Machine Learning-assisted Modeling Research Articles

Exam Assessor Tool: An Automated System for Efficient Answer Sheet Evaluation

With Education 4.0 and four quadrant approach number of innovations have gone into academics for efficient, experiential, and outcome-based education however assessment schemes are still very much dependent on manual assessment methods which are time-consuming and cumbersome. The grading system can sometimes be irrational, with diversified schemes for the same course and can also be biased. Covid 19 pandemic caused a global economic avalanche like we’ve never experienced in our lifetime. Many countries have implemented control measures such as blockades and curfews. The education system in this chaos saw a silver lining with academics shifting to online mode, with paradigm shift in teaching, assessment techniques too need to evolve. Work done is an effort to ease the process of assessment, a machine learning assisted model is developed that automates subjective answer evaluation in the education sector. Our project involved several crucial steps, including grayscale conversion, Natural Language Processing (NLP) for data cleansing, data splitting, and training an artificial neural network (ANN) to predict scores based on extracted features. ANN-based system grades subjective responses without human intervention, reducing the workload of teachers and professors. Model constructed an ANN architecture with three layers using Rectified Linear Activation Unit (ReLU) and Sigmoid activation functions. Trained model was incorporated into a user-friendly web application using the Streamlit library. Model design gives a major boost in grading efficiency and accuracy while providing valuable feedback to students. Research surveys were conducted, and a dataset was constructed for training and testing the model. study yielded an accuracy of 83.14% after employing techniques such as text cleaning, preprocessing, and feature extraction.

A comprehensive experimental and modeling study of the strain rate- and temperature-dependent deformation behavior of bio-degradable Mg-CeO2 nanocomposites

A comprehensive study was undertaken on the temperature-dependent and strain rate-sensitive deformation behavior of near-dense low-volume fraction magnesium-cerium dioxide (Mg-CeO2) nanocomposites synthesized by powder metallurgy technique. The process involved ball milling of elemental powders → cold compaction → sintering in an inert atmosphere, and in-situ hot extrusion. The Mg-CeO2 nanocomposites displayed strain rate and temperature sensitivity, exhibiting higher yield strength, superior compressive characteristics, greater hardness, and improved ductility compared to pure Mg and most commercial Mg alloys. Furthermore, a thorough micro-structural investigation was conducted to characterize the distributions of ceria nanoparticles, grain refinement degree, ceria-magnesium interface, formation of deformation twins and interfacial bonding between the reinforcement and matrix. The present study has proposed two modeling approaches, the Johnson–Cook (J–C) constitutive model and a machine learning-assisted model, to predict the mechanical behavior of monolithic Mg and Mg-CeO2 nanocomposites. The models effectively explained the deformation behavior under various strain rates and temperatures.

Effect of pulsed current cathodic protection on pipeline steel API 5L X65 corrosion mitigation: An investigation and machine learning-assisted modeling

Pulsed current cathodic protection (PCCP) could be more effective than direct current cathodic protection (DCCP) for mitigating corrosion in buried structures in the oil and gas industries if appropriate pulsed parameters are chosen. The purpose of this research is to present the corrosion prevention mechanism of the PCCP technique by taking into account the effects of duty cycle as well as frequency, modeling the relationships between pulse parameters (frequency and duty cycle) and system outputs (corrosion rate, protective current and pipe-to-soil potential) and finally identifying the most effective protection conditions over a wide range of frequency (2–10 kHz) and duty cycle (25%-75%). For this, pipe-to-soil potential, pH, current and power consumption, corrosion rate, surface deposits and investigation of pitting corrosion were taken into account. To model the input-output relationship in the PCCP method, a data-driven machine learning approach was used by training an artificial neural network (ANN). The results revealed that the PCCP system could yield the best protection conditions at 10 kHz frequency and 50% duty cycle, resulting in the longest protection length with the lowest corrosion rate at a consumption current 0.3 time that of the DCCP method. In the frequency range of 6–10 kHz and duty cycles of 50%-75%, SEM images indicated a uniform distribution of calcite deposits and no pits on cathode surface.

