RESUMEN
Interpretation of brain activity responses using motor imagery (MI) paradigms is vital for medical diagnosis and monitoring. Assessed by machine learning techniques, identification of imagined actions is hindered by substantial intra- and inter-subject variability. Here, we develop an architecture of Convolutional Neural Networks (CNN) with an enhanced interpretation of the spatial brain neural patterns that mainly contribute to the classification of MI tasks. Two methods of 2D-feature extraction from EEG data are contrasted: Power Spectral Density and Continuous Wavelet Transform. For preserving the spatial interpretation of extracting EEG patterns, we project the multi-channel data using a topographic interpolation. Besides, we include a spatial dropping algorithm to remove the learned weights that reflect the localities not engaged with the elicited brain response. We evaluate two labeled scenarios of MI tasks: bi-class and three-class. Obtained results in an MI database show that the thresholding strategy combined with Continuous Wavelet Transform improves the accuracy and enhances the interpretability of CNN architecture, showing that the highest contribution clusters over the sensorimotor cortex with a differentiated behavior of rhythms [Formula: see text] and [Formula: see text].
RESUMEN
The magnetocaloric effect and the universal character for the magnetic entropy change regarding the cubic crystal structures (SC, BCC, FCC) were investigated, in a qualitative way, using Monte Carlo simulations. A classical Heisenberg Hamiltonian with nearest neighbors, and next nearest neighbors interactions was implemented. In order to compute the critical temperature of the system depending on the coordination number, it was calculated the dependence of the magnetization and magnetic susceptibility as a function of temperature. Magnetic field dependence on the magnetization for isothermal processes was performed considering a magnetocrystalline anisotropy term. In this way, the magnetic entropy change (ΔSm) was computed. Results show that the rescaled ΔSm as well as the exponent (n) characterizing the field dependence of the magnetic entropy change curves, collapse onto a single curve for the studied crystal structures. By this reason, it can be assured that ΔSm exhibits a universal behavior regarding the strength and contribution of the magnetic exchange energy to the total magnetic energy.