Key points are not available for this paper at this time.
Abstract This study investigated available literature on leveraging the Internet of Things (IoT) to optimize the food fermentation process. Utilizing a subjective examination strategy through bibliometric investigation, this paper assessed 44 articles between 2013 and 2022. The bibliometric study focused on publications per author, publications per country, and a research center based on co‐occurrence keywords, and research patterns. While available publications in this domain show IoT can be used to optimize the fermentation process, uptake has been slow and has been in an infant stage in the past 8 years. The scholarly articles, using the co‐occurrence of keywords, showed five (5) clusters, which are (i) implementing IoT in forecasting the fermentation process to achieve effective quality control, (ii) remotely monitoring and automating the production process to achieve effective process control, (iii) monitoring temperature in real‐time during the fermentation process, (iv) digitally storing parameters during the fermentation process using WLAN, and (v) applying middleware in the processing properties of agricultural produce. These cluster areas revealed how IoT can be used to optimize the food fermentation process. Given the growth and interest in IoT technologies in the food fermentation process, this study explored available literature to highlight available IoT technologies in developing strategies for the food fermentation process and predictive analysis of fermented food products. Practical applications Using IoT technologies, manufacturers may optimize their regulatory procedures and product quality by monitoring food fermentation process parameters such as temperature, carbon dioxide, humidity, viscosity, and so on in real‐time. Food manufacturers may also obtain and use these real‐time data for food safety. Some cutting‐edge smart sensors and cloud‐based predictive analytics systems can equally predict stages of the fermentation process and possibly detect challenges along the process.
Adeleke et al. (Fri,) studied this question.