Performance comparison of physics-based and machine learning assisted multi-fidelity methods for the management of coastal aquifer systems

In this work we investigate the performance of various lower-fidelity models of seawater intrusion in coastal aquifer management problems. The variable density model is considered as the high-fidelity model and a pumping optimization framework is applied on a hypothetical coastal aquifer system in order to calculate the optimal pumping rates which are used as a benchmark for the lower-fidelity approaches. The examined lower-fidelity models could be classified in two categories: (1) physics-based models, which include several widely used variations of the sharp-interface approximation and (2) machine learning assisted models, which aim to improve the efficiency of the SI approach. The Random Forest method was utilized to create a spatially adaptive correction factor for the original sharp-interface model, which improves its accuracy without compromising its efficiency as a lower-fidelity model. Both the original sharp-interface and Machine Learning assisted model are then tested in a single-fidelity optimization method. The optimal pumping rated which were calculated using the Machine Learning based SI model sufficiently approximate the solution from the variable density model. The Machine Learning assisted approximation seems to be a promising surrogate for the high-fidelity, variable density model and could be utilized in multi-fidelity groundwater management frameworks.

Waste valorization as low-cost media engineering for auxin production from the newly isolated Streptomyces rubrogriseus AW22: Model development

Indole-3-acetic acid (IAA) represents a crucial phytohormone regulating specific tropic responses in plants and functions as a chemical signal between plant hosts and their symbionts. The Actinobacteria strain of AW22 with high IAA production ability was isolated in Algeria for the first time and was characterized as Streptomyces rubrogriseus through chemotaxonomic analysis and 16 S rDNA sequence alignment. The suitable medium for a maximum IAA yield was engineered in vitro and in silico using machine learning-assisted modeling. The primary low-cost feedstocks comprised various concentrations of spent coffee grounds (SCGs) and carob bean grounds (CBGs) extracts. Further, we combined the Box-Behnken design from response surface methodology (BBD-RSM) with artificial neural networks (ANNs) coupled with the genetic algorithm (GA). The critical process parameters screened via Plackett-Burman design (PBD) served as BBD and ANN-GA inputs, with IAA yield as the output variable. Analysis of the putative IAA using thin-layer chromatography (TLC) and (HPLC) revealed Rf values equal to 0.69 and a retention time of 3.711 min, equivalent to the authentic IAA. AW 22 achieved a maximum IAA yield of 188.290 ± 0.38 μg/mL using the process parameters generated by the ANN-GA model, consisting of L-Trp, 0.6%; SCG, 30%; T°, 25.8 °C; and pH 9, after eight days of incubation. An R2 of 99.98%, adding to an MSE of 1.86 × 10−5 at 129 epochs, postulated higher reliability of ANN-GA-approach in predicting responses, compared with BBD-RSM modeling exhibiting an R2 of 76.28%. The validation experiments resulted in a 4.55-fold and 4.46-fold increase in IAA secretion, corresponding to ANN-GA and BBD-RSM models, respectively, confirming the validity of both models.

Uncertainty Analysis of CO2 Storage in Deep Saline Aquifers Using Machine Learning and Bayesian Optimization

Geological CO2 sequestration (GCS) has been proposed as an effective approach to mitigate carbon emissions in the atmosphere. Uncertainty and sensitivity analysis of the fate of CO2 dynamics and storage are essential aspects of large-scale reservoir simulations. This work presents a rigorous machine learning-assisted (ML) workflow for the uncertainty and global sensitivity analysis of CO2 storage prediction in deep saline aquifers. The proposed workflow comprises three main steps: The first step concerns dataset generation, in which we identify the uncertainty parameters impacting CO2 flow and transport and then determine their corresponding ranges and distributions. The training data samples are generated by combining the Latin Hypercube Sampling (LHS) technique with high-resolution simulations. The second step involves ML model development based on a data-driven ML model, which is generated to map the nonlinear relationship between the input parameters and corresponding output interests from the previous step. We show that using Bayesian optimization significantly accelerates the tuning process of hyper-parameters, which is vastly superior to a traditional trial–error analysis. In the third step, uncertainty and global sensitivity analysis are performed using Monte Carlo simulations applied to the optimized surrogate. This step is performed to explore the time-dependent uncertainty propagation of model outputs. The key uncertainty parameters are then identified by calculating the Sobol indices based on the global sensitivity analysis. The proposed workflow is accurate and efficient and could be readily implemented in field-scale CO2 sequestration in deep saline aquifers.

