H
Holger Junker
Researcher at ETH Zurich
Publications - 23
Citations - 2044
Holger Junker is an academic researcher from ETH Zurich. The author has contributed to research in topics: Wearable computer & Activity recognition. The author has an hindex of 17, co-authored 23 publications receiving 1950 citations. Previous affiliations of Holger Junker include École Polytechnique Fédérale de Lausanne.
Papers
More filters
Journal ArticleDOI
Gesture spotting with body-worn inertial sensors to detect user activities
TL;DR: This work presents a method for spotting sporadically occurring gestures in a continuous data stream from body-worn inertial sensors based on a natural partitioning of continuous sensor signals and uses a two-stage approach for the spotting task.
Book ChapterDOI
Recognizing Workshop Activity Using Body Worn Microphones and Accelerometers
Paul Lukowicz,Jamie A. Ward,Holger Junker,Mathias Stäger,Gerhard Tröster,Amin Atrash,Thad Starner +6 more
TL;DR: In this article, the authors presented a technique to automatically track the progress of maintenance or assembly tasks using body worn sensors based on a novel way of combining data from accelerometers with simple frequency matching sound classification.
Proceedings ArticleDOI
Detection of eating and drinking arm gestures using inertial body-worn sensors
TL;DR: A two-stage recognition system for detecting arm gestures related to human meal intake that can be used for automatic dietary monitoring in the domain of behavioural medicine is proposed and it is demonstrated that arm gestures can be clustered and detected using inertial sensors.
Proceedings ArticleDOI
Using multiple sensors for mobile sign language recognition
TL;DR: This work builds upon a constrained, lab-based Sign Language recognition system with the goal of making it a mobile assistive technology and examines using multiple sensors for disambiguation of noisy data to improve recognition accuracy.
Book ChapterDOI
Where am i: recognizing on-body positions of wearable sensors
TL;DR: In this article, the location of an acceleration sensor placed on the user's body solely based on the sensor's signal is determined by using a location and orientation invariant algorithm to identify time periods where the user is walking and then leverages the specific characteristics of walking motion to determine the position of the body-worn sensor.