Artificial neural network-driven federated learning for heart stroke prediction in healthcare 4.0 underlying 5G

In recent years, smart healthcare, artificial intelligence (AI)-aided diagnostics, and automated surgical robots are just a few of the innovations that have emerged and gained popularity with the advent of Healthcare 4.0. Such technologies are powered by machine learning (ML) and deep learning (DL), which are preferable for disease diagnosis, identifying patterns, prescribing treatments, and forecasting diseases like stroke prediction, cancer prediction and so forth. Nevertheless, much data is needed for AI, ML, and DL-based systems to train effectively and provide the desired outcomes. Further, it raises concerns about data privacy, security, communication overhead, regulatory compliance and so forth. Federated learning (FL) is a technology that protects data security and privacy by limiting data sharing and utilizing model information of distributed systems to enhance performance. However, existing approaches are traditionally verified on pre-established datasets that fail to capture real-life applicability. Therefore, this study proposes an AI-enabled stroke prediction architecture consisting of FL based on the artificial neural network (ANN) model using data from actual stroke cases. This architecture can be implemented on healthcare-based wearable devices (WD) for real-time use as it is effective, precise, and computationally affordable. In order to continuously enhance the performance of the global model, the proposed FL-based architecture aggregates the optimizer weights of many clients using a fifth-generation (5G) communication channel. Then, the performance of the proposed FL-based architecture is studied based on multiple parameters such as accuracy, precision, recall, bit error rate, and spectral noise. It outperforms the traditional approaches regarding accuracy, which is 5% to 10% higher.     

Uncertain variables and their applications for a class of uncertain systems

This paper presents definitions and basic properties of uncertain variables and shows how they may be applied to the analysis and decision making in static systems with unknown parameters in their mathematical models. The unknown parameters are assumed to be uncertain variables described by certainty distributions given by an expert. Two versions of the uncertain variables are described. The uncertain variable in the first version may be considered as a special case of the fuzzy number with a specific interpretation. Two forms of systems are considered in the paper: a system described by a function (functional system) and a system described by a relation (relational system). In both cases the statements and general solutions of the analysis and decision problems are presented. Simple examples illustrating the application of the uncertain variables are included.     

Fluorine-Containing Drug Administration in Rats Results in Fluorination of Selected Proteins in Liver and Brain Tissue

In many pharmaceuticals, a hydrogen atom or hydroxyl group is replaced by a fluorine to increase bioavailability and biostability. The fate of fluorine released from fluorine-containing drugs is not well investigated. The aim of this study was to examine possible fluorination of proteins in rat liver and brain after administration of the fluorinated drug cinacalcet. We assigned 18 Wistar rats to a control group (n = 6) and a group treated with cinacalcet (2 mg kg⁻¹/body weight, 5 days/week), divided into 7 day (n = 6) and 21 day (n = 6) treatment subgroups. Fluorinated proteins were identified using a free proteomics approach; chromatographic separation and analysis by high-resolution mass spectrometry; peptide/protein identification using the Mascot search algorithm; manual verification of an experimentally generated MS/MS spectrum with the theoretical MS/MS spectrum of identified fluorinated peptides. Three fluorinated proteins (spectrin beta chain; carbamoyl-phosphate synthase [ammonia], mitochondrial; 6-phosphofructo-2-kinase/fructose-2, 6-bisphosphatase 1) were identified in the liver and four (spectrin beta chain, dihydropyrimidinase-related protein 4, prominin-2, dihydropyrimidinase-related protein 4) in the brain tissue after 21 days of cinacalcet treatment, but not in the control group. Introduction of fluorine into an organism by administration of fluorinated drugs results in tissue-specific fluorination of proteins.     

Synthesis of Azafluorenones

Syntheses of azafluorenones from monoazaphenanthrenes and phenanthrolines has ben investigated. 1- and 4-monoazaphenanthrenes have been oxidized by J₂O₅ in acetic acid to give quinones which were converted to 4- and 1-azafluoren-9-ones in alkaline media. Phenanthrolines can be oxidized directly by means of permanganate in alkaline medium to 1,5-, 1,6-, 1,8-, 2,5- and 3,5-diazafluoren-9-ones. From 1-, 4-azaphenanthrene- and 1,8-phenanthrolinequinones new benzopyrido- and dipyridophenazines have been synthesized.     

