Design of experiment (DOE) applied to artificial neural network architecture enables rapid bioprocess improvement.
Ontology highlight
ABSTRACT:
SUBMITTER: Rodriguez-Granrose D
PROVIDER: S-EPMC8144078 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Solubility of hydrogen sulfide (H2S) in 46 single and blended physical absorbents, amines, ionic liquids, and hybrid absorbents of amines + ionic liquids and amines + physical absorbents was successfully predicted based on artificial neural networks (ANNs). Three neural network algorithms of Levenberg-Marquardt (LM), Bayesian regularization (BR), and scaled conjugate gradient (SCG) were applied for architecting the ANN models. The results showed that both the number of hidden neurons and the prediction algorithm affected the prediction of H2S solubility. Based on the mean square error (MSE) and determination coefficient (R 2), the most attractive model was the LM-ANN model with 17 hidden neurons. As a result, very satisfactory prediction performance (for the testing data set) with an MSE of 0.0014 and an R 2 of 0.9817 was obtained from the developed LM-ANN model. Additionally, a parity chart confirmed that the predicted solubility of H2S well aligned with the experimental data. To effectively absorb H2S and maintain high solubility of H2S, the absorbent should be well complied with the operating pressure. For a low-pressure range of less than 100 kPa, amines are very attractive. As the pressure elevated to 100-1000 kPa, amines and hybrid amine + physical absorbents are suggested. Lastly, at a high pressure over 1000 kPa, physical absorbents and ionic liquids are recommended.
| S-EPMC8613862 | biostudies-literature
Project description:Despite advancements in prosthetic technologies, patients with amputation today suffer great diminution in mobility and quality of life. We have developed a modified below-knee amputation (BKA) procedure that incorporates agonist-antagonist myoneural interfaces (AMIs), which surgically preserve and couple agonist-antagonist muscle pairs for the subtalar and ankle joints. AMIs are designed to restore physiological neuromuscular dynamics, enable bidirectional neural signaling, and offer greater neuroprosthetic controllability compared to traditional amputation techniques. In this prospective, nonrandomized, unmasked study design, 15 subjects with AMI below-knee amputation (AB) were matched with 7 subjects who underwent a traditional below-knee amputation (TB). AB subjects demonstrated significantly greater control of their residual limb musculature, production of more differentiable efferent control signals, and greater precision of movement compared to TB subjects (P < 0.008). This may be due to the presence of greater proprioceptive inputs facilitated by the significantly higher fascicle strains resulting from coordinated muscle excursion in AB subjects (P < 0.05). AB subjects reported significantly greater phantom range of motion postamputation (AB: 12.47 ± 2.41, TB: 10.14 ± 1.45 degrees) when compared to TB subjects (P < 0.05). Furthermore, AB subjects also reported less pain (12.25 ± 5.37) than TB subjects (17.29 ± 10.22) and a significant reduction when compared to their preoperative baseline (P < 0.05). Compared with traditional amputation, the construction of AMIs during amputation confers the benefits of enhanced physiological neuromuscular dynamics, proprioception, and phantom limb perception. Subjects' activation of the AMIs produces more differentiable electromyography (EMG) for myoelectric prosthesis control and demonstrates more positive clinical outcomes.
| S-EPMC7936324 | biostudies-literature
Project description:This paper provides a novel procedure to estimate the education level of social network (SN) users by leveraging artificial neural networks (ANN). Additionally, it provides a robust methodology to extract explanatory insights from ANN models. It also contributes to the study of socio-demographic phenomena by utilizing less explored data sources, such as social media. It proposes Twitter data as an alternative data source for in-depth social studies, and ANN for complex patterns recognition. Moreover, cutting edge technology, such as face recognition, on social media data are applied to explain the social characteristics of country-specific users. We use nine variables and three hidden layers of neurons to identify high-skilled users. The resulted model describes well the level of education by correctly estimating it with an accuracy of 95% on the training set and an accuracy of 92% on a testing set. Approximately 30% of the analyzed users are highly skilled and this share does not differ among the two genders. However, it tends to be lower among users younger than 30 years old.Supplementary informationThe online version contains supplementary material available at 10.1007/s13278-021-00832-1.
