25 May 2021 in IEEE Journal of Biomedical and Health Informatics
Alzheimer’s disease (AD) is one of the deadliest neurodegenerative diseases ailing the elderly population all over the world. An ensemble of Deep learning (DL) models can learn highly complicated patterns from MRI scans for the detection of AD by utilizing diverse solutions. In this work, we propose a computationally efficient, DL-architecture agnostic, ensemble of deep neural networks, named ‘Deep Transfer Ensemble (DTE)’ trained using transfer learning for the classification of AD. DTE leverages the complementary feature views and diversity introduced by many different locally optimum solutions reached by individual networks through the randomization of hyper-parameters. DTE achieves an accuracy of 99.05% and 85.27% on two independent splits of the large dataset for cognitively normal (NC) vs AD classification task. For the task of mild cognitive impairment (MCI) vs AD classification, DTE achieves 98.71% and 83.11% respectively on the two independent splits. It also performs reasonable on a small dataset consisting of only 50 samples per class. It achieved a maximum accuracy of 85% for NC vs AD on the small dataset. It also outperformed snapshot ensembles along with several other existing deep models from similar kind of previous works by other researchers.
30 November 2005 in Fluid Dynamics Research
1 November 2016 in Powder Technology
5 May 2021 in The European Physical Journal Plus
1 November 2019 in Physics of Fluids
Fully developed forced convective flow inside a channel filled with a porous material bounded by two impermeable walls subject to a constant heat flux is considered. We consider the Brinkman-Forchheimer equation to govern the flow inside the porous medium, which accounts for the presence of the inertial term. We assume that the porous medium is anisotropic in nature and the permeability is varying along all the directions so that it appears as a positive semidefinite matrix in the momentum equation. We have obtained velocity, temperature, and Nusselt number numerically due to the presence of the nonlinear quadratic term in the momentum equation. Asymptotic solutions for small Darcy number (∼10−3) and high Darcy number (∼10) are obtained. The asymptotic behavior of the Nusselt number is discussed. The key purpose of this paper is to study the effect of anisotropic permeability ratio, anisotropic angle, and inertial parameter on the hydrodynamic quantities and heat transfer for the configuration considered. In particular, we observe that for the moderate range of Darcy number, 10−2 to 102, inertia plays a significant role in the Nusselt number. We observe that inclusion of anisotropic permeability enhances the relative heat transfer rate by almost 20% compared to the corresponding isotropic situation. We present a detailed analysis about the inclusion of the permeability matrix in the Brinkman-Forchheimer extended Darcy momentum equation.