Carlos Daniel Virgilio Gonzalez
Research Subjects
Carlos Daniel Virgilio Gonzalez has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Javier Mauricio Antelis
Tecnológico de Monterrey
3 shared publications - Alejandro Muñoz-Diosdado
Unidad Profesional Interdisciplinaria de Biotecnología, Instituto Politécnico Nacional, Mexico City 07340, Mexico
2 shared publications - Ana María Aguilar-Molina
Unidad Profesional Interdisciplinaria de Biotecnología, Instituto Politécnico Nacional, Mexico City 07340, Mexico
2 shared publications - Humberto Sossa
Centro de Investigación en Computación, Instituto Politécnico Nacional, Ciudad de México 07738, Mexico
2 shared publications - José Alberto Zamora-Justo
Basic Sciences Department, Unidad Profesional Interdisciplinaria de Biotecnología, Instituto Politécnico Nacional, Mexico City 07340, Mexico
2 shared publications Juan Humberto Sossa Azuela
2 shared publications
Latest Publications
- 21 October 2021
- Published by Springer Nature
- p. 253-264
Touchless Fingerphoto Extraction Based on Deep Learning and Image Processing Algorithms; A Preview
- 21 October 2021
- Published by Springer Nature
- p. 253-264
Touchless Fingerphoto Extraction Based on Deep Learning and Image Processing Algorithms; A Preview
- 1 February 2020
- Published by Elsevier in Neural Networks
- Vol. 122, 130-143
Spiking Neural Networks applied to the classification of motor tasks in EEG signals
- 1 February 2020
- Published by Elsevier in Neural Networks
- Vol. 122, 130-143
Spiking Neural Networks applied to the classification of motor tasks in EEG signals
- 18 May 2019
- Published by Springer Nature
- p. 14-24
Motor Imagery Task Classification in EEG Signals with Spiking Neural Network
- 18 May 2019
- Published by Springer Nature
- p. 14-24
Motor Imagery Task Classification in EEG Signals with Spiking Neural Network
- 1 January 2018
- Published by Springer Nature
- p. 110-122
Artificial Neural Networks and Common Spatial Patterns for the Recognition of Motor Information from EEG Signals
- 1 January 2018
- Published by Springer Nature
- p. 110-122
Artificial Neural Networks and Common Spatial Patterns for the Recognition of Motor Information from EEG Signals
- 1 January 2018
- Published by Springer Nature
- p. 123-135
Classification of Motor Imagery EEG Signals with CSP Filtering Through Neural Networks Models
- 1 January 2018
- Published by Springer Nature
- p. 123-135
Classification of Motor Imagery EEG Signals with CSP Filtering Through Neural Networks Models
- 1 January 2014
- Published by AIP Publishing in AIP Conference Proceedings
Holter registers and metabolic syndrome
There is a relationship between the state of the cardiovascular system and metabolic syndrome (MS). A way to diagnose the heart state of a person is to monitor the electrical activity of the heart using a 24 hours Holter monitor. Scanned ECG signal can be analyzed beat-by-beat by algorithms that separate normal of abnormal heartbeats. If the percentage of abnormal heartbeats is too high it could be argued that the patient has heart problems. We have algorithms that can not only identify the abnormal heartbeats, but they can also classify them, so we classified and counted abnormal heartbeats in patients with MS and subjects without MS. Most of our patients have large waist circumference, high triglycerides and high levels of LDL (high-density lipoprotein) cholesterol although some of them have high blood pressure. We enrolled adult patients with MS free of diabetes in a four month lifestyle intervention program including diet and physical aerobic exercise, and compared with healthy controls. We made an initial registration with a Holter, and 24 hours ECG signal is analyzed to identify and classify the different types of heartbeats. The patients then begin with diet or exercise (at least half an hour daily). Periodically Holter records were taken up and we describe the evolution in time of the number and type of abnormal heartbeats. Results show that the percentage of abnormal heartbeats decreases over time, in some cases the decline is very significant, and almost a reduction to half or less of abnormal heartbeats after several months since the patients changed their eating or physical activity habits.
- 1 January 2014
- Published by AIP Publishing in AIP Conference Proceedings
Holter registers and metabolic syndrome
There is a relationship between the state of the cardiovascular system and metabolic syndrome (MS). A way to diagnose the heart state of a person is to monitor the electrical activity of the heart using a 24 hours Holter monitor. Scanned ECG signal can be analyzed beat-by-beat by algorithms that separate normal of abnormal heartbeats. If the percentage of abnormal heartbeats is too high it could be argued that the patient has heart problems. We have algorithms that can not only identify the abnormal heartbeats, but they can also classify them, so we classified and counted abnormal heartbeats in patients with MS and subjects without MS. Most of our patients have large waist circumference, high triglycerides and high levels of LDL (high-density lipoprotein) cholesterol although some of them have high blood pressure. We enrolled adult patients with MS free of diabetes in a four month lifestyle intervention program including diet and physical aerobic exercise, and compared with healthy controls. We made an initial registration with a Holter, and 24 hours ECG signal is analyzed to identify and classify the different types of heartbeats. The patients then begin with diet or exercise (at least half an hour daily). Periodically Holter records were taken up and we describe the evolution in time of the number and type of abnormal heartbeats. Results show that the percentage of abnormal heartbeats decreases over time, in some cases the decline is very significant, and almost a reduction to half or less of abnormal heartbeats after several months since the patients changed their eating or physical activity habits.
- 1 January 2014
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1626, 155-158
Multifractal analysis and the NYHA index
We did multifractal analysis of heartbeat interval time series of healthy persons and patients with congestive heart failure (CHF). To analyze circadian rhythm variations we analyzed time series of 24 hours records and segments of six hours when the subject is asleep and segments of six hours when is awake. A decrease in the multifractality degree occurs in the heartbeat interval time series of CHF patients. This multifractality loss is associated with the width reduction of the spectrum and the complexity loss of the signal. Multifractal spectra of healthy persons are right skewed, but the spectra of CHF patients tend to be symmetrical and in some cases are left skewed. To determine the therapy for CHF patients, cardiologists use an index proposed by the NYHA (New York Heart Association). There is a correlation between this index and the multifractal analysis parameters, i.e. while higher is the NYHA index the width of the multifractal spectrum is lower and it is also more symmetrical. In contrast, patients with NYHA index equal to 1 have multifractal parameters similar to those of healthy subjects.
- 1 January 2014
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1626, 155-158
Multifractal analysis and the NYHA index
We did multifractal analysis of heartbeat interval time series of healthy persons and patients with congestive heart failure (CHF). To analyze circadian rhythm variations we analyzed time series of 24 hours records and segments of six hours when the subject is asleep and segments of six hours when is awake. A decrease in the multifractality degree occurs in the heartbeat interval time series of CHF patients. This multifractality loss is associated with the width reduction of the spectrum and the complexity loss of the signal. Multifractal spectra of healthy persons are right skewed, but the spectra of CHF patients tend to be symmetrical and in some cases are left skewed. To determine the therapy for CHF patients, cardiologists use an index proposed by the NYHA (New York Heart Association). There is a correlation between this index and the multifractal analysis parameters, i.e. while higher is the NYHA index the width of the multifractal spectrum is lower and it is also more symmetrical. In contrast, patients with NYHA index equal to 1 have multifractal parameters similar to those of healthy subjects.