News

Detecting Mistakes in CPR Training with Multimodal Data and Neural Networks

Detecting Mistakes in CPR Training with Multimodal Data and Neural Networks

Open access, Publication
This study investigated to what extent multimodal data can be used to detect mistakes during Cardiopulmonary Resuscitation (CPR) training. We complemented the Laerdal QCPR ResusciAnne manikin with the Multimodal Tutor for CPR, a multi-sensor system consisting of a Microsoft Kinect for tracking body position and a Myo armband for collecting electromyogram information. We collected multimodal data from 11 medical students, each of them performing two sessions of two-minute chest compressions (CCs). We gathered in total 5254 CCs that were all labelled according to five performance indicators, corresponding to common CPR training mistakes. Three out of five indicators, CC rate, CC depth and CC release, were assessed automatically by the ReusciAnne manikin. The remaining two, related to arms and body position, were annotated manually by the research team. We trained five…
Read More
Workshop Trusted Learning Analytics

Workshop Trusted Learning Analytics

Workshop
Im Rahmen des hessischen Projekts Digital gestütztes Lehren und Lernen in Hessen (digLL) hat das Innovationsforum Trusted Learning Analytics (TLA) am 1. Juli 2019 einen Workshop im Hause des DIPF | Leibniz-Institut für Bildungsforschung und Bildungsinformation durchgeführt. Elf Teilnehmer aus sechs hessischen Hochschulen und der zentralen digLL-Servicestelle haben intensiv über Möglichkeiten und Hindernisse einer Einführung von Learning Analytics an hessischen Hochschulen diskutiert. Schnell ist deutlich geworden, dass sowohl bei Lehrenden als auch bei Lernenden ein großes Interesse an den Möglichkeiten von Learning Analytics besteht, die Vorbehalte gegenüber einer breiten Datensammlung und -auswertung aber mindestens genauso groß sind. Dementsprechend ist die Einstellung der Datenschutzbeauftragten der Hochschulen gegenüber solcher Vorhaben sehr zurückhaltend bis ablehnend. Da die Teilnehmer des Workshops diese Einstellung teilen, wurde besprochen, wie datenschutzgerechtes und somit eine Trusted Form von Learning Analytics gestaltet werden…
Read More
DIPF & CEL Innovation Room #13: Learning Analytics in Higher Education

DIPF & CEL Innovation Room #13: Learning Analytics in Higher Education

Keynote, Workshop
On 8 April we contributed to the CEL 13th Innovation Room on Learning Analytics; an afternoon focusing on the topic of Learning Analytics. Prof. Dr. Marcus Specht, head of CEL, TU Delft kicked off the innovation room with a welcome and overview of the programme. Hendrik Drachsler, Professor of Educational Technologies and Learning Analytics, followed with a keynote on Tangible Trusted Learning Analytics. Interactive workshops followed the keynote. Participants could choose one workshop out of four, all exploring a different side of Learning Analytics. After thr coffee break the afternoon was wrapped up with a panel discussion about the Future of Learning Analytics. Marcus Specht moderated this interesting discussion with Claudia Hauff (Associate Prof., EEMCS TU Delft), Tinne de Laet (Associate Prof., Engineering Science KU Leuven), Heather Hamilton (Brightspace), Willem van…
Read More

SCRUM Workshop 5

Workshop
In April, the ET team held workshops on the SCRUM method at the Fürstenbergerschule in Frankfurt and at the AGORA Reform School in Roermond, the Netherlands. SCRUM is a process model for project and product management, especially for agile software development.
Read More
New team member

New team member

Team
Dr. Oliver Schneider joined us in the project Innovationsforum Trusted Learning Analytics funded by the DigLL project. Before he had a chair on Multimedia-Technologie, at the University of applied science in Darmstadt, Germany. His main subjects are: Multimediatechnics Web-Applikationen Social Media and Learning Management Systeme
Read More
Chinese-German Center for the Promotion of Science: Project Consulting

Chinese-German Center for the Promotion of Science: Project Consulting

Conference, Keynote, Project
As part of the CDZ-funded project "Intercultural Perspectives on CI-supported Educational Technologies", Hendrik Drachsler travelled to Wuhan, China from the 25th of March 2019 to the 29th of March 2019, together with representatives of the HU Berlin. He is involved in the project as a consulting expert. The aim is to submit an application for learning analysis together with China and the DFG by the end of the year.
Read More
Best Demo Award at LAK19

Best Demo Award at LAK19

Team
Jan Schneider und Hendrik Drachsler wurden auf der neunten International Learning Analytics and Knowledge Conference in den USA (siehe „Neues aus den Abteilungen“) gemeinsam mit Daniele Di Mitri von der Open University of the Netherlands (links) mit dem „Best Demonstration Award ausgezeichnet“ – für ihre Präsentation „Multimodal Tutor Builder Kit“.
Read More
Profiling sympathetic arousal in a physics course: How active are students?

Profiling sympathetic arousal in a physics course: How active are students?

Publication
Pijeira-Díaz, H.J., Drachsler, H., Kirschner, P.A. & Järvelä, S. (2018). Profiling sympathetic arousal in a physics course: How active are students? Journal of Computer Assisted Learning Abstract Low arousal states (especially boredom) have been shown to be more deleterious to learning than high arousal states, though the latter have received much more attention (e.g., test anxiety, confusion, and frustration). Aiming at profiling arousal in the classroom (how active students are) and examining how activation levels relate to achievement, we studied sympathetic arousal during two runs of an elective advanced physics course in a real classroom setting, including the course exam. Participants were high school students (N = 24) who were randomly selected from the course population. Arousal was indexed from electrodermal activity, measured unobtrusively via the Empatica E4 wristband. Low arousal was the level…
Read More
Read Between the Lines: An Annotation Tool for Multimedia Data for Learning

Read Between the Lines: An Annotation Tool for Multimedia Data for Learning

Open access, Publication
DiMitri, D., Schneider, J., Klemke, R., Specht, M. & Drachsler, H. (2019). Read Between the Lines: An Annotation Tool for Multimodal Data for Learning. In: Proceedings of International Conference on Learning Analytics and Knowledge, Arizona, US, March 7–9, 2019 (LAK ’19). This paper introduces the Visual Inspection Tool (VIT) which supports researchers in the annotation of multimodal data as well as the processing and exploitation for learning purposes. While most of the existing Multimodal Learning Analytics (MMLA) solutions are tailor-made for specific learning tasks and sensors, the VIT addresses the data annotation for different types of learning tasks that can be captured with a customisable set of sensors in a flexible way. The VIT supports MMLA researchers in 1) triangulating multimodal data with video recordings; 2) segmenting the multimodal data into…
Read More