Bachelor Degree: 1999, Electronics Engineer, Instituto Tecnológico de Ciudad Madero, Tamaulipas, México.
Master of Science Degree: 2001, Instituto Politécnico Nacional, Tijuana, Baja California, México.
PhD: Doctor of Science, 2022 Universidad Autónoma de Baja California, Ensenada, Baja California, México.
RESEARCH, TEACHING, or OTHER INTERESTS
Electrical and Electronic Engineering, Biomedical Engineering, Signal Processing
9
Scopus Publications
Scopus Publications
Enhancing Glioma Classification in Magnetic Resonance Imaging Using Vision Transformers and Convolutional Neural Networks Marco Antonio Gómez-Guzmán, José Jaime Esqueda-Elizondo, Laura Jiménez-Beristain, Gilberto Manuel Galindo-Aldana, Oscar Adrian Aguirre-Castro, et al. Electronics Switzerland, 2026 Brain tumors, encompassing subtypes with distinct progression and risk profiles, are a serious public health concern. Magnetic resonance imaging (MRI) is the primary imaging modality for non-invasive assessment, providing the contrast and detail necessary for diagnosis, subtype classification, and individualized care planning. In this paper, we evaluate the capability of modern deep learning models to classify gliomas as high-grade (HGG) or low-grade (LGG) using reduced training data from MRI scans. Utilizing the BraTS 2019 best-slice dataset (2185 images in two classes, HGG and LGG) divided in two folders, training and testing, with different images obtained from different patients, we created subsets including 10%, 25%, 50%, 75%, and 100% of the dataset. Six deep learning architectures, DeiT3_base_patch16_224, Inception_v4, Xception41, ConvNextV2_tiny, swin_tiny_patch4_window7_224, and EfficientNet_B0, were evaluated utilizing three-fold cross-validation (k = 3) and increasingly large training datasets. Explainability was assessed using Grad-CAM. With 25% of the training data, DeiT3_base_patch16_224 achieved an accuracy of 99.401% and an F1-Score of 99.403%. Under the same conditions, Inception_v4 achieved an accuracy of 99.212% and a F1-Score of 99.222%. Considering how the models performed across both data subsets and their compute demands, Inception_v4 struck the best balance for MRI-based glioma classification. Both convolutional networks and vision transformers achieved superior discrimination between HGGs and LGGs, even under data-limited conditions. Architectural disparities became increasingly apparent as training data diminished, highlighting unique inductive biases and efficiency characteristics. Even with a relatively limited amount of training data, current deep learning (DL) methods can achieve reliable performance in classifying gliomas from MRI scans. Among the architectures evaluated, Inception_v4 offered the most consistent balance between accuracy, F1-Score, and computational cost, making it a strong candidate for integration into MRI-based clinical workflows.
Enhanced Multi-Class Brain Tumor Classification in MRI Using Pre-Trained CNNs and Transformer Architectures Marco Antonio Gómez-Guzmán, Laura Jiménez-Beristain, Enrique Efren García-Guerrero, Oscar Adrian Aguirre-Castro, José Jaime Esqueda-Elizondo, et al. Technologies, 2025 Early and accurate identification of brain tumors is essential for determining effective treatment strategies and improving patient outcomes. Artificial intelligence (AI) and deep learning (DL) techniques have shown promise in automating diagnostic tasks based on magnetic resonance imaging (MRI). This study evaluates the performance of four pre-trained deep convolutional neural network (CNN) architectures for the automatic multi-class classification of brain tumors into four categories: Glioma, Meningioma, Pituitary, and No Tumor. The proposed approach utilizes the publicly accessible Brain Tumor MRI Msoud dataset, consisting of 7023 images, with 5712 provided for training and 1311 for testing. To assess the impact of data availability, subsets containing 25%, 50%, 75%, and 100% of the training data were used. A stratified five-fold cross-validation technique was applied. The CNN architectures evaluated include DeiT3_base_patch16_224, Xception41, Inception_v4, and Swin_Tiny_Patch4_Window7_224, all fine-tuned using transfer learning. The training pipeline incorporated advanced preprocessing and image data augmentation techniques to enhance robustness and mitigate overfitting. Among the models tested, Swin_Tiny_Patch4_Window7_224 achieved the highest classification Accuracy of 99.24% on the test set using 75% of the training data. This model demonstrated superior generalization across all tumor classes and effectively addressed class imbalance issues. Furthermore, we deployed and benchmarked the best-performing DL model on embedded AI platforms (Jetson AGX Xavier and Orin Nano), demonstrating their capability for real-time inference and highlighting their feasibility for edge-based clinical deployment. The results highlight the strong potential of pre-trained deep CNN and transformer-based architectures in medical image analysis. The proposed approach provides a scalable and energy-efficient solution for automated brain tumor diagnosis, facilitating the integration of AI into clinical workflows.
