Quantum Neural Network-Based EEG Filtering for a Brain-Computer Interface

• Published in: IEEE transaction on neural networks and learning systems Vol. 25; no. 2; pp. 278 - 288
• Main Authors: Gandhi, Vaibhav, Prasad, Girijesh, Coyle, Damien, Behera, Laxmidhar, McGinnity, Thomas Martin
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.02.2014; Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Biological and medical sciences; Brain - physiology; Brain modeling; Brain Waves - physiology; Brain-computer interface (BCI); Brain-Computer Interfaces; Classical and quantum physics: mechanics and fields; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Connectionism. Neural networks; Electrodiagnosis. Electric activity recording; electroencephalogram (EEG); Electroencephalography; Exact sciences and technology; Feature extraction; Humans; Investigative techniques, diagnostic techniques (general aspects); Lattices; Medical sciences; Nervous system; Neural Networks (Computer); Neurons; Noise; Physics; Potential energy; Quantum computation; Quantum information; recurrent quantum neural network (RQNN); Signal Processing, Computer-Assisted; Software; Signal estimation; Brain-computer interface (BCI); Electroencephalography; Unsupervised classification; Wave packets; Quantum computing; Filters; Cerebrum; Swarm intelligence; Modelling; Stochastic signal; Pattern extraction; Quantum communication; Recurrent neural nets; Statistical analysis; Filtering; Probabilistic approach; Wave equations; Signal-to-noise ratio; Non stationary condition; Pattern recognition; Particle swarm optimization; Time-varying systems; Unsupervised learning; electroencephalogram (EEG); Neural networks; recurrent quantum neural network (RQNN); User interfaces; Feature extraction; Schroedinger equation; Signal analysis
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2013.2274436

A novel neural information processing architecture inspired by quantum mechanics and incorporating the well-known Schrodinger wave equation is proposed in this paper. The proposed architecture referred to as recurrent quantum neural network (RQNN) can characterize a nonstationary stochastic signal as time-varying wave packets. A robust unsupervised learning algorithm enables the RQNN to effectively capture the statistical behavior of the input signal and facilitates the estimation of signal embedded in noise with unknown characteristics. The results from a number of benchmark tests show that simple signals such as dc, staircase dc, and sinusoidal signals embedded within high noise can be accurately filtered and particle swarm optimization can be employed to select model parameters. The RQNN filtering procedure is applied in a two-class motor imagery-based brain-computer interface where the objective was to filter electroencephalogram (EEG) signals before feature extraction and classification to increase signal separability. A two-step inner-outer fivefold cross-validation approach is utilized to select the algorithm parameters subject-specifically for nine subjects. It is shown that the subject-specific RQNN EEG filtering significantly improves brain-computer interface performance compared to using only the raw EEG or Savitzky-Golay filtered EEG across multiple sessions.