Rapid detection model of Bacillus subtilis in solid‐state fermentation of rapeseed meal

Solid-State Fermentation Engineering of Traditional Chinese Fermented Food

Solid-state fermentation (SSF) system involves solid, liquid, and gas phases, characterized by complex mass and heat transfer mechanisms and microbial complex interactions. The SSF processes for traditional Chinese fermented foods, such as vinegar, soy sauce, and baijiu primarily rely on experience, and most of the operations are replaced by auto machine now. However, there is still a lack of engineering in-depth study of the microbial process of SSF for complete process control. To meet the demands of smart manufacturing and green production, this paper emphasizes the engineering analysis of the mechanisms behind SSF. It reviews the progress in the engineering aspects of Chinese traditional SSF, including raw material pretreatment, process parameter detection, mathematical model construction, and equipment innovation. Additionally, it summarizes the challenges faced during intelligent upgrades and the opportunities brought by scientific and technological advancements, proposing future development directions. This review provides an overview of the SSF engineering aspects, offering a reference for the intelligent transformation and sustainable development of the Chinese traditional SSF food industry.

Fully nondestructive analysis of capsaicinoids electrochemistry data with deep neural network enables portable system

Electrochemical methods have been extensively applied for the detection of chemical information from food or other analytes. However, existing electrochemical methods are limited to focusing solely on the absorption peaks and disregard much of the hidden chemical fingerprint information. Consequently, electrochemical sensors are constrained by their ability to detect samples containing multiple source-material mixtures with overlapping constituents. We hypothesized that the target substances can be effectively identified and detected using differential sensor data combined with artificial intelligence (AI). In this study, we developed a novel signal array composed of five metal electrodes and used a convolutional neural network (CNN) model for feature extraction to detect capsaicinoids in stews. Our results indicate that the proposed method achieved satisfactory predictions with a root mean square error (RMSE) of 5.407 in independent brine samples. This provides a promising strategy and practical approach for the nondestructive analysis of multidimensional electrochemical data of mixed analytes.