Next Article in Journal
A Recommender System for Programming Online Judges Using Fuzzy Information Modeling
Next Article in Special Issue
Recognition of Physical Activities from a Single Arm-Worn Accelerometer: A Multiway Approach
Previous Article in Journal
A Smart Sensor Data Transmission Technique for Logistics and Intelligent Transportation Systems
Previous Article in Special Issue
A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment
Article Menu

Export Article

Open AccessArticle
Informatics 2018, 5(2), 16; https://doi.org/10.3390/informatics5020016

Detecting Transitions in Manual Tasks from Wearables: An Unsupervised Labeling Approach

1
Epilepsy Center, Department of Neurosurgery, Medical Center—University of Freiburg, 79106 Freiburg, Germany
2
Embedded Systems Group, Computer Science Institute, University of Freiburg, 79110 Freiburg, Germany
3
Ubiquitous Computing Group, Faculty of Science and Technology, University of Siegen, 57076 Siegen, Germany
This article is an expanded version of the original conference paper [1] and includes a new, in-depth review of related work, as well as additional classification results for some supervised methods on the same datasets and a performance comparison of all methods.
*
Author to whom correspondence should be addressed.
Received: 28 February 2018 / Revised: 23 March 2018 / Accepted: 26 March 2018 / Published: 29 March 2018
(This article belongs to the Special Issue Sensor-Based Activity Recognition and Interaction)
Full-Text   |   PDF [5859 KB, uploaded 3 May 2018]   |  

Abstract

Authoring protocols for manual tasks such as following recipes, manufacturing processes or laboratory experiments requires significant effort. This paper presents a system that estimates individual procedure transitions from the user’s physical movement and gestures recorded with inertial motion sensors. Combined with egocentric or external video recordings, this facilitates efficient review and annotation of video databases. We investigate different clustering algorithms on wearable inertial sensor data recorded on par with video data, to automatically create transition marks between task steps. The goal is to match these marks to the transitions given in a description of the workflow, thus creating navigation cues to browse video repositories of manual work. To evaluate the performance of unsupervised algorithms, the automatically-generated marks are compared to human expert-created labels on two publicly-available datasets. Additionally, we tested the approach on a novel dataset in a manufacturing lab environment, describing an existing sequential manufacturing process. The results from selected clustering methods are also compared to some supervised methods. View Full-Text
Keywords: human activity recognition; authoring; guidance; manual workflows; laboratory processes human activity recognition; authoring; guidance; manual workflows; laboratory processes
Figures

Graphical abstract

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Böttcher, S.; Scholl, P.M.; Van Laerhoven, K. Detecting Transitions in Manual Tasks from Wearables: An Unsupervised Labeling Approach. Informatics 2018, 5, 16.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Informatics EISSN 2227-9709 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top