Vairavel Madeshwaren

Inhaling formaldehyde a chemical that is widely used in many different industries can have serious health consequences. In order to precisely detect formaldehyde levels in industrial air quality environments, this study makes use of deep learning techniques. Using sensor data gathered from high-risk industrial areas the study focuses on variables like air quality index temperature and humidity. The data is processed by Convolutional Neural Networks (CNNs), which identify trends linked to increases in formaldehyde concentrations. To improve model accuracy preprocessing of the data is done including feature scaling and outlier elimination. The model's performance is assessed using evaluation metrics like Mean Squared Error (MSE), sensitivity, specificity, and prediction accuracy. Results show that when compared to conventional regression models the CNN-based model considerably lowers false positives while achieving a high prediction accuracy. Rapid reaction to hazardous formaldehyde levels is made possible by the deep learning frameworks' real-time monitoring capability which lowers possible health hazards. To improve long-term prediction accuracy and trend identification future research will investigate the use of recurrent neural networks (RNN) for time-series analysis.

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a dangerous substance commonly used in buildings, continues to present serious risks in urban areas, because of outdated infrastructure and inappropriate disposal methods.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.