Kunz, Pertami J. ; Zoubir, Abdelhak M. (2023)
Heterogeneity-Stratified Bootstrap Oversampling for Training a Spoiled Food Detector.
2023 24th International Conference on Digital Signal Processing. Rhodes, Greece (11.-13.06.2023)
doi: 10.1109/DSP58604.2023.10167943
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
We propose the Heterogeneity-Stratified Bootstrap (HSBoot), a stratification method that gives higher resampling probabilities to the sample points in the less homogeneous regions. We demonstrate its advantage in the case of training a detector by oversampling the under-represented class in an imbalanced data set. We took a case study of a spoiled food detector in form of an electronic nose. The performance metrics were calculated on the out-of-bag test set as well as on measurements collected from another sensor.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2023 |
| Autor(en): | Kunz, Pertami J. ; Zoubir, Abdelhak M. |
| Art des Eintrags: | Bibliographie |
| Titel: | Heterogeneity-Stratified Bootstrap Oversampling for Training a Spoiled Food Detector |
| Sprache: | Englisch |
| Publikationsjahr: | 5 Juli 2023 |
| Verlag: | IEEE |
| Buchtitel: | 24th DSP 2023: 2023 24th International Conference on Digital Signal Processing |
| Veranstaltungstitel: | 2023 24th International Conference on Digital Signal Processing |
| Veranstaltungsort: | Rhodes, Greece |
| Veranstaltungsdatum: | 11.-13.06.2023 |
| DOI: | 10.1109/DSP58604.2023.10167943 |
| Kurzbeschreibung (Abstract): | We propose the Heterogeneity-Stratified Bootstrap (HSBoot), a stratification method that gives higher resampling probabilities to the sample points in the less homogeneous regions. We demonstrate its advantage in the case of training a detector by oversampling the under-represented class in an imbalanced data set. We took a case study of a spoiled food detector in form of an electronic nose. The performance metrics were calculated on the out-of-bag test set as well as on measurements collected from another sensor. |
| Fachbereich(e)/-gebiet(e): | 18 Fachbereich Elektrotechnik und Informationstechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Nachrichtentechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Nachrichtentechnik > Signalverarbeitung Exzellenzinitiative Exzellenzinitiative > Graduiertenschulen Exzellenzinitiative > Graduiertenschulen > Graduate School of Computational Engineering (CE) |
| Hinterlegungsdatum: | 10 Jul 2023 10:21 |
| Letzte Änderung: | 10 Jul 2023 10:21 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum