Victor Baptista Frencl
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Victor Baptista Frencl has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Joao B. R. Do Val
School of Electrical and Computer Engineering, University of Campinas, Campinas, Sao Paulo, Brazil, 13083-852
3 shared publications- Aline E. Treml
Centre of Engineering and Exact Sciences – CECE, Universidade Estadual do Oeste do Paraná (UNIOESTE), Foz do Iguaçu, Brazil
1 shared publication - Anderson Luis Szejka
Pontificia Universidade Católica do Parana
1 shared publication João B.R. Do Val
School of Electrical and Computer Engineering University of Campinas Campinas SP Brazil
1 shared publication- João Bosco Ribeiro Do Val
Universidade Estadual de Campinas
1 shared publication - Leonardo Abdala Elias
Universidade Estadual de Campinas (UNICAMP)
1 shared publication
Latest Publications
- Open Access
- 31 October 2025
- Published by Springer Nature in Autonomous Intelligent Systems
- Vol. 5 (1) , 1-22
Comparative analysis of feature selection and classification techniques for robust broken rotor bar diagnosis in induction motors using current and vibration signals
This research addresses the diagnosis of broken rotor bar faults in three-phase induction motors, focusing on steady-state conditions under different load levels and fault severity. Although numerous techniques exist, there is still a significant gap in comprehensive comparative evaluations that rigorously assess the interaction between signal processing, feature selection, and pattern classifiers, particularly concerning their robustness to noise and multiple performance criteria. An experimental investigation was carried out with electrical current and mechanical vibration signals, several signal preprocessing techniques, two feature selection strategies, Correlation-Based Feature Selection (CFS) and Wrapper, and a wide range of pattern classifiers, Decision Tree (DT), Naive Bayes (NB), Artificial Neural Network (ANN), and Support Vector Machine (SVM). The performance of the configurations was quantified by a multicriteria indicator, complemented by a dedicated robustness assessment by introducing white noise into the input signals. The most significant results reveal that vibration signals exhibit superior diagnostic robustness compared to electrical current signals, especially under noisy conditions. Furthermore, Wrapper-based feature selection consistently outperforms CFS, and configurations combining Wrapper with DT or NB classifiers emerge as the most suitable for detecting and diagnosing broken bars. Furthermore, the Wrapper-DT configuration efficiently classified defects even with the inclusion of 40% noise. This work provides data-driven insights into robust configurations for broken bar diagnosis, guiding the development of more reliable predictive maintenance systems, emphasizing signal modality, robust feature selection, and real-time applications.
- 31 October 2025
- Published by Springer Nature in Autonomous Intelligent Systems
- Vol. 5 (1) , 1-22
Open AccessComparative analysis of feature selection and classification techniques for robust broken rotor bar diagnosis in induction motors using current and vibration signals
This research addresses the diagnosis of broken rotor bar faults in three-phase induction motors, focusing on steady-state conditions under different load levels and fault severity. Although numerous techniques exist, there is still a significant gap in comprehensive comparative evaluations that rigorously assess the interaction between signal processing, feature selection, and pattern classifiers, particularly concerning their robustness to noise and multiple performance criteria. An experimental investigation was carried out with electrical current and mechanical vibration signals, several signal preprocessing techniques, two feature selection strategies, Correlation-Based Feature Selection (CFS) and Wrapper, and a wide range of pattern classifiers, Decision Tree (DT), Naive Bayes (NB), Artificial Neural Network (ANN), and Support Vector Machine (SVM). The performance of the configurations was quantified by a multicriteria indicator, complemented by a dedicated robustness assessment by introducing white noise into the input signals. The most significant results reveal that vibration signals exhibit superior diagnostic robustness compared to electrical current signals, especially under noisy conditions. Furthermore, Wrapper-based feature selection consistently outperforms CFS, and configurations combining Wrapper with DT or NB classifiers emerge as the most suitable for detecting and diagnosing broken bars. Furthermore, the Wrapper-DT configuration efficiently classified defects even with the inclusion of 40% noise. This work provides data-driven insights into robust configurations for broken bar diagnosis, guiding the development of more reliable predictive maintenance systems, emphasizing signal modality, robust feature selection, and real-time applications.
- 12 January 2022
- Published by Springer Nature in Journal of Control, Automation and Electrical Systems
- Vol. 33 (4) , 1319-1328
A Case Study on the Removal of Blinking Artifact in Electroencephalogram Signals via Stochastic Filtering
- 12 January 2022
- Published by Springer Nature in Journal of Control, Automation and Electrical Systems
- Vol. 33 (4) , 1319-1328
A Case Study on the Removal of Blinking Artifact in Electroencephalogram Signals via Stochastic Filtering
- Open Access
- 17 May 2017
- Published by Institution of Engineering and Technology (IET) in IET Radar, Sonar & Navigation
- Vol. 11 (7) , 1099-1107
Turn rate estimation using range rate measurements for fast manoeuvring tracking
In critical tracking problems, it is important to follow fast manoeuvring targets and use each measurement at disposal to best estimate a fast curvilinear trajectory. The turn rate is important to that end, but it is not generally available for measurements in radar systems. This study develops a method that uses the information of the range rate, typically a fairly accurate measurement, together with the coordinate point measurement, in order to improve the turn rate estimation. It introduces an estimation method that applies a compatibility check between the range rate measurement and the estimated velocity projection on the range direction. Disagreement between these quantities indicates a turn rate change, leading to one step corrections. The particle filter combined with best linear unbiased estimator filters is used to improve state estimations and likelihood functions and the corrections are introduced independently to each particle. For comparisons, a method from the literature and the proposed method are implemented, tested and compared. Performance error analysis indicates the effectiveness of the present method for fast manoeuvrers.
