English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Indoor Positioning Systems (IPS) gained importance in many industrialapplications. State-of-the-art solutions heavily rely on externalinfrastructures and are subject to potential privacy compromises, externalinformation requirements, and assumptions, that make it unfavorable forenvironments demanding privacy and prolonged functionality. In certainenvironments deploying supplementary infrastructures for indoor positioningcould be infeasible and expensive. Recent developments in machine learning (ML)offer solutions to address these limitations relying only on the data fromonboard sensors of IoT devices. However, it is unclear which model fits bestconsidering the resource constraints of IoT devices. This paper presents amachine learning-based indoor positioning system, using motion and ambientsensors, to localize a moving entity in privacy concerned factory environments.The problem is formulated as a multivariate time series classification (MTSC)and a comparative analysis of different machine learning models is conducted inorder to address it. We introduce a novel time series dataset emulating theassembly lines of a factory. This dataset is utilized to assess and compare theselected models in terms of accuracy, memory footprint and inference speed. Theresults illustrate that all evaluated models can achieve accuracies above 80 %.CNN-1D shows the most balanced performance, followed by MLP. DT was found tohave the lowest memory footprint and inference latency, indicating itspotential for a deployment in real-world scenarios.

Machine Learning-based Positioning using Multivariate Time Series Classification for Factory Environments