A5061707879- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Tactile and Sensory Interactions
- Gaze Tracking and Assistive Technology
- Functional Brain Connectivity Studies
- Gestational Diabetes Research and Management
- Parkinson's Disease Mechanisms and Treatments
- Muscle activation and electromyography studies
- Blind Source Separation Techniques
- 3D Surveying and Cultural Heritage
- Obesity, Physical Activity, Diet
- Nutritional Studies and Diet
- Heart Rate Variability and Autonomic Control
- Breastfeeding Practices and Influences
- Neonatal and fetal brain pathology
- Body Composition Measurement Techniques
- Neural Networks and Applications
- Analog and Mixed-Signal Circuit Design
- Bariatric Surgery and Outcomes
- Cardiovascular Disease and Adiposity
- Voice and Speech Disorders
- Birth, Development, and Health
- Neural and Behavioral Psychology Studies
- Balance, Gait, and Falls Prevention
- 3D Shape Modeling and Analysis
Instituto Nacional de Perinatología
2020-2024
Universidad Autónoma Metropolitana
2006-2023
Ibero American University
2019
Ultra-processed food (UPF) consumption during gestation may lead to increased oxidative stress (OS) and could affect pregnancy outcomes. This study aims evaluate the association of UPF with circulating levels OS markers. Diet was assessed (average three assessments) in 119 pregnant women enrolled OBESO perinatal cohort (Mexico), obtaining quantitative data percentage energy that UPFs (NOVA) contributed total diet. Sociodemographic, clinical (pregestational body-mass index gestational weight...
This paper describes preliminary performance results of a reconfigurable hardware implementation support vector machine classifier, aimed at brain-computer interface applications, which require real-time decision making in portable device. The main constraint the design was that it could perform classification within time span an evoked potential recording epoch 300 ms, readily achieved for moderate-sized sets. Regardless its fixed-point implementation, FPGA-based model achieves equivalent...
P300 spellers have been widely modified to implement nonspelling tasks. In this work, we propose a “scenario” stimulation screen that is speller variation command wheelchair. Our approach utilized with an image background (scenario snapshot for wheelchair) and markers arranged asymmetrically over relevant landmarks, such as suitable paths, doors, windows, wall signs. Other scenario features were green/blue marker color scheme, variable Interstimulus Interval, single stimulus mode, optimized...
In this paper, a new method of rigid point cloud registration called Points Registration Learning (PREL) is presented. This algorithm based on Deep Neural Networks trained by sparse autoencoders and fed with set Euclidean Mahalanobis distance maps. Unlike other reported methods, we do not assume closeness between clouds or pairs. allows registering high degree displacement occlusion. PREL does require an iterative process, it estimates points distribution non-parametrically finer adjustment...
Edinburgh Postpartum Depression (EPDS) and Breastfeeding Self-Efficacy (BSES) scales are standardized questionnaires to screen for postpartum depression breastfeeding performance self-perception. On the other hand, Natural Language Processing (NLP) is a machine learning technique that analyses human language extract relevant computer-interpretable information. In this work we proposed application of an NLP toolchain includes typical preprocessing stage probabilistic topic modeling performed...
In this work, a novel multimodal learning approach for early prediction of birth weight is presented. Fetal one the most relevant indicators in assessment fetal health status. The aim to predict using maternal-fetal variables from first trimester gestation (Anthropometric data, as well metrics obtained Biometry, Doppler and Maternal Ultrasound). proposed methodology starts with optimal selection subset features an ensemble-based feature selectors. Subsequently, selected feed nonparametric...
A previously introduced variation of a conventional P300 speller, consisting on modifiable image background and asymmetrically arranged stimulation markers for controlling wheelchair navigation, was used in this study. Five commonly classifiers solving speller-like tasks, namely, Linear-SVM, RBF-SVM, LASSO-LDA, Shrinkage-LDA SWLDA, were designed trained their performances contrasted, seeking the classifier with highest performance our proposed screen. 19 able-bodied subjects participated The...
Electroencephalography (EEG) is the most frequently used technique to monitor functional activity of brain. It has been widely employed in brain-computer interfaces based on detection P300 potentials. However, waves often contain physiological and non-physiological artifacts such as steady state visually evoked potential, power line or environment noise. The aim this work eliminate undesirable periodic independent components from EEG, order enhance wave. proposed method combines component...
Fat-mass (FM) assessment since birth using valid methodologies is crucial excessive adiposity represents a risk factor for adverse metabolic outcomes.To develop infant FM prediction equations anthropometry and validate them against air-displacement plethysmography (ADP).Clinical, anthropometric (weight, length, body-mass index -BMI-, circumferences, skinfolds), (ADP) data were collected from healthy-term infants at 1 (n = 133), 3 105), 6 101) months enrolled in the OBESO perinatal cohort...
The identification of brain dynamical changes under different cognitive conditions with noninvasive techniques such as electroencephalography (EEG) is relevant for the understanding their underlying neural mechanisms. comprehension these mechanisms has applications in early diagnosis neurological disorders and asynchronous computer interfaces. In both cases, there are no reported features that could describe intersubject intra subject dynamics behavior accurately enough to be applied on a...
Pregnant women with diabetes often present impaired fetal growth, which is less common if maternal well-controlled. However, developing strategies to estimate body composition beyond growth that could better predict metabolic complications later in life essential. This study aimed evaluate subcutaneous fat tissue (femur and humerus) fetuses normal among pregnant well-controlled using a reproducible 3D-ultrasound tool offline TUI (Tomographic Ultrasound Imaging) analysis. Additionally, three...
Pregnant women with diabetes often present impaired fetal growth, which is less common if maternal well-controlled. However, developing strategies to estimate body composition beyond growth that could better predict metabolic complications later in life essential. This study aimed evaluate subcutaneous fat tissue (femur and humerus) fetuses normal among pregnant well-controlled using a reproducible 3D-ultrasound tool offline TUI (Tomographic Ultrasound Imaging) analysis. Additionally, three...
Asynchronous Brain Computer Interfaces (BCI) al-low system activation at free will. This scenario would be desirable for potential users such as patients with motor disabilities, however, there are still several limitations long calibration times and overall performance. Different approaches to improve these systems explore diverse linear electroencephalography (EEG) features in order describe cognitive states. Alternatively, the present study proposes use of recurrence quantification...