Refine
Year of publication
Document Type
- Article (5586)
- Conference Proceeding (1620)
- Book (1078)
- Part of a Book (548)
- Bachelor Thesis (297)
- Patent (172)
- Report (100)
- Doctoral Thesis (78)
- Other (77)
- Administrative publication (76)
- Part of Periodical (63)
- Lecture (30)
- Master's Thesis (20)
- Contribution to a Periodical (19)
- Review (17)
- Diploma Thesis (15)
- Working Paper (13)
- Course Material (9)
- Talk (7)
- Study Thesis (5)
Language
- German (5012)
- English (4801)
- Russian (14)
- Portuguese (6)
- Multiple languages (5)
- Spanish (3)
- nld (2)
- Italien (1)
Keywords
- Amtliche Mitteilung (71)
- Bachelor (33)
- Aachen University of Applied Sciences (31)
- Master (31)
- Prüfungsordnung (31)
- Bauingenieurwesen (30)
- Lesbare Fassung (28)
- Biosensor (25)
- Fachhochschule Aachen (23)
- Illustration (21)
- Studien- und Prüfungsordnung (21)
- Aachen / Fachhochschule Aachen (20)
- Änderungsordnung (20)
- Blitzschutz (18)
- Corporate Design (17)
- Elektromobilität (17)
- CAD (16)
- Finite-Elemente-Methode (16)
- Fotografie (16)
- civil engineering (14)
Institute
- Fachbereich Medizintechnik und Technomathematik (2052)
- Fachbereich Elektrotechnik und Informationstechnik (1150)
- Fachbereich Wirtschaftswissenschaften (1138)
- Fachbereich Energietechnik (1104)
- Fachbereich Maschinenbau und Mechatronik (866)
- Fachbereich Chemie und Biotechnologie (847)
- Fachbereich Luft- und Raumfahrttechnik (776)
- Fachbereich Bauingenieurwesen (705)
- IfB - Institut für Bioengineering (686)
- INB - Institut für Nano- und Biotechnologien (613)
- Fachbereich Gestaltung (484)
- Solar-Institut Jülich (339)
- Fachbereich Architektur (174)
- FH Aachen (153)
- ECSM European Center for Sustainable Mobility (112)
- ZHQ - Bereich Hochschuldidaktik und Evaluation (74)
- MASKOR Institut für Mobile Autonome Systeme und Kognitive Robotik (71)
- Nowum-Energy (70)
- Institut fuer Angewandte Polymerchemie (32)
- Sonstiges (24)
Analyzing electroencephalographic (EEG) time series can be challenging, especially with deep neural networks, due to the large variability among human subjects and often small datasets. To address these challenges, various strategies, such as self-supervised learning, have been suggested, but they typically rely on extensive empirical datasets. Inspired by recent advances in computer vision, we propose a pretraining task termed "frequency pretraining" to pretrain a neural network for sleep staging by predicting the frequency content of randomly generated synthetic time series. Our experiments demonstrate that our method surpasses fully supervised learning in scenarios with limited data and few subjects, and matches its performance in regimes with many subjects. Furthermore, our results underline the relevance of frequency information for sleep stage scoring, while also demonstrating that deep neural networks utilize information beyond frequencies to enhance sleep staging performance, which is consistent with previous research. We anticipate that our approach will be advantageous across a broad spectrum of applications where EEG data is limited or derived from a small number of subjects, including the domain of brain-computer interfaces.