/spl alpha/-EM algorithm and /spl alpha/-ICA learning based upon extended logarithmic information measures

Mtsuyama, Y.; Nimoto, T.; Katsumata, N; Suzuki, Yusuke; Furukawa, Satoshi

doi:10.1109/ijcnn.2000.861329

Cited by 6 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the computation complexities and convergence rates, many ICA implementations are slow processes. Researchers have proposed various algorithms to speed up the ICA-related processing using two methods, either introducing nonlinear learning parameters in ICA estimation processes and objective functions to improve the convergence rate, 5,6 or combining the ICA process with other pre-processing methods to share the computation burden. 7, 8 Hyvärunen 2 developed the FastICA algorithm, which was claimed to be a computationally very efficient practical ICA method.…”

Section: Introductionmentioning

confidence: 99%

Parallel ICA and its hardware implementation in hyperspectral image analysis

Peterson

2004

SPIE Proceedings

View full text Add to dashboard Cite

Advances in hyperspectral images have dramatically boosted remote sensing applications by providing abundant information using hundreds of contiguous spectral bands. However, the high volume of information also results in excessive computation burden. Since most materials have specific characteristics only at certain bands, a lot of these information is redundant. This property of hyperspectral images has motivated many researchers to study various dimensionality reduction algorithms, including Projection Pursuit (PP), Principal Component Analysis (PCA), wavelet transform, and Independent Component Analysis (ICA), where ICA is one of the most popular techniques. It searches for a linear or nonlinear transformation which minimizes the statistical dependence between spectral bands. Through this process, ICA can eliminate superfluous but retain practical information given only the observations of hyperspectral images. One hurdle of applying ICA in hyperspectral image (HSI) analysis, however, is its long computation time, especially for high volume hyperspectral data sets. Even the most efficient method, FastICA, is a very time-consuming process. In this paper, we present a parallel ICA (pICA) algorithm derived from FastICA. During the unmixing process, pICA divides the estimation of weight matrix into sub-processes which can be conducted in parallel on multiple processors. The decorrelation process is decomposed into the internal decorrelation and the external decorrelation, which perform weight vector decorrelations within individual processors and between cooperative processors, respectively. In order to further improve the performance of pICA, we seek hardware solutions in the implementation of pICA. Until now, there are very few hardware designs for ICA-related processes due to the complicated and iterant computation. This paper discusses capacity limitation of FPGA implementations for pICA in HSI analysis. A synthesis of Application-Specific Integrated Circuit (ASIC) is designed for pICA-based dimensionality reduction in HSI analysis. The pICA design is implemented using standard-height cells and aimed at TSMC 0.18 micron process. During the synthesis procedure, three ICA-related reconfigurable components are developed for the reuse and retargeting purpose. Preliminary results show that the standard-height cell based ASIC synthesis provide an effective solution for pICA and ICA-related processes in HSI analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Parallel ICA and its hardware implementation in hyperspectral image analysis

Peterson

2004

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…In many cases, using the nonlinear or adaptive learning parameter is computationally efficient in the improvement of the convergence speed. In 2000, for example, Matsuyama et al [10] presented an α-ICA algorithm that used the α-logarithm to speedup the convergence of ICA process. In 2003, Lou and Zhang [9] introduced the so-called fuzzy inference system (FIS) to the ICA-based neural network.…”

Section: Introductionmentioning

confidence: 99%