Artificial Neural Network Modeling to Predict the Non-Linearity in Reaction Conditions of Cholesterol Oxidase from &amp;lt;i&amp;gt;Streptomyces olivaceus&amp;lt;/i&amp;gt; &amp;lt;i&amp;gt;MTCC&amp;lt;/i&amp;gt; 6820

Sahu, S.N.; Shera, Shailendra Singh; Banik, Rathindra Mohan

doi:10.4236/jbm.2019.74002

Cited by 6 publications

(7 citation statements)

References 19 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a wide margin between the predicted and the actual values of the hydrogen as indicated by the R 2 of 0.46 and the MSE values of 205.19. Sahu et al 39 and Rosli et al 40 confirm the non‐linearity and complexity of processes involving chemical and biochemical. In Sahu et al, 39 ANN was employed to predict the non‐linearity in biochemical reaction conditions.…”

Section: Resultsmentioning

confidence: 94%

See 1 more Smart Citation

Modeling the effect of non‐linear process parameters on the prediction of hydrogen production by steam reforming of bio‐oil and glycerol using artificial neural network

2020

View full text Add to dashboard Cite

Biomass-derived substrates such as bio-oil and glycerol are gaining wide acceptability as feedstocks to produce hydrogen using a steam reforming process. The wide acceptability can be attributed to a huge amount of glycerol and bio-oil obtained as by-products of biodiesel production and pyrolysis processes. Several parameters have been reported to affect the production of hydrogen by biomass steam reforming. This study investigates the effect of non-linear process parameters on the prediction of hydrogen production by biomass (bio-oil and glycerol) steam reforming using artificial neural network (ANN) modeling technique. Twenty different multilayer ANN model architectures were tested using datasets obtained from the bio-oil and glycerol steam reforming. Two algorithms namely Levenberg-Marquardt and Bayesian regularization were employed for the training of the ANNs. An optimized network configuration consisting of 3 input layer 14 hidden neurons, 1 output layer, and 3 input layer, 5 hidden neurons, and 1 output layer were obtained for the Levenberg-Marquardt and Bayesian regularization trained network, respectively for hydrogen production by bio-oil steam reforming. While an optimized network configuration consisting of 5 input nodes, 9 hidden neurons, 1 output node, and 5 input nodes, 8 hidden neurons, and 1 output node were obtained for Levenberg-Marquardt and Bayesian regularization trained network, respectively for hydrogen production by glycerol steam reforming. Based on the optimized network, the predicted hydrogen production from the bio-oil and glycerol steam agreed with the actual values with the coefficient of determination (R 2) > 0.9. A low mean square error of 3.024 × 10 −24 and 6.22 × 10 −15 for the optimized for Levenberg-Marquardt and Bayesian regularization-trained ANN, respectively. The neural network analyses of the two processes showed that reaction temperature and glycerol-to-water molar ratio were the most relevant factors that influenced the production of hydrogen by bio-oil and glycerol steam reforming, respectively. This study has demonstrated the robustness of the ANN as a technique for investigating the effect of non-linear process parameters on hydrogen production by bio-oil and glycerol steam reforming.

show abstract

Section: Resultsmentioning

confidence: 94%

“…Sahu et al 39 and Rosli et al 40 confirm the non‐linearity and complexity of processes involving chemical and biochemical. In Sahu et al, 39 ANN was employed to predict the non‐linearity in biochemical reaction conditions. While Rosli et al 40 investigated the non‐linearity of the steam cracking furnace process.…”

Section: Resultsmentioning

confidence: 94%

Modeling the effect of non‐linear process parameters on the prediction of hydrogen production by steam reforming of bio‐oil and glycerol using artificial neural network

2020

View full text Add to dashboard Cite

show abstract

“…In a previous study, some physical factors including the initial pH of the medium, cultivation temperature and shaking speed affecting the production of CHO by Rhodococcus equi were studied [36]. Also, medium pH, incubation temperature, inoculum size, inoculum age, fermentation period and shaking speed were studied for augmenting the CHO production by S. olivaceus MTCC 6820 [37]. For microbial growth, metabolic characteristics and metabolite production, the pH value of the cultural medium is critical.…”

Section: Discussionmentioning

confidence: 99%

Production and statistical optimization of cholesterol-oxidase generated by Streptomyces sp. AN strain

