Constrained Attribute Selection for Stress Detection Based on Physiological Signals
Valentina Ilieva Markova, Todor Dimitrov Ganchev · International Conference on Sensors, Signal and Image Processing (SSIP) · 2018
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
International Conference on Sensors, Signal and Image Processing (SSIP) · OpenAlex · conference-paper · 2018
Abstract
We present a constrained attribute selection method that makes use of feature assessment based on the Fisher's separation criterion followed by variety reduction post-processing. The post-processing incorporates task-specific constrain into the feature selection process, as this is expected to facilitate the subsequent data modeling and classification stages. Here we validate the proposed method in an experimental setup oriented towards acute stress detection based on physiological signals.
The experimental results support that the proposed method brings advantage, when compared to three other cases: (i) the full set of features, (ii) a subset selected based on prior knowledge, (iii) and a subset selected based solely on Fisher's separation criterion.
Open the resolved locator · 10.1145/3290589.3290597
Metadata licence: OpenAlex metadata (CC0)