Affine transformations accelerate the training of physics-informed neural networks of a one-dimensional consolidation problem.

Physics-informed neural networks (PINNs) leverage data and knowledge about a problem. They provide a nonnumerical pathway to solving partial differential equations by expressing the field solution as an artificial neural network. This approach has been applied successfully to various types of differential equations. A major area of research on PINNs is the application to coupled partial differential equations in particular, and a general breakthrough is still lacking. In coupled equations, the optimization operates in a critical conflict between boundary conditions and the underlying equations, which often requires either many iterations or complex schemes to avoid trivial solutions and to achieve convergence. We provide empirical evidence for the mitigation of bad initial conditioning in PINNs for solving one-dimensional consolidation problems of porous media through the introduction of affine transformations after the classical output layer of artificial neural network architectures, effectively accelerating the training process. These affine physics-informed neural networks (AfPINNs) then produce nontrivial and accurate field solutions even in parameter spaces with diverging orders of magnitude. On average, AfPINNs show the ability to improve the [Formula: see text] relative error by [Formula: see text] after 25,000 epochs for a one-dimensional consolidation problem based on Biot's theory, and an average improvement by [Formula: see text] with a transfer approach to the theory of porous media.

The effect of Caspian Sea water on mechanical properties and durability of concrete containing rice husk ash, nano [Formula: see text], and nano [Formula: see text].

Various studies have been recently conducted aiming at developing more sustainable cementitious systems so that concrete structures may not have a negative effect on the environment and are decomposed. It has been attempted to build sustainable binders by substituting silica fume, cement with fly ash, nano-silica, nano-alumina, and rice husk ash. In this paper, a series of experiments on concrete with different contents of rice husk ash (10%, 15%, and 20%), nano[Formula: see text] (1%, 2%, 3%, 4%, 5%, 6%, 7%, 8%), and nano[Formula: see text] (1%, 2%, 3%, 4%) are performed to analyze the durability and mechanical properties of samples under the curing condition of Caspian seawater. The workability, density, water penetration, chloride ion penetration, and compressive strength (at 7, 14, 28, and 90 day) of the samples were determined. The experimental results showed that workability decreased gradually with increasing additives content, while the compressive gradually increased. Among the additives, adding 8% of the nano[Formula: see text] had the most significant effect on the improvement of compressive strength. Adding 8% nano[Formula: see text] and 4% nano[Formula: see text] reduced the depth of water permeability by 53% and 30%, respectively. Furthermore, adding 8% nano[Formula: see text] reduced chloride ion penetration by 85%.

Dual effect of F-actin targeted carrier combined with antimitotic drug on aggressive colorectal cancer cytoskeleton: Allying dissimilar cell cytoskeleton disrupting mechanisms.

A recent approach to colon cancer therapy is to employ selective drugs with specific extra/intracellular sites of action. Alteration of cytoskeletal protein reorganization and, subsequently, to cellular biomechanical behaviour during cancer progression highly affects the cancer cell progress. Hence, cytoskeleton targeted drugs are an important class of cancer therapy agents. We have studied viscoelastic alteration of the human colon adenocarcinoma cell line, SW48, after treatment with a drug delivery system comprising chitosan as the carrier and albendazole as the microtubule-targeting agent (MTA). For the first time, we have evaluated the biomechanical characteristics of the cell line, using the micropipette aspiration (MA) method after treatment with drug delivery systems. Surprisingly, employing a chitosan-albendazole pair, in comparison with both neat materials, resulted in more significant change in the viscoelastic parameters of cells, including the elastic constants (K1 and K2) and the coefficient of viscosity (µ). This difference was more pronounced for cancer cells after 48h of the treatment. Microtubule and actin microfilament (F-actin) contents in the cell line were studied by immunofluorescent staining. Good agreement was observed between the mechanical characteristics results and microtubule/F-actin contents of the treated SW48 cell line, which declined after treatment. The results showed that chitosan affected F-actin more, while MTA was more effective for microtubules. Toxicity studies were performed against two cancer cell lines (SW48 and MCF10CA1h) and compared to normal cells, MCF10A. The results showed cancer selectiveness, safety of formulation, and enhanced anticancer efficacy of the CS/ABZ conjugate. This study suggests that employing such a suitable pair of drug-carriers with dissimilar sites of action, thus allying the different cell cytoskeleton disrupting mechanisms, may provide a more efficient cancer therapy approach.