Laboratory of Optimization, Design, and Advanced Control, School of Chemical Engineering, Universidade Estadual de Campinas, Campinas 13083-970, SP, Brazil
Auto-generated profile, based on publicly available information
Maria Regina Wolf Maciel
Laboratory of Optimization, Design, and Advanced Control, School of Chemical Engineering, Universidade Estadual de Campinas, Campinas 13083-970, SP, Brazil
High energy demand, competitive fuel prices and the need for environmentally friendly processes have led to the constant development of the alcohol industry. Pervaporation is seen as a separation process, with low energy consumption, which has a high potential for application in the fermentation and dehydration of ethanol. This work presents the experimental ethanol recovery by pervaporation and the semi-empirical model of partial fluxes. Total permeate fluxes between 15.6–68.6 mol m h (289–1565 g m h), separation factor between 3.4–6.4 and ethanol molar fraction between 16–171 mM (4–35 wt%) were obtained using ethanol feed concentrations between 4–37 mM (1–9 wt%), temperature between 34–50 C and commercial polydimethylsiloxane (PDMS) membrane. From the experimental data a semi-empirical model describing the behavior of partial-permeate fluxes was developed considering the effect of both the temperature and the composition of the feed, and the behavior of the apparent activation energy. Therefore, the model obtained shows a modified Arrhenius-type behavior that calculates with high precision the partial-permeate fluxes. Furthermore, the versatility of the model was demonstrated in process such as ethanol recovery and both ethanol and butanol dehydration.
Predicting recurrence after a first venous thromboembolism episode remains difficult: existing risk scores use few variables and generalize poorly, whereas machine learning often lacks mechanistic interpretability. We developed a hybrid framework combining an artificial neural network with a mechanistic model of the coagulation cascade expressed as a system of ordinary differential equations, optimized using metaheuristic optimization algorithms, to infer patient-specific kinetic parameters from 39 clinical and hematological variables in 235 patients with a first venous thromboembolism (49 recurrences, 20.9%), divided into a single 70% training and 30% independent test partition, with 15 recurrent events in the test partition. The estimated kinetics were propagated into a spatiotemporal model of clot growth described by partial differential equations, and the resulting clot-size variable, together with hematological features, was used to train thirteen classifiers with interpretation based on Shapley additive explanations. Among the clinically compliant configurations, particle swarm optimization produced the most balanced hybrid model (area under the curve of 0.851 and F1-score of 0.800 in the test partition). Patient-specific parameterization significantly altered simulated clot-size predictions relative to population-averaged kinetics and was associated with improved discrimination of recurrent venous thromboembolism in the full cohort. A histogram-based gradient boosting classifier achieved the highest point-estimate predictive performance (area under the curve of 0.872 and F-measure of 0.750 in the test partition), with clot size emerging as the most influential feature in model interpretation. These findings support the potential of patient-specific mechanistic modeling to generate physiologically informed features for recurrent venous thromboembolism prediction while preserving interpretability, warranting external validation before clinical application.