Martha Lucía Rodríguez-López
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Martha Lucía Rodríguez-López has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Danny Múnera
Applied Telecommunications Research Group (GITA), Faculty of Engineering, University of Antioquia, Medellín 050010, Colombia
2 shared publications Diana P. Tobón
1 shared publication- Diana Patricia Tobón
Universidad de Antioquía
1 shared publication - Douglas Wildgrube Bertol
Universidade do Estado de Santa Catarina
1 shared publication Universidad de Antioquia
1 shared publication- Willy John Nakamura Goto
Universidade Estadual de Maringá
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Universidad de Antioquia in Revista Facultad de Ingeniería Universidad de Antioquia
Immune sliding mode control for formation tracking and obstacle avoidance of uncertain wheeled mobile robots
This paper proposes an immune fuzzy sliding mode kinematic controller integrated with a proportional derivative dynamic controller for trajectory tracking by a nonholonomic differential-drive wheeled mobile robot subject to uncertainties and disturbances as well as its extension to the leader-follower formation control by multiple robots using the separation-bearing strategy. To deal with the drawbacks of a traditional first-order sliding mode control, such as the chattering phenomenon and the requirement of a priori knowledge of the bounds of uncertainties and disturbances, inspired by a regulation mechanism of the humoral immune response, it is derived a fuzzy system to establish the control reaction effect for an artificial immune system design to adjust online the gains of the control robustness portion adaptively. Furthermore, this paper proposes an obstacle avoidance strategy based on a reactive approach, being a variable avoidance radius also considered, to navigate in execution time the leader robot around static obstacles during the trajectory tracking. Simulation and experimental results demonstrate the effectiveness of the proposed controller with obstacle avoidance, and the Lyapunov theory proves the stability of the closed-loop control system.
- 1 January 2025
- Published by Universidad de Antioquia in Revista Facultad de Ingeniería Universidad de Antioquia
Open AccessImmune sliding mode control for formation tracking and obstacle avoidance of uncertain wheeled mobile robots
This paper proposes an immune fuzzy sliding mode kinematic controller integrated with a proportional derivative dynamic controller for trajectory tracking by a nonholonomic differential-drive wheeled mobile robot subject to uncertainties and disturbances as well as its extension to the leader-follower formation control by multiple robots using the separation-bearing strategy. To deal with the drawbacks of a traditional first-order sliding mode control, such as the chattering phenomenon and the requirement of a priori knowledge of the bounds of uncertainties and disturbances, inspired by a regulation mechanism of the humoral immune response, it is derived a fuzzy system to establish the control reaction effect for an artificial immune system design to adjust online the gains of the control robustness portion adaptively. Furthermore, this paper proposes an obstacle avoidance strategy based on a reactive approach, being a variable avoidance radius also considered, to navigate in execution time the leader robot around static obstacles during the trajectory tracking. Simulation and experimental results demonstrate the effectiveness of the proposed controller with obstacle avoidance, and the Lyapunov theory proves the stability of the closed-loop control system.
- 1 January 2025
- Published by Universidad de Antioquia in Revista Facultad de Ingeniería Universidad de Antioquia
Anomaly classification in IIoT edge devices
An early Industrial Internet of Things (IIoT) Anomaly Detection reduces maintenance costs, minimizes machine downtime, increases safety, and improves product quality. A multi-class classifier that detects events, failures, or attacks is much more efficient than a simple binary classifier, as it relieves a human operator of the task of identifying anomaly causes, thereby avoiding wasted time that could compromise process performance and security. With these issues in mind, this paper aims to determine whether it can differentiate between a failure that generates a temperature increase in an IIoT device processor, a denial-of-service attack on an MQTT broker, and an event caused by an application executing on the IIoT edge device. Data used to perform the classification comes from a Raspberry Pi 3, specifically from its CPU (e.g., temperature, load, free memory, Wi-Fi sent and received packets). A k-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), and Multilayer Perceptron (MLP) algorithms were trained. Considering metrics such as false positive rate, false negative rate, accuracy, F1-score, and execution time, we concluded that SVM and MLP were the best methods for the case study because of their accuracy (78.6 and 76.1, respectively) and low execution time (17.3ms and 0.35ms).
- 1 January 2025
- Published by Universidad de Antioquia in Revista Facultad de Ingeniería Universidad de Antioquia
Anomaly classification in IIoT edge devices
An early Industrial Internet of Things (IIoT) Anomaly Detection reduces maintenance costs, minimizes machine downtime, increases safety, and improves product quality. A multi-class classifier that detects events, failures, or attacks is much more efficient than a simple binary classifier, as it relieves a human operator of the task of identifying anomaly causes, thereby avoiding wasted time that could compromise process performance and security. With these issues in mind, this paper aims to determine whether it can differentiate between a failure that generates a temperature increase in an IIoT device processor, a denial-of-service attack on an MQTT broker, and an event caused by an application executing on the IIoT edge device. Data used to perform the classification comes from a Raspberry Pi 3, specifically from its CPU (e.g., temperature, load, free memory, Wi-Fi sent and received packets). A k-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), and Multilayer Perceptron (MLP) algorithms were trained. Considering metrics such as false positive rate, false negative rate, accuracy, F1-score, and execution time, we concluded that SVM and MLP were the best methods for the case study because of their accuracy (78.6 and 76.1, respectively) and low execution time (17.3ms and 0.35ms).
- Open Access
- 12 May 2023
- Published by Elsevier in Intelligent Systems with Applications
- Vol. 18
Anomaly classification in industrial Internet of things: A review
- 12 May 2023
- Published by Elsevier in Intelligent Systems with Applications
- Vol. 18
Open AccessAnomaly classification in industrial Internet of things: A review