In this work, the internal impedance of the lithium-ion battery pack, an essential measure of the... more In this work, the internal impedance of the lithium-ion battery pack, an essential measure of the degradation level of the batteries, is estimated employing ensembles of machine learning models. In this study, we take the supervised learning techniques Multi-Layer Perceptron bagging neural network and gradient tree boosting into account. Characteristics of the electric power system, in which the battery pack is inserted, are extracted and used in the modeling and training phases. During this process, the architecture of the ensembles and the configuration of their base learners are tuned through validation iterations. Finally, with the application of statistical testing and similarity analysis techniques, the best ensembles of models are examined and compared to other methods found in the literature. Results indicate that our approach is a suitable manner to estimate the internal impedance of batteries.
The coronavirus disease (COVID-19) pandemic has increased the necessity of immediate clinical dec... more The coronavirus disease (COVID-19) pandemic has increased the necessity of immediate clinical decisions and effective usage of healthcare resources. Currently, the most validated diagnosis test for COVID-19 (RT-PCR) is in shortage in most developing countries, which may increase infection rates and delay important preventive measures. The objective of this study was to predict the risk of positive COVID-19 diagnosis with machine learning, using as predictors only results from emergency care admission exams. We collected data from 235 adult patients from the Hospital Israelita Albert Einstein in São Paulo, Brazil, from 17 to 30 of March, 2020, of which 102 (43%) received a positive diagnosis of COVID-19 from RT-PCR tests. Five machine learning algorithms (neural networks, random forests, gradient boosting trees, logistic regression and support vector machines) were trained on a random sample of 70% of the patients, and performance was tested on new unseen data (30%). The best predict...
In this work, the internal impedance of the lithium-ion battery pack, an essential measure of the... more In this work, the internal impedance of the lithium-ion battery pack, an essential measure of the degradation level of the batteries, is estimated employing ensembles of machine learning models. In this study, we take the supervised learning techniques Multi-Layer Perceptron bagging neural network and gradient tree boosting into account. Characteristics of the electric power system, in which the battery pack is inserted, are extracted and used in the modeling and training phases. During this process, the architecture of the ensembles and the configuration of their base learners are tuned through validation iterations. Finally, with the application of statistical testing and similarity analysis techniques, the best ensembles of models are examined and compared to other methods found in the literature. Results indicate that our approach is a suitable manner to estimate the internal impedance of batteries.
The coronavirus disease (COVID-19) pandemic has increased the necessity of immediate clinical dec... more The coronavirus disease (COVID-19) pandemic has increased the necessity of immediate clinical decisions and effective usage of healthcare resources. Currently, the most validated diagnosis test for COVID-19 (RT-PCR) is in shortage in most developing countries, which may increase infection rates and delay important preventive measures. The objective of this study was to predict the risk of positive COVID-19 diagnosis with machine learning, using as predictors only results from emergency care admission exams. We collected data from 235 adult patients from the Hospital Israelita Albert Einstein in São Paulo, Brazil, from 17 to 30 of March, 2020, of which 102 (43%) received a positive diagnosis of COVID-19 from RT-PCR tests. Five machine learning algorithms (neural networks, random forests, gradient boosting trees, logistic regression and support vector machines) were trained on a random sample of 70% of the patients, and performance was tested on new unseen data (30%). The best predict...
Uploads