Search

This work aims to evaluate the predictive performance of various Machine Learning algorithms when applied to the prediction of material constitutive parameters, particularly the parameters of the Swift hardening law. For this, datasets were generated from the results of the numerical simulations of uniaxial tensile tests. The Machine Learning algorithms considered for this study are: Gaussian Process, Multi-layer Perceptron, Support Vector Regression, Decision Tree and Random Forest. These algorithms were used to train metamodels based on training sets considering different numbers of materials and input parameters, which were then used to predict the hardening law parameters. The Gaussian Process algorithm achieved the overall best predictive performances. The results obtained show the potential of Machine Learning algorithms for application on the identification of material constitutive parameters.

Cancer patients, who have undergone surgical treatment, after the stabilization of the COVID-19 pandemic, have a greater complexity of repercussions, in the different dimensions of their lives. Therefore, they need an interprofessional team to achieve their rehabilitation. This study aims to analyze the national and international scientific evidence on the interprofessional team for the surgical rehabilitation of cancer patients; and establish recommendations for the formation of an interprofessional team, in the tertiary health context. This is an Integrative Review, based on Evidence-Based Practice, which will be carried out in six stages: identification of the theme and selection of the research question; establishing criteria for inclusion and exclusion; sample categorization; evaluation of the integrative review sample; interpretation of results and synthesis of knowledge of the main results evidenced in the analysis. The research question was established: “What is the scientific evidence on care elements and elements for the formation of the interprofessional team regarding the surgical rehabilitation of cancer patients?”. Searches will be carried out in the Latin American and Caribbean Health Sciences Information Literature (LILACS), Cumulative Index to Nursing and Allied Health Literature (CINAHL), SciVerse Scopus, Web of Science (WOS) and National Library of Medicine National Institutes of Health (PUBMED), according to inclusion and exclusion criteria. The data to be collected from the sample will be identification of the scientific article, methodological characteristics, evaluation of methodological rigor and the results, which will be analyzed, descriptively, to establish recommendations for the formation of this team, in the tertiary context.

Childhood cancers are a heterogeneous group of malignant neoplasms and the most common types include Leukemia, Central Nervous System neoplasms, Neuroblastoma, Lymphomas and Wilms Tumor. They represent the second leading cause of death in children aged 5 to 14 years in the world and, in Brazil, the first (8% of the total) among children and adolescents aged 1 to 19 years. Despite the fact that in the last 50 years there has been a significant improvement in the overall survival curve of childhood cancer, reaching the mark of 80% in 2021, compared to the rate close to 30% in the 1960s. However, due to socioeconomic differences not all children and adolescents benefit equally from these advances. Associated with this scenario, the COVID-19 pandemic may have greatly impacted both the diagnosis and treatment of these neoplasms. Therefore, this present research project aims to analyze the temporal trend and factors related to delay in cancer diagnosis and treatment before and during the COVID-19 pandemic of the five main childhood neoplasms.

Childhood and juvenile cancer represent a heterogeneous group of malignant neoplasms with some pre-established particularities, which is reflected in its characterization regarding the occurrence, etiology, survival, treatment, and risk of acute and late toxic effects related to the procedure. Therefore, it is pointed out that these malignant neoplasms are similar in terms of the uncontrolled proliferation of abnormal cells occurring anywhere in the body (ERDMANN et al., 2021). Nursing care for children with cancer is developed through diagnosis, treatment, and control. In this bias, it is highlighted that current treatments have two main objectives: to increase survival rates, minimize the late effects of treatment; and reintegrate the child into society with quality of life (MUTTI; PAULA; SOUTO, 2010). For effective care, it is essential that nursing care offers quality and safety, and is supported by actions based on a care methodology, such as the Nursing Process - NP. This method is “considered systematic”, as its operation consists of five distinct but interdependent and interrelated stages: History, Nursing Diagnosis, Planning, Implementation, and Evaluation. Therefore, this present research project aims to analyze the evidence about nursing care directed to pediatric cancer patients with malignant neoplasm in the central nervous system who have a seizure. In addition, the specific objective is to develop guidelines for nursing care aimed at pediatric cancer patients with malignant neoplasm in the central nervous system who have a seizure.

