JUAN MIGUEL COLORES VARGAS

Dr. JUAN MIGUEL COLORES VARGAS

Universidad Autónoma de Baja California
+1

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 June 2022 in Technologies
Verified
Journal Article
Open access
PDF file
Francisco J. Ramirez-AriasFrancisco J. Ramirez-Arias
Francisco J. Ramirez-Arias
EGEnrique García Guerrero
Enrique García Guerrero
Esteban Tlelo-CuautleEsteban Tlelo-Cuautle
Esteban Tlelo-Cuautle
JVJUAN MIGUEL COLORES VARGAS
JUAN MIGUEL COLORES VARGAS
Eloísa García-CansecoEloísa García-Canseco
Eloísa García-Canseco
Everardo Inzunza-GonzalezEverardo Inzunza-Gonzalez
Everardo Inzunza-Gonzalez
In brain–computer interfaces (BCIs), it is crucial to process brain signals to improve the accuracy of the classification of motor movements. Machine learning (ML) algorithms such as artificial neural networks (ANNs), linear discriminant analysis (LDA), decision tree (D.T.), K-nearest neighbor (KNN), naive Bayes (N.B.), and support vector machine (SVM) have made significant progress in classification issues. This paper aims to present a signal processing analysis of electroencephalographic (EEG) signals among different feature extraction techniques to train selected classification algorithms to classify signals related to motor movements. The motor movements considered are related to the left hand, right hand, both fists, feet, and relaxation, making this a multiclass problem. In this study, nine ML algorithms were trained with a dataset created by the feature extraction of EEG signals.The EEG signals of 30 Physionet subjects were used to create a dataset related to movement. We used electrodes C3, C1, CZ, C2, and C4 according to the standard 10-10 placement. Then, we extracted the epochs of the EEG signals and applied tone, amplitude levels, and statistical techniques to obtain the set of features. LabVIEW™2015 version custom applications were used for reading the EEG signals; for channel selection, noise filtering, band selection, and feature extraction operations; and for creating the dataset. MATLAB 2021a was used for training, testing, and evaluating the performance metrics of the ML algorithms. In this study, the model of Medium-ANN achieved the best performance, with an AUC average of 0.9998, Cohen’s Kappa coefficient of 0.9552, a Matthews correlation coefficient of 0.9819, and a loss of 0.0147. These findings suggest the applicability of our approach to different scenarios, such as implementing robotic prostheses, where the use of superficial features is an acceptable option when resources are limited, as in embedded systems or edge computing devices.

31 December 2019 in Revista de Sistemas Experimentales
Verified
Journal Article
Open access
CCCarlos Chávez-Guzmán
Carlos Chávez-Guzmán
Jose Jaime Esqueda ElizondoJose Jaime Esqueda Elizondo
Jose Jaime Esqueda Elizondo
JMJovan Merida-Rubio
Jovan Merida-Rubio
JVJUAN MIGUEL COLORES VARGAS
JUAN MIGUEL COLORES VARGAS
In this paper is proposed a solution to the tracking problem with robust H_∞ global control, applied to robot manipulator completely actuated with rotational joint in presence of external disturbances. The Hamilton-Jacobi-Isaacs inequality is verified by a strict function of Lyapunov and enough conditions will be found under which the equilibrium point of the closed-loop system is asymptotically stable globally while the disturbed system has a gain L_2 less than or equal to a predetermined constant. Currently, one of the disadvantages of the H_∞ control, with respect to other control techniques, is the linearization of the system around a point of equilibrium, which converts the Hamilton-Jacobi-Isaacs inequality into algebraic of Riccati equations, which facilitate the solution to the motion control problem H_∞, however, the controller becomes local. Now, through a strict function of Lyapunov it was possible to verify that the Hamilton-Jacobi-Isaacs inequality is satisfied globally. The theory is validated in a robot manipulator with l degree of freedom.

6 February 2024
Verified
Book Chapter
Closed access
PDF file
Francisco J. Ramirez-AriasFrancisco J. Ramirez-Arias
Francisco J. Ramirez-Arias
JVJUAN MIGUEL COLORES VARGAS
JUAN MIGUEL COLORES VARGAS
JMJován Oseas Mérida-Rubio
Jován Oseas Mérida-Rubio
EGEnrique García Guerrero
Enrique García Guerrero
Everardo Inzunza-GonzalezEverardo Inzunza-Gonzalez
Everardo Inzunza-Gonzalez
Brain-computer interfaces are a communication channel between the human brain and computers where no muscular action is required. Machine learning algorithms such as discriminant line analysis, decision trees, k-nearest neighbors, naive Bayes, and support vector machines have significantly progressed in classifying EEG signals. This study presents the analysis of EEG signal processing as well as the different extracted characteristics related to motor and imaginary movements to train the different signal classification algorithms selected. For the development of this study, 60 machine learning algorithms were trained with 12 datasets created by extracting features from EEG signals. The macro results of this study show a global accuracy of 0.9999, a global area under the curve of 0.9998, and a global loss of 0.00022. These findings suggest the applicability of our approach as well as the use of any of the different algorithms that provide exemplary performance in the classification of EEG signals, which can be used in scenarios such as robotic movement control, prosthetics, robotics, and electronic wheelchairs, where resources are limited. <!----> <!----> <!----> <!---->