This work explores the dielectric and electrochemical properties of solid biopolymer blend electrolytes(SBEs)based on a combination of alginate and polyvinyl alcohol(PVA),doped with varying concentrations of ammonium ...This work explores the dielectric and electrochemical properties of solid biopolymer blend electrolytes(SBEs)based on a combination of alginate and polyvinyl alcohol(PVA),doped with varying concentrations of ammonium iodide(NH4I).The SBEs were synthesized using the solution casting method,and their ac conductivity exhibited an optimal value of 1.01×10^(-5) S·cm^(-1) at 25 wt.%NH4I.Detailed dielectric and modulus spectroscopy analyses revealed distinctive trends in relation to NH4I concentration,suggesting complex dielectric relaxation behavior.The universal power law(UPL)analysis identified the Small Polaron Hopping(SPH)mechanism as the dominant conduction process in the optimal sample.These results demonstrate that NH4I-doped alginate-PVA SBEs possess favorable electrochemical properties,positioning them as potential candidates for energy storage and ionic transport devices.展开更多
Machine learning has been increasingly used in biochemistry.However,in organic chemistry and other experiment-based fields,data collected from real experiments are inadequate and the current coronavirus disease(COVID-...Machine learning has been increasingly used in biochemistry.However,in organic chemistry and other experiment-based fields,data collected from real experiments are inadequate and the current coronavirus disease(COVID-19)pandemic has made the situation even worse.Such limited data resources may result in the low performance of modeling and affect the proper development of a control strategy.This paper proposes a feasible machine learning solution to the problem of small sample size in the biopolymerization process.To avoid overfitting,the variational auto-encoder and generative adversarial network algorithms are used for data augmentation.The random forest and artificial neural network algorithms are implemented in the modeling process.The results prove that data augmentation techniques effectively improve the performance of the regression model.Several machine learning models were compared and the experimental results show that the random forest model with data augmentation by the generative adversarial network technique achieved the best performance in predicting the molecular weight on the training set(with an R^(2) of 0.94)and on the test set(with an R^(2) of 0.74),and the coefficient of determination of this model was 0.74.展开更多
基金University Malaysia Pahang Al-Sultan Abdullah(UMPSA)under the UMPSA Distinguish Grant(RDU233001)Ministry of Higher Education Malaysia(MOHE)under the FRGS fund(FRGS/1/2023/STG05/UMP/02/2).
文摘This work explores the dielectric and electrochemical properties of solid biopolymer blend electrolytes(SBEs)based on a combination of alginate and polyvinyl alcohol(PVA),doped with varying concentrations of ammonium iodide(NH4I).The SBEs were synthesized using the solution casting method,and their ac conductivity exhibited an optimal value of 1.01×10^(-5) S·cm^(-1) at 25 wt.%NH4I.Detailed dielectric and modulus spectroscopy analyses revealed distinctive trends in relation to NH4I concentration,suggesting complex dielectric relaxation behavior.The universal power law(UPL)analysis identified the Small Polaron Hopping(SPH)mechanism as the dominant conduction process in the optimal sample.These results demonstrate that NH4I-doped alginate-PVA SBEs possess favorable electrochemical properties,positioning them as potential candidates for energy storage and ionic transport devices.
文摘Machine learning has been increasingly used in biochemistry.However,in organic chemistry and other experiment-based fields,data collected from real experiments are inadequate and the current coronavirus disease(COVID-19)pandemic has made the situation even worse.Such limited data resources may result in the low performance of modeling and affect the proper development of a control strategy.This paper proposes a feasible machine learning solution to the problem of small sample size in the biopolymerization process.To avoid overfitting,the variational auto-encoder and generative adversarial network algorithms are used for data augmentation.The random forest and artificial neural network algorithms are implemented in the modeling process.The results prove that data augmentation techniques effectively improve the performance of the regression model.Several machine learning models were compared and the experimental results show that the random forest model with data augmentation by the generative adversarial network technique achieved the best performance in predicting the molecular weight on the training set(with an R^(2) of 0.94)and on the test set(with an R^(2) of 0.74),and the coefficient of determination of this model was 0.74.
