scholarly journals Development of interatomic potential for Al–Tb alloys using a deep neural network learning method

2020 ◽  
Vol 22 (33) ◽  
pp. 18467-18479 ◽  
Author(s):  
L. Tang ◽  
Z. J. Yang ◽  
T. Q. Wen ◽  
K. M. Ho ◽  
M. J. Kramer ◽  
...  
Keyword(s):  
Neural Network ◽  
Ab Initio ◽  
Structural Properties ◽  
Deep Neural Network ◽  
Interatomic Potential ◽  
Learning Method ◽  
Neural Network Learning ◽  
Network Learning ◽  
Formation Energies

The developed deep neural network (DNN) potential can describe the structural properties of the Al90Tb10 liquid and the formation energies of Al–Tb crystals with the accuracy of ab initio calculations.

scholarly journals Predictive Model for Brain Stroke in CT using Deep Neural Network

2020 ◽  
Vol 9 (1) ◽  
pp. 2011-2017
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Neural Network ◽  
Principal Component ◽  
World Population ◽  
Neural Network Learning ◽  
Machine Learning Classification ◽  
Network Learning ◽  
Brain Stroke ◽  
Aging World

The increasing in the incidence of stroke with aging world population would quickly place an economic burden on society. In proposed method we use different machine learning classification algorithms like Decision Tree, Deep Neural Network Learning, Maximum Expectization , Random Forest and Gaussian Naïve Bayesian Classifier is used with associated number of attributes to estimate the occurrence of stroke disease. The present research, mainly PCA (Principal Component Analysis) algorithm is used to limit the performance and scaling used to be adopted to extract splendid context statistics from medical records. We used those reduced features to determine whether or not the patient has a stroke disorder. We compared proposed method Deep neural network learning classifier with other machine-learning methods with respect to accuracy, sensitivity and specificity that yields 86.42%, 74.89 and 88.49% respectively. Hence it can be with the aid of both patients and medical doctors to treat viable stroke.

Sign in / Sign up

Export Citation Format

Share Document