RESUMEN
Among primates, humans are special in their ability to create and manipulate highly elaborate structures of language, mathematics, and music. Here we show that this sensitivity to abstract structure is already present in a much simpler domain: the visual perception of regular geometric shapes such as squares, rectangles, and parallelograms. We asked human subjects to detect an intruder shape among six quadrilaterals. Although the intruder was always defined by an identical amount of displacement of a single vertex, the results revealed a geometric regularity effect: detection was considerably easier when either the base shape or the intruder was a regular figure comprising right angles, parallelism, or symmetry rather than a more irregular shape. This effect was replicated in several tasks and in all human populations tested, including uneducated Himba adults and French kindergartners. Baboons, however, showed no such geometric regularity effect, even after extensive training. Baboon behavior was captured by convolutional neural networks (CNNs), but neither CNNs nor a variational autoencoder captured the human geometric regularity effect. However, a symbolic model, based on exact properties of Euclidean geometry, closely fitted human behavior. Our results indicate that the human propensity for symbolic abstraction permeates even elementary shape perception. They suggest a putative signature of human singularity and provide a challenge for nonsymbolic models of human shape perception.
Asunto(s)
Percepción de Forma/fisiología , Reconocimiento Visual de Modelos/fisiología , Percepción Visual/fisiología , Adulto , Animales , Preescolar , Femenino , Humanos , Lenguaje , Masculino , Persona de Mediana Edad , Redes Neurales de la Computación , Papio , Especificidad de la Especie , Visión Ocular/fisiologíaRESUMEN
Microalgae, a group of photosynthetic microorganisms, are a promising feedstock for biodiesel production, but their biomass retrieval is a challenging task. Flocculation is a feasible method for dewatering and harvesting microalgae biomass. In the current study, the effect of alum flocculation on Chlorella vulgaris biomass retrieval has been studied. Alum structural changes with pH were led to a full factorial design to address the effect of this chemical structure changes at different pH values. It is observed that the best flocculation efficiency could be achieved in the natural pH value of C. vulgaris growth medium (8.2) with less than 0.5 g/L flocculant addition, which would lead to the flocculation efficiency of more than 90%. An ensemble architecture of neural networks successfully employed for flocculation modeling.
Asunto(s)
Chlorella vulgaris , Microalgas , Compuestos de Alumbre , Biomasa , Floculación , Concentración de Iones de HidrógenoRESUMEN
Given the functional complexities of soft tissues and organs, it is clear that computational simulations are critical in their understanding and for the rational basis for the development of therapies and replacements. A key aspect of such simulations is accounting for their complex, nonlinear, anisotropic mechanical behaviors. While soft tissue material models have developed to the point of high fidelity, in-silico implementation is typically done using the finite element (FE) method, which remains impractically slow for translational clinical time frames. As a potential path toward addressing the development of high fidelity simulations capable of performing in clinically relevant time frames, we review the use of neural networks (NN) for soft tissue and organ simulation using two approaches. In the first approach, we show how a NN can learn the responses for a detailed meso-structural soft tissue material model. The NN material model not only reproduced the full anisotropic mechanical responses but also demonstrated a considerable efficiency improvement, as it was trained over a range of realizable fibrous structures. In the second approach, we go a step further with the use of a physics-based surrogate model to directly learn the displacement field solution without the need for raw training data or FE simulation datasets. In this approach we utilize a finite element mesh to define the domain and perform the necessary integrations, but not the finite element method (FEM) itself. We demonstrate with this approach, termed neural network finite element (NNFE), results in a trained NNFE model with excellent agreement with the corresponding "ground truth" FE solutions over the entire physiological deformation range on a cuboidal myocardium specimen. More importantly, the NNFE approach provided a significantly decreased computational time for a range of finite element mesh sizes. Specifically, as the FE mesh size increased from 2744 to 175,615 elements, the NNFE computational time increased from 0.1108 s to 0.1393 s, while the "ground truth" FE model increased from 4.541 s to 719.9 s, with the same effective accuracy. These results suggest that NNFE run times are significantly reduced compared with the traditional large-deformation-based finite element solution methods. We then show how a nonuniform rational B-splines (NURBS)-based approach can be directly integrated into the NNFE approach as a means to handle real organ geometries. While these and related approaches are in their early stages, they offer a method to perform complex organ-level simulations in clinically relevant time frames without compromising accuracy.
