IoT and Machine Learning in Smart Kitchen Monitoring for Enhanced Worker Health

Abstract

The significance of occupational health in culinary settings, particularly kitchens, is paramount due to the inherent health risks associated with these environments. This study addresses the necessity of maintaining optimal environmental conditions, such as temperature, humidity, and air quality, in kitchens to safeguard worker health. To achieve this, the study advocates for the implementation of sophisticated ventilation and air conditioning systems. The core focus of the research is the integration of Internet of Things (IoT) technology and advanced machine learning algorithms for the real-time monitoring and assessment of kitchen environments. Specifically, the study fine-tunes and evaluates several classification algorithms, including Decision Trees (DT), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN), aiming to accurately predict and manage kitchen conditions. The comparative analysis reveals that the DT algorithm outperforms others, demonstrating exceptional accuracy (97.41%), precision (95.35%), and proficiency in identifying relevant scenarios (88.57%). In contrast, the KNN algorithm registers the lowest accuracy (75.12%), while the SVM algorithm, despite being the least precise (86.55%), shows a relatively higher capability in recognizing pertinent cases (86.55%) compared to KNN (72.33%). This study underscores the potential of integrating IoT and machine learning in enhancing occupational health standards in kitchen settings.