Fusing voice and query data for non-invasive detection of laryngeal disordersShow others and affiliations
2015 (English)In: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 42, no 22, p. 8445-8453Article in journal (Refereed) Published
Abstract [en]
Topic of this study is exploration and fusion o fnon-invasive measurements for an accurate detection of pathological larynx. Measurements for human subject encompass answers to items of a specific survey and information extracted by the openSMILE toolkit from several audio recordings of sustained phonation (vowel/a/).
Place, publisher, year, edition, pages
Kidlington: Pergamon Press, 2015. Vol. 42, no 22, p. 8445-8453
Keywords [en]
Ensemble methods, Random forest, Variable importance, Imputation, Affinity analysis, Voice pathology detection
National Category
Mathematics Other Engineering and Technologies
Identifiers
URN: urn:nbn:se:hh:diva-29487DOI: 10.1016/j.eswa.2015.07.001ISI: 000361923100007Scopus ID: 2-s2.0-84940461705OAI: oai:DiVA.org:hh-29487DiVA, id: diva2:855194
Note
Initial results, excluding experiments with imputation and variable importance, were presented in the 14th International Conference on Artificial Intelligence, Knowledge Engineering and Data Bases (Vaiciukynas et al., 2015). This research was funded by a grant (No. MIP-075/2015) from the Research Council of Lithuania.
2015-09-192015-09-192022-09-13Bibliographically approved