Asunto(s)
Modelos Biológicos , Redes Neurales de la Computación , Simulación por Computador , Análisis de Elementos FinitosRESUMEN
Simulations of neural networks can be used to study the direct effect of internal or external changes on brain dynamics. However, some changes are not immediate but occur on the timescale of weeks, months, or years. Examples include effects of strokes, surgical tissue removal, or traumatic brain injury but also gradual changes during brain development. Simulating network activity over a long time, even for a small number of nodes, is a computational challenge. Here, we model a coupled network of human brain regions with a modified Wilson-Cowan model representing dynamics for each region and with synaptic plasticity adjusting connection weights within and between regions. Using strategies ranging from different models for plasticity, vectorization and a different differential equation solver setup, we achieved one second runtime for one second biological time.
RESUMEN
In this study, bamboo carrier based lab scale compost biofilter was evaluated to treat synthetic waste air containing trichloroethylene (TCE) under continuous operation mode. The effect of inlet TCE concentration and gas flow rate and its removal was investigated. Maximum TCE removal efficiency was found to be 89% under optimum conditions of inlet 0.986â¯g/m3 TCE concentration corresponding to a loading rate of 43â¯g/m3 h and 0.042â¯m3/h gas flow rate at empty bed residence time (EBRT) of 2â¯min. For the first time, Artificial Neural Network (ANN) was applied to predict the performance of the compost biofilter in terms of TCE removal. The ANN model used a three layer feed forward based Levenberg-Marquardt algorithm, and its topology consisted of 3-25-1 as the optimum number for the three layers (input, hidden and output). An excellent match between the experimental and ANN predicted the value of TCE removal was obtained with a coefficient of determination (R2) value greater than 0.99 during the model training, validation, testing and overall. Furthermore, statistical analysis of the ANN model performance mediated its prediction accuracy of the bioreactor to treat TCE contaminated systems.
Asunto(s)
Tricloroetileno , Biodegradación Ambiental , Reactores Biológicos , Filtración , Gases , Redes Neurales de la ComputaciónRESUMEN
Huber and O'Reilly (2003) proposed that neural habituation exists to solve a temporal parsing problem, minimizing blending between one word and the next when words are visually presented in rapid succession. They developed a neural dynamics habituation model, explaining the finding that short duration primes produce positive priming whereas long duration primes produce negative repetition priming. The model contains three layers of processing, including a visual input layer, an orthographic layer, and a lexical-semantic layer. The predicted effect of prime duration depends both on this assumed representational hierarchy and the assumption that synaptic depression underlies habituation. The current study tested these assumptions by comparing different kinds of words (e.g., words versus non-words) and different kinds of word-word relations (e.g., associative versus repetition). For each experiment, the predictions of the original model were compared to an alternative model with different representational assumptions. Experiment 1 confirmed the prediction that non-words and inverted words require longer prime durations to eliminate positive repetition priming (i.e., a slower transition from positive to negative priming). Experiment 2 confirmed the prediction that associative priming increases and then decreases with increasing prime duration, but remains positive even with long duration primes. Experiment 3 replicated the effects of repetition and associative priming using a within-subjects design and combined these effects by examining target words that were expected to repeat (e.g., viewing the target word 'BACK' after the prime phrase 'back to'). These results support the originally assumed representational hierarchy and more generally the role of habituation in temporal parsing and priming.