Alam

Goda

Soliman

et al. 2022

Journal of Genetic Engineering and Biotechnology

View full text Add to dashboard Cite

Background Cholesterol oxidases (CHOs) have attracted enormous attention because of their wide biotechnological potential. The present study explores the production of CHOs by Streptomyces sp. AN. Evaluation of culture conditions affecting enzyme production, medium optimization and released metabolite characteristics were also investigated. Results The current work reports the isolation of 37 colonies (bacteria/actinobacteria) with different morphotypes from different soil/water samples. The isolate-coded AN was selected for its high potency for CHO production. Morphological characteristics and the obtained partial sequence of 16srRNA of AN showed 99.38% identity to Streptomyces sp. strain P12–37. Factors affecting CHO production were evaluated using Plackett-Burman (PB) and Box-Behnken (BB) statistical designs to find out the optimum level of the most effective variables, namely, pH, starch, NH4NO3 and FeSO4.7H2O with a predicted activity of 6.56 U/mL. According to this optimization, the following medium composition was considered to be optimum (g/L): cholesterol 1, starch 6, MgSO4.7H2O 0.1, CaCl2 0.01, FeSO4.7H2O 0.1, NH4NO3 23.97, yeast extract (YE) 0.2, K2HPO4 0.01, KH2PO4 0.1, NaCl 0.01, Tween 20 0.01, pH 6.36 and incubation temperature (30 °C) for 9 days. Spectophotometric analysis for released metabolites against cholesterol (standard) via Fourier-transform infrared spectroscopy (FTIR) and differential scanning calorimetry (DSC) was carried out. FTIR spectrum showed the appearance of new absorption peaks at 1644 and 1725cm−1; this confirmed the presence of the Keto group (C=O) stretch bond. Besides, fermentation caused changes in thermal properties such as melting temperature peak (99.26; 148.77 °C), heat flow (− 8; − 3.6 Mw/mg), capacity (− 924.69; − 209.77 mJ) and heat enthalpy (− 385.29; 69.83 J/g) by comparison to the standard cholesterol as recognized through DSC thermogram. These changes are attributed to the action of the CHO enzyme and the release of keto derivatives of cholesterol with different properties. Conclusion Streptomyces sp. AN was endowed with the capability to produce CHO. Enzyme maximization was followed using a statistical experimental approach, leading to a 2.6-fold increase in the overall activity compared to the basal condition. CHO catalyzed the oxidation of cholesterol; this was verified by the appearance of a new keto group (C=O) peak at 1644 and 1725 cm−1 observed by FTIR spectroscopic analysis. Also, DSC thermogram demonstrates the alteration of cholesterol triggered by CHO.

show abstract

“…As mentioned in Section 1, very few papers focus specifically on predicting sensor data with non-linearity and neural networks. However, the literature presents relevant studies which apply NNs to predict non-linearity in other fields such as cholesterol estimation (Sahu et al, 2019) and rainfall forecasting (Chattopadhyay, 2007). These papers shall be discussed below.…”

Section: Related Workmentioning

confidence: 99%

“…In (Sahu et al, 2019), Sahu et al create an ANN for estimating the amount of Cholesterol oxidase (COX) in a species of Streptomyces by using pH, cholesterol concentration, 4-aminoan-tipyrine, crude COX volume and horseradish peroxidase as input. Despite good results, the work is not focused towards live varying data like manufacturing sensors.…”

Section: Related Workmentioning

confidence: 99%

Anticipating faults by predicting non-linearity of environment variables with neural networks: a case study in semiconductor manufacturing

Melchiades¹,

Schreiber²,

Ramos³

et al. 2022

LatinX in AI at International Conference on Machine Learning 2021

View full text Add to dashboard Cite

The present work proposes a neural network model capable of anticipating possible faults in a semiconductor manufacturing plant by predicting non-linearity spikes in sensor data. Early detection of significant variation can be crucial for identifying machinery degradation or issues in the process itself. We use non-linearity as it is not affected by regular process changes and autocorrelation, thus avoiding false-positives in the neural network caused by changes in demand and the presence of control systems. The developed model is able to predict up to 30min of future non-linearity with loss ≤ 0.5. Furthermore, the proposed model is flexible enough to present itself as a starting point for future work in the field of fault detection in other areas.

show abstract

Artificial Neural Network Modeling to Predict the Non-Linearity in Reaction Conditions of Cholesterol Oxidase from <i>Streptomyces olivaceus</i> <i>MTCC</i> 6820

Cited by 6 publications

References 19 publications

Modeling the effect of non‐linear process parameters on the prediction of hydrogen production by steam reforming of bio‐oil and glycerol using artificial neural network

Modeling the effect of non‐linear process parameters on the prediction of hydrogen production by steam reforming of bio‐oil and glycerol using artificial neural network

Production and statistical optimization of cholesterol-oxidase generated by Streptomyces sp. AN strain

Anticipating faults by predicting non-linearity of environment variables with neural networks: a case study in semiconductor manufacturing

Contact Info

Product

Resources

About