Machine learning-assisted prediction of polymer properties prior to synthesis has the potential to significantly accelerate the discovery and development of new polymer materials.To date,several approaches have been i...Machine learning-assisted prediction of polymer properties prior to synthesis has the potential to significantly accelerate the discovery and development of new polymer materials.To date,several approaches have been implemented to represent the chemical structure in machine learning models,among which Mol2Vec embeddings have attracted considerable attention in the cheminformatics community since their introduction in 2018.However,for small datasets,the use of chemical structure representations typically increases the dimensionality of the input dataset,resulting in a decrease in model performance.Furthermore,the limited diversity of polymer chemical structures hinders the training of reliable embeddings,necessitating complex task-specific architecture implementations.To address these challenges,we examined the efficacy of Mol2Vec pre-trained embeddings in deriving vectorized representations of polymers.This study assesses the impact of incorporating Mol2Vec compound vectors into the input features on the efficacy of a model reliant on the physical properties of 214 polymers.The results will hopefully highlight the potential for improving prediction accuracy in polymer studies by incorporating pre-trained embeddings or promote their utilization when dealing with modestly sized polymer databases.展开更多
Specific conductivity of the composite nanomaterial layers with micron and submicron dimensions, consisting of carboxymethyl cellulose (CMC) and multiwalled carbon nanotubes (MWCNT) was investigated. Ultradispersed aq...Specific conductivity of the composite nanomaterial layers with micron and submicron dimensions, consisting of carboxymethyl cellulose (CMC) and multiwalled carbon nanotubes (MWCNT) was investigated. Ultradispersed aqueous suspension was deposited on soft (aluminum foil, plates made from polyester and polyimide, cotton fabric, office paper) and solid (coverslip, silicon wafers with silicon oxide layer) substrates by silk-screen printing. Electrical resistance was measured by four-probe method and by the method of square on surface from which the conductivity and conductivity per square of surface were calculated taking into account layer’s geometric dimensions. Specific conductivity of the layers with thickness range 0.5 - 5 μm was? ~1.2×104÷4×104 S/m, and max conductivity per square was ~ 0.2 S. Investigated nanomaterial is attractive to electronic and biomedical applications.展开更多
The results of the research and development of the moisture-sensitive elements based on the carbon nanotubes (CNT) array are presented. It was shown that CNT arrays that were grown by low-temperature plasma enhanced c...The results of the research and development of the moisture-sensitive elements based on the carbon nanotubes (CNT) array are presented. It was shown that CNT arrays that were grown by low-temperature plasma enhanced chemical vapor deposition (PECVD) method on the planar Si structures exhibit extremely high moisture sensitivity. The structure resistance ratio in dry and moisture conditions exceed 400. Such relatively high change in resistances is conditioned by the pattern of change of the charge carrier’s conductivity between certain nanotubes in the bundle when water molecules adsorption occurs.展开更多
基金the framework of the program of state support for the centers of the National Technology Initiative(NTI)on the basis of educational institutions of higher education and scientific organizations(Center NTI"Digital Materials Science:New Materials and Substances"on the basis of the Bauman Moscow State Technical University).
文摘Machine learning-assisted prediction of polymer properties prior to synthesis has the potential to significantly accelerate the discovery and development of new polymer materials.To date,several approaches have been implemented to represent the chemical structure in machine learning models,among which Mol2Vec embeddings have attracted considerable attention in the cheminformatics community since their introduction in 2018.However,for small datasets,the use of chemical structure representations typically increases the dimensionality of the input dataset,resulting in a decrease in model performance.Furthermore,the limited diversity of polymer chemical structures hinders the training of reliable embeddings,necessitating complex task-specific architecture implementations.To address these challenges,we examined the efficacy of Mol2Vec pre-trained embeddings in deriving vectorized representations of polymers.This study assesses the impact of incorporating Mol2Vec compound vectors into the input features on the efficacy of a model reliant on the physical properties of 214 polymers.The results will hopefully highlight the potential for improving prediction accuracy in polymer studies by incorporating pre-trained embeddings or promote their utilization when dealing with modestly sized polymer databases.
文摘Specific conductivity of the composite nanomaterial layers with micron and submicron dimensions, consisting of carboxymethyl cellulose (CMC) and multiwalled carbon nanotubes (MWCNT) was investigated. Ultradispersed aqueous suspension was deposited on soft (aluminum foil, plates made from polyester and polyimide, cotton fabric, office paper) and solid (coverslip, silicon wafers with silicon oxide layer) substrates by silk-screen printing. Electrical resistance was measured by four-probe method and by the method of square on surface from which the conductivity and conductivity per square of surface were calculated taking into account layer’s geometric dimensions. Specific conductivity of the layers with thickness range 0.5 - 5 μm was? ~1.2×104÷4×104 S/m, and max conductivity per square was ~ 0.2 S. Investigated nanomaterial is attractive to electronic and biomedical applications.
文摘The results of the research and development of the moisture-sensitive elements based on the carbon nanotubes (CNT) array are presented. It was shown that CNT arrays that were grown by low-temperature plasma enhanced chemical vapor deposition (PECVD) method on the planar Si structures exhibit extremely high moisture sensitivity. The structure resistance ratio in dry and moisture conditions exceed 400. Such relatively high change in resistances is conditioned by the pattern of change of the charge carrier’s conductivity between certain nanotubes in the bundle when water molecules adsorption occurs.
