FCA: The Fractional Component Analysis

The goal of the ``Fractional component analysis'' proposed in this paper is to analyze the observed signal generated by the linear mixing process of unknown fractional component signals. Based on simple assumptions on the probability distributions of component signals and mixing fractions, we derive a new type of distribution, which we call ``mixed distribution,'' and characterize this model in terms of moments and cumulants. Its higher-order cumulants indicate that it is in fact either super-gaussian or sub-gaussian even if the distribution of component signals are gaussian. Finally we show methods for recovering fractional components from the observed signal.

文献情報

Asanobu KITAMOTO, "FCA: The Fractional Component Analysis", 第4回情報論的学習理論ワークショップ (IBIS 2001), pp. 297-302, 2001年08月 (in English)

BibTeX フォーマット

@InProceedings{ k:ibis01,
	author = {Asanobu KITAMOTO},
	title = {FCA: The Fractional Component Analysis},
	booktitle = {第4回情報論的学習理論ワークショップ (IBIS 2001)},
	pages = {297-302},
	year = 2001,
	month = 08,
	note = { (in English)},
}

予稿集の論文では、印刷時の不具合により、マイナス記号等の数学記号が多数抜け落ちています。ダウンロード版ではその不具合を修正しました。

関連資料・関連ウェブサイト

サイト内関連ページ

| リンク 1 |