Mindfulness-Based Intervention Effects on EEG and Executive Functions: A Systematic Review Gilberto Galindo-Aldana, Luis Arturo Montoya-Rivera, Jose Jaime Esqueda-Elizondo, Everardo Inzunza-Gonzalez, Enrique Efren Garcia-Guerrero, et al. Brain Sciences, 2025 Background. Mindfulness-based interventions (MBIs) have emerged as an alternative intervention for symptoms of psychological and psychiatric conditions, such as depression, anxiety, and emotional discomfort. Over the last ten years, MBIs have established a growing body of evidence that shows cognitive and neurophysiological benefits. Depression and anxiety are conditions with a high prevalence in the world population. In developing countries, it is reported that, given the conditions of being at a social disadvantage, anxiety and depression are higher, resulting in compromised psychological well-being and mental health. Objectives. This systematic review aims to quantitatively and qualitatively assess changes in the neuropsychological, particularly executive functioning and social cognition domains, and electroencephalographical (EEG) effects of MBIs. Methods. A systematic review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) in three databases, Web of Science, Scopus, and EBSCO MedLine complete; 14,464 articles were found, 141 articles evaluated the effects of MBI on executive functioning, and 16 included both as in qualitative and quantitative variables. Results. The qualitative results show that the research on the effects of MBI on behavior and cognitive skills, including executive function, social cognition, and EEG analysis, is very scarce but consistent in suggesting strong correlations on cognitive and electrophysiological alpha–beta proportions asymmetry on frontal areas. Undoubtedly, executive functions, as a behavioral regulatory and self-monitoring system, are the most popular study of interest in the literature, including emotional regulation, awareness, planning, social skills, and focused attention. Although there are fewer studies assessing the effects of MBIs on social cognition skills. The funnel plot showed a symmetrical distribution but ranked out of significant correlation. Most estimates of treatment effects are positive (58%); however, the average outcome observed did not significantly differ from zero. Conclusions. This study concludes that the research integrating the analysis of the electrophysiological and executive function effects of MBI shows important methodological variations and clinical conditions, which explains the significant results reported individually. Even when most of the literature reports positive effects of MBIs on several behavioral and neurophysiological domains, there are still confounding factors that must be taken into consideration by researchers and clinicians before attributing possible inaccurate or generalizable benefits.
Emotion Classification from Electroencephalographic Signals Using Machine Learning Jesus Arturo Mendivil Sauceda, Bogart Yail Marquez, José Jaime Esqueda Elizondo Brain Sciences, 2024 Background: Emotions significantly influence decision-making, social interactions, and medical outcomes. Leveraging emotion recognition through Electroencephalography (EEG) signals offers potential advancements in personalized medicine, adaptive technologies, and mental health diagnostics. This study aimed to evaluate the performance of three neural network architectures—ShallowFBCSPNet, Deep4Net, and EEGNetv4—for emotion classification using the SEED-V dataset. Methods: The SEED-V dataset comprises EEG recordings from 16 individuals exposed to 15 emotion-eliciting video clips per session, targeting happiness, sadness, disgust, neutrality, and fear. EEG data were preprocessed with a bandpass filter, segmented by emotional episodes, and split into training (80%) and testing (20%) sets. Three neural networks were trained and evaluated to classify emotions from the EEG signals. Results: ShallowFBCSPNet achieved the highest accuracy at 39.13%, followed by Deep4Net (38.26%) and EEGNetv4 (25.22%). However, significant misclassification issues were observed, such as EEGNetv4 predicting all instances as “Disgust” or “Neutral” depending on the configuration. Compared to state-of-the-art methods, such as ResNet18 combined with differential entropy, which achieved 95.61% accuracy on the same dataset, the tested models demonstrated substantial limitations. Conclusions: Our results highlight the challenges of generalizing across emotional states using raw EEG signals, emphasizing the need for advanced preprocessing and feature-extraction techniques. Despite these limitations, this study provides valuable insights into the potential and constraints of neural networks for EEG-based emotion recognition, paving the way for future advancements in the field.
