Artificial Intelligence and Deep Learning Based Agri & Food Quality and Safety Detection System

Abstract

Deep learning, also known as DL, is a technique that has been shown to be effective for evaluating enormous datasets, such as those that may be found in the fields of image processing, speech recognition, and popularity. Recent advancements have been made in this direction by the fields of food science and food engineering. No one has ever mentioned to us a similar study that made use of food in any capacity as a variable in the research. This article presents a succinct introduction to deep learning (DL), in addition to detailed descriptions of the building of a typical convolutional neural network (CNN), as well as the ways by which artificial intelligence and the internet of things convey information. We conducted a comprehensive literature review on the subject of deep learning as it relates to the identification of issues with computers that are related to food. Some of the topics that were covered in this review include, but are not limited to the following: food recognition; the calculation of calories; fruit; potato; meat; the safety of aquatic goods; the safety of the food supply chain; and food infection. Each inquiry assessed its own distinct set of problems, datasets, preparation techniques, network topologies, and system architectures to discover how well they functioned and how they stacked up against other possible solutions. This paper is an investigation into the use of big data to the issue of hunger, during which we discovered some fascinating trends. According to the findings of our research, DL is superior to more traditional methods of system analysis, such as guided attribute extractors and classical algorithms. They have the potential to become the subsequent generation of food safety regulators.