Bioprocess Optimization of L-Lysine Production by Using RSM and Artificial Neural Networks from Corynebacterium glutamicum ATCC13032

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Vanasi Bhushanam ◽  
Ramesh Malothu
Keyword(s):  
Neural Network ◽  
Amino Acid ◽  
Corynebacterium Glutamicum ◽  
Large Scale ◽  
Incubation Temperature ◽  
Scale Production ◽  
Feed Forward Neural Network ◽  
Lysine Production ◽  
Important Amino Acid ◽  
Artificial Neural

AbstractL-Lysine is one of the important amino acid required for humans and animals. It has a high commercial market. Large scale production of this amino acid is essential to meet the commercial demands. Typically, L-lysine is produced by batch fermentation. In the present study, the important process, as well as nutrient parameters such as glucose concentration (g/L), rpm, incubation temperature (°C), pH and incubation time for L-lysine production by Corynebacterium glutamicum ATCC13032, were optimized by a combined approach of response surface methodology (RSM) with artificial neural network (ANN) method. Initially, 32 runs face central composite design was employed. In the first step, the data was analyzed by the RSM and the optimum conditions for L-lysine production were determined. In the second step, the same data was used to train the neural network. A feed-forward neural network with error backpropagation was used. The best network was obtained by optimizing the no of neurons in the hidden layer. From the best network, the optimized weights and predicted responses were used to optimize the conditions of the selected parameters by genetic algorithm (GA). Overall with the combination of RSM-ANN-GA onefold of L-lysine production from Corynebacterium glutamicum ATCC 13032 was improved.

scholarly journals An Industrial Micro-Defect Diagnosis System via Intelligent Segmentation Region

Sensors ◽  
2019 ◽  
Vol 19 (11) ◽  
pp. 2636 ◽  
Author(s):  
Xia Fang ◽  
Wang Jie ◽  
Tao Feng
Keyword(s):  
Neural Network ◽  
Defect Detection ◽  
Large Scale ◽  
Detection System ◽  
Scale Production ◽  
System Matrix ◽  
Rotating Platform ◽  
Limited Region ◽  
The Neural Network ◽  
Large Scale Production

In the field of machine vision defect detection for a micro workpiece, it is very important to make the neural network realize the integrity of the mask in analyte segmentation regions. In the process of the recognition of small workpieces, fatal defects are always contained in borderline areas that are difficult to demarcate. The non-maximum suppression (NMS) of intersection over union (IOU) will lose crucial texture information especially in the clutter and occlusion detection areas. In this paper, simple linear iterative clustering (SLIC) is used to augment the mask as well as calibrate the score of the mask. We propose an SLIC head of object instance segmentation in proposal regions (Mask R-CNN) containing a network block to learn the quality of the predict masks. It is found that parallel K-means in the limited region mechanism in the SLIC head improved the confidence of the mask score, in the context of our workpiece. A continuous fine-tune mechanism was utilized to continuously improve the model robustness in a large-scale production line. We established a detection system, which included an optical fiber locator, telecentric lens system, matrix stereoscopic light, a rotating platform, and a neural network with an SLIC head. The accuracy of defect detection is effectively improved for micro workpieces with clutter and borderline areas.

scholarly journals Efficient Synthesis of Rare Disaccharides by Engineered β-Glucosidase Based on Hydropathy Index

2020 ◽  
Author(s):  
Kangle Niu ◽  
Zhengyao Liu ◽  
Yuhui Feng ◽  
Tianlong Gao ◽  
Zhenzhen Wang ◽  
...  
Keyword(s):  
Amino Acid ◽  
Rational Design ◽  
Large Scale ◽  
Catalytic Site ◽  
Scale Production ◽  
Total Production ◽  
Amino Acid Residues ◽  
Hydropathy Index ◽  
Reverse Hydrolysis ◽  
Hydrolysis Activity

