-
Evolutionary Training of Deep Belief Networks for Handwritten Digit Recognition
Two of the most representative deep architectures are Deep Convolutional Neural Networks and Deep Belief Networks (DBNs).Both of these can be applied to the problem of pattern... -
Blood Vessel Analysis on High Resolution Fundus Retinal Images
Image analysis is a relevant tool to improve the healthcare services. Fundus retinal image analysis allows the early detection of ophthalmic diseases such as diabetes and... -
An evolutionary algorithm of linear complexity: application to training of de...
The performance of deep neural networks, such as Deep Belief Networks formed by Restricted Boltzmann Machines (RBMs), strongly depends on their training, which is the process of... -
On the selection of the optimal topology for particle swarm optimization: a s...
In this paper, we deal with the problem of selecting the best topology in Particle Swarm Optimization. Unlike most state-of-the-art papers, where statistical analysis of a large... -
Comparison of Parallel Versions of SA and GA for Optimizing the Performance o...
Deep learning (DL) is playing an increasingly important role in our lives. It has already made a huge impact in areas, such as cancer diagnosis, precision medicine, self-driving... -
Industrial and Robotic Systems: LASIRS 2019
This work presents a solution of the problem of controlling an industrial robotic system based on visual information received from a stereo camera that monitors robots workcell.... -
Computation of the improvement directions of the Pareto front and its applica...
This paper introduces the mathematical development and algorithm of the Improvement-Directions Mapping (IDM) method, which computes improvement directions to "push" the current... -
Kinematic and dynamic design and optimization of a parallel rehabilitation robot
In this paper, a method for concurrent optimum design of a complex parallel manipulator is introduced. The manipulator is a three-degree-of-freedom mechanism used as a walking... -
The improvement direction mapping method
The Improvement Direction Mapping (IDM) is a novel multi-objective local-search method, that independently steers a solution set towards promising regions by computing... -
A two-stage mono-and multi-objective method for the optimization of general U...
This paper introduces a two-stage method based on bio-inspired algorithms for the design optimization of a class of general Stewart platforms. The first stage performs a... -
Efficient training of deep learning models through improved adaptive sampling
Training of Deep Neural Networks (DNNs) is very computationally demanding and resources are typically spent on training-instances that do not provide the most benefit to a... -
Robust parameter estimation of a PEMFC via optimization based on probabilisti...
Recent developments in maintenance modelling fuelled by data-based approaches such as machine learning (ML), have enabled a broad range of applications. In the automotive... -
Parameter Calibration of the Patch Growing Algorithm for Urban Land Change Si...
Urban growth modelling is a current trend in geo-computation due to its impact on the local living environment and the quality of life. The FUTure Urban-Regional Environment... -
On the best-performed time window size for homicide count forecasting
In the last two decades, violence and homicides have been consistently increasing in Mexico; the official data shows relations to other crimes and time-dependent territorial... -
Spatio-temporal interpolation of rainfall data in western Mexico
One of the most common problems related to meteorological information is the missing registers. This lack of data generates uncertainties in the analysis of climate, hydrology,... -
Automated dimensional synthesis of a portable sky scanner for measuring light...
Light pollution is often measured by a photometric sensor network distributed in the area of interest. However, photometric sensors usually have a narrow view angle, making... -
Mechatronic design of a planar robot using multiobjective optimization
The concurrent design optimization of robots refers to the problem of optimizing parameters that affects different kinds of features at the same time. For instance, this work... -
Evaluación comparativa de algoritmos de predicción aplicados al conteo de hom...
Este trabajo de investigación analiza el impacto de las elecciones subnacionales de 2021 en México en los niveles de homicidios dolosos. Se utilizaron series de tiempo... -
A self-validating method via the unification of multiple models for consisten...
Mathematical models are used for simulating the electrochemical phenomena of proton-exchange-membrane (PEM) fuel cells. They differ in the scale, modeling variables, precision... -
A reaction–convection–diffusion model for PEM fuel cells
In this paper, we present a novel 1D singularly perturbed reaction–convection–diffusion mathematical model, with non-linear coefficients (SP-RCD model), for the physical...
