Carlos Sotelo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Carlos Sotelo has a total of 76 co-authors. Here are the top co-authors by number of shared publications:
- David Sotelo
Tecnologico de Monterrey, School of Engineering and Sciences
34 shared publications - Francisco Beltran-Carbajal
Departamento de Energía, Unidad Azcapotzalco, Universidad Autónoma Metropolitana, Azcapotzalco, Ciudad de Mexico 02200, Mexico
17 shared publications - Antonio Favela-Contreras
School of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, Mexico
11 shared publications - Hugo Yañez-Badillo
Departamento de Investigación, Tecnológico de Estudios Superiores de Tianguistenco (TecNM), Santiago Tianguistenco 52650, Estado de México, Mexico
8 shared publications - Daniel Rodriguez-Guevara
Tecnologico de Monterrey, School of Engineering and Sciences, Ave. Eugenio Garza Sada 2501, Monterrey 64849, Mexico
4 shared publications - Jesús C. Hernández
Programa de Doctorado en Computación Avanzada, Energía y Plasmas, Universidad de Córdoba, Avd. Medina Azahara, 5, Poniente Sur, 14071 Córdoba, Spain
3 shared publications
Latest Publications
- Open Access
- 26 August 2026
- Published by Frontiers Media SA in Frontiers in Education
- Vol. 11, 1892138
Assessment of anxiety detection in students using machine learning and wearable sensors during virtual and in-person laboratory sessions
Introduction: Anxiety is an increasingly prevalent concern among graduate students, highlighting the need for objective approaches that complement conventional self-report assessments. Wearable sensing technologies combined with machine learning offer opportunities to characterize anxiety-related physiological patterns during authentic educational activities. This pilot study investigated the feasibility of multimodal physiological monitoring for participant-level anxiety screening in graduate engineering education. Methods: Eleven graduate students completed virtual and in-person Control Engineering laboratory activities while electroencephalographic (EEG) and peripheral physiological signals, including electrodermal activity (EDA), skin temperature (TEMP), heart rate (HR), inter-beat interval (IBI), and heart rate variability (HRV), were recorded using wearable devices. Participant-level anxiety reference labels were derived from a context-adapted administration of the Generalized Anxiety Disorder 7-item questionnaire (GAD-7). Six supervised machine learning classifiers were evaluated using subject-independent Leave-One-Subject-Out (LOSO) cross-validation. Model performance was assessed using accuracy, F1-score, ROC-AUC, and confusion matrices, complemented by feature importance analyses. Results: Physiological differences were observed between participant anxiety groups and across virtual and in-person laboratory conditions, with EDA and temperature showing comparatively larger effect sizes than cardiovascular measures. Logistic Regression achieved the highest classification performance, although this result requires cautious interpretation given the limited sample size. All evaluated models identified anxiety-labeled participants without false negatives. Feature importance analyses further indicated that EEG-derived variables, particularly frontal and temporal Gamma and Beta activity, contributed substantially to discrimination. Discussion: The findings provide preliminary evidence that integrating central and peripheral physiological signals with subject-independent machine learning evaluation may support anxiety screening during authentic educational activities. Rather than replacing established psychological assessment methods, wearable sensing may provide complementary objective evidence for wearable learning analytics and student well-being research. Given the small sample, single institutional context, and context-adapted GAD-7 reference labels, the results should be interpreted as evidence of feasibility rather than clinical validation.
