Artificial neural networks with conformable transfer function for improving the performance in thermal and environmental processes.

This research proposes a novel transfer function based on the hyperbolic tangent and the Khalil conformable exponential function. The non-integer order transfer function offers a suitable neural network configuration because of its ability to adapt. Consequently, this function was introduced into neural network models for three experimental cases: estimating the annular Nusselt number correlation to a helical double-pipe evaporator, the volumetric mass transfer coefficient in an electrochemical reaction, and the thermal efficiency of a solar parabolic trough collector. We found the new transfer function parameters during the training step of the neural networks. Therefore, weights and biases depend on them. We assessed the models applied to the three cases using the determination coefficient, adjusted determination coefficient, and the slope-intercept test. In addition, the MSE for the training set and the whole database were computed to show that there is no overfitting problem. The best-assessed models showed a relationship of 99%, 97%, and 95% with the experimental data for the first, second, and third cases. This novel proposal made reducing the number of neurons in the hidden layer feasible. Therefore, we show a neural network with a conformable transfer function (ANN-CTF) that learns well enough with less available information from the experimental database during its training.

Thrombin activation of PI3K/PDK1/Akt signaling promotes cyclin D1 upregulation and RPE cell proliferation.

The retinal pigment epithelium (RPE) plays an essential role in the survival and function of the neural retina. RPE uncontrolled proliferation leads to the development of proliferative ocular pathologies, among which proliferative vitreoretinopathy (PVR) is the main cause of retinal surgery failure. Upon the breakdown of the BRB due to trauma or metabolic imbalance the contact of RPE with serum-contained thrombin has been shown to stimulate the proliferation of otherwise quiescent RPE cells. Although the molecular mechanisms involved in this effect are still undetermined, thrombin proteolytic activation of protease-activated G protein coupled receptor-1 (PAR-1) activates PI3K and Akt, known to play an essential role in proliferation. The present study demonstrates that: 1) thrombin stimulates Ser 473 Akt phosphorylation without affecting Thr 308 basal phosphorylation in RPE cells; 2) thrombin-induced Akt stimulation promotes cyclin D1 accumulation through the phosphorylation/ inhibition of GSK-3ß, thus preventing Thr 286 cyclin D1 phosphorylation, nuclear export and degradation; 3) Akt signaling requires the upstream activation of PI3K and PLC. Since the pharmacological inhibition of these pathways or the silencing of cyclin expression prevent thrombin-induced RPE cell proliferation, these results contribute relevant evidence for establishing the mechanism involved in the development of proliferative eye diseases.