TY - JOUR A1 - Grieger, Niklas A1 - Schwabedal, Justus T. C. A1 - Wendel, Stefanie A1 - Ritze, Yvonne A1 - Bialonski, Stephan T1 - Automated scoring of pre-REM sleep in mice with deep learning JF - Scientific Reports N2 - Reliable automation of the labor-intensive manual task of scoring animal sleep can facilitate the analysis of long-term sleep studies. In recent years, deep-learning-based systems, which learn optimal features from the data, increased scoring accuracies for the classical sleep stages of Wake, REM, and Non-REM. Meanwhile, it has been recognized that the statistics of transitional stages such as pre-REM, found between Non-REM and REM, may hold additional insight into the physiology of sleep and are now under vivid investigation. We propose a classification system based on a simple neural network architecture that scores the classical stages as well as pre-REM sleep in mice. When restricted to the classical stages, the optimized network showed state-of-the-art classification performance with an out-of-sample F1 score of 0.95 in male C57BL/6J mice. When unrestricted, the network showed lower F1 scores on pre-REM (0.5) compared to the classical stages. The result is comparable to previous attempts to score transitional stages in other species such as transition sleep in rats or N1 sleep in humans. Nevertheless, we observed that the sequence of predictions including pre-REM typically transitioned from Non-REM to REM reflecting sleep dynamics observed by human scorers. Our findings provide further evidence for the difficulty of scoring transitional sleep stages, likely because such stages of sleep are under-represented in typical data sets or show large inter-scorer variability. We further provide our source code and an online platform to run predictions with our trained network. Y1 - 2021 U6 - http://dx.doi.org/10.1038/s41598-021-91286-0 SN - 2045-2322 N1 - Corresponding author: Stephan Bialonski VL - 11 IS - Art. 12245 PB - Springer Nature CY - London ER - TY - CHAP A1 - Blaneck, Patrick Gustav A1 - Bornheim, Tobias A1 - Grieger, Niklas A1 - Bialonski, Stephan T1 - Automatic readability assessment of german sentences with transformer ensembles T2 - Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text N2 - Reliable methods for automatic readability assessment have the potential to impact a variety of fields, ranging from machine translation to self-informed learning. Recently, large language models for the German language (such as GBERT and GPT-2-Wechsel) have become available, allowing to develop Deep Learning based approaches that promise to further improve automatic readability assessment. In this contribution, we studied the ability of ensembles of fine-tuned GBERT and GPT-2-Wechsel models to reliably predict the readability of German sentences. We combined these models with linguistic features and investigated the dependence of prediction performance on ensemble size and composition. Mixed ensembles of GBERT and GPT-2-Wechsel performed better than ensembles of the same size consisting of only GBERT or GPT-2-Wechsel models. Our models were evaluated in the GermEval 2022 Shared Task on Text Complexity Assessment on data of German sentences. On out-of-sample data, our best ensemble achieved a root mean squared error of 0:435. Y1 - 2022 U6 - http://dx.doi.org/10.48550/arXiv.2209.04299 N1 - Proceedings of the 18th Conference on Natural Language Processing/Konferenz zur Verarbeitung natürlicher Sprache (KONVENS 2022) 12-15 September, 2022 University of Potsdam Potsdam, Germany SP - 57 EP - 62 PB - Association for Computational Linguistics CY - Potsdam ER - TY - CHAP A1 - Osterhage, Hannes A1 - Bialonski, Stephan A1 - Staniek, Matthäus A1 - Schindler, Kaspar A1 - Wagner, Tobias A1 - Elger, Christian E. A1 - Lehnertz, Klaus T1 - Bivariate and multivariate time series analysis techniques and their potential impact for seizure prediction T2 - Seizure Prediction in Epilepsy: From Basic Mechanisms to Clinical Applications Y1 - 2008 SN - 978-3-527-62519-2 U6 - http://dx.doi.org/10.1002/9783527625192.ch15 SP - 189 EP - 208 PB - Wiley-VCH CY - Weinheim ER - TY - JOUR A1 - Bialonski, Stephan A1 - Ansmann, Gerrit A1 - Kantz, Holger T1 - Data-driven prediction and prevention of extreme events in a spatially extended excitable system JF - Physical Review E Y1 - 2015 U6 - http://dx.doi.org/10.1103/PhysRevE.92.042910 SN - 2470-0053 VL - 92 IS - 4 SP - 042910 ER - TY - JOUR A1 - Bialonski, Stephan A1 - Grieger, Niklas T1 - Der KI-Chatbot ChatGPT: Eine Herausforderung für die Hochschulen JF - Die neue Hochschule N2 - Essays, Gedichte, Programmcode: ChatGPT generiert automatisch Texte auf bisher unerreicht hohem Niveau. Dieses und nachfolgende Systeme werden nicht nur die akademische Welt nachhaltig verändern. Y1 - 2023 U6 - http://dx.doi.org/10.5281/zenodo.7533758 SN - 0340-448X VL - 2023 IS - 1 SP - 24 EP - 27 PB - HLB CY - Bonn ER - TY - JOUR A1 - Allefeld, Carsten A1 - Bialonski, Stephan T1 - Detecting synchronization clusters in multivariate time series via coarse-graining of Markov chains JF - Physical Review E Y1 - 2007 U6 - http://dx.doi.org/10.1103/PhysRevE.76.066207 SN - 2470-0053 VL - 76 IS - 6 SP - 066207 ER - TY - JOUR A1 - Karnatak, Rajat A1 - Kantz, Holger A1 - Bialonski, Stephan T1 - Early warning signal for interior crises in excitable systems JF - Physical Review E Y1 - 2017 U6 - http://dx.doi.org/10.1103/PhysRevE.96.042211 SN - 2470-0053 VL - 96 IS - 4 SP - 042211 ER - TY - CHAP A1 - Lehnertz, Klaus A1 - Bialonski, Stephan A1 - Horstmann, Marie-Therese A1 - Krug, Dieter A1 - Rothkegel, Alexander A1 - Staniek, Matthäus A1 - Wagner, Tobias T1 - Epilepsy T2 - Reviews of Nonlinear Dynamics and Complexity, Volume 2 Y1 - 2010 SN - 9783527628001 U6 - http://dx.doi.org/10.1002/9783527628001.ch5 SP - 159 EP - 200 PB - Wiley-VCH ER - TY - JOUR A1 - Ngamga, Eulalie Joelle A1 - Bialonski, Stephan A1 - Marwan, Norbert A1 - Kurths, Jürgen A1 - Geier, Christian A1 - Lehnertz, Klaus T1 - Evaluation of selected recurrence measures in discriminating pre-ictal and inter-ictal periods from epileptic EEG data JF - Physics Letters A N2 - We investigate the suitability of selected measures of complexity based on recurrence quantification analysis and recurrence networks for an identification of pre-seizure states in multi-day, multi-channel, invasive electroencephalographic recordings from five epilepsy patients. We employ several statistical techniques to avoid spurious findings due to various influencing factors and due to multiple comparisons and observe precursory structures in three patients. Our findings indicate a high congruence among measures in identifying seizure precursors and emphasize the current notion of seizure generation in large-scale epileptic networks. A final judgment of the suitability for field studies, however, requires evaluation on a larger database. Y1 - 2016 U6 - http://dx.doi.org/10.1016/j.physleta.2016.02.024 SN - 0375-9601 VL - 380 IS - 16 SP - 1419 EP - 1425 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Schindler, Kaspar A. A1 - Bialonski, Stephan A1 - Horstmann, Marie-Therese A1 - Elger, Christian E. A1 - Lehnertz, Klaus T1 - Evolving functional network properties and synchronizability during human epileptic seizures JF - Chaos: An Interdisciplinary Journal of Nonlinear Science Y1 - 2008 U6 - http://dx.doi.org/10.1063/1.2966112 SN - 1089-7682 VL - 18 IS - 3 SP - 033119 ER -