Marcos Yamir Gómez-Ramos

Marcos Yamir Gómez-Ramos

Auto-generated profile, based on publicly available information

Marcos Yamir Gómez-Ramos

Universidad Politéctica Metropolitana de Hidalgo, Mexico

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
10 November 2026
Verified
Book Chapter
Closed access
JAJaime Aguilar-Ortiz
Jaime Aguilar-Ortiz
ODOcotlán Diáz-Parra
Ocotlán Diáz-Parra
Jorge A. Ruiz-VanoyeJorge A. Ruiz-Vanoye
Jorge A. Ruiz-Vanoye
MJMARCO ANTONIO VERA JIMENEZ
MARCO ANTONIO VERA JIMENEZ
VZVíctor M. Zamudio-García
Víctor M. Zamudio-García
MGMarcos Yamir Gómez-Ramos
Marcos Yamir Gómez-Ramos
A model-based topological digital twin is developed for warehouse processes by joining MBSE requirements, synchronized event streams, persistent homology, Mapper graphs, and operational indicators. Synthetic data enable regeneration, controlled parameters, and internal validation; they do not support causal or industrial-performance claims. The illustrative experiment is extended across 30 seeds, point-cloud and Mapper sensitivity analyses, and two conventional comparators. Reconfiguration reduces dwell time and queue length while increasing throughput. Its topological effects are less uniform: several H_{2} measures and alert counts improve, but H_{1} indicators remain sensitive to sampling and do not consistently return to baseline. KPI rules identify disruption, whereas PCA also marks reconfigured states. Topology therefore supplies complementary rather than universally superior evidence. The pipeline produces auditable outputs suitable for future VR/AR integration, although neither an immersive interface nor a user study is implemented.

25 September 2026
Verified
Book Chapter
Closed access
JAJaime Aguilar-Ortiz
Jaime Aguilar-Ortiz
ODOcotlán Diáz-Parra
Ocotlán Diáz-Parra
Jorge A. Ruiz-VanoyeJorge A. Ruiz-Vanoye
Jorge A. Ruiz-Vanoye
MJMARCO ANTONIO VERA JIMENEZ
MARCO ANTONIO VERA JIMENEZ
VZVíctor M. Zamudio-García
Víctor M. Zamudio-García
MGMarcos Yamir Gómez-Ramos
Marcos Yamir Gómez-Ramos
This chapter presents CrimeRisk-BigData, a reproducible big data framework for forecasting neighborhood-level crime risk in smart heterogeneous networks. Its purpose is to connect responsible predictive policing with an executable Python architecture that integrates geospatial, temporal, contextual, and network-aware variables. The objective is to transform heterogeneous urban records into calibrated probabilistic risk estimates, interpretable spatial outputs, fairness diagnostics, and operational evidence for preventive planning rather than automated enforcement. The framework formalizes crime events as spatio-temporal stochastic processes, constructs lagged and graph-based predictors, evaluates classical and ensemble learners under strict temporal validation, and organizes results into performance, spatial-temporal, and governance-oriented outputs. Experiments on a synthetic but realistic urban panel show that transparent models can achieve strong discrimination, competitive calibration, and auditable explanations when they are embedded in a carefully governed analytical pipeline.

