English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a novel methodology for automated feature subset selection from apool of physiological signals using Quantum Annealing (QA). As a case study, wewill investigate the effectiveness of QA-based feature selection techniques inselecting the optimal feature subset for stress detection. Features areextracted from four signal sources: foot EDA, hand EDA, ECG, and respiration.The proposed method embeds the feature variables extracted from thephysiological signals in a binary quadratic model. The bias of the featurevariable is calculated using the Pearson correlation coefficient between thefeature variable and the target variable. The weight of the edge connecting thetwo feature variables is calculated using the Pearson correlation coefficientbetween two feature variables in the binary quadratic model. Subsequently,D-Wave's clique sampler is used to sample cliques from the binary quadraticmodel. The underlying solution is then re-sampled to obtain multiple goodsolutions and the clique with the lowest energy is returned as the optimalsolution. The proposed method is compared with commonly used feature selectiontechniques for stress detection. Results indicate that QA-based feature subsetselection performed equally as that of classical techniques. However, underdata uncertainty conditions such as limited training data, the performance ofquantum annealing for selecting optimum features remained unaffected, whereas asignificant decrease in performance is observed with classical featureselection techniques. Preliminary results show the promise of quantum annealingin optimizing the training phase of a machine learning classifier, especiallyunder data uncertainty conditions.

Quantum Annealing for Automated Feature Selection in Stress Detection