| S-EPMC8558764 | biostudies-literature
Project description:To effectively predict the thermal conductivity and viscosity of alumina (Al₂O₃)-water nanofluids, an artificial neural network (ANN) approach was investigated in the present study. Firstly, using a two-step method, four Al₂O₃-water nanofluids were prepared respectively by dispersing different volume fractions (1.31%, 2.72%, 4.25%, and 5.92%) of nanoparticles with the average diameter of 30 nm. On this basis, the thermal conductivity and viscosity of the above nanofluids were analyzed experimentally under various temperatures ranging from 296 to 313 K. Then a radial basis function (RBF) neural network was constructed to predict the thermal conductivity and viscosity of Al₂O₃-water nanofluids as a function of nanoparticle volume fraction and temperature. The experimental results showed that both nanoparticle volume fraction and temperature could enhance the thermal conductivity of Al₂O₃-water nanofluids. However, the viscosity only depended strongly on Al₂O₃ nanoparticle volume fraction and was increased slightly by changing temperature. In addition, the comparative analysis revealed that the RBF neural network had an excellent ability to predict the thermal conductivity and viscosity of Al₂O₃-water nanofluids with the mean absolute percent errors of 0.5177% and 0.5618%, respectively. This demonstrated that the ANN provided an effective way to predict the thermophysical properties of nanofluids with limited experimental data.
| S-EPMC5459072 | biostudies-other
Project description:Impact of wetting and drying on soil carbon cycling and microbial community composition: An artificial soil column experiment
| PRJEB28313 | ENA
Project description:Background and study aims Scoring endoscopic disease activity in colitis represents a complex task for artificial intelligence (AI), but is seen as a worthwhile goal for clinical and research use cases. To date, development attempts have relied on large datasets, achieving reasonable results when comparing normal to active inflammation, but not when generating subscores for the Mayo Endoscopic Score (MES) or ulcerative colitis endoscopic index of severity (UCEIS). Patients and methods Using a multi-task learning framework, with frame-by-frame analysis, we developed a machine-learning algorithm (MLA) for UCEIS trained on just 38,124 frames (73 patients with biopsy-proven ulcerative colitis). Scores generated by the MLA were compared to consensus scores from three independent human reviewers. Results Accuracy and agreement (kappa) were calculated for the following differentiation tasks: (1) normal mucosa vs active inflammation (UCEIS 0 vs ≥ 1; accuracy 0.90, κ = 0.90); (2) mild inflammation vs moderate-severe (UCEIS 0-3 vs ≥ 4; accuracy 0.98, κ = 0.96); (3) generating total UCEIS score (κ = 0.92). Agreement for UCEIS subdomains was also high (κ = 0.80, 0.83 and 0.88 for vascular pattern, bleeding and erosions respectively). Conclusions We have demonstrated that, using modified data science techniques and a relatively smaller datasets, it is possible to achieve high levels of accuracy and agreement with human reviewers (in some cases near-perfect), for AI in colitis scoring. Further work will focus on refining this technique, but we hope that it can be used in other tasks to facilitate faster development.
| S-EPMC9010092 | biostudies-literature
Project description:BACKGROUND: Little is known about bacterial transcriptional regulatory networks (TRNs). In Escherichia coli, which is the organism with the largest wet-lab validated TRN, its set of interactions involves only approximately 50% of the repertoire of transcription factors currently known, and ~25% of its genes. Of those, only a small proportion describes the regulation of processes that are clinically relevant, such as drug resistance mechanisms. RESULTS: We designed feed-forward (FF) and bi-fan (BF) motif predictors for E. coli using multi-layer perceptron artificial neural networks (ANNs). The motif predictors were trained using a large dataset of gene expression data; the collection of motifs was extracted from the E. coli TRN. Each network motif was mapped to a vector of correlations which were computed using the gene expression profile of the elements in the motif. Thus, by combining network structural information with transcriptome data, FF and BF predictors were able to classify with a high precision of 83% and 96%, respectively, and with a high recall of 86% and 97%, respectively. These results were found when motifs were represented using different types of correlations together, i.e., Pearson, Spearman, Kendall, and partial correlation. We then applied the best predictors to hypothesize new regulations for 16 operons involved with multidrug resistance (MDR) efflux pumps, which are considered as a major bacterial mechanism to fight antimicrobial agents. As a result, the motif predictors assigned new transcription factors for these MDR proteins, turning them into high-quality candidates to be experimentally tested. CONCLUSION: The motif predictors presented herein can be used to identify novel regulatory interactions by using microarray data. The presentation of an example motif to predictors will make them categorize whether or not the example motif is a BF, or whether or not it is an FF. This approach is useful to find new "pieces" of the TRN, when inspecting the regulation of a small set of operons. Furthermore, it shows that correlations of expression data can be used to discriminate between elements that are arranged in structural motifs and those in random sets of transcripts.
