Compressive Sensing of Multichannel EEG Signals Based on Graph Fourier Transform and Cosparsity
- 35 Downloads
Cosparsity as a useful prior has been extensively applied in accurate compressive sensing (CS) recovery of multichannel electroencephalogram (EEG) signals from only a few measurements. Latest studies proved that exploiting cosparsity and channel correlation in a unified framework can obtain accurate recovery results. However, all these methods ignore the adjacent relationship between the real physical electrodes and exploit the inaccurate channel correlation. Another problem is that most methods employ convex regularizations to exploit cosparsity and channel correlation, which cannot obtain competitive results. In this paper, a novel graph Fourier transform and nonconvex optimization (GFTN)-based method is proposed to enforce inherent correlation across different channels and cosparsity. Alternative direction method of multipliers is used to solve the resulting nonconvex optimization problem. Experiments show that GFTN can remarkably improve the performance of CS recovery for multichannel EEG signals.
KeywordsCompressive sensing Multichannel EEG signals Cosparsity Graph Fourier transform Alternative direction method of multipliers
The authors would like to express their gratitude to the anonymous referees as well as the Editor and Associate Editor for their valuable comments, which led to substantial improvements of the paper. This work was supported by the National Natural Science Foundation of China (Nos. 61772272 and 61801199), the Natural Science Fund Project of Colleges in Jiangsu Province (No. 18KJB520017) and the High-level Talent Scientific Research Foundation of Jinling Institute of Technology (No. jit-b-201801).
- 5.Chartrand R, Yin W (2008) Iteratively reweighted algorithms for compressive sensing. In: IEEE international conference on acoustics, speech & signal processing, pp 3869–3872Google Scholar
- 9.Higashi H, Tanaka T, Tanaka Y (2015) Smoothing of spatial filter by graph Fourier transform for eeg signals. In: Asia-Pacific signal and information processing association, 2014 summit and conferenceGoogle Scholar
- 10.Hooda A, Sharma S (2013) Wireless body area network. In: Proceedings of international symposium on medical information & communication technology, vol 3, no 3, pp 203–210Google Scholar
- 11.Hosseini Kamal M, Shoaran M, Leblebici Y, Schmid A (2013) Compressive multichannel cortical signal recording. In: IEEE international conference on acoustics, speech & signal processing, pp 4305–4309Google Scholar
- 18.Shu X, Yang J, Ahuja N (2014) Non-local compressive sampling recovery. In: International conference on computational photography, pp 1–8Google Scholar
- 23.Xie Y (2015) Weighted schatten $p$-norm minimization for image denoising with local and nonlocal regularization. Eprint ArxivGoogle Scholar