TWI456516B - 獨立成分分析處理器 - Google Patents

獨立成分分析處理器 Download PDF

Info

Publication number
TWI456516B
TWI456516B TW099144420A TW99144420A TWI456516B TW I456516 B TWI456516 B TW I456516B TW 099144420 A TW099144420 A TW 099144420A TW 99144420 A TW99144420 A TW 99144420A TW I456516 B TWI456516 B TW I456516B
Authority
TW
Taiwan
Prior art keywords
unit
ica
initial data
matrix
independent component
Prior art date
Application number
TW099144420A
Other languages
English (en)
Other versions
TW201227544A (en
Inventor
Chiu Kuo Chen
Wai Chi Fang
Ericson Chua
Chih Chung Fu
Shao Yen Tseng
Original Assignee
Univ Nat Chiao Tung
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Univ Nat Chiao Tung filed Critical Univ Nat Chiao Tung
Priority to TW099144420A priority Critical patent/TWI456516B/zh
Priority to US13/149,323 priority patent/US9031816B2/en
Publication of TW201227544A publication Critical patent/TW201227544A/zh
Application granted granted Critical
Publication of TWI456516B publication Critical patent/TWI456516B/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2134Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis
    • G06F18/21342Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis using statistical independence, i.e. minimising mutual information or maximising non-gaussianity
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/94Hardware or software architectures specially adapted for image or video understanding
    • G06V10/955Hardware or software architectures specially adapted for image or video understanding using specific electronic processors
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00Aspects of pattern recognition specially adapted for signal processing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Complex Calculations (AREA)

Claims (11)

  1. 一種獨立成分分析處理器,係用以對多通道平行信號進行獨立成分分析之運算,包括:輸入記憶體單元,係接收及儲存該多通道平行信號,其中,該多通道平行信號具有初始資料,且該輸入記憶體單元輸出該初始資料,該輸入記憶體單元係包含交錯的記憶體,該記憶體具有至少三個記憶庫;平均與共變異單元,係計算該初始資料的平均值和共變異值;中心化單元,係依據該初始資料的平均值對該初始資料進行中心化而取得零均值資料;白化單元,係接收該初始資料的共變異值和該零均值資料以進行白化處理,以得到白化矩陣和不相關資料流;ICA訓練單元,係從該白化單元接收該不相關資料流,並據以計算出非混合權重矩陣;以及ICA計算單元,係接收該非混合權重矩陣和該白化矩陣以計算出白化非混合矩陣,再依據該白化非混合矩陣及該初始資料計算出該多通道平行信號之獨立成分,其中,該至少三個記憶庫係供依序填充該多通道平行信號中的初始資料,且該輸入記憶體單元採用該具有至少三個記憶庫的記憶體之架構來實現滑動的視窗,該滑動的視窗於該至少三個記憶庫中循序選擇兩者為工作視窗; 其中,由該輸入記憶體單元所接收的初始資料係依次填充至第一、第二及第三記憶庫,當該初始資料開始填充該第三記憶庫時,儲存在該第一及第二記憶庫的初始資料會開始依次輸出,而當該初始資料填滿該第三記憶庫時,所輸入的初始資料將循環回繼續填充該第一記憶庫。
  2. 如申請專利範圍第1項所述之獨立成分分析處理器,其中,該ICA訓練單元係透過疊代法來計算該非混合權重矩陣,其中,若該ICA訓練單元執行該疊代法所得之結果未符合一預定值,則發出一通知至該輸入記憶體單元,以令該輸入記憶體單元輸出同一個視窗中的初始資料,而若執行該疊代法所得之結果符合該預定值,則令該ICA訓練單元輸出該非混合權重矩陣至該ICA計算單元。
  3. 如申請專利範圍第1項所述之獨立成分分析處理器,其中,該輸入記憶體單元在傳輸該初始資料至該ICA計算單元及該中心化單元之前,發出一通知至該ICA訓練單元以令該ICA訓練單元將由前一個視窗所算出的非混合權重矩陣送至該ICA計算單元。
  4. 如申請專利範圍第1項所述之獨立成分分析處理器,其中,該輸入記憶體單元中所執行之該初始資料之依序填充、該中心化單元之中心化、該白化單元之白化處理、該ICA訓練單元及該ICA計算單元之計算係平行處理。
  5. 如申請專利範圍第1項所述之獨立成分分析處理器,其 中,該平均與共變異單元包含乘法累加器,而該平均與共變異單元利用該乘法累加器計算該初始資料的平均值和共變異值。
  6. 如申請專利範圍第1項所述之獨立成分分析處理器,其中,該中心化單元包含減法器,而該中心化單元利用該減法器去除該初始資料中各通道的直流成分。
  7. 如申請專利範圍第1項所述之獨立成分分析處理器,其中,該白化單元包括:奇異值分解處理元件,係接收該初始資料的共變異值以計算出該共變異值的特徵值矩陣和特徵向量矩陣;平方根倒數元件,係接收該特徵值矩陣以計算出該特徵值矩陣的平方根倒數;及乘法累加器,係依據該特徵向量矩陣和該特徵值矩陣的平方根倒數,計算出該白化矩陣,再依據該白化矩陣和該零均值資料計算出不相關資料流。
  8. 如申請專利範圍第7項所述之獨立成分分析處理器,其中,該奇異值分解處理元件包括複數個座標旋轉器。
  9. 如申請專利範圍第1項所述之獨立成分分析處理器,其中,該ICA訓練單元包括向量乘法器、向量加法器及查找表,而該ICA訓練單元利用該向量乘法器、該向量加法器及該查找表計算出該非混合權重矩陣。
  10. 如申請專利範圍第1項所述之獨立成分分析處理器,其中,該ICA計算單元包括乘法累加器,而該ICA計算單元利用該乘法累加器計算出該白化非混合矩陣。
  11. 如申請專利範圍第1項所述之獨立成分分析處理器,其中,該ICA訓練單元和該ICA計算單元係執行Infomax ICA演算法。
TW099144420A 2010-12-17 2010-12-17 獨立成分分析處理器 TWI456516B (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
TW099144420A TWI456516B (zh) 2010-12-17 2010-12-17 獨立成分分析處理器
US13/149,323 US9031816B2 (en) 2010-12-17 2011-05-31 Independent component analysis processor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW099144420A TWI456516B (zh) 2010-12-17 2010-12-17 獨立成分分析處理器