Asunto(s)
Habituación Psicofisiológica/fisiología , Modelos Psicológicos , Psicolingüística , Memoria Implícita/fisiología , Adulto , Humanos , Lectura , Adulto JovenRESUMEN
Egg size is one of the important properties of egg that is judged by customers. Accordingly, in egg sorting and grading, the size of eggs must be considered. In this research, a new method of egg volume prediction was proposed without need to measure weight of egg. An accurate and efficient image processing algorithm was designed and implemented for computing major and minor diameters of eggs. Two methods of egg size modeling were developed. In the first method, a mathematical model was proposed based on Pappus theorem. In second method, Artificial Neural Network (ANN) technique was used to estimate egg volume. The determined egg volume by these methods was compared statistically with actual values. For mathematical modeling, the R(2), Mean absolute error and maximum absolute error values were obtained as 0.99, 0.59 cm(3) and 1.69 cm(3), respectively. To determine the best ANN, R(2) test and RMSEtest were used as selection criteria. The best ANN topology was 2-28-1 which had the R(2) test and RMSEtest of 0.992 and 0.66, respectively. After system calibration, the proposed models were evaluated. The results which indicated the mathematical modeling yielded more satisfying results. So this technique was selected for egg size determination.
RESUMEN
Perception of the external world is based on the integration of inputs from different sensory modalities. Recent experimental findings suggest that this phenomenon is present in lower-level cortical areas at early processing stages. The mechanisms underlying these early processes and the organization of the underlying circuitries are still a matter of debate. Here, we investigate audiovisual interactions by means of a simple neural network consisting of two layers of visual and auditory neurons. We suggest that the spatial and temporal aspects of audio-visual illusions can be explained within this simple framework, based on two main assumptions: auditory and visual neurons communicate via excitatory synapses; and spatio-temporal receptive fields are different in the two modalities, auditory processing exhibiting a higher temporal resolution, while visual processing a higher spatial acuity. With these assumptions, the model is able: i) to simulate the sound-induced flash fission illusion; ii) to reproduce psychometric curves assuming a random variability in some parameters; iii) to account for other audio-visual illusions, such as the sound-induced flash fusion and the ventriloquism illusions; and iv) to predict that visual and auditory stimuli are combined optimally in multisensory integration. In sum, the proposed model provides a unifying summary of spatio-temporal audio-visual interactions, being able to both account for a wide set of empirical findings, and be a framework for future experiments. In perspective, it may be used to understand the neural basis of Bayesian audio-visual inference.
Asunto(s)
Estimulación Acústica/métodos , Corteza Auditiva/fisiología , Percepción Auditiva/fisiología , Ilusiones/fisiología , Modelos Neurológicos , Corteza Visual/fisiología , Percepción Visual/fisiología , Simulación por Computador , Señales (Psicología) , Humanos , Red Nerviosa/fisiología , Vías Nerviosas/fisiologíaRESUMEN
This study investigated the coexistence and contamination of manganese (Mn(II)) and arsenite (As(III)) in groundwater and examined their oxidation behavior under different equilibrating parameters, including varying pH, bicarbonate (HCO3-) concentrations, and sodium hypochlorite (NaClO) oxidant concentrations. Results showed that if the molar ratio of NaClO: As(III) was >1, the oxidation of As(III) could be achieved within a minute with an extremely high oxidation rate of 99.7 %. In the binary system, the removal of As(III) prevailed over Mn(II). The As(III) oxidation efficiency increased from 59.8 ± 0.6 % to 70.8 ± 1.9 % when pH rose from 5.7 to 8.0. The oxidation reaction between As(III) and NaClO releases H+ ions, decreasing the pH from 6.77 to 6.19 and reducing the removal efficiency of Mn(II). The presence of HCO3- reduced the oxidation rate of Mn(II) from 63.2 % to 13.9 % within four hours. Instead, the final oxidation rate of Mn(II) increased from 68.1 % to 87.7 %. This increase can be attributed to HCO3- ions competing with the free Mn(II) for the adsorption sites on the sediments, inhibiting the formation of H+. Moreover, kinetic studies revealed that the oxidation reaction between Mn(II) and NaClO followed first-order kinetics based on their R2 values. The significant factors affecting the Mn(II) oxidation efficiency were the initial concentration of NaClO and pH. Applying an artificial neural network (ANN) model for data analysis proved to be an effective tool for predicting Mn(II) oxidation rates under different experimental conditions. The actual Mn(II) oxidation data and the predicted values obtained from the ANN model showed significant consistency. The training and validation data sets yielded R2 values of 0.995 and 0.992, respectively. Moreover, the ANN model highlights the importance of pH and NaClO concentrations in influencing the oxidation rate of Mn(II).