- 17 May 2017
- Published by Institution of Engineering and Technology (IET) in IET Radar, Sonar & Navigation
- Vol. 11 (7) , 1099-1107
Open AccessTurn rate estimation using range rate measurements for fast manoeuvring tracking
In critical tracking problems, it is important to follow fast manoeuvring targets and use each measurement at disposal to best estimate a fast curvilinear trajectory. The turn rate is important to that end, but it is not generally available for measurements in radar systems. This study develops a method that uses the information of the range rate, typically a fairly accurate measurement, together with the coordinate point measurement, in order to improve the turn rate estimation. It introduces an estimation method that applies a compatibility check between the range rate measurement and the estimated velocity projection on the range direction. Disagreement between these quantities indicates a turn rate change, leading to one step corrections. The particle filter combined with best linear unbiased estimator filters is used to improve state estimations and likelihood functions and the corrections are introduced independently to each particle. For comparisons, a method from the literature and the proposed method are implemented, tested and compared. Performance error analysis indicates the effectiveness of the present method for fast manoeuvrers.
- 1 May 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A trajectory simulator for individual movements using probabilistic distribution profiles
In this paper, a trajectory simulator for individuals, walking or running, is proposed. The individuals' movements are based on position and velocity kinematics relying on the heading angle. This angle is obtained from one of the three probabilistic profiles ("drop", "leaf" or "balloon"), which defines the possible directions that the individual will take. The trajectory simulator presented here explores different types of terrain. They are classified by the difficulty in locomotion of the individuals, and this difficulty is represented by different colors. Some trajectories are generated in order to observe the behavior of the simulator and evaluate the quality of individual trajectories.
- 1 May 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A trajectory simulator for individual movements using probabilistic distribution profiles
In this paper, a trajectory simulator for individuals, walking or running, is proposed. The individuals' movements are based on position and velocity kinematics relying on the heading angle. This angle is obtained from one of the three probabilistic profiles ("drop", "leaf" or "balloon"), which defines the possible directions that the individual will take. The trajectory simulator presented here explores different types of terrain. They are classified by the difficulty in locomotion of the individuals, and this difficulty is represented by different colors. Some trajectories are generated in order to observe the behavior of the simulator and evaluate the quality of individual trajectories.
- 1 April 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10975659,p. 1-6
State estimation using GM-PHD filter applied to the tracking of individuals
The target tracking problem becomes more realistic when factors as time varying target number, measurements immersed in clutter and/or false alarms are introduced in the problem modeling. The Random Finite Sets theory provides an appropriate framework to deal with multiple targets in a dynamic scenario for the mathematical modeling and stochastic filtering. This paper analyzes the tracking problem of walking/running people in a surveillance system using the Gaussian Mixture PHD Filter. This filter is specially suited to cope with multiple targets in presence of dense cluttering. In order to observe the filter behavior in front of a large number of individuals, a random path generator based on simple dynamics is devised, comprising birth and spawned trajectories.
- 1 April 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10975659,p. 1-6
State estimation using GM-PHD filter applied to the tracking of individuals
The target tracking problem becomes more realistic when factors as time varying target number, measurements immersed in clutter and/or false alarms are introduced in the problem modeling. The Random Finite Sets theory provides an appropriate framework to deal with multiple targets in a dynamic scenario for the mathematical modeling and stochastic filtering. This paper analyzes the tracking problem of walking/running people in a surveillance system using the Gaussian Mixture PHD Filter. This filter is specially suited to cope with multiple targets in presence of dense cluttering. In order to observe the filter behavior in front of a large number of individuals, a random path generator based on simple dynamics is devised, comprising birth and spawned trajectories.
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0287-0292
Tracking with range rate measurements: Turn rate estimation and particle filtering
In target tracking problems a combination of the constant velocity (CV) and constant turn (CT) motion models are suitable to describe the target evolution and hence for state estimation purposes. For the CT motion the turn rate value is required and needs to be estimated. The method here chooses to apply the range rate measurement to this purpose, which is generally very accurate and available in surveillance and tracking radars. It introduces a verification regarding the compatibility between the estimated velocity projection on the range direction and the range rate measurement. A disagreement indicates a change in the turn rate, which is treated by appropriated draws in a particle filter (PF) combined with a BLUE filter. Simulation results, based on values of RMS position and velocity errors, show that this new method is more effective in estimating the turn rate than the results in literature.
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0287-0292
Tracking with range rate measurements: Turn rate estimation and particle filtering
In target tracking problems a combination of the constant velocity (CV) and constant turn (CT) motion models are suitable to describe the target evolution and hence for state estimation purposes. For the CT motion the turn rate value is required and needs to be estimated. The method here chooses to apply the range rate measurement to this purpose, which is generally very accurate and available in surveillance and tracking radars. It introduces a verification regarding the compatibility between the estimated velocity projection on the range direction and the range rate measurement. A disagreement indicates a change in the turn rate, which is treated by appropriated draws in a particle filter (PF) combined with a BLUE filter. Simulation results, based on values of RMS position and velocity errors, show that this new method is more effective in estimating the turn rate than the results in literature.