Antonio Gustavo Juarez Gracia

Dr. Antonio Gustavo Juarez Gracia

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 January 2019 in Sensors
Verified
Journal Article
Open access
MMMoisés Márquez-Olivera
Moisés Márquez-Olivera
AGAntonio Gustavo Juarez Gracia
Antonio Gustavo Juarez Gracia
VHViridiana Hernández-Herrera
Viridiana Hernández-Herrera
Amadeo ArgüellesAmadeo Argüelles
Amadeo Argüelles
ILItzamá López-Yáñez
Itzamá López-Yáñez
Face recognition is a natural skill that a child performs from the first days of life; unfortunately, there are people with visual or neurological problems that prevent the individual from performing the process visually. This work describes a system that integrates Artificial Intelligence which learns the face of the people with whom the user interacts daily. During the study we propose a new hybrid model of Alpha-Beta Associative memories (Amαβ) with Correlation Matrix (CM) and K-Nearest Neighbors (KNN), where the Amαβ-CMKNN was trained with characteristic biometric vectors generated from images of faces from people who present different facial expressions such as happiness, surprise, anger and sadness. To test the performance of the hybrid model, two experiments that differ in the selection of parameters that characterize the face are conducted. The performance of the proposed model was tested in the databases CK+, CAS-PEAL-R1 and Face-MECS (own), which test the Amαβ-CMKNN with faces of subjects of both sexes, different races, facial expressions, poses and environmental conditions. The hybrid model was able to remember 100% of all the faces learned during their training, while in the test in which faces are presented that have variations with respect to those learned the results range from 95.05% in controlled environments and 86.48% in real environments using the proposed integrated system.

10 April 2026 in Vehicles
Verified
Journal Article
Open access
PDF file
JSJulio Cesar Saucedo Soto
Julio Cesar Saucedo Soto
VHViridiana Hernández-Herrera
Viridiana Hernández-Herrera
MMMoisés Marquez-Olivera Márquez-Olivera
Moisés Marquez-Olivera Márquez-Olivera
OSOctavio Sánchez
Octavio Sánchez
AGAntonio Gustavo Juarez Gracia
Antonio Gustavo Juarez Gracia
Given that approximately 70% of traffic accidents are attributable to driver-related factors, it is necessary for vehicles to incorporate technologies that reduce risk through preventive actions derived from traffic-scene analysis. Interpreting the driving environment is non-trivial and is commonly decomposed into sub-tasks; among them, traffic light perception is critical due to its role in regulating vehicular flow. This paper evaluates five YOLO CNN families (YOLOv8–YOLOv12) on two tasks: (i) traffic light detection and (ii) traffic light state recognition (green, yellow, red). The evaluation uses a hybrid dataset comprising the public LISA traffic light dataset and a custom dataset with images from Mexico City captured under diverse lighting conditions—a relevant setting given the city’s high traffic intensity. The results show mAP@0.50 = 94.4–96.3% for traffic light detection and mAP@0.50 = 99.3–99.4% for traffic light state recognition, indicating that modern YOLO variants provide highly reliable performance for both tasks under natural illumination variability.

3 January 2024 in International Journal of Radiation Biology
Verified
Journal Article
Closed access
ARAlejandro Rojas
Alejandro Rojas
EHErnesto Hernández-Rosales
Ernesto Hernández-Rosales
JMJesús Montúfar
Jesús Montúfar
AGAntonio Gustavo Juarez Gracia
Antonio Gustavo Juarez Gracia
UNUriel Nogal
Uriel Nogal
JCJosé Antonio Calderón
José Antonio Calderón
Evaluate the structural damage and the changes in the photosynthesis and transpiration rates of aquatic lirium leaves caused by ultrasound (US) irradiation in search of environmentally friendly methodologies for the control of this weed. Aquatic lirium plants were extracted from Xochimilco water canals in Mexico City. A part of the group of plants was selected for irradiation, and the rest formed the control group. The irradiation plants group was exposed to US irradiation of 17 kHz frequency and 30 W × 4 output power for 2 h, at noon and 25 °C room temperature. The structural analysis was done with a MOTICAM 1 digital camera, 800 × 600 pixels, incorporated into the MOTIC PSM-1000 optical microscope and edited with Motic Images Plus 2.0 ML software. The total stomata density and the damaged stomata density were determined by dividing the numbers of total and damaged stomata by the visual field area (67,917 mm2), respectively. The leaves' photosynthesis and transpiration rates were measured using an LI-6400XT Portable Photosynthesis System. Significant damage was observed in the stomata and epidermal cells, finding that the average ratio between the damaged and total stomata densities as a function of time (days) showed an exponential increase described by a Box-Lucas equation with a saturation value near unity and a maximum rate of change of the density of damaged stomata on zero-day (immediately after irradiation), decreasing as the days go by. The transpiration rate showed a sudden increase during the first hour after irradiation, reaching a maximum of 36% of its value before irradiation. It then quickly fell during the next 6 days and more slowly until the 21st day, decreasing 79.9% of its value before irradiation. The photosynthetic rate showed similar behavior with a 37.7% maximum increment and a 73.6% minimum decrease of its value before irradiation. The results of structural stomata damage on the ultrasound-irradiated aquatic lirium leaves are consistent with an excessive ultrasound stimulation on stomata's mechanical operation by guard cells that produce the measured significant increase of the photosynthetic and transpiration rates during the first hour after irradiation. The initial high evaporation could alter the water potential gradient, with a possible generation of tensions in the xylem that could cause embolism in their conduits. The loss of xylem conductivity or hydraulic failure would be consistent with the observed significant fall in the photosynthesis and transpiration rates of the aquatic lirium leaves after its sudden rise in the first hour after irradiation.