Asunto(s)
Arsenitos , Manganeso , Redes Neurales de la Computación , Oxidación-Reducción , Manganeso/química , Arsenitos/química , Cinética , Halogenación , Contaminantes Químicos del Agua/química , Concentración de Iones de Hidrógeno , Purificación del Agua , Bicarbonatos/químicaRESUMEN
Recently, Zhang et al. (Nature communications, 9(1), 3730, 2018) proposed an interesting model of attention guidance that uses visual features learnt by convolutional neural networks (CNNs) for object classification. I adapted this model for search experiments, with accuracy as the measure of performance. Simulation of our previously published feature and conjunction search experiments revealed that the CNN-based search model proposed by Zhang et al. considerably underestimates human attention guidance by simple visual features. Using target-distractor differences instead of target features for attention guidance or computing attention map at lower layers of the network could improve the performance. Still, the model fails to reproduce qualitative regularities of human visual search. The most likely explanation is that standard CNNs that are trained on image classification have not learnt medium- or high-level features required for human-like attention guidance.
Asunto(s)
Aprendizaje , Redes Neurales de la Computación , HumanosRESUMEN
Helichrysum italicum (immortelle) essential oil is one of the most popular essential oils worldwide and it has many beneficial properties, including antimicrobial. However, in this plant, the chemical diversity of the essential oil is very pronounced. The aim of this work was to process the GC-MS results of four samples of H. italicum essential oil of Serbian origin by chemometric tools, and evaluate the antimicrobial activity in vitro and in silico. Overall, 47 compounds were identified, the most abundant were γ-curcumene, α-pinene, and ar-curcumene, followed by α-ylangene, neryl acetate, trans-caryophyllene, italicene, α-selinene, limonene, and italidiones. Although the four samples of H. italicum essential oil used in this study were obtained from different producers in Serbia, they belong to the type of essential oil rich in sesquiterpenes (γ-curcumene and ar-curcumene chemotype). In vitro antimicrobial potential showed that five were sensitive among ten strains of tested microorganisms: Staphylococcus aureus, Listeria monocytogenes, Bacillus cereus, Saccharomyces cerevisiae, and Candida albicans. Therefore, these microorganism models were used further for in silico molecular docking through the mechanism of ATP-ase inhibitory activity. Results showed that among all compounds from H. italicum essential oil, neryl acetate has the highest predicted binding energy. Artificial neural network modeling (ANN) showed that two major compounds γ-curcumene and α-pinene, as well as minor compounds such as trans-ß-ocimene, terpinolene, terpinene-4-ol, isoitalicene, italicene, cis-α-bergamotene, trans-α-bergamotene, italidiones, trans-ß-farnesene, γ-selinene, ß-selinene, α-selinene, and guaiol are responsible for the antimicrobial activity of H. italicum essential oil. The results of this study indicate that H. italicum essential oil samples rich in γ-curcumene, α-pinene, and ar-curcumene cultivated in Serbia (Balkan) have antimicrobial potential both in vitro and in silico. In addition, according to ANN modeling, the proportion of neryl acetate and other compounds detected in these samples has the potential to exhibit antimicrobial activity.
RESUMEN
In the adult brain, structural and functional parameters, such as synaptic sizes and neuronal firing rates, follow right-skewed and heavy-tailed distributions. While this organization is thought to have significant implications, its development is still largely unknown. Here, we address this knowledge gap by investigating a large-scale dataset recorded from the prefrontal cortex and the olfactory bulb of mice aged 4-60 postnatal days. We show that firing rates and spike train interactions have a largely stable distribution shape throughout the first 60 postnatal days and that the prefrontal cortex displays a functional small-world architecture. Moreover, early brain activity exhibits an oligarchical organization, where high-firing neurons have hub-like properties. In a neural network model, we show that analogously right-skewed and heavy-tailed synaptic parameters are instrumental to consistently recapitulate the experimental data. Thus, functional and structural parameters in the developing brain are already extremely distributed, suggesting that this organization is preconfigured and not experience dependent.
