Refine
Year of publication
- 2024 (47)
- 2023 (167)
- 2022 (219)
- 2021 (218)
- 2020 (218)
- 2019 (300)
- 2018 (248)
- 2017 (254)
- 2016 (251)
- 2015 (284)
- 2014 (265)
- 2013 (283)
- 2012 (291)
- 2011 (305)
- 2010 (317)
- 2009 (332)
- 2008 (289)
- 2007 (271)
- 2006 (276)
- 2005 (263)
- 2004 (286)
- 2003 (218)
- 2002 (232)
- 2001 (210)
- 2000 (234)
- 1999 (232)
- 1998 (236)
- 1997 (214)
- 1996 (200)
- 1995 (192)
- 1994 (174)
- 1993 (154)
- 1992 (144)
- 1991 (100)
- 1990 (108)
- 1989 (110)
- 1988 (103)
- 1987 (105)
- 1986 (81)
- 1985 (83)
- 1984 (75)
- 1983 (70)
- 1982 (57)
- 1981 (54)
- 1980 (61)
- 1979 (58)
- 1978 (52)
- 1977 (32)
- 1976 (30)
- 1975 (28)
- 1974 (17)
- 1973 (12)
- 1972 (17)
- 1971 (11)
- 1970 (2)
- 1969 (2)
- 1968 (2)
- 1967 (1)
- 1963 (1)
Document Type
- Article (5464)
- Conference Proceeding (1393)
- Book (1056)
- Part of a Book (544)
- Patent (172)
- Bachelor Thesis (156)
- Report (81)
- Doctoral Thesis (78)
- Other (68)
- Contribution to a Periodical (19)
- Master's Thesis (17)
- Review (17)
- Working Paper (8)
- Talk (5)
- Habilitation (4)
- Preprint (4)
- Diploma Thesis (3)
- Poster (3)
- Part of Periodical (2)
- Examination Thesis (1)
Language
Has Fulltext
- no (9096) (remove)
Keywords
- Corporate Design (9)
- Illustration (9)
- Erscheinungsbild (8)
- Gamification (8)
- Nachhaltigkeit (8)
- Redesign (7)
- Animation (6)
- Datenschutz (6)
- Digitalisierung (6)
- avalanche (6)
- App (5)
- Earthquake (5)
- Editorial (5)
- Enterprise Architecture (5)
- Fotografie (5)
- Geschichte (5)
- MINLP (5)
- solar sail (5)
- Aktionskunst (4)
- Design (4)
Institute
- Fachbereich Medizintechnik und Technomathematik (1907)
- Fachbereich Elektrotechnik und Informationstechnik (1116)
- Fachbereich Wirtschaftswissenschaften (1100)
- Fachbereich Energietechnik (1056)
- Fachbereich Chemie und Biotechnologie (829)
- Fachbereich Maschinenbau und Mechatronik (799)
- Fachbereich Luft- und Raumfahrttechnik (749)
- Fachbereich Bauingenieurwesen (658)
- IfB - Institut für Bioengineering (623)
- INB - Institut für Nano- und Biotechnologien (584)
- Solar-Institut Jülich (334)
- Fachbereich Gestaltung (333)
- Fachbereich Architektur (161)
- ECSM European Center for Sustainable Mobility (106)
- MASKOR Institut für Mobile Autonome Systeme und Kognitive Robotik (66)
- Nowum-Energy (64)
- ZHQ - Bereich Hochschuldidaktik und Evaluation (62)
- Institut fuer Angewandte Polymerchemie (32)
- Sonstiges (24)
- IBB - Institut für Baustoffe und Baukonstruktionen (21)
- Freshman Institute (19)
- Kommission für Forschung und Entwicklung (18)
- Verwaltung (11)
- IaAM - Institut für angewandte Automation und Mechatronik (4)
- FH Aachen (3)
- IMP - Institut für Mikrowellen- und Plasmatechnik (3)
- Arbeitsstelle fuer Hochschuldidaktik und Studienberatung (2)
- Datenverarbeitungszentrale (1)
- Digitalisierung in Studium & Lehre (1)
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.