Today, the vast majority of design tasks are based on simulation tools. However, the success of the simulation depends on the accurate identification of the constitutive parameters of materials, i.e., its calibration. The classical parameter identification strategy, which relies on homogeneous tests, does not provide accurate and robust results required by the automotive and aerospace industry. Recently, numerical inverse methods, such as the Finite Element Model Updating and the Virtual Fields Method, have been developed for identifying constitutive parameters based on heterogeneous tests. Although these methods have proven effective for linear and non-linear models, the parameter identification process is complex, making it computationally expensive. In this work, a machine learning (ML) algorithm is used to pursue the goal of parameter identification of non-linear models using heterogeneous tests. For that purpose, a ML inverse model is trained using the Finite Element model as data source. A statistical analysis is conducted to identify the correlation between the training dataset size, mechanical tests results and the material parameters. The goal is to understand the importance of the different inputs and to reduce the computational time. published

This work presents an exploratory study for the development of a dataset-supported strategy to identify the plastic behaviour of metal sheets. Datasets were generated from numerical simulation results obtained from the biaxial tensile test on a cruciform-shaped sample, for 4000 hypothetical materials. These datasets were used to simultaneously estimate the yield criterion and hardening law parameters of reference materials, resourcing to two types of objective function. Sensitivity analyses showed that the performance of the proposed identification strategy depends on the size of the dataset and the reference material. published

Sem resumo disponível. published

The industrial demand for products with better quality and lower production costs have encouraged the widespread application of the finite element analysis (FEA) in the development and optimization of sheet metal forming processes. To ensure that the FEA solutions are reliable and robust it is important to take into account the uncertainties that inevitably arise in a real industrial environment. In this context, a numerical study on the influence of the material and process uncertainty in the stamping results of a square cup is presented. In this analysis, it is assumed uncertainty in the elasticity properties, hardening law parameters, anisotropy coefficients, blank thickness, friction coefficient and in the blank holder force. The effect of the uncertainty in these input parameters is evaluated in the punch force, equivalent plastic strain, thickness and cup geometry. Firstly, quasi-Monte Carlo method was used to evaluate the variability in the simulation outputs, considering the uncertainty of the input parameters. This analysis shows that the geometry is the output most sensitive to the uncertainty of the input parameters. Afterwards, a variance-based sensitivity analysis was carried out to identify the input parameters that most influence the output variability. It was concluded that the hardening law parameters and the anisotropy coefficients have the most influence in the stamping results variability of a square cup. published

Recent concerns with data privacy in machine learning have led to the development of privacypreserving machine learning methods, such as Federated Learning [1]. This method involves multiple parties to privately train local machine learning models with their own data, sharing with the global server only the models’ parameters that will be averaged to update the global model. Such environments are constantly at the risk of suffering cyber-attacks that can compromise the information used in the process and/or the complete machine learning training. One of those attacks are known as data poisoning [2], which is a threat to most machine learning models, in particular for the federated learning method, because of the communication design and the different nodes participating in the training. In this work, it was investigated the application of Digital Envelopes [3] combined with Federated Learning, to improve data integrity and authenticity in order to prevent the machine learning models to be training with poisoned data. Also, this combination improves the confidentiality by assuring the information is not made available or disclosed to unauthorized individuals or entities. The proposed approach was able to identify when the dataset was compromised by a corrupted agent, that impacted the results of the machine learning and prevented the specific dataset to participate in the training process. published

The Federated Learning method was developed to to provide an alternative for the recent concerns with data privacy in machine learning. This method involves multiple parties to privately train local machine learning models with their own data, sharing with the global server only the models’ parameters that will be averaged to update the global model. Although private, such environments are constantly at the risk of suffering cyber-attacks that can compromise the information used in the process and/or the complete machine learning training. This work investigates the application of Digital Envelopes combined with Federated Learning, to improve protection against attacks to either the clients and the server. published

In this work, a numerical analysis of the hole expansion test is presented. This analysis focuses on the impact that certain geometric and material features have on the strain path and maximum values achieved for the principal strains, during the test. The features analysed are the die diameter, the sheet thickness and the material hardening behaviour. In order to study the impact of each feature individually, a reference study case was defined, which strictly follows the ISO 16630 standard, to serve as a basis of comparison. Then, other study cases were created from the reference one, by changing each feature in study. The results show that a uniaxial tension strain path is observed at the outer edge of the blank hole, which is not significantly changed with the variation of the features under study.