Sustainable Agriculture-Based Food Security Analysis using Healthcare Data Modelling and Deep Learning Techniques

The earth’s ecosystems are negatively impacted by the development of agriculture in both terrestrial and marine environments. Cropland losses, water scarcity, species infestations, land degradation, and climate change all work together to generate a 25% reduction in agricultural productivity. In order to achieve sustainable food production and security through the green revolution and environmentally benign methods, the world requires a paradigm shift in the development of agriculture. Therefore, agricultural practices must be supported by farmland’s capacity to produce enough food to meet human requirements forever, as well as by having long-term effects on the environment. This study offers a novel method for analysing healthcare in metropolitan areas based on food security using machine learning and remote sensing. In this instance, the data was gathered as health analysis data based on food security and processed to eliminate missing values. Then, a reinforcement recurrent term frequency Markov bi-directional Bayesian neural network was used to choose and classify this data. Two components: a text data training model and a server-side module for attribute estimation techniques. We tested with multiple food categories, each with hundreds of photographs, machine learning training, in an effort to achieve higher categorisation accuracy. In terms of F1-score, RMSE, recall, precision, and accuracy of predictions, an experimental investigation has been conducted. Proposed technique attained prediction accuracy 98%, F-1 score 95%, PRECISION 94%, Recall 97%, RMSE 52%.