CCNP Wireless 642-747 IUWMS Summary Notes 6 : Location Tracking Techniques – Pattern Recognition

This technique is based on sampling and recording radio signal behaviour patterns in specific areas.

Commercial solutions usually base the signature on RSSI but it can also use ToA, AoA and TDoA based RF signatures.

Deployment of these systems is based on  2 phases:

  1. Calibration phase
    • A walk around is done with a mobile device and the receiving sensors (APs) sample the RSS of the device ( network side implementation of location tracking).
      • At each sample location, an array of RSS values is recorded into the database (radio map or training set). The size of the location vector (array) depends on the number of APs that receive the signal). Signal of the device during sampling varies due to fading and this variation needs to be accounted for during calculations depending on the technique.
      • The RSS of the device is used to determine the location vector.                    2015-03-04 00_25_06-Untitled - Paint
  2. Operation phase
    • The solutions rely on the ability to match the reported RF signature of the tracked device against the database of the RF signatures from the calibration phase.


  1. It does not require specialized hardware in either mobile device or receiving sensor ( but RTLS requires proprietary RFID tags and sofware on each client device to enable client side reporting of RSSI to it’s positioning server.
  2. Can be implemented totally on software hence reduced complexity and costs

Assumptions made with this technique:

  1. Each floor or subsection has a unique signal propagation characteristics
  2. Each potential device location has a distinct RF signature

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s