Neural Network Based Near- Lossless Compression of EEG Signals with Non Uniform Quantization

Abstract

Efficient compression technique is highly essential for the transmission and storage of large amount of biomedical signals. In this paper, a near- lossless scheme for the compression of EEG signals using artificial neural networks is proposed. The error (residue) signals which is obtained due to the difference between the original and the predicted EEG signals are thresolded based on a term referred as absolute error limit (AEL) such that, any error samples above the limit require more number of bits than the samples below the limit that require less number of bits. The thresholded error samples are quantized in a non-uniform manner by varying the actual bits assigned to the error samples. An arithmetic encoder is further used to improve the compression efficiency. Three adaptive neural network models, namely, single and multilayer perceptrons and Elman neural network and two classical adaptive predictors such as autoregressive model(AR) and normalized least mean-square FIR filter are used. EEG signals recorded under different physiological conditions are considered and the performance of the proposed scheme is evaluated in terms of compression ratio and the fidelity parameter, percent of root-mean-square-difference (PRD). It is found from the experimental results that the variation of error limit and quantization step decides the overall compression performance. Single- layer perceptron yields the best compression results in terms of utilizing less bit rate as well achieving low PRD values compared to other predictors.

A novel approach using WAAVES coder for the EEG signal compression

“…But before, EEG signals have to satisfy several criteria: 1) Each Signal from all the multichannel EEG signals must be statistically independent. Correlation dimension based lossless compression of EEG signals 3.20 N/A Lossy [6] Wavelets packets decomposition 9.13 PRD = 5.25 [7] Matrix and tensor decompositions 12.13 PRD = 5.40 [8] Neural network predictor and AC 6.50 PRD = 7 [9] Compressing sensing preceded by ICA 15.00 PRD = 10.95 [10] Pre-Processing of Multi-Channel EEG and SPIHT 5.00 PRD = 7 [11] PCA, ICA and 1D-SPIHT 29.44 PRD = 7.73…”

Compressive Sampling of EEG Signals with Finite Rate of Innovation

“…In order to understand the local distortions between the original and the reconstructed signals, two metrics, the maximum error (MAXERR) and the peak amplitude related error (PARE) [19], will be computed. The maximum error metric is defined as MAXERR = max x orig − x recon (9) and it shows how large the error is between every sample of the original and reconstructed signals. This metric should ideally be small if both signals are similar.…”

“…Nielsen et al proposed a signal-dependent wavelet compression scheme that adapted optimal wavelets to biomedical signals for compression [8]. A near-lossless 2 EURASIP Journal on Advances in Signal Processing compression method described in [9] compressed EEG signals using neural network predictors followed by nonuniform quantization. More recently, a new compression method based on the construction process of the classified signature and envelop vector sets of the EEG signals [4].…”

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

“…A context-based error model using linear and neural network predictors has shown the removal of offset bias for attaining some improvement in compression efficiency [ 6 , 12 ]. The effect of uniform quantization and nonuniform quantization on compression gain using the near-lossless compression of EEG signals has been reported in [ 6 , 13 , 14 ]. Gopikrishna and Makur proposed a near-lossless compression scheme using wavelets and ARX model [ 15 ].…”