Prediction of hyoscyamine content in Datura stramonium L. hairy roots using different modeling approaches: Response Surface Methodology (RSM), Artificial Neural Network (ANN) and Kriging

Amdoun, Ryad; Benyoussef, El-Hadi; Benamghar, Ahcène; Khelifi, Lakhdar

doi:10.1016/j.bej.2019.01.002

Cited by 26 publications

(20 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN is inspired by the way of biological neuron network that discovers a complex connection between the responses and predicted variables. In contrast to RSM, ANN is a more accurate method of interpolation, prediction, and validation [26].…”

Section: Introductionmentioning

confidence: 99%

Optimization of salicylic acid and chitosan treatment for bitter secoiridoid and xanthone glycosides production in shoot cultures of Swertia paniculata using response surface methodology and artificial neural network

et al. 2020

View full text Add to dashboard Cite

Background: In this study, response surface methodology (RSM) and artificial neural network (ANN) was used to construct the predicted models of linear, quadratic and interactive effects of two independent variables viz. salicylic acid (SA) and chitosan (CS) for the production of amarogentin (I), swertiamarin (II) and mangiferin (III) from shoot cultures of Swertia paniculata Wall. These compounds are the major therapeutic metabolites in the Swertia plant, which have significant role and demand in the pharmaceutical industries. Results: Present study highlighted that different concentrations of SA and CS elicitors substantially influenced the % yield of (I), (II) and (III) compounds in the shoot culture established on modified ½ MS medium (supplemented with 2.22 mM each of BA and KN and 2.54 mM NAA). In RSM, different response variables with linear, quadratic and 2 way interaction model were computed with five-factor-three level full factorial CCD. In ANN modelling, 13 runs of CCD matrix was divided into 3 subsets, with approximate 8:1:1 ratios to train, validate and test. The optimal enhancement of (I) (0.435%), (II) (4.987%) and (III) (4.357%) production was achieved in 14 days treatment in shoot cultures of S. paniculata elicited by 9 mM and 12 mg L − 1 concentrations (SA) and (CS). Conclusions: In optimization study, (I) show 0.170-0.435%; (II) display 1.020-4.987% and (III) upto 2.550-4.357% disparity with varied range of SA (1-20 mM) and CS (1-20 mg L − 1). Overall, optimization of elicitors to promote secoiridoid and xanthone glycoside production with ANN modeling (r 2 = 100%) offered more significant results as compared to RSM (r 2 = 99.8%).

show abstract

Section: Introductionmentioning

confidence: 99%

Optimization of salicylic acid and chitosan treatment for bitter secoiridoid and xanthone glycosides production in shoot cultures of Swertia paniculata using response surface methodology and artificial neural network

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Furthermore, it is difficult to measure the concentration of both glycerol and 1,3‐PDO online, which creates a barrier to the fermentation process. An artificial neural network (ANN) originated from biological neurons (Amdouna, Benyoussef, Benamghar, & Khelifi, 2019; Susanna, Dhanapal, Mahalingam, & Ramamurthy, 2019; Tavasoli et al, 2019) and evolved into a nonlinear function approximation model after modification and development, which has been widely used in various biological systems (Del Rio‐Chanona, Manirafasha, Zhang, Yue, & Jing, 2016; Del Rio‐Chanona et al, 2019; Gopakumar, Tiwari, & Rahman, 2018). At the same time, bases (such as NaOH) or acids (such as H 3 PO 4 ) were used as a neutralizer to maintain the pH in a certain value throughout the fermentation process, the volume of which could be recorded online by many fermenter software.…”

Section: Introductionmentioning

confidence: 99%

A robust soft sensor to monitor 1,3‐propanediol fermentation process by Clostridium butyricum based on artificial neural network