14 September 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
LVLuis Daniel Reséndiz ventura
Luis Daniel Reséndiz ventura
MMMoisés Marquez-Olivera Márquez-Olivera
Moisés Marquez-Olivera Márquez-Olivera
VHViridiana Hernández-Herrera
Viridiana Hernández-Herrera
LMLaura Marrujo-García
Laura Marrujo-García
AGAntonio Gustavo Juarez Gracia
Antonio Gustavo Juarez Gracia
IPIrlanda Pacheco-Bravo
Irlanda Pacheco-Bravo
Background/Objectives: Lung cancer outcomes depend strongly on early detection, highlighting the need for accurate, robust, and interpretable methods for identifying pulmonary nodules on computed tomography (CT). This study proposes a multi-organ anatomical-contextual framework based on YOLOv8–YOLOv12, in which supporting thoracic structures are incorporated as spatial references during training while the pulmonary nodule is retained as a single invariant pathological class. Methods: The models were trained and internally validated on 5000 2D axial CT slices from 320 patients in the LUNG-PET-CT-DX dataset and externally evaluated on an independent LIDC-IDRI subset comprising 700 axial slices from 70 patients, without retraining or fine-tuning. A controlled ablation study comparing Nodule-only with Nodule + Anatomical Context was performed. Results: The anatomical-contextual scheme showed consistent improvements across all five architectures, with mean absolute gains of +0.078 in Precision, +0.122 in Recall, +0.101 in F1-score, +0.079 in mAP@50, and +0.190 in mAP@50–95. During internal validation, YOLOv10m achieved the highest Precision (0.979) and mAP@50 (0.987), as well as the shortest inference time (9.25 ms), whereas YOLOv11m achieved the highest Recall (0.971) and F1-score (0.962). During external evaluation, YOLOv10m retained the highest Precision (0.924) and mAP@50 (0.956), while YOLOv8m achieved the highest Recall (0.930) and mAP@50–95 (0.845); both models achieved an F1-score of 0.922. Conclusions: These findings provide experimental evidence that anatomical-contextual learning improves pulmonary nodule detection while maintaining competitive performance across datasets, supporting its potential as an anatomically informed and interpretable strategy for AI-assisted thoracic CT analysis.

22 September 2026 in Smart Cities
Verified
Journal Article
Open access
PDF file
JSJulio Cesar Saucedo Soto
Julio Cesar Saucedo Soto
VHViridiana Hernández-Herrera
Viridiana Hernández-Herrera
MMMoisés Marquez-Olivera Márquez-Olivera
Moisés Marquez-Olivera Márquez-Olivera
AGAntonio Gustavo Juarez Gracia
Antonio Gustavo Juarez Gracia
OSOctavio Sánchez
Octavio Sánchez
Amadeo ArgüellesAmadeo Argüelles
Amadeo Argüelles
Urban road user detection supports safety-critical applications in Intelligent Transportation Systems, but architecture assessment requires balancing predictive performance with computational efficiency under controlled and leakage-aware evaluation conditions. This study adopts a three-stage benchmarking framework for vehicle, motorcycle, and pedestrian detection using a hybrid dataset of 4983 images derived from LISA and traffic scenes captured at 18 complex intersections in Mexico City. Stage I provides an exploratory comparison of six medium-sized YOLO architectures (YOLOv8m, YOLOv9m, YOLOv10m, YOLOv11m, YOLOv12m, and YOLOv26m), whereas Stage II restricts leakage-controlled confirmatory evaluation to three selected architectures: YOLOv10m, YOLOv11m, and YOLOv26m. Stage III examines the corresponding YOLOv10n and YOLOv26n nano variants. Both sources were manually annotated under a unified three-class protocol, producing 3483 quantitative images with 6624 ground truth instances and 1500 images for qualitative inference. Annotation reproducibility reached a mean pairwise IoU of 0.85 ± 0.11 and Fleiss’ κ of 0.968. A retrospective audit of the original image-level split identified acquisition group overlap and confirmed near duplicates across partitions. A corrected group-disjoint split eliminated shared groups, exact duplicates, and confirmed near duplicates while preserving the aggregate source and class distributions. Under three-seed leakage-controlled confirmatory evaluation, YOLOv26m achieved the highest mAP@0.50:0.95 among the three Stage II confirmatory models (0.5717 ± 0.0013), followed by YOLOv11m (0.5632 ± 0.0012) and YOLOv10m (0.5516 ± 0.0014), with paired bootstrap analysis supporting all three pairwise differences after Holm correction. Source-specific evaluation revealed consistently lower performance on the Mexico City subset than on LISA. YOLOv11m showed the lowest overall calibration error (ECE = 0.052 ± 0.003). At the nano-scale, YOLOv10n provided higher mAP@0.50:0.95, lower latency, and greater throughput than YOLOv26n, whereas YOLOv26n required fewer GFLOPs and less benchmark energy. The Stage II group-disjoint protocol produced more conservative performance estimates than Stage I; however, the observed mAP reduction cannot be quantified as the effect of leakage removal alone because the two stages also differed in optimization configuration and repeated-run design. These findings support multi-objective model selection based on predictive performance, calibration, latency, complexity, memory, energy consumption, and deployment constraints.