Dataset supporting the conference paper "Power- and Deadline-Aware Dynamic Inference on Intermittent Computing Systems"

This dataset supports the publication: "Power- and Deadline-Aware Dynamic Inference on Intermittent Computing Systems" by Hengrui Zhao, Lei Xun, Jagmohan Chauhan and Geoff Merrett CONFERENCE: Design, Automation and Test in Europe Conference 2025 This dataset includes the experimental results for Figure 1, 6, 7, 8, 9 of the paper. This dataset contains: 'Fig1.csv': Data supporting Fig. 1. Comparison of accuracy and inference latency of ePerceptron with the baseline. 'Fig6.csv': Data supporting Fig. 6. The operating cycles of the system when running the largest sub-network of DualAdaptNet at different current inputs. 'Fig7.csv': Data supporting Fig. 7. The accuracy and inference latency of DualAdaptNet, ePerceptive, and Zygarde under continuous power supply. 'Fig8.csv': Data supporting Fig. 8. The number of completed and correct inferences performed by the three models (DualAdaptNet, ePerceptive, and Zygarde) under constant current supply. 'Fig9.csv': Data supporting Fig. 9. The number of completed and correct inferences performed by the three models (DualAdaptNet, ePerceptive, and Zygarde) under varying current supply.