Asunto(s)
Encéfalo , Animales , Ratones , Encéfalo/crecimiento & desarrollo , Bulbo Olfatorio/crecimiento & desarrollo , Neuronas/metabolismo , Ratones Endogámicos C57BL , Sinapsis/metabolismo , Sinapsis/fisiología , Corteza Prefrontal/crecimiento & desarrollo , Corteza Prefrontal/citología , Potenciales de Acción/fisiología , Red Nerviosa/crecimiento & desarrollo , Modelos NeurológicosRESUMEN
This paper presents a new method of process parameter optimization, adequate for 3D printing of PLA (Polylactic Acid) components. The authors developed a new piece of Hybrid Manufacturing Equipment (HME), suitable for producing complex parts made from a biodegradable thermoplastic polymer, to promote environmental sustainability. Our new HME equipment produces PLA parts by both additive and subtractive techniques, with the aim of obtaining accurate PLA components with good surface quality. A design of experiments has been applied for optimization purposes. The following manufacturing parameters were analyzed: rotation of the spindle, cutting depth, feed rate, layer thickness, nozzle speed, and surface roughness. Linear regression models and neural network models were developed to improve and predict the surface roughness of the manufactured parts. A new test part was designed and manufactured from PLA to validate the new mathematical models, which can now be applied for producing complex parts made from polymer materials. The neural network modeling (NNM) allowed us to obtain much better precision in predicting the final surface roughness (Ra), as compared to the conventional linear regression models (LNM). Based on these modelling methods, the authors developed a practical methodology to optimize the process parameters in order to improve the surface quality of the 3D-printed components and to predict the actual roughness values. The main advantages of the results proposed for hybrid manufacturing using polymer materials like PLA are the optimized process parameters for both 3D printing and milling. A case study has been undertaken by the authors, who designed a specific test part for their new hybrid manufacturing equipment (HME), in order to test the new methodology of optimizing the process parameters, to validate the capability of the new HME. At the same time, this new methodology could be replicated by other researchers and is useful as a guideline on how to optimize the process parameters for newly developed equipment. The innovative approach holds potential for widespread equipment functionality enhancement among other users.
RESUMEN
Aiming at the accurate prediction of the inception of instability in a compressor, a dynamic system stability model is proposed based on a sparrow-inspired meta-heuristic optimization algorithm in this article. To achieve this goal, a spatial mode is employed for flow field feature extraction and modeling object acquisition. The nonlinear characteristic presented in the system is addressed using fuzzy entropy as the identification strategy to provide a basis for instability determination. Using Sparrow Search Algorithm (SSA) optimization, a Radial Basis Function Neural Network (RBFNN) is achieved for the performance prediction of system status. A Logistic SSA solution is first established to seek the optimal parameters of the RBFNN to enhance prediction accuracy and stability. On the basis of the RBFNN-LSSA hybrid model, the stall inception is detected about 35.8 revolutions in advance using fuzzy entropy identification. To further improve the multi-step network model, a Tent SSA is introduced to promote the accuracy and robustness of the model. A wider range of potential solutions within the TSSA are explored by incorporating the Tent mapping function. The TSSA-based optimization method proves a suitable adaptation for complex nonlinear dynamic modeling. And this method demonstrates superior performance, achieving 42 revolutions of advance warning with multi-step prediction. This RBFNN-TSSA model represents a novel and promising approach to the application of system modeling. These findings contribute to enhancing the abnormal warning capability of dynamic systems in compressors.
