Public Health Monitoring Based on Food Security Measures in Sustainable Smart City Development Using Machine Learning Techniques

Public health is still threatened by food safety. Large, newly available datasets could be leveraged by machine learning to enhance food supply safety as well as lessen effects of food safety events. Novel data streams, such as text, transactional, trade data, and foodborne pathogen genomes have been found to have emerging uses made possible by a machine learning technique. These applications include pathogen source attribution, foodborne outbreak detection and risk assessment, and antibiotic resistance prediction. Major aim for this research is to enhance public health by monitoring system based on food security model in implementing sustainable smart city using machine learning model. here the regional food supply chain in smart city modelling with security analysis based on mobile cloud computing network. then based on this food chain management the public health monitoring has been carried out and health record data analysis is done using reinforcement fuzzy convolutional vector model with whale binary metaheuristic optimization. The data analysis output shows food chain change based health change in smart city. The simulation results has been analysed for various electronic health record dataset in terms of detection accuracy, mean precision, mean error, F1 score, network throughput. Proposed technique achieved detection accuracy of 97%, F-1 score of 92%, mean precision of 95%, network throughput of 98%, ROC of 94%.