A Deep Neural Network-Based Permanent Magnet Localization for Tongue Tracking

• Published in: IEEE sensors journal 2019-10, Vol.19 (20), p.9324-9331
• Main Authors: Sebkhi, Nordine, Sahadat, Nazmus, Hersek, Sinan, Bhavsar, Arpan, Siahpoushan, Shayan, Ghoovanloo, Maysam, Inan, Omer T.
• Format: Article
• Language: English
• Subjects: Algorithm; articulograph; Artificial neural networks; biomedical device; Datasets; deep learning; Iterative algorithms; Iterative methods; Localization; Machine learning; Magnetic recording; Magnetic resonance imaging; Magnetometers; motion tracking; neural network; Neural networks; nonlinear optimization; Parameter sensitivity; permanent magnet localization; Permanent magnets; Sensors; speech; Tongue; tongue tracking; Tracking; Tracking systems; Two dimensional displays; wearable
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2019.2923585

Permanent magnet localization (PML) is a nascent method of wireless motion tracking that can estimate the 5D state (3D position and 2D orientation) of a cylindrical magnet from its magnetic field. PML is well suited for applications where a wireless tracking is crucial, and in particular for tongue motion which opens up many new interesting applications. To allow its usage outside of a research lab, our tongue tracking system relies on the PML to avoid impeding tongue's natural motion due to its wireless tracking method and ensure safe use inside the mouth. Our tracking module is embedded in a headset to be portable and simple to use while being affordable by relying on the mass-produced components. The classical implementation of PML has many shortcomings that limit its practicality for real-world applications because it is computationally intensive due to its iterative algorithm, subject to local minimum convergence issues, and sensitive to its initial state and calibration parameters. Additionally, its physical model is an approximation that is only valid in limited tracking conditions. In this paper, we investigated the potential of deep learning to create a PML model for tongue tracking by training a feedforward neural network (3 layers, 100 neurons per layer) on a dataset composed of ∼1.7 million states spanning a volume of 10\times 10\times 10 cm 3 . Our PML was validated on 337 000 states in a 4\times 6\times 7 cm 3 volume and tested on 100 000 samples emulating a more natural tongue motion with curves and twists. A fully automated 5D positional stage was engineered by our team to collect these large datasets of the 5D magnet states. Our PML prediction, limited to the magnet's 3D positions in this paper, reaches positional errors of 1.4 mm (median) and 1.8 mm (Q3).