Víctor Manuel Zamudio Garcia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Víctor Manuel Zamudio Garcia has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Jaime Aguilar-Ortiz
Universidad Politécnica de Pachuca, México
31 shared publications - Carlos Roberto Dominguez Mayorga
Universidad Politécnica de Pachuca, México
25 shared publications - Marco Antonio Vera Jimenez
Universidad Politécnica de Pachuca, México
24 shared publications - Francisco Rafael Trejo-Macotela
Universidad Politécnica de Pachuca, México
19 shared publications Ocotlán Diáz-Parra
Universidad Politécnica de Pachuca, México
19 shared publications- Jorge Alberto Ruiz Vanoye
Universidad Politécnica de Pachuca, México
18 shared publications
Latest Publications
- 5 January 2027
- Published by IGI Global Scientific Publishing
- p. 375-402
Toward Topological Digital Twins for Virtual Warehousing and Intelligent Inventory Management
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.
- 5 January 2027
- Published by IGI Global Scientific Publishing
- p. 375-402
Toward Topological Digital Twins for Virtual Warehousing and Intelligent Inventory Management
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.
- 3 November 2026
- Published by IGI Global Scientific Publishing
- p. 183-216
Immersive Stock Control for Virtual Depots via Process Digital Twins and Topological Data Analysis
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.
- 3 November 2026
- Published by IGI Global Scientific Publishing
- p. 183-216
Immersive Stock Control for Virtual Depots via Process Digital Twins and Topological Data Analysis
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.
- 20 October 2026
- Published by IGI Global Scientific Publishing
- p. 259-296
Topology-Driven Intelligence for Circular Technologies
This chapter presents a geometry-regularized deep-learning framework for the structural sustainability assessment of a synthetic network of e-waste circularity. We performed the training of AE and VAE models with various regularizations like reconstruction, probabilistic, isometric, k-nn and graph-Laplacian as well as the application of persistent homology to act as a diagnostic synchronization-independent processing layer, instead of claiming a new topological neural architecture. The contributions consist of a workflow for localization of structural distortion through application, candidate interpretation circularity pattern types and topological indicators into operational decision-support tools and identifying.
- 20 October 2026
- Published by IGI Global Scientific Publishing
- p. 259-296
Topology-Driven Intelligence for Circular Technologies
This chapter presents a geometry-regularized deep-learning framework for the structural sustainability assessment of a synthetic network of e-waste circularity. We performed the training of AE and VAE models with various regularizations like reconstruction, probabilistic, isometric, k-nn and graph-Laplacian as well as the application of persistent homology to act as a diagnostic synchronization-independent processing layer, instead of claiming a new topological neural architecture. The contributions consist of a workflow for localization of structural distortion through application, candidate interpretation circularity pattern types and topological indicators into operational decision-support tools and identifying.
- 15 October 2026
- Published by IGI Global Scientific Publishing
- p. 283-312
Responsible AI for Crime-Risk Prediction in Digital Marketing
Digital marketing can support customer protection, yet crime-risk analytics may reproduce surveillance and exclusion. This chapter develops a Responsible AI Marketing Risk Observatory for aggregate zone-week decisions without individual profiling. A panel of 5,616 synthetic observations supports temporal model comparison, isotonic calibration, companion-model SHAP diagnostics, fairness auditing, and conformal prediction sets. Calibrated logistic regression achieved ROC AUC 0.912, Brier score 0.094, and ECE 0.028. The TPR disparity was 0.110; empirical coverage was 0.940, with 16.6% ambiguous sets requiring review. These results support methodological feasibility within the simulation, not field effectiveness or an unconditional coverage guarantee. The observatory links estimates to reversible safeguards and accountable human decisions. Customer trust and actual harm reduction remain unmeasured and require external validation.
- 15 October 2026
- Published by IGI Global Scientific Publishing
- p. 283-312
Responsible AI for Crime-Risk Prediction in Digital Marketing
Digital marketing can support customer protection, yet crime-risk analytics may reproduce surveillance and exclusion. This chapter develops a Responsible AI Marketing Risk Observatory for aggregate zone-week decisions without individual profiling. A panel of 5,616 synthetic observations supports temporal model comparison, isotonic calibration, companion-model SHAP diagnostics, fairness auditing, and conformal prediction sets. Calibrated logistic regression achieved ROC AUC 0.912, Brier score 0.094, and ECE 0.028. The TPR disparity was 0.110; empirical coverage was 0.940, with 16.6% ambiguous sets requiring review. These results support methodological feasibility within the simulation, not field effectiveness or an unconditional coverage guarantee. The observatory links estimates to reversible safeguards and accountable human decisions. Customer trust and actual harm reduction remain unmeasured and require external validation.
