• TV Azteca.

• Channel 22-TV.

• Polytechnic gazette (Institute Polytechnic National).

• MILENIO (Mexican newspaper).

Deep Learning applied to Attention detection, University Medical Center Freiburg

I am working on a project related to attention detection. The main idea is to classify attention brain Patterns (EEG signals) using innovative deep learning models such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The project is implemented in the Neuromedical AI Lab.

Neuroscience and Machine Learning project

Researchers from the University of Cambridge (Cambridge Neuroscience) and the University of Cardiff (School of Computer Science and Informatics) participated in this project. The idea after the estimation of the forward/inverse models (EEG data) is finding a common sensor space. Therefore, the next steps for each subject will be employed:

• map subject to source space
• map it back in the 'common sensor space.'
• GitHub project: https://github.com/RickLicona/3-Layer-BEM-model

The final step is the evaluation of the employed method, using some techniques such as group decoding.

Python Machine Learning Developer at CIDETEC-IPN

Gamma Framework V1.0.

As a member of the Alfa-Beta research group, I transformed the theory of the Mexican Gamma classifier into Python 3.0 code. The Gamma Framework V1.0 with its methods, has the capacity to:

• Generate descriptive statistics
• Show the correlation that exists between the features
• Verify the existence of the missing values
• Scale and prepare the data for the Gamma classifier
• Divide the data using a Hold-Out stratified method
• Generate a confusion matrix after the prediction of the test data
• Give performance metrics such as accuracy and mean absolute error
• GitHub project: https://github.com/RickLicona/GammaClassifier

Research stay at the Cognitive Systems Laboratory, University of Bremen, Germany 🇩🇪

Development of the Riemannian MDM Framework, its purpose was the recognition of emotions from EEG signals. The Framework has the following characteristics:

• It is a Passive Brain-Computer Interface system
• For classification, you can use the Riemannian and classifiers based on hyperplanes such as Support Vector Machine using the Tangent Space concept
• It is possible to filter frequencies in different ranges due to the implementation of Butterworth order four filter
• Generate CSV files performance reports, as well as plots
• The performance metrics that use are ROC curve, AUC, and F1
• GitLab project: https://gitlab.csl.uni-bremen.de/rlicona/deap_pbci_riemannian

System analyst at Central Bank of Mexico (Banxico)

Participation in the project "Enlace Universitario Banxico." It is a project that recognizes academic talent employing the following technologies:

• Java Enterprise Edition (JEE)
• Javascript and jQuery
• Bootstrap
• CSS3
• JSON with Ajax
• Web services
• Selenium Automatization Testing
• Google Maps API

Math teacher in High School at Official Preparatory School Number 100

I taught math at the same time that we used the C language to create solutions to some problems. My students showed more interest in the subject

• Algebra
• Differential Calculus
• Integral Calculus
• Mathematical Reasoning

Computer teacher in High School at UAEM

I taught the language C and Bash fundamentals to my pupils using the Operative System Ubuntu. We use the emacs terminal editor to develop our code.

• Language C
• Language Bash (Shell Scripting) and Batch

"The power of the mind", Institute Polytechnic National-CECyT 8 "Narciso Bassols"

"Sistema Biométrico Inteligente", Institute Polytechnic National-CECyT 8 "Narciso Bassols"

“Smart analysis of brain computer waves for confidence tests”, 13th International Congress Technological Trends in Computing, Institute Polytechnic National-CIDETEC

Distinguished Graduate, Institute Polytechnic National-CECyT 8 "Narciso Bassols"

Honorific Mention, Master in Computer Science, Institute Polytechnic National-CIDETEC

Currently, in the platform of Google, I achieved with my team the 3rd place of more than 600 teams in the classification of Forest Types based on information about the area.

GitHub project: https://github.com/RickLicona/Classification_of_Forest_Types_Challenge