Classifying Brain Tumors on Magnetic Resonance Imaging by Using Convolutional Neural Networks Marco Antonio Gómez-Guzmán, Laura Jiménez-Beristaín, Enrique Efren García-Guerrero, Oscar Roberto López-Bonilla, Ulises Jesús Tamayo-Perez, et al. Electronics Switzerland, 2023 The study of neuroimaging is a very important tool in the diagnosis of central nervous system tumors. This paper presents the evaluation of seven deep convolutional neural network (CNN) models for the task of brain tumor classification. A generic CNN model is implemented and six pre-trained CNN models are studied. For this proposal, the dataset utilized in this paper is Msoud, which includes Fighshare, SARTAJ, and Br35H datasets, containing 7023 MRI images. The magnetic resonance imaging (MRI) in the dataset belongs to four classes, three brain tumors, including Glioma, Meningioma, and Pituitary, and one class of healthy brains. The models are trained with input MRI images with several preprocessing strategies applied in this paper. The CNN models evaluated are Generic CNN, ResNet50, InceptionV3, InceptionResNetV2, Xception, MobileNetV2, and EfficientNetB0. In the comparison of all CNN models, including a generic CNN and six pre-trained models, the best CNN model for this dataset was InceptionV3, which obtained an average Accuracy of 97.12%. The development of these techniques could help clinicians specializing in the early detection of brain tumors.
Integration of Low-Cost Digital Tools for Preservation of a Sustainable Agriculture System Alejandra Serrano-Trujillo, José Jaime Esqueda-Elizondo, Laura Jiménez-Beristáin Electronics Switzerland, 2022 This work presents an electronic sensing approach composed of a pair of Physical–Chemical and Imaging modules to preserve an aquaponic system. These modules offer constant measurements of the physical–chemical characteristics within the fish tank and the grow bed, and an indication of the health of the growing plants through image processing techniques. This proposal is implemented in a low-cost computer, receiving measurements from five sensors, including a camera, and processing the signals using open-source libraries and software. Periodic measurements of the temperature, water level, light, and pH within the system are collected and shared to a cloud platform that allows their display in a dashboard, accessible through a web page. The health of the vegetables growing in the system is estimated by analyzing visible and infrared spectra, applying feature extraction, and computing vegetation indices. This work provides a low-cost solution for preserving sustainable urban farming systems, suitable for new farming communities.
Lessons learned deploying an oyster farm monitoring auto-sustainable wireless sensor network and trial of a temperature and relative humidity-based transmission power control scheme César Ortega-Corral, José Jaime Esqueda Elizondo, Oscar Ricardo Acosta Del Campo, Luis E Palafox, Leocundo Aguilar, et al. International Journal of Distributed Sensor Networks, 2017 We present challenges faced deploying a solar-powered wireless sensor network base station and nodes, at a remote oyster farm. It involved installing the base station system and a data server at the shore of a shallow bay, where there is no electrical power available. To solve the problem, we set up a photovoltaic array with an energy monitoring node, from which performance metrics were recorded and plotted. At the water, we deployed two wireless sensor nodes on a raft, a kilometre away from the base station. One node was configured for sea water pH and water temperature ( Tw) measurements. The other node was configured for salinity and Tw measurements. Furthermore, both nodes measured air temperature and relative humidity, for a more complete characterization. At the salinity node, temperature and relative humidity knowledge was crucial to determine a gain factor for doing a trial of a transmission power control scheme, using a novel temperature and relative humidity algorithm. To enable a fair comparison, the pH nodes transmitter was configured with a fixed power level. The nodes performances were measured locally at the base station, recording metrics such as received signal strength indicator and packet received rates.
