Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models
Journal Title: Informatics - Year 2018, Vol 5, Issue 3
Abstract
Personal wearables such as smartphones or smartwatches are increasingly utilized in everyday life. Frequently, activity recognition is performed on these devices to estimate the current user status and trigger automated actions according to the user’s needs. In this article, we focus on the creation of a self-adaptive activity recognition system based on inertial measurement units that includes new sensors during runtime. Starting with a classifier based on Gaussian Mixture Models, the density model is adapted to new sensor data fully autonomously by issuing the marginalization property of normal distributions. To create a classifier from that, label inference is done, either based on the initial classifier or based on the training data. For evaluation, we used more than 10 h of annotated activity data from the publicly available PAMAP2 benchmark dataset. Using the data, we showed the feasibility of our approach and performed 9720 experiments, to get resilient numbers. One approach performed reasonably well, leading to a system improvement on average, with an increase in the F-score of 0.0053, while the other one shows clear drawbacks due to a high loss of information during label inference. Furthermore, a comparison with state of the art techniques shows the necessity for further experiments in this area.
Authors and Affiliations
Martin Jänicke, Bernhard Sick and Sven Tomforde
Keywords
Related Articles
- EP ID EP44145
- DOI https://doi.org/10.3390/informatics5030038
- Views 262
- Downloads 0
LabelFlow Framework for Annotating Workflow Provenance
Scientists routinely analyse and share data for others to use. Successful data (re)use relies on having metadata describing the context of analysis of data. In many disciplines the creation of contextual metadata is re...
A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment
Accurate recognition of Activities of Daily Living (ADL) plays an important role in providing assistance and support to the elderly and cognitively impaired. Current knowledge-driven and ontology-based techniques model...
Modelling Digital Knowledge Transfer: Nurse Supervisors Transforming Learning at Point of Care to Advance Nursing Practice
Limited adoption of mobile technology for informal learning and continuing professional development within Australian healthcare environments has been explained primarily as an issue of insufficient digital and ehealth...
A Data Quality Strategy to Enable FAIR, Programmatic Access across Large, Diverse Data Collections for High Performance Data Analysis
To ensure seamless, programmatic access to data for High Performance Computing (HPC) and analysis across multiple research domains, it is vital to have a methodology for standardization of both data and services. At th...
Exploiting Rating Abstention Intervals for Addressing Concept Drift in Social Network Recommender Systems
One of the major problems that social networks face is the continuous production of successful, user-targeted information in the form of recommendations, which are produced exploiting technology from the field of recom...