<p>Oligosaccharides have important therapeutic applications. A useful route for oligosaccharides synthesis, especially rare disaccharides, is reverse hydrolysis by <i>β</i>-glucosidase. However, the low conversion efficiency of disaccharides from monosaccharides limits its large-scale production because the equilibrium is biased in the direction of hydrolysis. Based on the analysis of the docking results, we hypothesized that the hydropathy index of key amino acid residues in the catalytic site is closely related with disaccharide synthesis and more hydrophilic residues located in the catalytic site would enhance reverse hydrolysis activity. In this study, positive variants<i> Tr</i>Cel1b<sup>I177S</sup>, <i>Tr</i>Cel1b<sup>I177S/I174S</sup>, and <i>Tr</i>Cel1b<sup>I177S/I174S/W173H</sup>, and one negative variant <i>Tr</i>Cel1b<sup>N240I</sup> were designed according to the <u>H</u>ydropathy <u>I</u>ndex <u>F</u>or <u>E</u>nzyme <u>A</u>ctivity (HIFEA) strategy. The reverse hydrolysis with <i>Tr</i>Cel1b<sup>I177S/I174S/W173H </sup>was accelerated and then the maximum total production (<a>195.8 mg/ml/mg enzyme</a>) of the synthesized disaccharides was increased 3.5-fold compared to that of wildtype. On the contrary, <a><i>Tr</i>Cel1b</a><sup>N240I</sup> lost reverse hydrolysis activity. The results demonstrate that<a> </a><a>the average hydropathy index</a> of <a>the key amino acid residues </a>in the catalytic site of<i> Tr</i>Cel1b is an important factor for the synthesis of laminaribiose, sophorose, and cellobiose. The HIFEA strategy provides a new perspective for the rational design of <i>β</i>-glucosidases used for the synthesis of oligosaccharides.</p>

Adaptive Power-Saving Mechanism for VoIP Over WiMAX Based on Artificial Neural Network

2019 ◽  
pp. 158-177
Author(s):  
Tamer Emara
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Power Saving ◽  
Ieee 802.16 ◽  
Feed Forward Neural Network ◽  
Artificial Neural ◽  
Adaptive Power ◽  
Artificial Neural Network Ann ◽  
Hidden Layer

The IEEE 802.16 system offers power-saving class type II as a power-saving algorithm for real-time services such as voice over internet protocol (VoIP) service. However, it doesn't take into account the silent periods of VoIP conversation. This chapter proposes a power conservation algorithm based on artificial neural network (ANN-VPSM) that can be applied to VoIP service over WiMAX systems. Artificial intelligent model using feed forward neural network with a single hidden layer has been developed to predict the mutual silent period that used to determine the sleep period for power saving class mode in IEEE 802.16. From the implication of the findings, ANN-VPSM reduces the power consumption during VoIP calls with respect to the quality of services (QoS). Experimental results depict the significant advantages of ANN-VPSM in terms of power saving and quality-of-service (QoS). It shows the power consumed in the mobile station can be reduced up to 3.7% with respect to VoIP quality.

Contributions to Predict the Malfunction Probability of the Human-Machine-Environment System, Using Artificial Neural Networks

2015 ◽  
Vol 760 ◽  
pp. 771-776
Author(s):  
Daniel Constantin Anghel ◽  
Nadia Belu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Design Experiment ◽  
Manufacturing Processes ◽  
Feed Forward Neural Network ◽  
Feed Forward ◽  
Linear Relationships ◽  
The Neural Network ◽  
Artificial Neural

This paper presents the application of Artificial Neural Networks to predict the malfunction probability of the human-machine-environment system, in order to provide some guidance to designers of manufacturing processes. Artificial Neural Networks excel in gathering difficult non-linear relationships between the inputs and outputs of a system. We used, in this work, a feed forward neural network in order to predict the malfunction probability. The neural network is simulated with Matlab. The design experiment presented in this paper was realized at University of Pitesti, at the Faculty of Mechanics and Technology, Technology and Management Department.

scholarly journals AraR, an l-Arabinose-Responsive Transcriptional Regulator in Corynebacterium glutamicum ATCC 31831, Exerts Different Degrees of Repression Depending on the Location of Its Binding Sites within the Three Target Promoter Regions

2015 ◽  
Vol 197 (24) ◽  
pp. 3788-3796 ◽  
Author(s):  
Takayuki Kuge ◽  
Haruhiko Teramoto ◽  
Masayuki Inui
Keyword(s):  
Corynebacterium Glutamicum ◽  
Binding Sites ◽  
Large Scale ◽  
Transcriptional Regulator ◽  
Scale Production ◽  
Primary Role ◽  
Promoter Regions ◽  
Independent Manner ◽  
Content Type

