Quality-on-Demand Compression of EEG Signals for Telemedicine Applications Using Neural Network Predictors
2011

Quality-on-Demand Compression of EEG Signals for Telemedicine

publication Evidence: moderate

Author Information

Author(s): Sriraam N.

Primary Institution: Center for Biomedical Informatics and Signal Processing, Department of Biomedical Engineering, SSN College of Engineering, Chennai, India

Hypothesis

Can neural network predictors achieve better compression of EEG signals while preserving clinical information?

Conclusion

The study found that a two-stage compression scheme using neural network predictors yields better compression results while maintaining the quality of the reconstructed EEG signals.

Supporting Evidence

  • The study compared three neural network models and found that the single-layer perceptron performed best.
  • Compression efficiency improved with higher quantization levels.
  • The fidelity of the reconstructed EEG signal was assessed using parameters like PRD and SNR.

Takeaway

This study shows how we can make brain wave signals smaller so they can be sent over the internet without losing important information.

Methodology

The study used a two-stage compression scheme with neural network predictors and an entropy encoder to compress EEG signals.

Digital Object Identifier (DOI)

10.1155/2011/860549

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication