Romanian Journal of Information Science and Technology (ROMJIST)

An open – access publication

  |  HOME  |   GENERAL INFORMATION  |   ROMJIST ON-LINE  |  KEY INFORMATION FOR AUTHORS  |   COMMITTEES  |  

ROMJIST is a publication of Romanian Academy,
Section for Information Science and Technology

Editor – in – Chief:
Academician Dan Dascalu

Secretariate (office):
Adriana Neagu
Adress for correspondence: romjist@nano-link.net (after 1st of January, 2019)

Editing of the printed version: Mihaela Marian (Publishing House of the Romanian Academy, Bucharest)

Technical editor
of the on-line version:
Lucian Milea (University POLITEHNICA of Bucharest)

Sponsors:
• National Institute for R & D
in Microtechnologies
(IMT Bucharest), www.imt.ro
• Association for Generic
and Industrial Technologies (ASTEGI), www.astegi.ro

ROMJIST Volume 23, No. 4, 2020, pp. 354-367, Paper no. 667/2020
 

Aman KATARIA, Smarajit GHOSH, Vinod KARAR
Data Prediction of Electromagnetic Head Tracking using Self Healing Neural Model for Head-Mounted Display

ABSTRACT: In Avionics, Helmet Mounted Display (HMD) is used by the pilot to display the synchronized view of the external environment and the vital parameters related to the aircraft on the visor. For perfect synchronization of the view on the visor, it is necessary that the coordinates of the external environment, as well as the coordinates of the head movement of the pilot, should be synchronized. To locate the coordinates of the pilots head motion, the process known as Head Tracking plays an important role. Head tracking can be performed using different tracking techniques such as Optical tracking, Magnetic tracking or Inertial tracking. In this paper, a six-degrees-of-freedom (6-DoF) magnetic motion tracking device(Polhemus PatriotTM) is used to acquire the coordinates of the pilot’s head movement in real time on the simulator bed. During acquisition process by the tracker, the data may get missed due to magnetic field interference caused by ferromagnetism. For this, a Self-Healing Neural Model (SHNM) is employed to predict the missed data. The data used for the recovery has 5200 6-DoF samples of the head movement. SHNM yields more than 85% of accuracy to predict the three different sets of missing data. The accuracy of the predicted data by the proposed model is compared with the Back Propagation Neural Network (BPNN) model and it has been observed that accuracy achieved by the SHNM model is better than the BPNN model.

KEYWORDS: Head Tracking, Neural Network, Self Healing, Recovery, Avionics

Read full text (pdf)






  |  HOME  |   GENERAL INFORMATION  |   ROMJIST ON-LINE  |  KEY INFORMATION FOR AUTHORS  |   COMMITTEES  |