Josafat Leal Filho

According to our database, Josafat Leal Filho authored at least 15 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Empirical Stability Analysis of Kolmogorov-Arnold Networks in Hard-Constrained Recurrent Physics-Informed Discovery.

Enzo Nicolás Spotorno Bieger, Josafat Leal Filho, Antônio Augusto Fröhlich

CoRR, February, 2026

Supervised Metric Regularization Through Alternating Optimization for Multi-Regime Physics-Informed Neural Networks.

Enzo Nicolás Spotorno Bieger, Josafat Ribeiro Leal Filho, Antônio Augusto Fröhlich

CoRR, February, 2026

Verifying Physics-Informed Neural Network Fidelity using Classical Fisher Information from Differentiable Dynamical System.

Josafat Ribeiro Leal Filho, Antônio Augusto Fröhlich

CoRR, January, 2026

Linking Physical Fidelity to Downstream Performance in Physics-Informed Fault Diagnosis.

Enzo Nicolás Spotorno, Josafat Ribeiro Leal Filho, Antônio Augusto Fröhlich

IEEE Access, 2026

2025

Hard-Constrained Neural Networks with Physics-Embedded Architecture for Residual Dynamics Learning and Invariant Enforcement in Cyber-Physical Systems.

Enzo Nicolás Spotorno, Josafat Leal Filho, Antônio Augusto Fröhlich

CoRR, November, 2025

Physics-informed neural networks for monitoring dynamic systems: ring bearing system study case.

Josafat Leal Filho, Matheus Wagner, Antônio Augusto Fröhlich

Des. Autom. Embed. Syst., June, 2025

Multi-Component Temporal-Correlation Seismic Data Compression Algorithm Based on the PCA and DWT.

Mateus Martínez De Lucena, Josafat Ribeiro Leal Filho, Matheus Wagner, Antônio Augusto Fröhlich

Algorithms, 2025

Adaptive QoS to Handle Transient Overloads in Time-Sensitive Vehicular Networks Caused by ADAS.

Leonardo Passig Horstmann, Antônio Augusto Fröhlich, Josafat Leal Filho, José Luis Conradi Hoffmann

Proceedings of the 18th IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip, 2025

A Dynamic Bayesian Deep Learning Approach to Structural Health Monitoring.

Josafat Ribeiro Leal Filho, Alexander Kocian, Antônio Augusto Fröhlich, Stefano Chessa

Proceedings of the IEEE Symposium on Computers and Communications, 2025

Predicting Transient Overloads Related to ADAS in Time-sensitive Vehicular Networks.

Josafat Leal Filho, Antônio Augusto Fröhlich, Leonardo Passig Horstmann, José Luis Conradi Hoffmann, Jozimar C. Xavier

Proceedings of the IEEE Symposium on Computers and Communications, 2025

Physics-Informed Residual-Based Anomaly Detection and Open-Set Recognition System: A Case Study on Ring Bearings.

Enzo Nicolás Spotorno, Josafat Leal Filho, Antônio Augusto Fröhlich

Proceedings of the 51st Annual Conference of the IEEE Industrial Electronics Society, 2025

2024

Combining PCA and DCT for Improved Passive Seismic Data Compression.

Matheus Wagner, Mateus Martínez De Lucena, Josafat Leal Filho, Antônio Augusto Fröhlich

IEEE Access, 2024

Comparison of Neural Network Training Approaches That Preserve Physical Properties of Cyber-Physical System.

Josafat Leal Filho, Stephan Paul, Antônio Augusto Fröhlich

Proceedings of the XIV Brazilian Symposium on Computing Systems Engineering, 2024

Continual Learning in Recurrent Neural Networks for the Internet of Things: A Stochastic Approach.

Josafat Ribeiro Leal Filho, Alexander Kocian, Antônio Augusto Fröhlich, Stefano Chessa

Proceedings of the IEEE Symposium on Computers and Communications, 2024

2023

Physics-Informed Neural Networks for Monitoring Dynamic Systems: Wind Turbine Study Case.

Josafat Leal Filho, Matheus Wagner, Antônio Augusto Fröhlich

Proceedings of the XIII Brazilian Symposium on Computing Systems Engineering, 2023