Poster Abstract: Trade-off Analysis of Inference Accuracy and Resource Usage for Energy-Positive Activity Recognition

Energy-positive activity recognition classifies human activities, including walking, running, and sitting, while harvesting kinetic energy from such activities. In this setting, the device's lifetime depends on the user's activity profile and the resources needed to run inference to classify activities. Thus, the selection of machine learning classification models for energy-positive activity recognition must consider both model's classification accuracy and energy consumption compared to the harvested energy from human activities. In this paper, we study the trade-off between accuracy and resource usage of a neural network model when different feature extraction techniques are used. Our results indicate that an on-board scheduling algorithm can be used to dynamically switch between the optimal feature input tuned for accuracy and energy consumption.