Artificial intelligence approach based on near-infrared spectral data for monitoring of solid-state fermentation

Abstract

This work aimed to establish a chemometric technique for quantifying amylase and protease activities as well as protein concentration in aqueous extracts of Rhizopus microsporus var. oligosporus obtained via solid-state fermentation (SSF). The kinetics of four agro-industrial wastes (wheat bran, soybean meal, type II wheat flour and sugarcane bagasse) were studied for 144 h, along with two different sets of their ternary mixtures, at a constant fermentation time of 120 h, to obtain primary data (biochemical parameters as well as near-infrared (NIR) spectral data). Then, models such as artificial neural network (ANN) and partial least squares (PLS) were calibrated to predict biochemical parameters using the spectral data. Primary data and three methods of preprocessing data -first, second and third derivatives -were assessed as inputs for both chemometric tools. The third derivative, that is, spectral pre-processing plus an optimized ANN, showed the least relative errors (<8.3% ± 10.5%). The third-derivative spectrum was found to be suitable as the ANN input data for monitoring amylase and protease activities and protein concentration in the SSF under study. The proposed methodology can serve as a foundation for at-line sensor development and decrease the time and cost of bioprocess development using Rhizopus microsporus var. oligosporus.

UV/Vis spectroscopy combined with chemometrics for monitoring solid‐state fermentation with Rhizopus microsporus var. oligosporus

“…The relative errors for the ANN models that describe the three biochemical parameters were similar to others reported for the same SSF quantified by models using NIR spectroscopy (<8.3 ± 10.5%) . These results demonstrate that UV‐Vis spectroscopy in combination with an ANN model is useful for quantifying enzymes in SSF with suitable accuracy.…”

“…The amylolytic activity in extracts was determined by released sugars with reducing groups (µmol of glucose equivalent per min), using starch as the substrate, by means of a modification of a previously described method . The specific procedure and calculations of the modified method were previously published …”

“…The protease activity was determined using a modified method, previously reported by Leighton et al The protease method utilized was recently described in detail …”

Ethanol biosynthesis by fast hydrolysis of cassava bagasse using fungal amylases produced in optimized conditions

“…One unit of amylase activity was defined as the amount of enzyme that releases 1 μmol of reducing sugars per minute and expressed as units per gram of dry substrate (U/g). Detailed steps and equation performed to measure amylase activity are described by Barchi et al (2016).…”

Prediction of gas velocity in two-phase flow using developed fuzzy logic system with differential evolution algorithm

“…Thus, while the novel experimental techniques and CFD tool measure fluid velocity with high accuracy, given the limitations of these methods like high cost, complicated engineering problems, difficult implementation, lengthy process, and the like, using the intelligent method can be an answer to the complicated problems like predicting the bubbly flows in reactors 12 – 17 . There are several AI techniques proposed by studies like fuzzy logic 18 , neural networks, neuro-fuzzy, or artificial bee colony (ABC) algorithm and differential evolution (DE) algorithm 19 – 22 . One of the notable artificial intelligence methods is the fuzzy logic introduced by Zadeh 23 .…”