Machine learning-based positioning using multivariate time series classification for factory environments

Article Number
9
Citation
Smart and Sustainable Applications. - Oklahoma City, USA, 2024. -(Chronicle of Computing)
Publisher DOI
10.55432/978-1-6692-0005-5_9
Publisher
Oklahoma International Publishing
ISBN
978-1-6692-0005-5
978-1-6692-0006-2
Indoor Positioning Systems have gained significance in numerous industrial applications. While state-of-the-art solutions are accurate, their reliance on external infrastructures can lead to considerable costs, deployment complexities, and privacy concerns, making them suboptimal for specific contexts. Recent advancements in machine learning have surfaced as a potential solution, leveraging data solely from onboard IoT sensors. Nonetheless, the optimal machine learning models for IoT's resource constraints remain uncertain. This research introduces an indoor positioning system using motion and ambient sensors tailored for factories and similar settings with predetermined paths. The problem is framed as multivariate time series classification, comparing various ML models. A novel dataset simulating factory assembly lines is utilized for evaluation. Results demonstrate models achieving over 80% accuracy, with 1 Dimensional-Convolutional Neural Networks showing the most balanced performance followed by Multilayer Perceptrons, considering accuracy, memory footprint and latency. Decision Trees exhibit the lowest memory footprint and latency, rendering its potential for practical implementation.
Subjects
Indoor positioning
Machine learning
Sensor fusion
Multivariate time series classification
DDC Class
620: Engineering
621: Applied Physics
004: Computer Sciences