Project Overview
Smart critical infrastructure systems are increasingly powered by artificial intelligence. While these AI-driven systems offer transformative potential, their deployment in safety-critical and socially impactful domains raises fundamental concerns around trustworthiness, robustness, privacy, fairness, and transparency. This project focuses on advancing Trustworthy and Responsible AI methodologies that ensure reliable, ethical, and secure decision-making in smart critical infrastructure.
This research integrates advances in machine learning, wireless sensing, cyber-physical systems, and human-centered AI to address real-world challenges in smart farms and healthcare systems. We develop privacy-preserving, fair, and explainable AI models for applications such as disease detection, animal behavior monitoring, and intelligent sensing, while accounting for uncertainty, data heterogeneity, and system-level constraints. Key technical thrusts include uncertainty-aware deep learning, federated and distributed learning, misclassification detection, explainability, and robustness against adversarial and environmental perturbations.
The project is supported by multiple funding programs, including the National Science Foundation (NSF) and the Commonwealth Cyber Initiative (CCI). It spans a portfolio of interdisciplinary efforts in intelligent wireless sensor systems, secure IoT platforms, and uncertainty-aware AI frameworks. Through close collaboration among researchers, this initiative aims to establish principled foundations and practical solutions for responsible AI deployment in smart, critical infrastructure, bridging theory and practice to enable systems that are not only intelligent but also secure, fair, interpretable, and trustworthy.
Projects
Computer and Network Systems Smart Farm
This project focuses on designing a wireless sensor network (WSN) to monitor key cattle biometrics, enabling continuous assessment of animal behavior and health to improve animal welfare and reduce labor costs. The system leverages LoRa-based wireless technologies to support long-range, low-power communication, allowing remote monitoring through Internet-connected platforms. Recognizing the cyberbiosecurity risks introduced by wireless sensing, the project also emphasizes secure system design to protect against cyber threats and ensure reliable and resilient smart farming operations.
Trustworthy and Responsible AI
This project advances trustworthy and responsible artificial intelligence by developing principled machine learning methods that promote transparency, fairness, and reliability in real-world applications. It focuses on designing explainable, privacy-preserving, and uncertainty-aware AI models that support accountable decision-making and mitigate bias and model failures. The approach integrates responsible AI principles throughout the model development and evaluation pipeline to ensure dependable and ethical AI behavior. These efforts aim to enable AI systems that can be confidently deployed in high-impact domains where trust, robustness, and accountability are essential.
Robust and Failure-Aware AI
This project advances trustworthy artificial intelligence by developing methods to identify and analyze misclassifications in machine learning models. It focuses on leveraging explainable AI (XAI) techniques to provide insight into model decision-making, enabling the detection of erroneous, uncertain, or unreliable predictions. By integrating explanation-driven signals into the learning and evaluation process, the approach improves model robustness and supports more reliable and transparent AI deployment. These efforts enhance trust in AI systems by ensuring that model outputs can be better understood, validated, and safely used in real-world applications.
Publications
- R. Kudupudi, F. Lohrabi Pour, D. S. Ha, S. S. Ha, and K. Ramezanpour, “Analysis of Deep Learning Models Towards High Performance Digital Predistortion for RF Power Amplifiers,” International Symposium on Circuits and Systems (ISCAS), 5 pages, May 2022.
- A. P. Damle, S. S. Ha, Z. Zhao, B. R. dos Reis, R. White, and D. S. Ha, “Power Efficient Wireless Sensor Node through Edge Intelligence,” International Symposium on Circuits and Systems (ISCAS), 5 pages, May 2022.
- Q. Zhang, Y. Mahajan, I.R. Chen, D. Ha, and J.H. Cho, “An Attack-Resilient and Energy-Adaptive Monitoring System for Smart Farms,” IEEE GLOBECOM, Dec. 2022
- A. Gadre et al., “MiLTOn: Sensing Product Integrity without Opening the Box using Non-Invasive Acoustic Vibrometry,” 2022 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), 2022, pp. 390-402, doi: 10.1109/IPSN54338.2022.00038.
- J. Zhang, G. Balakrishnan, S. Srinidhi, A. Bhat, S. Kumar and C. Bettinger, “NFCapsule: An Ingestible Sensor Pill for Eosinophilic Esophagitis Detection Based on Near-field Coupling”, SenSys 2022
- D. Chen, Q. Zhang, I. -R. Chen, D. S. Ha and J. -H. Cho, “Energy-Adaptive and Robust Monitoring for Smart Farms Based on Solar-Powered Wireless Sensors,” in IEEE Internet of Things Journal, vol. 11, no. 18, pp. 29781-29797, 15 Sept.15, 2024, doi: 10.1109/JIOT.2024.3409525.
- D. Chen, P. Yang, D. S. Ha and J. -H. Cho, “susFL: Federated Learning-based Monitoring for Sustainable, Attack-Resistant Smart Farms,” 2024 IEEE International Conference on Big Data (BigData), Washington, DC, USA, 2024, pp. 199-208, doi: 10.1109/BigData62323.2024.10825116.
- Dian Chen, Qi Zhang, Lance Kaplan, Audun Josang, Donghyun Jeong, Feng Chen, and Jin-Hee Cho. 2025. Ethical AI for Healthcare Systems: Uncertainty-Aware, Fair Federated Learning. In Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE ’25). Association for Computing Machinery, New York, NY, USA, 222–233. https://doi.org/10.1145/3721201.3721367
Meet Our Team
Principal Investigators
Graduate Students
Project Sponsors
- CCI Fellows Program
- Project: Intelligent and Secure Agricultural Systems: A Cyber-Physical-Social Approach to Precision Farming
Performance Period: 08/2025 — 07/2026
- Project: Intelligent and Secure Agricultural Systems: A Cyber-Physical-Social Approach to Precision Farming
- Commonwealth Cyber Initiative (CCI) Southwest Virginia
- Project: Intelligent and Secure Wireless Sensor System for Monitoring Cattle on Farms
Performance Period: 01/01/2025 — 12/31/2025
- Project: Intelligent and Secure Wireless Sensor System for Monitoring Cattle on Farms
- National Science Foundation (NSF), CNS: Medium
- Project: Energy Centric Wireless Sensor Node System for Smart Farms
Performance Period: 10/01/2021 — 09/30/2025
- Project: Energy Centric Wireless Sensor Node System for Smart Farms
- National Science Foundation (NSF), III: Medium
- Project: MUDL: Multidimensional Uncertainty-Aware Deep Learning Framework
Performance Period: 10/01/2021 — 06/30/2026
- Project: MUDL: Multidimensional Uncertainty-Aware Deep Learning Framework
- Commonwealth Cyber Initiative (CCI)
- Project: 5 G-Enabled Smart Farms through Secure and Intelligent Wireless Sensors
Performance Period: 01/2021 — 06/2021
- Project: 5 G-Enabled Smart Farms through Secure and Intelligent Wireless Sensors
- ICTAS EFO Opportunity Seed Investment Grant (Internal Funding)
- Project: Secure Wireless IoT Sensors for Smart Farms
Performance Period: 01/2021 — 06/2021
- Project: Secure Wireless IoT Sensors for Smart Farms
- Commonwealth Cyber Initiative (CCI) Southwest Virginia Node Institutions
- Project: Secure Wireless IoT Sensors for Smart Farms
Performance Period: 07/2020 — 12/2020
- Project: Secure Wireless IoT Sensors for Smart Farms