ABSTRACTInCorynebacterium glutamicumATCC 31831, a LacI-type transcriptional regulator AraR, represses the expression ofl-arabinose catabolism (araBDA), uptake (araE), and the regulator (araR) genes clustered on the chromosome. AraR binds to three sites: one (BSB) between the divergent operons (araBDAandgalM-araR) and two (BSE1and BSE2) upstream ofaraE.l-Arabinose acts as an inducer of the AraR-mediated regulation. Here, we examined the roles of these AraR-binding sites in the expression of the AraR regulon. BSBmutation resulted in derepression of botharaBDAandgalM-araRoperons. The effects of BSE1and/or BSE2mutation onaraEexpression revealed that the two sites independently function as theciselements, but BSE1plays the primary role. However, AraR was shown to bind to these sites with almost the same affinityin vitro. Taken together, the expression ofaraBDAandaraEis strongly repressed by binding of AraR to a single site immediately downstream of the respective transcriptional start sites, whereas the binding site overlapping the −10 or −35 region of thegalM-araRandaraEpromoters is less effective in repression. Furthermore, downregulation ofaraBDAandaraEdependent onl-arabinose catabolism observed in the BSBmutant and the AraR-independentaraRpromoter identified withingalM-araRadd complexity to regulation of the AraR regulon derepressed byl-arabinose.IMPORTANCECorynebacterium glutamicumhas a long history as an industrial workhorse for large-scale production of amino acids. An important aspect of industrial microorganisms is the utilization of the broad range of sugars for cell growth and production process. MostC. glutamicumstrains are unable to use a pentose sugarl-arabinose as a carbon source. However, genes forl-arabinose utilization and its regulation have been recently identified inC. glutamicumATCC 31831. This study elucidates the roles of the multiple binding sites of the transcriptional repressor AraR in the derepression byl-arabinose and thereby highlights the complex regulatory feedback loops in combination withl-arabinose catabolism-dependent repression of the AraR regulon in an AraR-independent manner.

scholarly journals Online Rotor and Stator Resistance Estimation Based on Artificial Neural Network Applied in Sensorless Induction Motor Drive

Energies ◽  
2020 ◽  
Vol 13 (18) ◽  
pp. 4946
Author(s):  
Tuan Pham Van ◽  
Dung Vo Tien ◽  
Zbigniew Leonowicz ◽  
Michal Jasinski ◽  
Tomasz Sikorski ◽  
...  
Keyword(s):  
Neural Network ◽  
Induction Motor ◽  
Learning Rate ◽  
Accurate Estimation ◽  
Motor Drive ◽  
Induction Motor Drive ◽  
Feed Forward Neural Network ◽  
The Neural Network ◽  
Artificial Neural ◽  
Stator Resistance

This paper presents a new approach method for online rotor and stator resistance estimation of induction motors using artificial neural networks for the sensorless drive. In this method, the rotor resistance is estimated by a feed-forward neural network with the learning rate as a function. The stator resistance is also estimated using the two-layered neural network with learning rate as a function. The speed of the induction motor is also estimated by the neural network. Therefore, the accurate estimation of the rotor and stator resistance improved the quality of the sensorless induction motor drive. The results of simulation and experiment show that the estimated speed tracks the real speed of the induction motor; simultaneously, the error between the estimated rotor and stator resistance using neural network and the normal rotor and stator resistance is very small.

Increasing l-lysine production in Corynebacterium glutamicum by engineering amino acid transporters

Amino Acids ◽  
2020 ◽  
Vol 52 (10) ◽  
pp. 1363-1374
Author(s):  
Jing Xiao ◽  
Datao Wang ◽  
Lei Wang ◽  
Yanjun Jiang ◽  
Le Xue ◽  
...  
Keyword(s):  
Amino Acid ◽  
Corynebacterium Glutamicum ◽  
Amino Acid Transporters ◽  
Lysine Production

Artificial Neural Network to Predict Patient Body Circumferences and Ligament Thicknesses

2013 ◽  
Author(s):  
Neil Vaughan ◽  
Venketesh N. Dubey ◽  
Michael Y. K. Wee ◽  
Richard Isaacs
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Patient Specific ◽  
Feed Forward Neural Network ◽  
Training Experience ◽  
Thigh Circumference ◽  
Data Set ◽  
Artificial Neural ◽  
Body Circumferences ◽  
Space Data

An artificial neural network has been implemented and trained with clinical data from 23088 patients. The aim was to predict a patient’s body circumferences and ligament thickness from patient data. A fully connected feed-forward neural network is used, containing no loops and one hidden layer and the learning mechanism is back-propagation of error. Neural network inputs were mass, height, age and gender. There are eight hidden neurons and one output. The network can generate estimates for waist, arm, calf and thigh circumferences and thickness of skin, fat, Supraspinous and interspinous ligaments, ligamentum flavum and epidural space. Data was divided into a training set of 11000 patients and an unseen test data set of 12088 patients. Twenty five training cycles were completed. After each training cycle neuron outputs advanced closer to the clinically measured data. Waist circumference was predicted within 3.92cm (3.10% error), thigh circumference 2.00cm, (2.81% error), arm circumference 1.21cm (2.48% error), calf circumference 1.41cm, (3.40% error), triceps skinfold 3.43mm, (7.80% error), subscapular skinfold 3.54mm, (8.46% error) and BMI was estimated within 0.46 (0.69% error). The neural network has been extended to predict ligament thicknesses using data from MRI. These predictions will then be used to configure a simulator to offer a patient-specific training experience.

Sign in / Sign up

Export Citation Format

Share Document