Peter Domanski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Peter Domanski has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Krishnendu Chakrabarty
Arizona State University
4 shared publications Farshad Firouzi
Arizona State University, Tempe, AZ, USA
2 shared publications- Amirhossein Mahmoudi
Sharif University of Technology, Tehran, Iran
1 shared publication Aritra Ray
Duke Univ, 534 Res Dr, Durham, NC 27705 USA
1 shared publication- Bahar Farahani
Cyberspace Research Institute, Shahid Beheshti University, Tehran, Iran
1 shared publication - Deepesh Sahoo
Arizona State University, Tempe, AZ, USA
1 shared publication
Latest Publications
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (4) , 1369-1382
TIDE-S: Telemetry Informed Delay Testing With Optimized Sensor Placement
Silent data corruption (SDC) refers to undetected errors that yield incorrect results without triggering system alerts or error logs. Existing test methodologies are inadequate for capturing dynamic voltage fluctuations that occur under realistic workload conditions, thereby limiting their effectiveness for detecting SDCs. We present TIDE-S, a telemetry-informed delay testing (TIDE) framework that integrates presilicon sensor placement strategies to improve telemetry accuracy. By evaluating different sensor allocation schemes—uniform, $K$ -means, and energy-aware clustering—TIDE-S improves the spatial granularity of voltage observation, enabling more accurate correlation between voltage fluctuations and path delay behavior. The combined telemetry- and sensor-aware methodology significantly improves the detection of timing-sensitive SDCs. The proposed framework incurs minimal infrastructure overhead by leveraging standard pad-based voltage observation, making it practical for real system-on-chip (SoC) designs. We demonstrate the effectiveness of TIDE-S across multiple RISC-V-based SoCs and a diverse set of real-world benchmarks, showing quantifiable improvements in voltage estimation, slack prediction, and test coverage.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (4) , 1369-1382
TIDE-S: Telemetry Informed Delay Testing With Optimized Sensor Placement
Silent data corruption (SDC) refers to undetected errors that yield incorrect results without triggering system alerts or error logs. Existing test methodologies are inadequate for capturing dynamic voltage fluctuations that occur under realistic workload conditions, thereby limiting their effectiveness for detecting SDCs. We present TIDE-S, a telemetry-informed delay testing (TIDE) framework that integrates presilicon sensor placement strategies to improve telemetry accuracy. By evaluating different sensor allocation schemes—uniform, $K$ -means, and energy-aware clustering—TIDE-S improves the spatial granularity of voltage observation, enabling more accurate correlation between voltage fluctuations and path delay behavior. The combined telemetry- and sensor-aware methodology significantly improves the detection of timing-sensitive SDCs. The proposed framework incurs minimal infrastructure overhead by leveraging standard pad-based voltage observation, making it practical for real system-on-chip (SoC) designs. We demonstrate the effectiveness of TIDE-S across multiple RISC-V-based SoCs and a diverse set of real-world benchmarks, showing quantifiable improvements in voltage estimation, slack prediction, and test coverage.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-14
DiabLLM: An LLM-Based Framework for Blood Glucose Prediction in Type 1 Diabetes
Accurate Blood Glucose (BG) prediction is essential for enabling glycemic control in individuals with Type 1 Diabetes Mellitus (T1DM), particularly within Smart and Connected Health (SCH) systems that integrate Continuous Glucose Monitoring (CGM) and automated insulin delivery. The adaptability of Large Language Models (LLMs) provides a promising foundation for unified, fine-tunable forecasting models. We introduce DiabLLM, a framework based on two recent LLM-based architectures: Time-LLM, which incorporates a lightweight projection layer and alignment techniques to transform time-series data into embeddings interpretable by pre-trained LLMs, and Chronos, which employs time-series-aware tokenization and quantization to convert continuous inputs into discrete sequences for forecasting. Both models process 30-minute sequences of six historical BG values and predict 30- and 45-minute horizons. Experimental results on the OhioT1DM and D1NAMO datasets demonstrate that DiabLLM outper forms state-of-the-art baselines, including a Deep Reinforcement Learning model and an ensemble of LSTM, GRU, and WaveNet, achieving up to 27% improvement in RMSE and 37% in MAE. To enhance robustness to noisy and missing input data, a denoising autoencoder was employed for input reconstruction, yielding improved predictive performance. In addition, knowledge distillation was shown to significantly compress the model, making it a practical candidate for efficient deployment on resource-constrained edge devices without compromising accuracy.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-14
