on Balangero’s Mine Site (Italy),” Proceedings of the 2nd International Conference on Image Processing and Vision Engineering, 2022, doi: 10.5220/0011059400003209. 10.3390/ijerph19074031 T.-A. Berry et al., “Asbestos and Other Hazardous Fibrous Minerals: Potential Exposure Pathways and Associated Health Risks,” International Journal of Environmental Research and Public Health, vol. 19, no. 7, p. 4031, Mar. 2022, doi: 10.3390/ijerph19074031. N. Ubels, “Classifying asbestos roofs in the Dutch province of Drenthe using hyperspectral imagery and deep learning,” Doctoral dissertation, 2019. 10.1177/0734242x16683271 E. Wilk, M. Krówczyńska, P. Pabjanek, and P. Mędrzycki, “Estimation of the amount of asbestos-cement roofing in Poland,” Waste Manage. Res., vol. 35, no. 5, pp. 491–499, 2017. 10.3390/s23198021 S.-C. Baek, K.-H. Lee, I.-H. Kim, D.-M. Seo, and K. Park, “Construction of Asbestos Slate Deep-Learning Training-Data Model Based on Drone Images,” Sensors, vol. 23, no. 19, p. 8021, Sep. 2023, doi: 10.3390/s23198021. 10.3390/su151512071 G. Frangioudakis Khatib., “Australia’s Ongoing Challenge of Legacy Asbestos in the Built Environment: A Review of Contemporary Asbestos Exposure Risks,” Sustainability, vol. 15, no. 15, p. 12071, Aug. 2023, doi: 10.3390/su151512071.