Bionics and human-computer interfaces

Graphic of a human with an artificial arm and leg. Credit: Claus Lunau, Science Photo Library

A human-computer interface is a device that lets humans communicate control and monitor systems, using physiological signals from the brain, muscle, heart or eye movements. It measures human physiological activity and coverts it into artificial output that can be used for monitoring, replacing, restoring, enhancing, supplementing and improving the natural nervous system.

The general components of human-computer interfaces include:

  • Signal acquisition
  • Pre-processing
  • Feature extraction
  • Feature translation (classification)
  • Output of the application.

This starts with signal acquisition, using biosensors such as electroencephalogram (EEG) for brain signals, electrocardiogram (ECG) for heart signals, electrooculogram (EOG) for eye signals, electromyogram (EMG) for muscle signals and inertial measurement unit (IMU) for body movement information.

Then, a signal pre-processing module improves the signal-to-noise ratio and a feature extraction module transforms the signal into useful features. The features are processed into a feature translation algorithm and output is linked with the applications.

Our research at Swinburne covers a range of projects:

  • Brain-controlled wheelchairs
  • Driver fatigue detection
  • Rehabilitation
  • Bionic eyes
  • Brain-computer interfaces