6 September 2026 in International Journal of Combinatorial Optimization Problems and Informatics
Verified
Journal Article
Open access
PDF file
JAJaime Aguilar-Ortiz
Jaime Aguilar-Ortiz
VZVíctor M. Zamudio-García
Víctor M. Zamudio-García
MGMarcos Yamir Gómez-Ramos
Marcos Yamir Gómez-Ramos
CDCarlos R. Domínguez-Mayorga
Carlos R. Domínguez-Mayorga
This study develops a comparative benchmark for software effort estimation using the benchmark suite implemented in Python and the result package generated by that suite. Eleven regressors were compared under a leakage-safe protocol on a COCOMO-like dataset of 62 projects and 20 numeric predictors, with 49 projects reserved for model development and 13 for final hold-out testing. The evaluated methods were a three-hidden-layer deep neural network, CatBoost, XGBoost, stacked ensemble regression, random forest, support vector regression with radial basis kernel, Gaussian process regression, LightGBM, an optimized M5P model tree, gradient boosting, and AdaBoost. Model quality was judged through repeated 5×2 cross-validation on the training partition and through an independent hold-out test set, using MAE, RMSE, R², MMRE, MdMRE, and PRED(25). The repeated-CV ranking identified Gaussian process regression as the most accurate and stable model, with mean rank = 1.0000, RMSE = 0.2152, R² = 0.8998, and PRED(25) = 0.9289. The same model also dominated the hold-out evaluation, achieving MAE = 0.1444, RMSE = 0.1835, R² = 0.9084, MMRE = 0.0850, MdMRE = 0.0634, and PRED(25) = 0.9231. The overall order of precision from repeated cross-validation was: Gaussian process regression, optimized model tree (M5P), stacked ensemble regressor, gradient boosting regressor, XGBoost regressor, random forest regressor, CatBoost regressor, AdaBoost regressor, support vector regression, deep neural network, and LightGBM regressor. Permutation importance of the best model showed KDSI, ACAP, PCAP, RELY, and AAF as the most influential predictors. The evidence indicates that, for the present small-sample COCOMO-like setting, kernel-based and piecewise linear/tree-based methods outperform the deeper neural alternative. Spanish-language metadata / Metadatos en españolTítulo en español:Benchmark comparativo de once modelos de regresión para la estimación del esfuerzo de software en un conjunto de datos similar a COCOMO Resumen:Este estudio desarrolla un benchmark comparativo para la estimación del esfuerzo de software utilizando la batería de evaluación implementada en Python y el paquete de resultados generado por dicha batería. Se compararon once regresores mediante un protocolo diseñado para evitar fugas de información (data leakage) sobre un conjunto de datos similar a COCOMO compuesto por 62 proyectos y 20 predictores numéricos, de los cuales 49 proyectos se reservaron para el desarrollo de los modelos y 13 para la prueba final con un conjunto hold-out. Los métodos evaluados fueron una red neuronal profunda con tres capas ocultas, CatBoost, XGBoost, regresión mediante un ensamble apilado (stacked ensemble), bosque aleatorio, regresión de vectores de soporte con kernel de base radial, regresión mediante procesos gaussianos, LightGBM, un árbol de modelos M5P optimizado, gradient boosting y AdaBoost. La calidad de los modelos se evaluó mediante validación cruzada repetida 5×2 sobre la partición de entrenamiento y mediante un conjunto independiente de prueba hold-out, utilizando MAE, RMSE, R², MMRE, MdMRE y PRED(25). La clasificación obtenida mediante validación cruzada repetida identificó la regresión mediante procesos gaussianos como el modelo más preciso y estable, con un rango medio = 1,0000, RMSE = 0,2152, R² = 0,8998 y PRED(25) = 0,9289. El mismo modelo también dominó la evaluación hold-out, alcanzando MAE = 0,1444, RMSE = 0,1835, R² = 0,9084, MMRE = 0,0850, MdMRE = 0,0634 y PRED(25) = 0,9231. El orden global de precisión obtenido mediante validación cruzada repetida fue el siguiente: regresión mediante procesos gaussianos, árbol de modelos optimizado (M5P), regresor de ensamble apilado, regresor de gradient boosting, regresor XGBoost, regresor de bosque aleatorio, regresor CatBoost, regresor AdaBoost, regresión de vectores de soporte, red neuronal profunda y regresor LightGBM. El análisis de importancia por permutación del mejor modelo mostró que KDSI, ACAP, PCAP, RELY y AAF fueron los predictores más influyentes. La evidencia indica que, para el presente escenario de tamaño muestral reducido y similar a COCOMO, los métodos basados en kernels y los enfoques lineales por tramos o basados en árboles superan a la alternativa neuronal más profunda. Palabras Claves:estimación del esfuerzo de software, estimación del coste de software, regresión mediante procesos gaussianos, árbol de modelos, stacking, benchmark, MMRE, PRED(25), conjunto de datos similar a COCOMO, clasificación de regresores Smart citations: SciteAI. Dimensions.Open Alex.

13 August 2026
Verified
Book Chapter
Closed access
MRMarcos Yamir Gomez Ramos
Marcos Yamir Gomez Ramos
LHLaura Araceli Guerrero Herrera
Laura Araceli Guerrero Herrera
JAJaime Aguilar-Ortiz
Jaime Aguilar-Ortiz
While Artificial Intelligence enhances Science, Technology, Engineering, Arts and Mathematics education, reliance on complex “black-box” models undermines transparency, teacher agency, and student trust. This chapter presents a practical, accessible framework for implementing Explainable Artificial Intelligence in STEAM educational tools. Moving beyond theoretical algorithmic advancements, the approach leverages open-source platforms and low-code environments to democratize AI. The text examines how embedding explainability mechanisms into learning analytics and intelligent tutors enhances pedagogical decision-making and fosters student metacognition. Additionally, the framework aligns XAI implementation with global ethical standards, including the EU AI Act and UNESCO recommendations, addressing fairness, accountability, and responsible data use. Through illustrative real-world use cases, this work bridges the gap between machine learning research and educational practice, positioning XAI as a foundational enabler of trustworthy, transparent, and human-centered learning ecosystems.

3 November 2026
Verified
Book Chapter
Closed access
JAJaime Aguilar-Ortiz
Jaime Aguilar-Ortiz
ODOcotlán Diáz-Parra
Ocotlán Diáz-Parra
Francisco Rafael Trejo-MacotelaFrancisco Rafael Trejo-Macotela
Francisco Rafael Trejo-Macotela
Jorge A. Ruiz-VanoyeJorge A. Ruiz-Vanoye
Jorge A. Ruiz-Vanoye
MJMARCO ANTONIO VERA JIMENEZ
MARCO ANTONIO VERA JIMENEZ
MGMarcos Yamir Gómez-Ramos
Marcos Yamir Gómez-Ramos
This chapter presents the development of an advanced inventory management model for virtual warehouses. By combining process digital twins with Topological Data Analysis, this model strives to support supervisors in pinpointing bottleneck formations that standard performance indicators are unable to reveal. The methodology describes how IoT-like intralogistics events are interpreted as augmented point clouds. The methodology also describes how persistent homology is computed through Vietoris-Rips and Alpha-complex filtrations, and how topological indicators are transformed into an immersive decision layer through the framework's comprehensive approach to bottleneck and Wasserstein distances. The computational case interprets fragmentation, routing loops, and volumetric cavities as congestion, vulnerability, and latent capacity indicators. The results show how the persistent topology of the model offers a candidate articulate layer for the process digital twins. The model still needs additional empirical calibration, for operational interventions in a physical warehouse.