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 359-388
Machine Learning-Based Crime Prediction for Smart Policing
This chapter builds and validates a replicable machine-learning framework for estimating crime risk in smart heterogeneous policing environments. A reproducible Python application combines networked data collection, edge analytics, interpretable models, and responsible decision support. Privacy is preserved with a synthetic zone-day panel covering incident counts, IoT variables, emergency-call intensity, mobility indicators, network reliability, and spatial spillovers. Prediction is framed as probabilistic risk estimation, not a deterministic judgment about places or people. Four classifiers are evaluated on a temporal holdout using ROC-AUC, PR-AUC, Brier score, precision, recall, F1, threshold burden, spatial error, and SHAP explanations. In this synthetic proof of concept, boosted models show the strongest discrimination and F1 scores, while calibration, threshold selection, provenance, and model behavior remain reviewable. The results support computational feasibility and auditability, but not operational validity, causal effectiveness, or municipal deployment readiness.
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 359-388
Machine Learning-Based Crime Prediction for Smart Policing
This chapter builds and validates a replicable machine-learning framework for estimating crime risk in smart heterogeneous policing environments. A reproducible Python application combines networked data collection, edge analytics, interpretable models, and responsible decision support. Privacy is preserved with a synthetic zone-day panel covering incident counts, IoT variables, emergency-call intensity, mobility indicators, network reliability, and spatial spillovers. Prediction is framed as probabilistic risk estimation, not a deterministic judgment about places or people. Four classifiers are evaluated on a temporal holdout using ROC-AUC, PR-AUC, Brier score, precision, recall, F1, threshold burden, spatial error, and SHAP explanations. In this synthetic proof of concept, boosted models show the strongest discrimination and F1 scores, while calibration, threshold selection, provenance, and model behavior remain reviewable. The results support computational feasibility and auditability, but not operational validity, causal effectiveness, or municipal deployment readiness.
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 1-28
A Reproducible Framework for Crime Forecasting in Smart Heterogeneous Networks
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.
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 1-28
A Reproducible Framework for Crime Forecasting in Smart Heterogeneous Networks
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.
- Open Access
- 6 September 2026
- Published by Editorial Académica Dragón Azteca in International Journal of Combinatorial Optimization Problems and Informatics
- Vol. 17 (5) , 80-105
Comparative Benchmark of Eleven Regression Models for Software Effort Estimation on a COCOMO-Like Dataset
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.
- 6 September 2026
- Published by Editorial Académica Dragón Azteca in International Journal of Combinatorial Optimization Problems and Informatics
- Vol. 17 (5) , 80-105
Open AccessComparative Benchmark of Eleven Regression Models for Software Effort Estimation on a COCOMO-Like Dataset
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.
- 20 August 2026
- Published by IGI Global Scientific Publishing
- p. 285-318
Topological Data Analysis for Anomaly Detection in Video Surveillance
Video anomaly detection remains challenging because abnormal events are scarce, context-dependent, and operationally sensitive. The objective of this chapter is to develop and evaluate an unsupervised TDA-based framework for modeling surveillance windows without relying on reconstruction error. Trajectories are encoded as weighted spatio-temporal point clouds. Vietoris–Rips persistent homology yields H0 and H1 signatures, persistence images, Betti curves, and interpretable scalar descriptors. Models trained solely on normal data are evaluated across six controlled event classes. Isolation Forest achieved a ROC-AUC of 0.967 and average precision of 0.959, while the Mapper graph separated normal regions from anomaly-dense nodes. Results show that global connectivity and loop structure provide stable, privacy-aware support for explainable surveillance analytics and establish a reproducible bridge between mathematical topology and deployable computer vision.