| S-EPMC2453137 | biostudies-literature
Project description:Adsorption of hydroxychloroquine (HCQ) onto H3PO4-activated Cystoseira barbata (Stackhouse) C. Agardh (derived from algal biodiesel industry waste) biochar was investigated via batch experiments and mathematical models. The activated biochar (BC-H) was produced in a single step by using the microwave irradiation method. Thus, it was obtained with a low cost, energy efficiency and by promoting clean production processes. BC-H exhibited a remarkable adsorption efficiency (98.9%) and large surface area (1088.806 m2 g-1) for removal of HCQ. The Langmuir isotherm and the pseudo-second-order kinetic models were the best fit for the equilibrium adsorption and kinetics experiments, and the maximum monolayer adsorption capacity (qmax) was found to be 353.58 µg g-1. Additionally, the experiments with real wastewater showed that BC-H's ability to adsorb HCQ was not affected by competitive ions in the water. The Taguchi orthogonal array (L16 OA) experimental design was applied for the effective cost optimization analyses of the adsorption process by considering four levels and four controllable factors (initial pH, HCQ concentration, amount of adsorbent and contact time). Scanning electron microscopy, Fourier transform infrared spectroscopy and Brunauer-Emmett-Teller analyses were used for characterizing the adsorbent. The findings showed that BC-H can be used as an effective and low-cost adsorbent in the removal of HCQ from water.Graphical abstractSupplementary informationThe online version contains supplementary material available at 10.1007/s13369-021-06235-w.
| S-EPMC8505786 | biostudies-literature
Project description:Live cell segmentation is a crucial step in biological image analysis and is also a challenging task because time-lapse microscopy cell sequences usually exhibit complex spatial structures and complicated temporal behaviors. In recent years, numerous deep learning based methods have been proposed to tackle this task and obtained promising results. However, designing a network with excellent performance requires professional knowledge and expertise and is very time-consuming and labor-intensive. Recently emerged neural architecture search (NAS) methods hold great promise in eliminating these disadvantages, because they can automatically search an optimal network for the task. We propose a novel NAS based solution for deep-learning based cell segmentation in time-lapse microscopy images. Different from current NAS methods, we propose 1) jointly searching non-repeatable micro architectures to construct the macro network for exploring greater NAS potential and better performance and 2) defining a specific search space suitable for the live cell segmentation task, including the incorporation of a convolutional long short-term memory network for exploring the temporal information in time-lapse sequences. Comprehensive evaluations on the 2D datasets from the cell tracking challenge demonstrate the competitiveness of the proposed method compared to the state of the art. The experimental results show that the method is capable of achieving more consistent top performance across all ten datasets than the other challenge methods. The executable files of the proposed method as well as configurations for each dataset used in the presented experiments will be available for non-commercial purposes from https://github.com/291498346/nas_cellseg. Supplementary data are available at Bioinformatics online.
| S-EPMC8665766 | biostudies-literature
Project description:This paper presents a study of the Ti-6Al-4V alloy milling under different lubrication conditions, using the minimum quantity lubrication approach. The chosen material is widely used in the industry due to its properties, although they present difficulties in terms of their machinability. A minimum quantity lubrication (MQL) prototype valve was built for this purpose, and machining followed a previously defined experimental design with three lubrication strategies. Speed, feed rate, and the depth of cut were considered as independent variables. As design-dependent variables, cutting forces, torque, and roughness were considered. The desirability optimization function was used in order to obtain the best input data indications, in order to minimize cutting and roughness efforts. Supervised artificial neural networks of the multilayer perceptron type were created and tested, and their responses were compared statistically to the results of the factorial design. It was noted that the variables that most influenced the machining-dependent variables were the feed rate and the depth of cut. A lower roughness value was achieved with MQL only with the use of cutting fluid with graphite. Statistical analysis demonstrated that artificial neural network and the experimental design predict similar results.
| S-EPMC7504553 | biostudies-literature