This paper presents a novel methodology to analyze nursing surveys. It is based on ELM and SOM. The goal is to identify which variables lead to the likelihood to report the medication errors. ELM are accurate by extremely fast prediction models. SOM are performing nonlinear dimensionality reduction to get an accurate visualization of the data. Combining both techniques reduces the curse of dimensionality and improves furthermore the interpretability of the visualization. The methodology is tested on a nursing survey datasets.
|Title of host publication||Proceedings of ELM2019|
|Editors||Jiuwen Cao, Chi Man Vong, Yoan Miche, Amaury Lendasse|
|Number of pages||10|
|Publication status||Published - 2021|
|MoE publication type||A3 Book chapter|
|Name||Proceedings of ELM2019|