Publications (2)

Publication Number Publication Date
TW201227544A TW201227544A (en) 2012-07-01
TWI456516B true TWI456516B (zh) 2014-10-11

Family

ID=46235512

Family Applications (1)

Application Number Title Priority Date Filing Date
TW099144420A TWI456516B (zh) 2010-12-17 2010-12-17 獨立成分分析處理器

Country Status (2)

Country Link
US (1) US9031816B2 (zh)
TW (1) TWI456516B (zh)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9966088B2 (en) * 2011-09-23 2018-05-08 Adobe Systems Incorporated Online source separation
CN103149514B (zh) * 2013-03-01 2015-04-22 山东电力集团公司电力科学研究院 一种gis内多绝缘缺陷模式识别方法
TWI492740B (zh) * 2013-05-23 2015-07-21 Univ Nat Chiao Tung 基於線上遞回獨立成分分析之即時多通道腦波訊號處理器
US20160113587A1 (en) * 2013-06-03 2016-04-28 The Regents Of The University Of California Artifact removal techniques with signal reconstruction
TWI508702B (zh) * 2013-07-10 2015-11-21 Univ Nat Chiao Tung 即時多通道自動眼動雜訊去除器
CN103679199B (zh) * 2013-12-11 2017-03-01 中国石油大学(华东) 基于入侵性杂草算法的有噪独立分量分析方法
US10325006B2 (en) 2015-09-29 2019-06-18 International Business Machines Corporation Scalable architecture for analog matrix operations with resistive devices
US10387778B2 (en) 2015-09-29 2019-08-20 International Business Machines Corporation Scalable architecture for implementing maximization algorithms with resistive devices
US11152014B2 (en) 2016-04-08 2021-10-19 Dolby Laboratories Licensing Corporation Audio source parameterization
CN109009092B (zh) * 2018-06-15 2020-06-02 东华大学 一种去除脑电信号噪声伪迹的方法
CN110222307B (zh) * 2019-06-12 2022-10-28 哈尔滨工程大学 基于fpga的实对称矩阵的特征值分解的并行实现方法
CN111160317B (zh) * 2020-01-06 2023-03-28 西南电子技术研究所(中国电子科技集团公司第十研究所) 微弱信号盲提取方法
KR102330171B1 (ko) * 2020-12-07 2021-11-23 한국과학기술정보연구원 주성분분석제어장치 및 그 동작 방법
KR102594818B1 (ko) * 2021-06-09 2023-10-26 금오공과대학교 산학협력단 공분산 디센터링을 이용한 아이겐 페이스 뇌파 신호 분류방법 및 이를 이용한 뇌파 신호 분류장치