- 20 August 2026
- Published by IGI Global Scientific Publishing
- p. 285-318
Topological Data Analysis for Anomaly Detection in Video Surveillance
Video anomaly detection remains challenging because abnormal events are scarce, context-dependent, and operationally sensitive. The objective of this chapter is to develop and evaluate an unsupervised TDA-based framework for modeling surveillance windows without relying on reconstruction error. Trajectories are encoded as weighted spatio-temporal point clouds. Vietoris–Rips persistent homology yields H0 and H1 signatures, persistence images, Betti curves, and interpretable scalar descriptors. Models trained solely on normal data are evaluated across six controlled event classes. Isolation Forest achieved a ROC-AUC of 0.967 and average precision of 0.959, while the Mapper graph separated normal regions from anomaly-dense nodes. Results show that global connectivity and loop structure provide stable, privacy-aware support for explainable surveillance analytics and establish a reproducible bridge between mathematical topology and deployable computer vision.
- 14 August 2026
- Published by IGI Global Scientific Publishing
- p. 389-418
Educational Transformation With AI and Development of a Web-Based Adaptive Learning System
This article presents the development of an AI-based adaptive learning prototype enhanced with a ChatGPT-powered generative agent, implemented as a functional web application that personalizes education according to each learner's abilities, pace, and recent performance. Through machine learning, data analytics, and real-time natural language interaction, the system dynamically adapts instructional materials, explains personalized recommendations, and offers formative feedback in human-like language. Built with Python for the backend and Plotly and Dash for the interactive frontend, the prototype embodies the vision of AI-driven independent learning combining data-driven personalization with conversational guidance to foster inclusivity, autonomy, and engagement while redefining the collaboration between educators, learners, and intelligent systems. The article code can be found at: https://github.com/JAIME6609/EDUCATION/blob/main/CODE-EDUCATIONAL-TRANSFORMATION-06.py
- 14 August 2026
- Published by IGI Global Scientific Publishing
- p. 389-418
Educational Transformation With AI and Development of a Web-Based Adaptive Learning System
This article presents the development of an AI-based adaptive learning prototype enhanced with a ChatGPT-powered generative agent, implemented as a functional web application that personalizes education according to each learner's abilities, pace, and recent performance. Through machine learning, data analytics, and real-time natural language interaction, the system dynamically adapts instructional materials, explains personalized recommendations, and offers formative feedback in human-like language. Built with Python for the backend and Plotly and Dash for the interactive frontend, the prototype embodies the vision of AI-driven independent learning combining data-driven personalization with conversational guidance to foster inclusivity, autonomy, and engagement while redefining the collaboration between educators, learners, and intelligent systems. The article code can be found at: https://github.com/JAIME6609/EDUCATION/blob/main/CODE-EDUCATIONAL-TRANSFORMATION-06.py
- 14 August 2026
- Published by IGI Global Scientific Publishing
- p. 175-200
Intelligent Digital Mentors for Student Autonomy Through Adaptive Learning Systems
This chapter aims to explain how artificial intelligence (AI) agents can function as intelligent digital mentors that strengthen student autonomy through adaptive learning systems. It proposes an integrative model in which the ChatGPT application programming interface (API), learning analytics, and adaptive dashboards work together in a Python–Dash–Plotly environment to personalize guidance, interpret performance, and support self-regulation. Grounded in Piaget, Vygotsky, and Ausubel, the chapter presents a functional web-based prototype and discusses its pedagogical, ethical, and organizational implications. Rather than replacing educators, the proposed mentor architecture is designed to complement teaching, enhance contextual feedback, and promote equitable, meaningful, and continuously monitored independent learning. The code can be accessed at the following link: https://github.com/JAIME6609/EDUCATION/blob/main/CODE-IDM-04-E.py
- 14 August 2026
- Published by IGI Global Scientific Publishing
- p. 175-200
Intelligent Digital Mentors for Student Autonomy Through Adaptive Learning Systems
This chapter aims to explain how artificial intelligence (AI) agents can function as intelligent digital mentors that strengthen student autonomy through adaptive learning systems. It proposes an integrative model in which the ChatGPT application programming interface (API), learning analytics, and adaptive dashboards work together in a Python–Dash–Plotly environment to personalize guidance, interpret performance, and support self-regulation. Grounded in Piaget, Vygotsky, and Ausubel, the chapter presents a functional web-based prototype and discusses its pedagogical, ethical, and organizational implications. Rather than replacing educators, the proposed mentor architecture is designed to complement teaching, enhance contextual feedback, and promote equitable, meaningful, and continuously monitored independent learning. The code can be accessed at the following link: https://github.com/JAIME6609/EDUCATION/blob/main/CODE-IDM-04-E.py