Hidden Markov Model-Based Smart Annotation for Benchmark Cyclic Activity Recognition Database Using Wearables

• Published in: Sensors (Basel, Switzerland) Vol. 19; no. 8; p. 1820
• Main Authors: Martindale, Christine F., Sprager, Sebastijan, Eskofier, Bjoern M.
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI 16.04.2019; MDPI AG
• Subjects: activity recognition; benchmark database; cyclic activities; gait analysis; gait phases; home monitoring; inertial measurement unit; semi-supervised learning; smart annotation; inertial measurement unit; home monitoring; cyclic activities; benchmark database; semi-supervised learning; gait phases; smart annotation; gait analysis; activity recognition
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s19081820

Activity monitoring using wearables is becoming ubiquitous, although accurate cycle level analysis, such as step-counting and gait analysis, are limited by a lack of realistic and labeled datasets. The effort required to obtain and annotate such datasets is massive, therefore we propose a smart annotation pipeline which reduces the number of events needing manual adjustment to 14%. For scenarios dominated by walking, this annotation effort is as low as 8%. The pipeline consists of three smart annotation approaches, namely edge detection of the pressure data, local cyclicity estimation, and iteratively trained hierarchical hidden Markov models. Using this pipeline, we have collected and labeled a dataset with over 150,000 labeled cycles, each with 2 phases, from 80 subjects, which we have made publicly available. The dataset consists of 12 different task-driven activities, 10 of which are cyclic. These activities include not only straight and steady-state motions, but also transitions, different ranges of bouts, and changing directions. Each participant wore 5 synchronized inertial measurement units (IMUs) on the wrists, shoes, and in a pocket, as well as pressure insoles and video. We believe that this dataset and smart annotation pipeline are a good basis for creating a benchmark dataset for validation of other semi- and unsupervised algorithms.