DiabLLM: An LLM-Based Framework for Blood Glucose Prediction in Type 1 Diabetes
Accurate Blood Glucose (BG) prediction is essential for enabling glycemic control in individuals with Type 1 Diabetes Mellitus (T1DM), particularly within Smart and Connected Health (SCH) systems that integrate Continuous Glucose Monitoring (CGM) and automated insulin delivery. The adaptability of Large Language Models (LLMs) provides a promising foundation for unified, fine-tunable forecasting models. We introduce DiabLLM, a framework based on two recent LLM-based architectures: Time-LLM, which incorporates a lightweight projection layer and alignment techniques to transform time-series data into embeddings interpretable by pre-trained LLMs, and Chronos, which employs time-series-aware tokenization and quantization to convert continuous inputs into discrete sequences for forecasting. Both models process 30-minute sequences of six historical BG values and predict 30- and 45-minute horizons. Experimental results on the OhioT1DM and D1NAMO datasets demonstrate that DiabLLM outper forms state-of-the-art baselines, including a Deep Reinforcement Learning model and an ensemble of LSTM, GRU, and WaveNet, achieving up to 27% improvement in RMSE and 37% in MAE. To enhance robustness to noisy and missing input data, a denoising autoencoder was employed for input reconstruction, yielding improved predictive performance. In addition, knowledge distillation was shown to significantly compress the model, making it a practical candidate for efficient deployment on resource-constrained edge devices without compromising accuracy.
- Open Access
- 9 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
ML-TIME: ML-driven Timing Analysis of Integrated Circuits in the Presence of Process Variations and Aging Effects
Integrated circuits at advanced technology nodes are prone to process variations and early life failures due to aging. Variations in transistor parameters lead to a degraded on-current which, in turn, results in increasing gate-level propagation delay. Similarly, threshold voltage shifts due to aging effects result in increased path delays and erstwhile latent defects manifesting as early life failures (ELFs). We propose ML-TIME, a novel machine learning-based framework to simulate path delays in an integrated circuit in the presence of process variations and aging effects. While conventional static timing analysis (STA) tools can only compute path delays at well-defined process-voltage-temperature corners, ML-TIME can be used to obtain a statistical distribution of the path delays under user-defined process variations and aging specifications. Such distributions can be used to identify paths that are susceptible to either process variations or aging effects or both and can enable designers to make remedial changes. Simulation results across multiple benchmarks and standard cell libraries demonstrate that the ML-TIME can accurately predict critical path delays under variations and aging, with an error margin of less than 1.7%, all without the need for computationally expensive circuit simulations.
- 9 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessML-TIME: ML-driven Timing Analysis of Integrated Circuits in the Presence of Process Variations and Aging Effects
Integrated circuits at advanced technology nodes are prone to process variations and early life failures due to aging. Variations in transistor parameters lead to a degraded on-current which, in turn, results in increasing gate-level propagation delay. Similarly, threshold voltage shifts due to aging effects result in increased path delays and erstwhile latent defects manifesting as early life failures (ELFs). We propose ML-TIME, a novel machine learning-based framework to simulate path delays in an integrated circuit in the presence of process variations and aging effects. While conventional static timing analysis (STA) tools can only compute path delays at well-defined process-voltage-temperature corners, ML-TIME can be used to obtain a statistical distribution of the path delays under user-defined process variations and aging specifications. Such distributions can be used to identify paths that are susceptible to either process variations or aging effects or both and can enable designers to make remedial changes. Simulation results across multiple benchmarks and standard cell libraries demonstrate that the ML-TIME can accurately predict critical path delays under variations and aging, with an error margin of less than 1.7%, all without the need for computationally expensive circuit simulations.
- Open Access
- 12 August 2024
- Published by Elsevier in Biocybernetics and Biomedical Engineering
- Vol. 44 (3) , 481-500
Advancing blood glucose prediction with neural architecture search and deep reinforcement learning for type 1 diabetics
- 12 August 2024
- Published by Elsevier in Biocybernetics and Biomedical Engineering
- Vol. 44 (3) , 481-500
Open AccessAdvancing blood glucose prediction with neural architecture search and deep reinforcement learning for type 1 diabetics