Magnetic Disturbance Detection for Smartphone-based Indoor Positioning Systems with Unsupervised Learning

Research output: Contribution to journalArticlepeer-review


The smartphone magnetometer has been used in many indoor positioning systems to provide location information, such as orientation, user trajectory construction, and magnetic field-based fingerprint. However, suffering from magnetic disturbance, the magnetometer measurements are vulnerable to interference from metal infrastructures, electrical equipment, and other electronic devices in complex indoor environments. This paper extracts and explores the statistical features of the smartphone magnetometer measurements. Extensive experiments in various conditions show that the covariance and the magnitude difference can help detect the magnetic disturbance. Based on this, two unsupervised learning-based methods using Gaussian Mixture Model and k-means are developed to explore the two features mentioned above in magnetic disturbance detection. Experimental results demonstrate that the two proposed approaches have superior detection accuracy, which is 5% to 20% higher than the widely adopted vector selection methods in the literature.
Original languageEnglish
Article number2506411
Pages (from-to)1-1
Number of pages1
JournalIEEE Transactions on Instrumentation and Measurement
Early online date29 Mar 2022
Publication statusE-pub ahead of print - 29 Mar 2022


  • Magnetic field measurement
  • Magnetometers
  • Magnetic fields
  • Feature extraction
  • Magnetic devices
  • Trajectory
  • Fingerprint recognition
  • smartphone
  • magnetometer
  • Clustering
  • unsupervised learning
  • indoor positioning system
  • magnetic disturbance


Dive into the research topics of 'Magnetic Disturbance Detection for Smartphone-based Indoor Positioning Systems with Unsupervised Learning'. Together they form a unique fingerprint.

Cite this