2009
DOI: 10.4304/jcp.4.3.208-214
|View full text |Cite
|
Sign up to set email alerts
|

Stream Data Classification Using Improved Fisher Discriminate Analysis

Abstract: <p class="MsoNormal" style="text-align: left; margin: 0cm 0cm 0pt; layout-grid-mode: char;" align="left"><span class="text"><span style="font-family: ";Arial";,";sans-serif";; font-size: 9pt;">A modified Fisher discriminate analysis method for classifying stream data is presented. To satisfy the realtime demand in classifying stream data, this method defines a new criterion for Fisher discriminate analysis. Since the new criterion requires less computation and memory space, it is much faster … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
1
0
2

Year Published

2010
2010
2012
2012

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 21 publications
0
1
0
2
Order By: Relevance
“…' << , which is highly dimensional and so the dimensionality of the matrix is reduced using LPP. The LPP is a linear dimensionality reduction algorithm that shares most of the properties of data representation of nonlinear techniques, namely, locally linear Embedding or Laplacian Eigenmaps (Chen, 2009). The LPP procedure for dimensionality reduction constitutes of three steps, namely, (1) generation of Distance matrix (2) determining adjacency matrix and (3) Calculating dimensionality reduced matrix.…”
Section: Dimensionality Reduction By Lppmentioning
confidence: 99%
“…' << , which is highly dimensional and so the dimensionality of the matrix is reduced using LPP. The LPP is a linear dimensionality reduction algorithm that shares most of the properties of data representation of nonlinear techniques, namely, locally linear Embedding or Laplacian Eigenmaps (Chen, 2009). The LPP procedure for dimensionality reduction constitutes of three steps, namely, (1) generation of Distance matrix (2) determining adjacency matrix and (3) Calculating dimensionality reduced matrix.…”
Section: Dimensionality Reduction By Lppmentioning
confidence: 99%
“…O problema de classificação em FCD pode ser definido da seguinte forma (Chen et al, 2009). Assuma que o FCD consiste em uma sequência de exemplos, sendo que cada exemplo consiste em um conjunto de d atributos.…”
Section: Classificação Em Fcdunclassified
“…De acordo com Aggarwal (2006), o desafio mais importante encontrado na classificação em FCD está relacionado à mudança de conceito, ou seja, a evolução dos dados ao longo do tempo. Para Chen et al (2009), o principal impulsionador da mineração de FCD no contexto de classificação é a exigência de uma única varredura nos dados. Assim, é impossível usar os algoritmos convencionais de classificação que assumem que os dados cabem na memória, fazem várias varredura sobre os dados e criam modelos de decisão estáticos.…”
Section: Classificação Em Fcdunclassified