Analytical stable CGPC design for minimum-phase systems

The continuous-time generalized predictive control (CGPC) using a long horizon cost function has superior robustness as compared to several other control strategies suitable for adaptive control. The main purpose of this paper is to put forward an analytical, explicit stable CGPC control design method for minimum-phase SISO systems that is based on a set of closed-loop characteristics with definite time-domain specifications. Explicit formulae for closed-loop characteristic polynomials are given and then the prototype design characteristic polynomials are catalogued that can serve as a basis for fully analytical design procedure assuring both the nominal stability and nominal performance specifications. A numerical example is given in order to illustrate the approach.     

Evaporation rate and separation factor of molecular distillation in a falling film apparatus

During molecular distillation in a falling film apparatus, temperature and concentration of the more volatile components undergo a marked decrease in axial and radial directions, due to the distillation in vacuo. The gradients produce changes in the rate of surface evaporation and separation efficiency along the flow path. A theoretical study of this problem is presented for binary mixtures. The respective differential equations for heat and mass transfer in the liquid film are solved numerically. As the results demonstrate, the aspect ratio of an apparatus should be large when a high separation is required and small when a high distillation rate is more important.     

Initial cutting conditions by abrasive grain fixed flexibly

In the paper, the initial cutting conditions by an abrasive grain fixed flexibly have been described. These conditions have been determined by incision angle at the beginning of machining zone as well as the occurring phenomena resulting from a mechanical cooperation of abrasive grain with machined material. It has been revealed that the incision angle may affect the direction of changes of roughness of the smoothed surface, making it possible to forecast this output magnitude. The dependences of this angle on the machining parameters have been derived for the conditions of forward and backward machining. They make it possible to choose these parameters as a rationale for the smoothing effects of finishing. The presented considerations and the conclusions coming out of them have been verified by experiment, and some exemplary proofs of these cognitive actions are described in the paper.     

Mixed-Mode Oscillations in a Modified Chua’s Circuit

We consider a singularly perturbed system of differential equations of the form ε u′=g(u,v,λ), v′=f(u,v,λ), where (u,v)∈R ³, 0<ε?1, and λ is a set of parameters. Such a system describes a modified Chua’s circuit with mixed-mode oscillations (MMOs). MMOs consist of a series of small-amplitude oscillations (canard solutions) and large-amplitude relaxations. In the paper we provide a series of both numerical and analytical analyses of the singularly perturbed system for the modified Chua’s circuit with nonlinear f and g. In particular, we analyze the occurrence of the Farey sequence $\it L^{s}$ , where $\it L$ and $\it s$ are the numbers of large and small oscillations, respectively.     

Numerical modeling of gland seal erosion in a geothermal turbine

Excessive erosion of the low-pressure rotor end gland seal of a 25 MWe geothermal turbine produced a partial loss of turbine vacuum that degraded cycle efficiency. This study used computational fluid dynamics (CFD) to identify the causes of erosion and the optimal steam seal system flow conditions for reducing the erosion problem. The predictions were based upon a numerical calculation using a commercial CFD code (Adapco Star-CD) to model the rotor end gland seal with a steam flow containing hard solid particles. The results confirmed that flow conditions play a major role in rotor gland seal erosion. By changing steam seal flow pressures to vary flow, it was confirmed that there is a threshold seal flow condition below which erosion does not occur, or is minimized. Optimizing the rotor end gland seal supply pressure and intercondenser pressure reduced the turbulent flow kinetic energy by 49%, with a corresponding decrease in the erosion rate of the rotor gland seal surface. The erosion rate is related directly to the particle velocity and turbulent flow kinetic energy. Recommendations are provided for adjusting the rotor end gland seal system to avoid erosion.