Resilience Engineering

Description

Resilience engineering is a complex, hierarchal and multi-disciplinary, finding applications in a diverse spectrum of engineering and social science domains, in which the performance level is degraded due to aging or externals shocks but is proactively maintained to preserve nominal performance equivalent to the fully operational state in reliability modeling. For decades, a variety of resilience metrics to quantify the resilience of systems enables retrospective analysis to assess how well a system performed under stress and inform future design and operational decisions. This project is developing predictive models to project when the system will recover to a specified level of performance and what actions to take in order to reach a target level of performance quickly and cost effectively. To promote the application of predictive models, an open-source tool is also being developed which will help researchers and organizations track and predict resilience by including different activities that contributes positively and negatively to system performance. This tool will not require any coding knowledge or mathematical background.

The Predictive System Resilience Assessment Tool (PSRAT)

Description

PSRAT is a tool for predicting system resilience in terms of the external activities that impact system performance. The tool enables visualizations of model fit with different covariates to the performance data, and computation of goodness-of-fit, resilience metrics, and confidence intervals to guide decision-making. The tool implements various regression models that can be compared against each other.
PSRAT runs using python3.x on Windows, MacOS, and Linux. It can also be run with docker for stable deployments.

Resources:

Publications

13. F. Salboukh, H. Saki, and L. Fiondella, Resilience Prediction: A Transformer-based Approach, In Proc. 72nd Annual Reliability and Maintainability Symposium (RAMS 2026), Las Vegas, NV, Jan 2026.

12. P. Silva, D. Rodrigues, and L. Fiondella, Resilience Estimation of Radar Systems, In Proc. IEEE Radio & Wireless Week, Los Angeles, CA, Jan 2026.

11. P. Silva, B. Gaspard, M. Hotchkiss, G. Kul, N. Bastian, and L. Fiondella, Regression and Time Series Mixture Approaches to Predict System Performance and Assess Resilience, IEEE Transactions on Reliability (T-Rel), 74(3), pp. 3002-3016, 2025. DOI: https://doi.org/10.1109/TR.2024.3471409.

10. Z. Faddi, K. da Mata, P. Silva, V. Nagaraju, S. Ghosh, G. Kul, and L. Fiondella, Quantitative Assessment of Machine Learning Reliability and Resilience, Risk Analysis, 45(4), pp. 790-807, 2025. DOI: https://doi.org/10.1111/risa.14666.

9. S. Ghosh, A. Chatterjee, and L. Fiondella, An Active Learning Framework for Adversarial Training of Deep Neural Networks, Neural Computing and Applications, 37, pp. 6849–6876, 2025. DOI: https://doi.org/10.1007/s00521-024-10851-6.

8. K. da Mata, P. Silva, F. Salboukh, and L. Fiondella, Resilience Comparison of CNN-enabled Systems under Adversarial Attacks on Different Computing Environments, In Proc. International Conference on Reliability and Quality in Design (ISSAT), Honolulu, HI, August 2025.

7. P. Silva, M. Hermosillo Hidalgo, M. Hotchkiss, I. Linkov, L. Dharmasena, and L. Fiondella, Predictive Resilience Modeling using Statistical Regression Methods, Mathematics, 12(15), pp. 2380, 2024. DOI: https://doi.org/10.3390/math12152380.

6. P. Silva, K. da Mata, F. Salboukh, J. Dantas, and L. Fiondella, Resilience Assessment of Cloud Video Transcoding Services, In Proc. Resilience Engineering in Computer Systems (RECS), Recife, Brazil, Nov 2024.

5. F. Salboukh, P. Silva, and L. Fiondella, Enhancing Multiple Regression-based Resilience Model Prediction with Transfer Function, In Proc. International Conference on Reliability and Quality in Design (ISSAT), Miami, FL, August 2024.

4. L. Fiondella, L. Hogewood, A. Ligo, and I. Linkov, Edge Computing as an Enabler of Energy and Water System Resilience, Engineering Management Review, 2023. DOI: https://doi.org/10.1109/EMR.2023.3320876

3. K. da Mata, P. Silva, and L. Fiondella, Predicting Resilience with Neural Networks, In Proc. International Conference on Reliability and Quality in Design (ISSAT), San Francisco, CA, August 2023.

2. A. Jin, L. Hogewood, S. Fries, J. Lambert, L. Fiondella, A. Strelzoff, J. Boone, K. Fleckner, and I. Linkov, Resilience of Cyber-Physical Systems: Role of AI, Digital Twins and Edge Computing, Engineering Management Review, 2022. DOI: https://doi.org/10.1109/EMR.2022.3172649

1. P. Silva, M. Hermosillo Hidalgo, I. Linkov, and L. Fiondella, Predictive Resilience Modeling, In Proc. Resilience Week, Oct 2022.

Invited Talks

5. Resilience Engineering: Models and Applications, National Taipei University of Technology, November 27, 2025.

4. Resilience Engineering: Theory and Applications, National Taipei University of Technology, November 25, 2025.

3. Quantitative Assessment of Machine Learning Reliability and Resilience, American Society for Quality (ASQ) Fall Technical Conference, Nashville, TN, October 10, 2024.

2. Quantitative Assessment of Machine Learning Reliability and Resilience, Reliability, Maintenance & Managing Risk Conference (RMMR 2024), Pittsburgh, PA, July 26, 2024.