Zhang

Zhu

Zhuang

et al. 2020

Biotech & Bioengineering

View full text Add to dashboard Cite

With the aggravation of environmental pollution and energy crisis, the sustainable microbial fermentation process of converting glycerol to 1,3-propanediol (1,3-PDO) has become an attractive alternative. However, the difficulty in the online measurement of glycerol and 1,3-PDO creates a barrier to the fermentation process and then leads to the residual glycerol and therefore, its wastage. Thus, in the present study, the four-input artificial neural network (ANN) model was developed successfully to predict the concentration of glycerol, 1,3-PDO, and biomass with high accuracy. Moreover, an ANN model combined with a kinetic model was also successfully developed to simulate the fed-batch fermentation process accurately. Hence, a soft sensor from the ANN model based on NaOH-related parameters has been successfully developed which cannot only be applied in software to solve the difficulty of glycerol and 1,3-PDO online measurement during the industrialization process, but also offer insight and reference for similar fermentation processes. K E Y W O R D S 1, 3-propanediol, artificial neural network, Clostridium butyricum, soft sensor 1 | INTRODUCTION 1,3-Propanediol (1,3-PDO), an important chemical also used as a biochemical raw material, has been used for the synthesis of polymers, such as polytrimethylene terephthalate (PTT) and polytrimethylene ether glycol, and is endowed with numerous exceptional characteristics, such as good elasticity, inherent stain resistance, and low static

show abstract

“…(2) Challenge 2: The regression models, such as the linear and second-order formulations were widely applied to depict the relations between the processing inputs and machining parameters in the optimisation models. Unfortunately, these approaches result in a low predictive accuracy due to the approximate behavior [22]. Therefore, it is necessary to investigate higher accurate models for optimisation of the turning-burnishing process.…”

Section: Introductionmentioning

confidence: 99%

Optimization of compressed air assisted-turning-burnishing process for improving machining quality, energy reduction and cost-effectiveness

Nguyen

2020

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

The burnishing process is used to enhance the machining quality via improving the surface finish, surface hardness, wear-resistance, fatigue, and corrosion resistance, and it is mostly used in aerospace, biomedical, and automotive industries to improve reliability and performance of the component. The combined turning and burnishing process is therefore considered as an effective solution to enhance both machining quality and productivity. However, the trade-off analysis between energy consumption, surface characteristics, and production costs has not been well-addressed and investigated. This study presents an optimization of the compressed air assisted-turning-burnishing (CATB) process for aluminum alloy 6061, aimed to decrease the energy consumption as well as surface roughness and to enhance the Vicker hardness of the machined surface. The machining parameters for consideration include the machining speed, feed rate, depth of cut, burnishing force, and the ball diameter. The improved Kriging models were used to construct the relations between machining parameters and the technological response characteristics of the machined surface. The optimal machining parameters were obtained utilizing the desirability approach. The energy based-cost model was developed to assess the effectiveness of the proposed CATB process. The findings showed that the selected optimal outcomes of the depth of cut, burnishing force, diameter, feed rate, and machining speed are 0.66 mm, 196.3 N, 8.0 mm, 0.112 mm/rev, and 110.0 m/min, respectively. The energy consumption and surface roughness are decreased by 20.15% and 65.38%, respectively, while the surface hardness is improved by 30.05%. The production cost is decreased by 17.19% at the optimal solution. Finally, the proposed CATB process shows a great potential to replace the traditional techniques which are used to machine non-ferrous metals.

show abstract

Prediction of hyoscyamine content in Datura stramonium L. hairy roots using different modeling approaches: Response Surface Methodology (RSM), Artificial Neural Network (ANN) and Kriging

Cited by 26 publications

References 38 publications

Optimization of salicylic acid and chitosan treatment for bitter secoiridoid and xanthone glycosides production in shoot cultures of Swertia paniculata using response surface methodology and artificial neural network

Optimization of salicylic acid and chitosan treatment for bitter secoiridoid and xanthone glycosides production in shoot cultures of Swertia paniculata using response surface methodology and artificial neural network

A robust soft sensor to monitor 1,3‐propanediol fermentation process by Clostridium butyricum based on artificial neural network

Optimization of compressed air assisted-turning-burnishing process for improving machining quality, energy reduction and cost-effectiveness

Contact Info

Product

Resources

About