Hot-deformation kinetics analysis and extrusion parameter optimization of a dilute rare-earth free magnesium alloy

The fundamental research on thermo-mechanical conditions provides an experimental basis for high-performance Mg-Al-Ca-Mn alloys. However, there is a lack of systematical investigation for this series alloys on the hot-deformation kinetics and extrusion parameter optimization. Here, the flow behavior, constitutive model, dynamic recrystallization (DRX) kinetic model and processing map of a dilute rare-earth free Mg-1.3Al-0.4Ca-0.4Mn (AXM100, wt.%) alloy were studied under different hot-compressive conditions. In addition, the extrusion parameter optimization of this alloy was performed based on the hot-processing map. The results showed that the conventional Arrhenius-type strain-related constitutive model only worked well for the flow curves at high temperatures and low strain rates. In comparison, using the machine learning assisted model (support vector regression, SVR) could effectively improve the accuracy between the predicted and experimental values. The DRX kinetic model was established, and a typical necklace-shaped structure preferentially occurred at the original grain boundaries and the second phases. The DRX nucleation weakened the texture intensity, and the further growth caused the more scattered basal texture. The hot-processing maps at different strains were also measured and the optimal hot-processing range could be confirmed at the deformation temperatures of 600∼723 K and the strain rates of 0.018∼0.563 s−1. Based on the optimum hot-processing range, a suitable extrusion parameter was considered as 603 K and 0.1 mm/s and the as-extruded alloy in this parameter exhibited a good strength-ductility synergy (yield strength of ∼ 232.1 MPa, ultimate strength of ∼ 278.2 MPa and elongation-to-failure of ∼ 20.1%). Finally, the strengthening-plasticizing mechanisms and the relationships between the DRXed grain size, yield strength and extrusion parameters were analyzed.

A machine learning-assisted model for renal urate underexcretion with genetic and clinical variables among Chinese men with gout

ObjectivesThe objective of this study was to develop and validate a prediction model for renal urate underexcretion (RUE) in male gout patients.MethodsMen with gout enrolled from multicenter cohorts in China were analyzed as the development and validation data sets. The RUE phenotype was defined as fractional excretion of uric acid (FEUA) <5.5%. Candidate genetic and clinical features were screened by the least absolute shrinkage and selection operator (LASSO) with 10-fold cross-validation. Machine learning algorithms (stochastic gradient descent (SGD), logistic regression, support vector machine) were performed to construct a predictive classifier of RUE. Models were assessed by the area under the receiver operating characteristic curve (AUC) and the precision-recall curve (PRC).ResultsOne thousand two hundred thirty-eight and two thousand twenty-three patients were enrolled as the development and validation cohorts, with 1220 and 754 randomly chosen patients genotyped, respectively. Rs3775948.GG of SLC2A9/GLUT9, rs504915.AA of NRXN2/URAT1, and 7 clinical features (age, hypertension, nephrolithiasis, blood glucose, serum urate, urea nitrogen, and creatinine) were generated by LASSO. Two additional SNP variants (rs2231142.GG of ABCG2 and rs11231463.GG of SLC22A9/OAT7) were selected based on their contributions to gout in the development cohort and their reported effects on renal urate handling. The optimized classifiers yielded AUCs of ~0.914 and PRCs of ~0.980 using these 11 variables. The SGD model was conducted in the validation cohort with an AUC of 0.899 and the PRC of 0.957.ConclusionsA prediction model for RUE composed of four SNPs and readily accessible clinical features was established with acceptable accuracy for men with gout.

Machine learning assisted fast prediction of inertial lift in microchannels.

Inertial effect has been extensively used in manipulating both engineered particles and biocolloids in microfluidic platforms. The design of inertial microfluidic devices largely relies on precise prediction of particle migration that is determined by the inertial lift acting on the particle. In spite of being the only means to accurately obtain the lift forces, direct numerical simulation (DNS) often consumes high computational cost and even becomes impractical when applied to microchannels with complex geometries. Herein, we proposed a fast numerical algorithm in conjunction with machine learning techniques for the analysis and design of inertial microfluidic devices. A database of inertial lift forces was first generated by conducting DNS over a wide range of operating parameters in straight microchannels with three types of cross-sectional shapes, including rectangular, triangular and semicircular shapes. A machine learning assisted model was then developed to gain the inertial lift distribution, by simply specifying the cross-sectional shape, Reynolds number and particle blockage ratio. The resultant inertial lift was integrated into the Lagrangian tracking method to quickly predict the particle trajectories in two types of microchannels in practical devices and yield good agreement with experimental observations. Our database and the associated codes allow researchers to expedite the development of the inertial microfluidic devices for particle manipulation.