2013 IEEE International Conference on Bioinformatics and Biomedicine 2013
DOI: 10.1109/bibm.2013.6732715
|View full text |Cite
|
Sign up to set email alerts
|

An ensemble classifier with random projection for predicting multi-label protein subcellular localization

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
2
0
1

Year Published

2014
2014
2017
2017

Publication Types

Select...
6
1

Relationship

3
4

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 36 publications
0
2
0
1
Order By: Relevance
“…Recently, several state-of-the-art multi-label predictors have been proposed, such as Hum-mPLoc 2.0 [51], iLoc-Hum [27], mGOASVM [61], HybridGO-Loc [62], R3P-Loc [63], mPLRLoc [64] and other predictors [65,66,67]. They all use the GO information as the features and apply different multi-label classifiers to tackle the multi-label classification problem.…”
Section: Introductionmentioning
confidence: 98%
“…Recently, several state-of-the-art multi-label predictors have been proposed, such as Hum-mPLoc 2.0 [51], iLoc-Hum [27], mGOASVM [61], HybridGO-Loc [62], R3P-Loc [63], mPLRLoc [64] and other predictors [65,66,67]. They all use the GO information as the features and apply different multi-label classifiers to tackle the multi-label classification problem.…”
Section: Introductionmentioning
confidence: 98%
“…Many state-of-the-art multi-label predictors – such as iLoc-Hum [ 27 ], Hum-mPLoc 2.0 [ 43 ], mGOASVM [ 44 ], HybridGO-Loc [ 45 ], R3P-Loc [ 46 ], mPLR-Loc [ 47 ] and others [ 48 50 ] – use GO information as features and apply different multi-label classifiers to tackle the multi-label classification problem. Nevertheless, due to the high dimensionality of GO features, these GO-based predictors often have the following drawbacks: Lack of interpretability .…”
Section: Introductionmentioning
confidence: 99%
“…(PHUOC; KIM, 2011) propõe um método que analisa a distância entre os pontos de treinamento para agrupá-los em espaços onde há maior densidade de dados, de forma a evitar os comportamentos irregulares e aproveitar corretamente os recursos disponíveis. Os autores em (WAN et al, 2013) propõem um método com aplicação de Random Projection (RP) para a construção de um conjunto classificador, com uso de SVM para redução de dimensão no espaço de informações, que melhora a predição e reduz overfitting. Para minimizar erros de predição (LUCENA et al, 2013) desenvolve um modelo de regressão linear para previsão da concentração de proteína de trigo, medindo centenas de variáveis correlacionadas com as propriedades físico-químicas e que pode ser utilizada para estimar a concentração de proteína.…”
Section: Estado Da Arte De Pspunclassified