In this research a recent developed practical modeling technique is applied for the glucose regulation system identification. By using this technique a set of mathematical models is obtained instead of single one to compensate for the  loss of information caused by the optimization technique in curve fitting algorithms, the diversity of members inside the single set is interpreted in term of restricted range of its parameters, also a diagnosis criteria is developed for detecting any disorder in the glucose regulation system by investigating the influence of variation of the parameters on the response of the system, this technique is applied in this research practically  for 20 cases with association of  National Center for

Abstract

The present investigation aimed to formulate a liquid self-microemulsifying drug delivery system (SMEDDS) of tacrolimus to enhance its oral bioavailability by improving its dispersibility and dissolution rate. Four liquid SMEDDS were prepared using maisine CC as oil phase, labrasol ALF as surfactant and transcutol HP as co-surfactant based on the solubility studies of tacrolimus in these components. The phase behavior of the components and the area of microemulsion were evaluated using pseudoternary phase diagrams. The formulations were also assessed for thermodynamic stability, robustness to dilution, self-emulsification time, drug content, globule size and polydispersity index. The prepared SMEDDS formulations exhibi

Vehicular ad hoc networks (VANETs) are considered an emerging technology in the industrial and educational fields. This technology is essential in the deployment of the intelligent transportation system, which is targeted to improve safety and efficiency of traffic. The implementation of VANETs can be effectively executed by transmitting data among vehicles with the use of multiple hops. However, the intrinsic characteristics of VANETs, such as its dynamic network topology and intermittent connectivity, limit data delivery. One particular challenge of this network is the possibility that the contributing node may only remain in the network for a limited time. Hence, to prevent data loss from that node, the information must reach the destina

This paper presents a comparative study of two learning algorithms for the nonlinear PID neural trajectory tracking controller for mobile robot in order to follow a pre-defined path. As simple and fast tuning technique, genetic and particle swarm optimization algorithms are used to tune the nonlinear PID neural controller's parameters to find the best velocities control actions of the right wheel and left wheel for the real mobile robot. Polywog wavelet activation function is used in the structure of the nonlinear PID neural controller. Simulation results (Matlab) and experimental work (LabVIEW) show that the proposed nonlinear PID controller with PSO
learning algorithm is more effective and robust than genetic learning algorithm; thi

Background/Objectives: Early and accurate discrimination of neurological conditions, dementia, stroke and healthy aging, remains a critical clinical challenge. Electroencephalography (EEG) is a non-invasive measure of brain dynamics and entropy-based features obtained from multichannel EEG have shown strong discriminative ability. However, existing deep learning approaches do not sufficiently address the combined challenges of small clinical cohorts and high-dimensional entropy feature spaces. In this study, a novel architecture is proposed for multi-class neurological EEG classification under extreme small-sample conditions. Methods: A novel dual-branch Channel-wise Transformer and Attention-Branch Network (EEG-ChTABNet) are pr to