Epilepsy is a neurological disorder that causes seizures of many different types. The article presents an analysis of heart rate variability (HRV) for epileptic seizure prediction. Considering that HRV is nonstationary, our research focused on the quantitative analysis of a Poincare plot feature, i.e. cardiac sympathetic index (CSI). It is reported that the CSI value increases before the epileptic seizure. An algorithm using a 1D-convolutional neural network (1D-CNN) was proposed for CSI estimation. The usability of this method was checked for 40 epilepsy patients. Our algorithm was compared with the method proposed by Toichi et al. The mean squared error (MSE) for testing data was 0.046 and the mean absolute percentage error (MAPE) amounted to 0.097. The 1D-CNN algorithm was also compared with regression methods. For this purpose, a classical type of neural network (MLP), as well as linear regression and SVM regression, were tested. In the study, typical artifacts occurring in ECG signals before and during an epileptic seizure were simulated. The proposed 1D-CNN algorithm estimates CSI well and is resistant to noise and artifacts in the ECG signal.

Polymer coatings are increasingly used in varied fields and applications from simple coatings of barrier to intricated nanotechnology based composite. In the present study, polyvinylidene fluoride(PVDF)/Hydroxyapatite (HA )coatings were produced by spin coating technique over 316L SS. Scanning Electron Microscopy (SEM) and Atomic Force Microscopy (AFM) were used to observe the coated 316L SS substrates surface morphology. The corrosion protection efficiency of pure polyvinylidene fluoride and polyvinylidene fluoride/HA nanocomposite coatings on 316L SS was inspected using potentiodynamic polarization along with the ions release techniques in Hank’s solution. A superior biocompatibility and an improved protection performance against corrosion were obtained for the 316L SS samples with nanocomposite coatings compared with the pure polyvinylidene fluoride coatings and pristine 316L SS counterparts. The 316L SS samples coated by PVDF/HA nanocomposite showed enhanced corrosion protection within Hank’s solution. The corrosion of 316L SS samples within Hank’s solution increased from 92.99% to 99.99% when using 3wt% HA due to increasing the PVDF inhibition efficiency. Good agreements in the electrochemical corrosion parameters were obtained from using ions release and potentiodynamic polarization tests.

This article deals with the design of slewing rings (slewing bearings). A fully parametric, 3D virtual model of a ball slewing ring with four-point contact was created in the PTC/Creo Parametric CAD system. This model was subsequently used for finite-element analysis using Ansys/Workbench CAE software. The purpose of the FEM analysis was to determine the axial stiffness characteristics. Results of FEM analysis were experimentally verified using a test bench. At the end of the article, we present the nomograms of the deformation constant for different pitch diameters, rolling element diameters and contact angles.

Voice acoustic analysis can be a valuable and objective tool supporting the diagnosis of many neurodegenerative diseases, especially in times of distant medical examination during the pandemic. The article compares the application of selected signal processing methods and machine learning algorithms for the taxonomy of acquired speech signals representing the vowel a with prolonged phonation in patients with Parkinson’s disease and healthy subjects. The study was conducted using three different feature engineering techniques for the generation of speech signal features as well as the deep learning approach based on the processing of images involving spectrograms of different time and frequency resolutions. The research utilized real recordings acquired in the Department of Neurology at the Medical University of Warsaw, Poland. The discriminatory ability of feature vectors was evaluated using the SVM technique. The spectrograms were processed by the popular AlexNet convolutional neural network adopted to the binary classification task according to the strategy of transfer learning. The results of numerical experiments have shown different efficiencies of the examined approaches; however, the sensitivity of the best test based on the selected features proposed with respect to biological grounds of voice articulation reached the value of 97% with the specificity no worse than 93%. The results could be further slightly improved thanks to the combination of the selected deep learning and feature engineering algorithms in one stacked ensemble model.