RESUMEN
This study explores the unexploited potential of Artificial Neural Network (ANN) optimization techniques in enhancing different drying methods and their influence on the characteristics of various sweet potato varieties. Focusing on the intricate interplay between drying methods and the unique characteristics of white, pink, orange, and purple sweet potatoes, the presented experimental study indicates the impact of ANN-driven optimization on food-related characteristics such as color, phenols content, biological activities (antioxidant, antimicrobial, anti-hyperglycemic, and anti-inflammatory), chemical, and mineral contents. The results unveil significant variations in drying method efficacy across different sweet potato types, underscoring the need for tailored optimization strategies. Specifically, purple sweet potatoes emerge as robust carriers of phenolic compounds, showcasing superior antioxidant activities. Furthermore, this study reveals the optimized parameters of dried sweet potato, such as total phenols content of 1677.76 mg/100 g and anti-inflammatory activity of 8.93%, anti-hyperglycemic activity of 24.42%. The upgraded antioxidant capability is presented through DPPHâ, ABTSâ+, RP, and SoA assays with values of 1500.56, 10,083.37, 3130.81, and 22,753.97 µg TE/100 g, respectively. Additionally, the moisture content in the lyophilized sample reached a minimum of 2.97%, holding favorable chemical and mineral contents. The utilization of ANN optimization proves instrumental in interpreting complex interactions and unlocking efficiencies in sweet potato drying processes, thereby contributing valuable insights to food science and technology.
RESUMEN
Anti-NMDA receptor autoantibodies (NMDAR-Abs) in patients with NMDAR encephalitis cause severe disease symptoms resembling psychosis and cause cognitive dysfunction. After passive transfer of patients' cerebrospinal fluid or human monoclonal anti-GluN1-autoantibodies in mice, we find a disrupted excitatory-inhibitory balance resulting from CA1 neuronal hypoexcitability, reduced AMPA receptor (AMPAR) signaling, and faster synaptic inhibition in acute hippocampal slices. Functional alterations are also reflected in widespread remodeling of the hippocampal proteome, including changes in glutamatergic and GABAergic neurotransmission. NMDAR-Abs amplify network γ oscillations and disrupt θ-γ coupling. A data-informed network model reveals that lower AMPAR strength and faster GABAA receptor current kinetics chiefly account for these abnormal oscillations. As predicted in silico and evidenced ex vivo, positive allosteric modulation of AMPARs alleviates aberrant γ activity, reinforcing the causative effects of the excitatory-inhibitory imbalance. Collectively, NMDAR-Ab-induced aberrant synaptic, cellular, and network dynamics provide conceptual insights into NMDAR-Ab-mediated pathomechanisms and reveal promising therapeutic targets that merit future in vivo validation.
Asunto(s)
Hipocampo , Transmisión Sináptica , Humanos , Ratones , Animales , Hipocampo/metabolismo , Receptores de N-Metil-D-Aspartato/metabolismo , Neuronas/metabolismo , Autoanticuerpos , Receptores AMPA/metabolismoRESUMEN
Popular social media platforms, such as Twitter, have become an excellent source of information with their swift information dissemination. Individuals with different backgrounds convey their opinions through social media platforms. Consequently, these platforms have become a profound instrument for collecting enormous datasets. We believe that compiling, organizing, exploring, and analyzing data from social media platforms, such as Twitter, can offer various perspectives to public health organizations and decision makers in identifying factors that contribute to vaccine hesitancy. In this study, public tweets were downloaded daily from Tweeter using the Tweeter API. Before performing computation, the tweets were preprocessed and labeled. Vocabulary normalization was based on stemming and lemmatization. The NRCLexicon technique was deployed to convert the tweets into ten classes: positive sentiment, negative sentiment, and eight basic emotions (joy, trust, fear, surprise, anticipation, anger, disgust, and sadness). t-test was used to check the statistical significance of the relationships among the basic emotions. Our analysis shows that the p-values of joy-sadness, trust-disgust, fear-anger, surprise-anticipation, and negative-positive relations are close to zero. Finally, neural network architectures, including 1DCNN, LSTM, Multiple-Layer Perceptron, and BERT, were trained and tested in a COVID-19 multi-classification of sentiments and emotions (positive, negative, joy, sadness, trust, disgust, fear, anger, surprise, and anticipation). Our experiment attained an accuracy of 88.6% for 1DCNN at 1744 s, 89.93% accuracy for LSTM at 27,597 s, while MLP achieved an accuracy of 84.78% at 203 s. The study results show that the BERT model performed the best, with an accuracy of 96.71% at 8429 s.
