Adaptive Evaluation: Challenges in Biomedical Engineering

When:
April 14, 2017 @ 1:30 pm – 2:30 pm
2017-04-14T13:30:00-06:00
2017-04-14T14:30:00-06:00
Where:
CCSB G.0208

Dr. Ricardo Rodríguez Jorge, Autonomous University of Ciudad Juarez

Abstract:

Quadratic and cubic neural units are types of a higher-order neural units which can be used for prediction tasks among others, in the medical field. The example of the tasks includes monitoring cardiac behavior in real-time either for preemptive treatment, or for supporting a doctor to reach a more accurate diagnosis. This work proposes a predictive model which has been developed as an application with the aim to make it accessible for medical professionals and to decrease the implementation cost. The proposed model uses sample-by-sample adaptation of the gradient descent method with error back-propagation. This work presents an application of quadratic and cubic neural units as a prediction mechanism for abnormal cardiac behaviors, and it describes a new adaptive methodology based on application of dynamic quadratic and cubic neural units for cardiac arrhythmia prediction. To validate the model, it has been tested on the data from the Massachusetts Institute of Technology-Beth Israel Hospital Cardiac Record Database. This work is focused on premature ventricular contraction, atrial premature contraction and normal heartbeat records.

 

Keywords. Quadratic neural unit, cubic neural unit, predictive model, cardiac arrhythmia, adaptive methodology

 

Biosketch

Dr. Ricardo Rodríguez Jorge (ricardo.jorge@uacj.mx, http://rodriguezricardo.net/)

Full Time Professor, Department of Industrial and Manufacturing Engineering

Autonomous University of Ciudad Juarez

Ricardo Rodriguez Jorge received his Ph.D. from the Department of Instrumentation and Control Engineering from the Czech Technical University in Prague, Faculty of Mechanical Engineering in 2012. He is a Researcher in the Department of Industrial and Manufacturing Engineering, Autonomous University of Ciudad Juarez, Mexico. His research interests mainly focus on time series prediction, signal processing, artificial neural networks, adaptive control systems, pattern recognition, mechatronics, and artificial intelligence. He serves as Associate Editor of Intelligent Automation and Soft Computing published by Taylor & Francis (Master Journal List) and also on several peer-reviewed international journal Editorial Boards like International Journal DYNA published by DYNA Engineering & Industry (Master Journal List), Journal of Advanced Computer Science and Information Technology published by Elvedit.Com, International Journal of Humanitarian Technology published by Interscience Publishers. He has participated in nearly 40 international conferences/workshops as technical program committee, and he has also participated as a reviewer in about 52 conferences. He has (co-) authored more than 36 book chapters, journal and international conference papers. Dr. Rodriguez has been keynote speaker in national and international conferences, as well as he gave many invited talks. Currently, his research papers are referenced by other research works all over the world. In 2012 one of his papers earned the 2nd place in a conference in Czech Technical University in Prague, Czech Republic. Furthermore, he earned the 1st place in a conference in Krakow University of Technology, Poland. In 2013, one of his coauthored papers earned the best paper award presented in the 6th International Conference on Research, in the Computer Science field. In 2016 the research group that he belongs to has been awarded by PRODEP as (In consolidation research group): UACJ-CA-109 Artificial Vision, Control & Robotics. Currently, He serves as General Chair of the Eighth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2017) to be held in Autonomous University of Ciudad Juarez in Mexico.