No abstract

No abstract

Drought is one of the main environmental factors that limit plant growth. For this reason, it is necessary to apply nursery cultural practices to produce quality seedlings for successful reforestation in drought- prone sites. In this study, the extreme learning machines and multilayer are applied to predict survival in 5-month-old Pinus radiataseedlings belonging to 98 families of a genetic improvement program and subjected to a period of water restriction in the nursery. After applying the water restriction, survival was registered in each seedling as a categorical variable (1 = alive seedling, 0 = dead seedling). Additionally, the following morphological attributes of each seedling were also measured: total height, root collar diameter, slenderness index, dry weight of needles, stems and roots, total dry weight, and the root to shoot ratio. The extreme learning machines predicted with a better rate the survival of the “alive” class compared to the “dead” class. On the other hand, the multilayer-extreme learning machines improved the precision of survival concerning the class of “dead” seedlings. According to the results of the model, an overall precision of 74% was obtained. This may be due to the great genetic variability presented by each of the Pinus radiatafamily used in the database. However, this technique allowed predicting the survival of a group of seedlings grown in the nursery, which can be a tool to support the selection process of high quality planting stock.

Orthogonal transformations, proper decomposition, and the Moore–Penrose inverse are traditional methods of obtaining the output layer weights for an extreme learning machine autoencoder. However, an increase in the number of hidden neurons causes higher convergence times and computational complexity, whereas the generalization capability is low when the number of neurons is small. One way to address this issue is to use the fast iterative shrinkage-thresholding algorithm (FISTA) to minimize the output weights of the extreme learning machine. In this work, we aim to improve the convergence speed of FISTA by using two fast algorithms of the shrinkage-thresholding class, called greedy FISTA (G-FISTA) and linearly convergent FISTA (LC-FISTA). Our method is an exciting proposal for decision-making involving the resolution of many application problems, especially those requiring longer computational times. In our experiments, we adopt six public datasets that are frequently used in machine learning: MNIST, NORB, CIFAR10, UMist, Caltech256, and Stanford Cars. We apply several metrics to evaluate the performance of our method, and the object of comparison is the FISTA algorithm due to its popularity for neural network training. The experimental results show that G-FISTA and LC-FISTA achieve higher convergence speeds in the autoencoder training process; for example, in the Stanford Cars dataset, G-FISTA and LC-FISTA are faster than FISTA by 48.42% and 47.32%, respectively. Overall, all three algorithms maintain good values of the performance metrics on all databases.

Determining the response to the forces applied to an elastic solid containing an ideal fluid with constant density is essential in the engineering and biomedical fields. Therefore this paper aims to present and analyze a mixed finite element method for an interaction problem solid-fluid that contributes to understanding these areas. It is assumed transmission conditions are maintained at the fluid boundary and are given by the balance of forces and the equality of normal displacements. The mixed variational formulation that avoids the locking phenomenon, for the coupled problem is in terms of displacement, stress tensor, and rotation in the solid and by pressure and scalar potential in the fluid, the main contribution of this work. The first transmission condition is imposed in the definition of the space and the rest of the conditions appear naturally, which means Lagrange multipliers are not needed at the coupling border. The unknowns for the fluid and the solid are approximated by finite element subspaces of Lagrange and Arnold-Falk-Winther of order 1, which lead to a Galerkin scheme for the continuous problem. Also, the resulting Galerkin scheme is convergent and derives optimal convergence rates. Finally, the model is illustrated using a numerical example.