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0736858A (ja) * 1993-07-21 1995-02-07 Hitachi Ltd 信号処理プロセッサ
TW408298B (en) * 1997-08-28 2000-10-11 Texas Instruments Inc Improved method for switched-predictive quantization
US6095980A (en) * 1997-10-02 2000-08-01 Sunnybrook Health Science Centre Pulse inversion doppler ultrasonic diagnostic imaging
SE521024C2 (sv) * 1999-03-08 2003-09-23 Ericsson Telefon Ab L M Metod och anordning för att separera en blandning av källsignaler
US20050149462A1 (en) * 1999-10-14 2005-07-07 The Salk Institute For Biological Studies System and method of separating signals
US6424960B1 (en) 1999-10-14 2002-07-23 The Salk Institute For Biological Studies Unsupervised adaptation and classification of multiple classes and sources in blind signal separation
US7050483B2 (en) * 2001-12-13 2006-05-23 Motorola, Inc. Low-cost two-stage receiver system for DS-CDMA
US6718504B1 (en) * 2002-06-05 2004-04-06 Arc International Method and apparatus for implementing a data processor adapted for turbo decoding
KR100675555B1 (ko) * 2003-07-07 2007-01-29 유선국 맥박 산소포화도 측정 장치 및 방법
GB0326539D0 (en) 2003-11-14 2003-12-17 Qinetiq Ltd Dynamic blind signal separation
US7353491B2 (en) * 2004-05-28 2008-04-01 Peter Pius Gutberlet Optimization of memory accesses in a circuit design
US7711762B2 (en) * 2004-11-15 2010-05-04 Qualcomm Incorporated Efficient computation for eigenvalue decomposition and singular value decomposition of matrices
JP2007034184A (ja) * 2005-07-29 2007-02-08 Kobe Steel Ltd 音源分離装置,音源分離プログラム及び音源分離方法
US7818357B2 (en) * 2005-11-23 2010-10-19 Rambus Inc. Systems and methods for implementing CORDIC rotations for projectors and related operators
US9015399B2 (en) * 2007-08-20 2015-04-21 Convey Computer Multiple data channel memory module architecture
US8583428B2 (en) * 2010-06-15 2013-11-12 Microsoft Corporation Sound source separation using spatial filtering and regularization phases

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Chen, Chiu-Kuo and Chua, Ericson and Tseng, Shao-Yen and Fu, Chih-Chung and Fang, Wai-Chi. Implementation of a hardware-efficient EEG processor for brain monitoring systems. . SoCC. editor(s) Büchner, Thomas and Sridhar, Ramalingam and Marshall, Andrew and Schuhmann, Norbert. 164-168, IEEE, Year 2010.09.27-29 *

Also Published As

Publication number Publication date
US9031816B2 (en) 2015-05-12
TW201227544A (en) 2012-07-01
US20120158367A1 (en) 2012-06-21

Similar Documents

Publication Publication Date Title
TWI456516B (zh) 獨立成分分析處理器
JP2014530441A5 (zh)
JP2013137747A5 (zh)
JP2012253444A5 (zh)
JP2007274299A5 (zh)
JP2012185517A5 (zh)
JP2012143547A5 (zh)
JP2013081683A5 (zh)
TWI699709B (zh) 視線追蹤設備中確定參數的方法和裝置
RU2014116610A (ru) Генерирование изображений глубины с использованием псевдокадров, каждый из которых содержит множество фазовых изображений
TWI314405B (en) Array processing for linear system solutions
WO2014032008A3 (en) Method and system for generating mesh from images
TWI456982B (zh) 影像處理裝置與空間影像雜訊消除方法
JP2012249968A5 (zh)
JP2009533784A5 (zh)
JP2019185548A5 (zh)
KR101586007B1 (ko) 데이터 처리 장치 및 방법
JP2006203296A5 (zh)
CN104750455B (zh) 一种基于蒙哥马利模乘的数据处理方法和装置
JP2011512556A5 (ja) 楕円曲線上の点のスカラー倍を計算する装置及び方法
JP2010117371A5 (zh)
JP2016086959A5 (zh)
JP2021502575A5 (zh)
JP2011254262A5 (zh)
JP2013519409A5 (zh)