Asunto(s)
COVID-19 , Medios de Comunicación Sociales , Humanos , Análisis de Sentimientos , Vacunas contra la COVID-19 , Salud Pública , COVID-19/prevención & control , Minería de Datos , Redes Neurales de la Computación , VacunaciónRESUMEN
An ever-growing population together with globally depleting water resources pose immense stresses for water supply systems. Desalination technologies can reduce these stresses by generating fresh water from saline water sources. Reverse osmosis (RO), as the industry leading desalination technology, typically involves a complex network of membrane modules that separate unwanted particles from water. The optimal design and operation of these complex RO systems can be computationally expensive. In this work, we present a modeling and optimization strategy for addressing the optimal operation of an industrial-scale RO plant. We employ a feed-forward artificial neural network (ANN) surrogate modeling representation with rectified linear units as activation functions to capture the membrane behavior accurately. Several ANN set-ups and surrogate models are presented and evaluated, based on collected data from the H2Oaks RO desalination plant in South-Central Texas. The developed ANN is then transformed into a mixed-integer linear programming formulation for the purpose of minimizing energy consumption while maximizing water utilization. Trade-offs between the two competing objectives are visualized in a Pareto front, where indirect savings can be uncovered by comparing energy consumption for an array of water recoveries and feed flows.
RESUMEN
Membranes for carbon capture have improved significantly with various promoters such as amines and fillers that enhance their overall permeance and selectivity toward a certain particular gas. They require nominal energy input and can achieve bulk separations with lower capital investment. The results of an experiment-based membrane study can be suitably extended for techno-economic analysis and simulation studies, if its process parameters are interconnected to various membrane performance indicators such as permeance for different gases and their selectivity. The conventional modelling approaches for membranes cannot interconnect desired values into a single model. Therefore, such models can be suitably applicable to a particular parameter but would fail for another process parameter. With the help of artificial neural networks, the current study connects the concentrations of various membrane materials (polymer, amine, and filler) and the partial pressures of carbon dioxide and methane to simultaneously correlate three desired outputs in a single model: CO2 permeance, CH4 permeance, and CO2/CH4 selectivity. These parameters help predict membrane performance and guide secondary parameters such as membrane life, efficiency, and product purity. The model results agree with the experimental values for a selected membrane, with an average absolute relative error of 6.1%, 4.2%, and 3.2% for CO2 permeance, CH4 permeance, and CO2/CH4 selectivity, respectively. The results indicate that the model can predict values at other membrane development conditions.
RESUMEN
A near-infrared (NIR) spectrometer can perceive the change in characteristics of the grain reflectance spectrum quickly and nondestructively, which can be used to determine grain quality information. The full-band spectral information of samples of multiple physical states can be measured using existing instruments, yet it is difficult for the full-band instrument to be widely used in grain quality detection due to its high price, large size, non-portability, and inability to directly output the grain quality information. Because of the above problems, a phenotypic sensor about grain quality was developed for wheat, and four wavelengths were chosen. The interference of noise signals such as ambient light was eliminated by the phenotypic sensor using the modulated light signal and closed sample pool, the shape and size of the incident light spot of the light source were determined according to the requirement for collecting the reflectance spectrum of the grain, and the luminous units of the light source with stable light intensity and balanced luminescence were developed. Moreover, the sensor extracted the reflectance spectrum information using a weak optical signal conditioning circuit, which improved the resolution of the reflectance signal. A grain quality prediction model was created based on the actual moisture and protein content of grain obtained through Physico-chemical analyses. The calibration test showed that the R2 of the relative diffuse reflectance (RDR) of all four wavelengths of the phenotypic sensor and the reflectance of the diffusion fabrics were higher than 0.99. In the noise level and repeatability tests, the standard deviations of the RDR of two types of wheat measured by the sensor were much lower than 1.0%, indicating that the sensor could accurately collect the RDR of wheat. In the calibration test, the root mean square errors (RMSE) of protein and moisture content of wheat in the Test set were 0.4866 and 0.2161%, the mean absolute errors (MAEs) were 0.6515 and 0.3078%, respectively. The results showed that the NIR phenotypic sensor about grain quality developed in this study could be used to collect the diffuse reflectance of grains and the moisture and protein content in real-time.