Search

• It is possible to obtain good classification results of cardiovascular autonomic neuropathy using supervised machine learning. • The best classifier is the random forest classifier with a F1-score of 60% on the reduced dataset. • In the ensembled data no standard clinical biochemical analytes were present in the 10 best classifiers. Using supervised machine learning to classify the severity of cardiovascular autonomic neuropathy (CAN). The aims were 1) to investigate which features contribute to characterising CAN 2) to generate an ensembled set of features that best describes the variation in CAN classification. Eighty-two features from demographic, beat-to-beat, biochemical, and inflammation were obtained from 204 people with diabetes and used in three machine-learning-classifiers, these are: support vector machine, decision tree, and random forest. All data were ensembled using a weighted mean of the features from each classifier. The 10 most important features derived from the domains: Beat-to-beat, inflammation markers, disease-duration, and age. Beat-to-beat measures associate with CAN as diagnosis is mainly based on cardiac reflex responses, disease-duration and age are also related to CAN development throughout disease progression. The inflammation markers may reflect the underlying disease process, and therefore, new treatment modalities targeting systemic low-grade inflammation should potentially be tested to prevent the development of CAN. Cardiac reflex responses should be monitored closely to diagnose and classify severity levels of CAN accurately. Standard clinical biochemical analytes, such as glycaemic level, lipidic level, or kidney function were not included in the ten most important features. Beat-to-beat measures accounted for approximately 60% of the features in the ensembled data. [ABSTRACT FROM AUTHOR]

Modal parameters are crucial in investigating structural vibration problems and virtual sensing of vibration responses. This work proposes machine learning (ML) models such as Decision Tree, Random Forest, Adaboost Trees and RUSboost Trees to correlate 13 finite element (FE) modal shapes with the experimental ones. A catamaran's FE model was assembled and used as a case study. Firstly, a full FE model with 93591 DOFs was reduced to 174 DOFs using SEREP. Secondly, as the experimental mode shapes have a low spatial resolution (only six measured DOFs), another goal of this work is to expand these 6 DOFs to the 174 DOFs of the reduced FE model, that had not been measured. The ML models were used to correlate and expand the experimental mode shapes, thus, solving their lack of spatial resolution. As a result, the ML models identified the most relevant parameters for the scaling process of each of the 13 numerical modes using a supervised database. Adaboost Trees and Random Forest were used to correlate and expand five mode shapes each and RUSboost Trees were used to correlate and expand three mode shapes. In conclusion, Adaboost Trees and Random Forest models showed better performance during the correlation process. • Machine Learning models were used to correlate and expand the experimental modes. • Relevant degrees of freedom and modes were identified in the modes' correlation task. • Decision Tree, Random Forest, Adaboost and RUSboost were used in modes' correlation. • Supervised databases were used to correlate and expand modes at unmeasured locations. [ABSTRACT FROM AUTHOR]