FPGA Implementation of FastICA Algorithm for On-line EEG Signal Separation

Zhao, Dongsheng; Jiang, Jiang; Wang, Chang; Lu, Bao-Liang; Zhu, Yongxin

doi:10.1007/978-3-662-45815-0_6

Cited by 5 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a divider and a square root circuit to perform all the operations of FastICA can save hardware resources but speed performance cannot be achieved in such cases as in [12]. In [50] a System on Chip (SoC, programable logic along with an Arm processor) is used for [51] (2011) [33] (2014) [10] (2015) [53] (2015) [11] (2015) [52] (2016) [12] (2018) [50] (2019) [54] (2019) [39] (2020) [20] This Work implementing these operations. In [51] no hardware utilization or power consumption is reported so we cannot have a fair comparison.…”

Section: Comparing Design Parametersmentioning

confidence: 99%

“…Although non-scalable implementations can be better optimized compared to scalable implementations but adapting them to changing dimensionality needs a redesign. In [53] a high-speed scalable implementation is reported for a Virtex-6 device. These devices are high performance but have large packaging sizes and high cost.…”

Section: E Comparing Commercial Aspectsmentioning

confidence: 99%

“…They are combinational circuits and the amount and direction of the shifts are determined by the signed integer at the selection input of the circuit. The encoders represent the signed priority encoders [53] (2015) [52] (2020) [20]…”

Section: F Hardware Saving By the Spamentioning

confidence: 99%

See 2 more Smart Citations

An Efficient VLSI Architecture for FastICA by Using the Algebraic Jacobi Method for EVD

et al. 2021

View full text Add to dashboard Cite

Blind source separation (BSS) is a problem that appears in many research fields. Fast Independent components analysis (FastICA) is one of the techniques to solve the problem. The researchers have verified the effectiveness of the technique through the offline analysis of the public datasets. The development of a real-time portable system involving such a computationally complex analysis requires an efficient hardware implementation of FastICA. A Field programmable gate array (FPGA) and an applicationspecific integrated circuit (ASIC) are two promising hardware platforms to implement FastICA. This work proposes a new method, called ALgebraic Jacobi Method (ALJM), for performing eigenvalue decomposition (EVD) required for the implementation of FastICA. We use a simplification, a polynomial approximation, and the Newton-Raphson method for calculating the Jacobi rotation. In this way, we ensure hardware reusability between the EVD stage and the weight vector estimation (WVE) stage of FastICA which reduces the computational complexity and the power consumption, without compromising its computation speed. We evaluate the ALJM-based FastICA by performing BSS on the linear mixtures of the deterministic and the random signals and comparing the performance results with the existing methods. After verifying its functionality and numerical stability, we propose a scalable systolic processing array (SPA) for the ALJMbased FastICA and implement it on Spartan-6 FPGA. By comparing the existing implementations of FastICA, in terms of speed, area, and power, we conclude that the ALJM-based FastICA is one of the most efficient methods for prototyping and commercializing a real-time portable system comprising FastICA.

show abstract

Section: Comparing Design Parametersmentioning

confidence: 99%

Section: E Comparing Commercial Aspectsmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient VLSI Architecture for FastICA by Using the Algebraic Jacobi Method for EVD

et al. 2021

View full text Add to dashboard Cite

show abstract

“…FastICA is a much mature algorithm developed from blind source technology. FastICA simplifies the problem and operation which greatly improves the work efficiency, it is widely used in the analysis and processing of EEG [14,15].The structure between the interical and preictal data are different which means that the source signal components are also different,so it will be possible to distinguish between the interical and preictal data by FastICA. FastICA algorithm has many forms like basing on maximum likelihood estimation, negative entropy and so on.…”

Section: Fastica Algorithmmentioning

confidence: 99%

Extraction and Analysis of Independent Components in Interictal and Preictal Data

2017

2017 6th International Conference on Advanced Materials and Computer Science (ICAMCS 2017)

View full text Add to dashboard Cite

“…Independent component analysis (ICA) is a method for separating data into underlying informal components [9]. It is one of the techniques to solve blind source separation (BSS) problems [22], [23] in many fields including biomedical data processing [7], [24], [25], speech [26], or image [27]. In BSS, the measured signals are separated into its underlying sources without any prior knowledge about the source signals and the mixing system.…”

Section: Data Decompositionmentioning

confidence: 99%

Model-Driven Development Methodology Applied to Real-Time MEG Signal Preprocessing System Design

Chen

Suslov

Schiek

et al. 2017

2017 European Modelling Symposium (EMS)

View full text Add to dashboard Cite

FPGA Implementation of FastICA Algorithm for On-line EEG Signal Separation

Cited by 5 publications

References 9 publications

An Efficient VLSI Architecture for FastICA by Using the Algebraic Jacobi Method for EVD

An Efficient VLSI Architecture for FastICA by Using the Algebraic Jacobi Method for EVD

Extraction and Analysis of Independent Components in Interictal and Preictal Data

Model-Driven Development Methodology Applied to Real-Time MEG Signal Preprocessing System Design

Contact Info

Product

Resources

About