1. Quantitative Assessment of Machine Learning Reliability and Resilience, Joint Meeting of the 40th ASA Quality and Productivity Research Conference and the 29th ASA/IMS Spring Research Conference, University of Waterloo, CA, June 19, 2024.

Presentations and Tutorials

20. P. Silva, F. Salboukh, and L. Fiondella, A Mathematical Theory of Resilience, Duke International Workshop on Dependability and Performance Evaluation, Durham, NC, August 2025.

19. Z. Faddi, K. da Mata, P. Silva, V. Nagaraju, S. Ghosh, G. Kul, and L. Fiondella, Cyber and Autonomous System Resilience Engineering, UMass Dartmouth Marine and Undersea Technology (MUST) Day, Dartmouth, MA, July 2025.

18. Z. Faddi, K. da Mata, P. Silva, V. Nagaraju, S. Ghosh, G. Kul, and L. Fiondella, Quantitative Assessment of Machine Learning Reliability and Resilience, WG17 Logistics, Reliability and Maintainability and WG35 AI and Autonomous Systems, 93rd Military Operations Research Symposium (MORS 2025), Leesburg, VA, June 2025.

17. K. da Mata, Z. Faddi, P. Silva, V. Nagaraju, S. Ghosh, G. Kul, and L. Fiondella, Quantitative Reliability and Resilience Assessment of a Machine Learning Algorithm, National Defense Industrial Association (NDIA) Annual Systems & Mission Engineering Conference, Norfolk, VA, October 2024.

16. K. da Mata, Z. Faddi, P. Silva, V. Nagaraju, S. Ghosh, G. Kul, and L. Fiondella, Quantitative Assessment of Machine Learning Reliability and Resilience, Department of the Air Force Data, Analytics, and AI Forum, Miramar Beach, FL, April 2024.

15. F. Salboukh, P. Silva, and L. Fiondella, Enhancing Time Series-based Resilience Model Prediction with Transfer Functions, Defense and Aerospace Test and Analysis (DATA) Workshop, Alexandria, VA, April 2024.

14. P. Silva, B. Gaspard, M. Hotchkiss, G. Kul, N. Bastian, and L. Fiondella, Regression and Time Series Mixture Approaches to Predict System Resilience, Defense and Aerospace Test and Analysis (DATA) Workshop, Alexandria, VA, April 2024.

13. K. da Mata, Z. Faddi, P. Silva, V. Nagaraju, S. Ghosh, G. Kul, and L. Fiondella, Quantitative Reliability and Resilience Assessment of a Machine Learning Algorithm, Defense and Aerospace Test and Analysis (DATA) Workshop, Alexandria, VA, April 2024.

12. P. Silva and L. Fiondella, Predictive System Resilience Modeling, Mathematical Opportunities in Digital Twins Workshop (MATH-DT 2023), Fairfax, VA, Dec 2023.

11. P. Silva and L. Fiondella, Predictive Resilience Modeling, Annual International Test & Evaluation (ITEA) Symposium, Destin, FL, December 2023.

10. P. Silva and L. Fiondella, Tracking and Predicting System Resilience, 9th International Engineering Systems Symposium (CESUN 2023), Evanston, IL, Nov 2023.

9. P. Silva and L. Fiondella, Predictive Resilience Modeling, National Defense Industrial Association (NDIA) Annual Systems Engineering Conference, Norfolk, VA, October 2023.

8. P. Silva, M. Hermosillo Hidalgo, M. Hotchkiss, I. Linkov, L. Dharmasena, and L. Fiondella, Predictive Resilience Modeling, American Society for Quality (ASQ) Fall Technical Conference, Raleigh, NC, October 2023.

7. P. Silva, M. Hermosillo Hidalgo, M. Hotchkiss, I. Linkov, L. Dharmasena, and L. Fiondella, Predictive Resilience Modeling, Reliability, Maintenance & Managing Risk Conference (RMMR), Minneapolis, MN, July 2023.

6. P. Silva and L. Fiondella, Predictive Resilience Modeling, Presented to WG17 Logistics, Reliability and Maintainability, 91st Military Operations Research Symposium (MORS 2023), West Point, NY, June 2023.

5. P. Silva and L. Fiondella, Predictive Resilience Modeling, American Society for Quality (ASQ) World Conference on Quality & Improvement (WCQI), Philadelphia, PA, May 2023.

4. Z. Faddi, K. da Mata, P. Silva, V. Nagaraju, S. Ghosh, and L. Fiondella, Application of Reliability and Resilience Models to Machine Learning, Defense and Aerospace Test and Analysis (DATA) Workshop, Alexandria, VA, April 2023. Outstanding poster presentation.

3. K. da Mata, P. Silva, and L. Fiondella, Neural Network for Quantitative Resilience Prediction, Defense and Aerospace Test and Analysis (DATA) Workshop, Alexandria, VA, April 2023.

2. P. Silva, A. Bajumpaa, D. Borden, C. Taylor, and L. Fiondella, Covariate Resilience Modeling, Defense and Aerospace Test and Analysis (DATA) Workshop, Alexandria, VA, April 2023.

1. L. Fiondella, A. Ligo, L. Hogewood, and I. Linkov, Edge Computing as an Enabler of Energy and Water System Resilience, In Proc. Society for Risk Analysis (SRA) Annual Meeting, December 2022.

Acknowledgments

This material is based upon work supported by the National Science Foundation under Grant Number 1749635 and the Homeland Security Community of Best Practices (HS CoBP) through the U.S. Department of the Air Force under contract FA8075-18-D-0002/FA8075-21-F-0074.