One of the main challenges that deep mining faces is the occurrence of rockburst phenomena. Rockburst risk assessment with the use of machine learning is currently gaining increased attention, due to the fact that outperforms the widely used empirical approaches. However, the limited and imbalanced instance records, combined with the multiparametric nature of the phenomenon, can lead to unstable estimations. This study focuses on the enhancement of the prediction performance of five machine learning algorithms, including Decision Trees, Naïve Bayes, K-Nearest Neighbor, Random Forest and Logistic Regression, by utilizing the oversampling technique SMOTE (Synthetic Minority Oversampling TEchnique).The initial database consists of 249 rockburst incidents, from which approximately 70% was used as the training set and the remaining 30% as the test set. Parametric analyses were conducted regarding different indicator combinations, such as the maximum tangential stress, the rock’s uniaxial compressive and tensile strength, the stress coefficient, two brittleness coefficients and the elastic energy index. The models were trained with the original dataset and afterwards a gradual increase of the database with synthetic instances was made until the obtainment of a balanced dataset. Subsequently the creation of synthetic instances was continued until the real incidents used for training and the synthetic incidents were of the same amount. The results from the following analysis show that SMOTE technique has a considerable effect in the evaluation metrics of the models, even after the balancing of the dataset, and can be a valuable asset for the rockburst prediction.
One of the main challenges that deep mining faces is the occurrence of rockburst phenomena. Rockburst risk assessment with the use of machine learning is currently gaining increased attention, due to the fact that outperforms the widely used empirical approaches. However, the limited and imbalanced instance records, combined with the multiparametric nature of the phenomenon, can lead to unstable estimations. This study focuses on the enhancement of the prediction performance of five machine learning algorithms, including Decision Trees, Naïve Bayes, K-Nearest Neighbor, Random Forest and Logistic Regression, by utilizing the oversampling technique SMOTE (Synthetic Minority Oversampling TEchnique).The initial database consists of 249 rockburst incidents, from which approximately 70% was used as the training set and the remaining 30% as the test set. Parametric analyses were conducted regarding different indicator combinations, such as the maximum tangential stress, the rock's uniaxial compressive and tensile strength, the stress coefficient, two brittleness coefficients and the elastic energy index. The models were trained with the original dataset and afterwards a gradual increase of the database with synthetic instances was made until the obtainment of a balanced dataset. Subsequently the creation of synthetic instances was continued until the real incidents used for training and the synthetic incidents were of the same amount. The results from the following analysis show that SMOTE technique has a considerable effect in the evaluation metrics of the models, even after the balancing of the dataset, and can be a valuable asset for the rockburst prediction.
Στην παρούσα διδακτορική διατριβή μελετάται η αριθμητική επίλυση, δευτέρου βαθμού συνήθων διαφορικών εξισώσεων με λύση ταλαντωτικής μορφής. Για την αριθμητική ολοκλήρωση των εξισώσεων αυτών, αναπτύσσονται άμεσες μέθοδοι Runge–Kutta–Nyström.Αρχικά, παράγεται μια βελτιστοποιημένη μέθοδος τέταρτης αλγεβρικής τάξης με άπειρη τάξη υστέρηση φάσης. Η νέα μέθοδος που προκύπτει, μαζί με άλλες μεθόδους που κάνουν χρήση της ιδιότητας της ελάχιστης ή μηδενικής υστέρησης φάσης, εφαρμόζονται σε τέσσερα γνωστά προβλήματα με ταλαντωτική λύση.Στη συνέχεια αναπτύσσεται μια μέθοδος τέταρτης τάξης, που συνδυάζει τις ιδιότητες της μηδενικής υστέρησης φάσης και μηδενικής απώλειας, για την αριθμητική ολοκλήρωση της ανεξάρτητης του χρόνου, μονοδιάστατης εξίσωσης Schrödinger. Κατόπιν γίνεται σύγκριση των αποτελεσμάτων που εξήχθησαν με αυτά άλλων μεθόδων που χρησιμοποιούνται για την αριθμητική επίλυση της Schrödinger.Τέλος με τον μηδενισμό των παραγώγων της υστέρησης φάσης και της απώλειας, κατασκευάζεται μια νέα μέθοδος τέταρτης τάξης. Τα αριθμητικά αποτελέσματα φανερώνουν ότι η νέα μέθοδος είναι πολύ πιο αποδοτική, σε σύγκριση με άλλες μεθόδους, για την αριθμητική επίλυση της εξίσωσης Schrödinger και συναφών προβλημάτων.
Objective:A non-immediate hypertensive response short after COVID-19 vaccination has been reported. Mild to moderate elevated arterial blood pressure (BP) levels have been documented few days after a single or two-doses vaccine. This study sought to investigate this observation as a potential side effect in patients with known hypertension and healthy controls.Design and method:A total of 100 vaccinated patients between the age of 50 to 70 years old were studied. They were randomly assigned to one of the approved and available vaccines (Pfizer, Astra Zeneca, Moderna, Johnson & Johnson). Half of them were hypertensives under medical treatment and half of them were not. All participants had systolic BP < 140mmHg and diastolic BP < 90mmHg before vaccination and volunteered for standard daily home BP measurements (HBPM) and ambulatory BP measurements (ABPM) between the 1st and the 21st day after considered fully COVID-19 vaccinated.Results:All patients, hypertensives or not, had at some point a recorded hypertensive response for both systolic (SBP) and diastolic (DBP) BP after considered fully vaccinated. Hypertensives were older and with higher body mass index (BMI). Some of the hypertensive patients received additional medication whereas some of the non-hypertensive patients started life modification changes and systematic BP measurements for a possible diagnosis of hypertension.Conclusions:Vaccination for COVID-19 seems to be related with a short period of hypertensive response. This phenomenon was partial and mostly observed in older overweight hypertensives.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.