- 26 August 2026
- Published by Frontiers Media SA in Frontiers in Education
- Vol. 11, 1892138
Open AccessAssessment of anxiety detection in students using machine learning and wearable sensors during virtual and in-person laboratory sessions
Introduction: Anxiety is an increasingly prevalent concern among graduate students, highlighting the need for objective approaches that complement conventional self-report assessments. Wearable sensing technologies combined with machine learning offer opportunities to characterize anxiety-related physiological patterns during authentic educational activities. This pilot study investigated the feasibility of multimodal physiological monitoring for participant-level anxiety screening in graduate engineering education. Methods: Eleven graduate students completed virtual and in-person Control Engineering laboratory activities while electroencephalographic (EEG) and peripheral physiological signals, including electrodermal activity (EDA), skin temperature (TEMP), heart rate (HR), inter-beat interval (IBI), and heart rate variability (HRV), were recorded using wearable devices. Participant-level anxiety reference labels were derived from a context-adapted administration of the Generalized Anxiety Disorder 7-item questionnaire (GAD-7). Six supervised machine learning classifiers were evaluated using subject-independent Leave-One-Subject-Out (LOSO) cross-validation. Model performance was assessed using accuracy, F1-score, ROC-AUC, and confusion matrices, complemented by feature importance analyses. Results: Physiological differences were observed between participant anxiety groups and across virtual and in-person laboratory conditions, with EDA and temperature showing comparatively larger effect sizes than cardiovascular measures. Logistic Regression achieved the highest classification performance, although this result requires cautious interpretation given the limited sample size. All evaluated models identified anxiety-labeled participants without false negatives. Feature importance analyses further indicated that EEG-derived variables, particularly frontal and temporal Gamma and Beta activity, contributed substantially to discrimination. Discussion: The findings provide preliminary evidence that integrating central and peripheral physiological signals with subject-independent machine learning evaluation may support anxiety screening during authentic educational activities. Rather than replacing established psychological assessment methods, wearable sensing may provide complementary objective evidence for wearable learning analytics and student well-being research. Given the small sample, single institutional context, and context-adapted GAD-7 reference labels, the results should be interpreted as evidence of feasibility rather than clinical validation.
- Open Access
- 13 May 2026
- Published by Taylor & Francis in Systems Science & Control Engineering
- Vol. 14 (1)
Dynamic battery-aware auxiliary reference system for improving real-time model predictive control implementation in quadrotors
- 13 May 2026
- Published by Taylor & Francis in Systems Science & Control Engineering
- Vol. 14 (1)
Open AccessDynamic battery-aware auxiliary reference system for improving real-time model predictive control implementation in quadrotors
- Open Access
Differential Flatness-Based Model Predictive Speed Control for Direct Current Motor–Gearhead Drive Systems
This paper introduces a new speed control framework design for direct current electric motors coupled with a gearhead. The proposed framework suitably integrates differential flatness, model predictive control, and Kalman filter theory for efficient speed tracking in disturbed scenarios. The performance of the proposed control framework is compared against a flat feed-forward proportional–integral–derivative controller, an extended state offset-free model predictive control, and a linear quadratic integral controller. The results show improved tracking performance with reductions of up to 60% in NRMSE and 50% in ITAE compared to the baseline controllers while maintaining a comparable and bounded control effort due to the constraints enforced in the framework formulation. These results show that the proposed approach effectively captures the dominant disturbance behaviour under varying operating conditions. Thus, it is demonstrated that the flat system formulation allows for proper speed control, providing practical insights for advanced motor control in industrial automation, robotics, and electric mobility applications.
