Process Research Group
                                  Bluetooth
Mechatronics,
Signal Processing, Control and Artificial Neural Networks
Department of Information and communications technologies
Technological Centre Ceit /“Researching Today, Creating the Future” 
   
 
   
Adaptive control
<< TO BE UPDATED, PLEASE VISIT AGAIN >>
 
Th adaptive technology makes use of a neural models with error back-propagation and explores the gradient-decent method for sample-by-sample adaptation. The implementations of the higher-order neural models have been developed in Python language.
There are several types of adaptive methodologies, such as multilayer neural networks, higher-order neural networks, adaptive self-organized maps, and adaptive radial basis function neural networks, among others.
 
Artificial Neural Networks for adaptive identification and control
 
ProcessOfHandControl 
General architecture of the project [1]  
 
Adaptive control for industrial systems
 
 
Adative methods for hydraulic system control
 
 
Adaptive methods for signal and data processing
 
The adaptive threshold technique is one of the more significant part of the detection method. The adaptive threshold is performed by using a pair of threshold limits called the upper limited threshold and the lower limited threshold.

The adaptive threshold is generally determined based on an amount of most recent data. This work uses a pair of thresholds (upper and lower thresholds), which are initialized in regard to the maximum value attained by the current frame.
EMGBlockDiagram
Block diagram of the EMG signal analysis process [2] 
AdaptiveThreshold
The red line stands for the upper limited threshold, and the green line stands for the lower limited threshold [3].
 
 
References:
 
[1] Cuong Nguyen Cong, Ricardo Rodriguez-Jorge, Nghien Nguyen Ba, Chuong Trinh Trong, Nghia Nguyen An, Design of Optimal PI Controllers using the Chemical Reaction Optimization Algorithm for Indirect Power Control of a DFIG model with MPPT, In: Web, Artificial Intelligence and Network Applications. WAINA 2020. Advances in Intelligent Systems and Computing, vol 1150. Springer, Cham (Web of Science, Core Rank B). April 2020.
 
[2] N. B. Nghien, Rodriguez-Jorge, Ricardo, Building an Early Warning Model for Detecting Environmental Pollution of Wastewater in Industrial Zones. In: Barolli L., Hellinckx P., Natwichai J. (eds) Advances on P2P, Parallel, Grid, Cloud and Internet Computing. 3PGCIC 2019. Lecture Notes in Networks and Systems, vol 96. Springer, Cham. (Web of Science, Proceedings Citation Index).
 
[3] J.U. Reyes Munoz, E.A. Martínez-García, R. Rodriguez Jorge, R. Torres-Cordoba, Chapter: Wheeled Robot Planning Using an Underactuated Mechanism for Absolute Goal-Direction, Book: Kinematics, IntechOpen, Croacia, ISBN: 978-953-51-5624-6. (Web of Science, Book Citation Index, EBSCO A-to-Z).
 
[4] Rodriguez Jorge, R., Bila, J., Mizera-Pietraszko, J., Loya Orduño, R. E., Martinez Garcia, E., & Torres Córdoba, R. (2017). Adaptive methodology for designing a predictive model of cardiac arrhythmia symptoms based on cubic neural unit. In Frontiers in Artificial Intelligence and Applications (Vol. 295, pp. 232–239). IOS Press. https://doi.org/10.3233/978-1-61499-773-3-232.
 
[5] Cancino Herrera, José Elías; Rodríguez Jorge, Ricardo; Vergara Villegas, Osslan Osiris; Cruz Sánchez, Vianey Guadalupe; Bila, Jiri; Nandayapa Alfaro, Manuel de Jesus; Ponce, Israel U.; Soto Marrufo, Ángel Israel; Flores Abad, Ángel, "Monitoring of Cardiac Arrhythmia Patterns by Adaptive Analysis," 2016 11th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC), November 2016, Asan, Korea.
 
[6] Rodriguez Jorge, R., García, E. M., Córdoba, R. T., Bila, J., & Mizera-Pietraszko, J. (2017). Adaptive Threshold, Wavelet and Hilbert Transform for QRS Detection in Electrocardiogram Signals (pp. 777–786). https://doi.org/10.1007/978-3-319-69835-9_73
 
[7] Bachelor Thesis: “Development of a control system for a hand-held robotic prosthesis through the processing of myoelectric signals,” by the student Mauricio Pérez Lozano, to get the title of Engineer in Mechatronics. Mechatronics Program. Autonomous University of Ciudad Juárez. May 2017. (Advisor: Dr. Ricardo Rodriguez Jorge).
 
[8] Bachelor Thesis: “Control of a robotic hand integrated by means of myoelectric signals,” by the student Laura Ivonne Figueroa Puebla, to get the title of Engineer in Mechatronics. Mechatronics Program. Autonomous University of Ciudad Juárez. Dec 2017. (Advisor: Dr. Ricardo Rodriguez Jorge).
 
[9] Ricardo Rodriguez, Ivo Bukovsky, Noriasu Homma. “Potentials of Quadratic Neural Unit for Applications”. International Journal of Software Science and Computational Intelligence, (IJSSCI), Volume 3, Issue 3, pp. 1-12, July- September 2011. DOI: 10.4018/IJSSCI.2011070101, ISSN: 1942- 9045, EISSN: 1942-9037.
 
[10] Rodriguez Jorge, Ricardo, "Artificial Neural Networks: Challenges in Science and Engineering Applications," Proceedings of 8th International Conference on Applications of Digital Information and Web Technologies 2017, Ciudad Juarez, Chihuahua, Mexico.
 
[11] Rodriguez Jorge, Ricardo; Bila, Jiri; Mizera-Pietraszko, Jolanta; Martinez-Garcia, Edgar A., Weight Adaptation Stability of Linear and Higher-Order Neural Units for Prediction Applications, Proceedings of the 11th International Conference MISSI 2018.(Web of Science, Procceddings Citation Index).
 
[12] Cuong Nguyen Cong, Ricardo Rodriguez-Jorge, Nghien Nguyen Ba, Chuong Trinh Trong, Nghia Nguyen An, Design of Optimal PI Controllers using the Chemical Reaction Optimization Algorithm for Indirect Power Control of a DFIG model with MPPT, In: Web, Artificial Intelligence and Network Applications. WAINA 2020. Advances in Intelligent Systems and Computing, vol 1150. Springer, Cham (Web of Science, Core Rank B). April 2020.