LGSep 22, 2020
Stacked Generalization for Human Activity Recognition
arXiv:2009.10312v1
Originality Synthesis-oriented
AI Analysis
This work addresses activity recognition for applications like health monitoring, but it appears incremental as it applies existing methods without new data.
The paper tackled human activity recognition by proposing Extra Trees and a Stacked Classifier, focusing on best practices to maximize performance, but did not report specific numerical results.
This short paper aims to discuss the effectiveness and performance of classical machine learning approaches for Human Activity Recognition (HAR). It proposes two important models - Extra Trees and Stacked Classifier with the emphasize on the best practices, heuristics and measures that are required to maximize the performance of those models.