Open AccessDifferential Flatness-Based Model Predictive Speed Control for Direct Current Motor–Gearhead Drive Systems
This paper introduces a new speed control framework design for direct current electric motors coupled with a gearhead. The proposed framework suitably integrates differential flatness, model predictive control, and Kalman filter theory for efficient speed tracking in disturbed scenarios. The performance of the proposed control framework is compared against a flat feed-forward proportional–integral–derivative controller, an extended state offset-free model predictive control, and a linear quadratic integral controller. The results show improved tracking performance with reductions of up to 60% in NRMSE and 50% in ITAE compared to the baseline controllers while maintaining a comparable and bounded control effort due to the constraints enforced in the framework formulation. These results show that the proposed approach effectively captures the dominant disturbance behaviour under varying operating conditions. Thus, it is demonstrated that the flat system formulation allows for proper speed control, providing practical insights for advanced motor control in industrial automation, robotics, and electric mobility applications.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
An Adaptive Control Framework for the UAS-S45 Using Differential Flatness and Input–Output Formulations
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Open AccessAn Adaptive Control Framework for the UAS-S45 Using Differential Flatness and Input–Output Formulations
- Open Access
- 28 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 205612-205630
Neural Networks and Sliding Modes in Controlled Uncertain Synchronous Motor Systems
A new robust motion tracking control design framework for uncertain synchronous motors based on differential flatness, artificial neural networks, sliding modes and swarm intelligence, is proposed. Robustness with respect to significant dynamic generalized uncertainty is proved. Knowledge of system parameters and variable load torque are unnecessary. Dependence on mathematical modeling based on physics is reduced. The presented control design approach is extended for a wide class of highly uncertain and multi-input multi-output, nonlinear flat dynamic systems. Incorporation of observer algorithms for accurate real-time disturbance estimation is not required. The introduced robust flat output-feedback control design framework considers radial basis function and B-spline artificial neural networks to dynamically tune in real-time sliding mode parameters. In this fashion, active attenuation of chattering is achieved from a dynamic artificial intelligence control design perspective. Reliable control performance under exogenous disturbances and endogenous uncertainty is demonstrated. A key insight is that B-splines networks offer fast and localized adaptation with lower computational cost compared to traditional radial basis function networks, making them more suitable for embedded real-time applications. Particle swarm optimization is employed to optimize initial neural weights. The control scheme offers a scalable and efficient solution suitable for embedded real-time applications, as demonstrated through various operating scenarios involving nonlinear disturbances, load torque variations, and parametric uncertainty. The findings reveal the robust performance of the proposed synchronous motor system control strategy for the efficient tracking of smooth speed reference trajectories in presence of a wide spectrum of dynamic uncertainties. Moreover, numerical results confirm the superiority of the proposed robust adaptive neural-network trajectory tracking control framework for highly uncertain operating environments over previous model-based design studies. Efficiency, robustness and uncertain system stability are guaranteed from the introduced dynamic artificial intelligence control design perspective.
- 28 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 205612-205630
Open AccessNeural Networks and Sliding Modes in Controlled Uncertain Synchronous Motor Systems
A new robust motion tracking control design framework for uncertain synchronous motors based on differential flatness, artificial neural networks, sliding modes and swarm intelligence, is proposed. Robustness with respect to significant dynamic generalized uncertainty is proved. Knowledge of system parameters and variable load torque are unnecessary. Dependence on mathematical modeling based on physics is reduced. The presented control design approach is extended for a wide class of highly uncertain and multi-input multi-output, nonlinear flat dynamic systems. Incorporation of observer algorithms for accurate real-time disturbance estimation is not required. The introduced robust flat output-feedback control design framework considers radial basis function and B-spline artificial neural networks to dynamically tune in real-time sliding mode parameters. In this fashion, active attenuation of chattering is achieved from a dynamic artificial intelligence control design perspective. Reliable control performance under exogenous disturbances and endogenous uncertainty is demonstrated. A key insight is that B-splines networks offer fast and localized adaptation with lower computational cost compared to traditional radial basis function networks, making them more suitable for embedded real-time applications. Particle swarm optimization is employed to optimize initial neural weights. The control scheme offers a scalable and efficient solution suitable for embedded real-time applications, as demonstrated through various operating scenarios involving nonlinear disturbances, load torque variations, and parametric uncertainty. The findings reveal the robust performance of the proposed synchronous motor system control strategy for the efficient tracking of smooth speed reference trajectories in presence of a wide spectrum of dynamic uncertainties. Moreover, numerical results confirm the superiority of the proposed robust adaptive neural-network trajectory tracking control framework for highly uncertain operating environments over previous model-based design studies. Efficiency, robustness and uncertain system stability are guaranteed from the introduced dynamic artificial intelligence control design perspective.
- 15 January 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (14) , 11395-11407
A qLPV-MPC Control Strategy for Fast Nonlinear Systems with Stability and Feasibility Conditions
- 15 January 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (14) , 11395-11407
A qLPV-MPC Control Strategy for Fast Nonlinear Systems with Stability and Feasibility Conditions