Author: Admin

DOI: 10.3390/s21217090 This article proposes two ensemble neural network-based models for blood glucose prediction at three different prediction horizons—30, 60, and 120 min—and compares their performance with ten recently proposed neural networks. The twelve models’ performances are evaluated under the same OhioT1DM Dataset, preprocessing workflow, and tools at the three prediction horizons using the most…

Continue reading Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes

DOI: 10.1134/S1027451021040145 A method is proposed to calculate the microscopic residual stresses in extruded cylindrical samples of non-ageing aluminium alloy 5083 (Al–Mg), arising from quenching in fresh water from 530°C. We start from the premise that the alloy is single-phase and non-isotropic on a microscopic scale; it consists of many grains that exhibit different mechanical…

Continue reading Study of Microscopic Residual Stresses in an Extruded Aluminium Alloy Sample after Thermal Treatment

DOI: 10.1134/S1027451021030071 A model found by finite element method was developed in COMSOL Multiphysics to describe the evolution of residual stress after quenching of cylindrical samples of aluminium alloys AA2014 and AA5083. The treatment consisted of annealing followed by quenching in fresh water. The thermal and mechanical properties of both alloys at the annealing and…

Continue reading Residual Stress Distribution after Quenching Treatment Obtained from Diffraction Experiments and Simulation by Finite Element Method

DOI: 10.1007/978-3-030-72699-7_27 Residual stresses are originated during manufacturing processes of metallic materials, so its study is important to avoid catastrophic accidents during component service. There are two main types of residual stresses, according to the length scale; macroscopic and microscopic. While the determination of tmacroscopic ones is almost a routine analysis, determining the microscopic stress…

Continue reading Estimation of Grain-Level Residual Stresses in a Quenched Cylindrical Sample of Aluminum Alloy AA5083 Using Genetic Programming

DOI: 10.1016/j.jallcom.2020.158506 The stress equilibrium, SE, method has been shown to be a very powerful, reliable tool for calculating the un-stressed lattice parameter, a0, as a critical requirement for the determination of the residual stress, RS, by diffraction techniques. The method can be used in cases where others, such as the powder or comb ones, are…

Continue reading Further insights on the stress equilibrium method to investigate macroscopic residual stress fields: Case of aluminum alloys cylinders

DOI: 10.1007/s00500-020-05062-9 In this paper, we analyze the population diversity of grammatical evolution (GE) on multiple levels of genetic information: chromosome diversity, expression diversity, and output diversity. Thereby, we use a tree-similarity metric from tree-based GP literature to determine similarity of expression trees generated in GE. The similarity of outputs is determined via their correlation.…

Continue reading Multilayer analysis of population diversity in grammatical evolution for symbolic regression

DOI: 10.1109/TVLSI.2019.2961782 This article presents an approach to providing fault tolerance to permanent effects in the substrate of dynamic, partially reconfigurable field-programmable gate arrays (FPGAs). Our proposal consists of modifying FPGA configuration at runtime to avoid permanently damaged regions of the FPGA. It demands that the circuit design fulfills several requirements regarding the functionality and…

Continue reading Optimal Runtime Algorithm to Improve Fault Tolerance of Bus-Based Reconfigurable Designs

DOI: 10.1002/ese3.568 Grammatical Swarm is a search and optimization algorithm that belongs to the more general Grammatical Evolution family, which works with a set of solutions called individuals or particles. It uses the Particle Swarm Optimization algorithm as the search engine in the evolution of solutions. In this paper, we present a Grammatical Swarm algorithm for total…

Continue reading Particle swarm grammatical evolution for energy demand estimation

DOI: 10.1145/3319619.3326769 Residual stresses, both macroscopic and microscopic, are originated during conventional metallurgical processes. Knowing their magnitude and distribution is of great importance in the structural design of applications where fatigue, stress corrosion or thermal cycling occur (e.g., in the nuclear industry). The importance of these stresses is reflected in the large number of articles…

Continue reading Determination of microscopic residual stresses using diffraction methods, EBSD maps, and evolutionary algorithms