Active learning algorithm for threshold of decision probability on imbalanced text classification based on protein-protein interaction documents

Abstract

The study of host pathogen protein-protein interactions (PPIs) is essential to understand the disease-causing mechanisms of human pathogens. A large number of scientific findings about PPIs are generated in the biomedical literatures. Building a document classification system can accelerate the process of mining and curation of PPI knowledge. With more and more imbalanced dataset appearing, how to handle the imbalanced classification problem is becoming a hot topic in machine learning field. In this paper, we propose an Active Learning algorithm for Threshold of Decision Probability (ALTDP) to solve problem of misclassifying the minority class based on imbalanced host pathogen PPIs data set. The results demonstrate the proposed approach is significant to improve the accuracy of classification on imbalanced data set.

Original language	English
Title of host publication	DSDE 2010 - International Conference on Data Storage and Data Engineering
Pages	78-82
Number of pages	5
DOIs	https://doi.org/10.1109/DSDE.2010.28
Publication status	Published - 2010
Event	2010 International Conference on Data Storage and Data Engineering, DSDE 2010 - Bangalore, India Duration: 9 Feb 2010 → 10 Feb 2010

Publication series

Name	DSDE 2010 - International Conference on Data Storage and Data Engineering

Conference

Conference	2010 International Conference on Data Storage and Data Engineering, DSDE 2010
Country/Territory	India
City	Bangalore
Period	9/02/10 → 10/02/10

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Imbalanced text classification
Machine learning
Protein-protein interaction

Access to Document

10.1109/DSDE.2010.28

Cite this

Author
BIBTEX
RIS
Vancouver

@inproceedings{3104752f7b7c49f681c92a45e4c2f2f3,

title = "Active learning algorithm for threshold of decision probability on imbalanced text classification based on protein-protein interaction documents",

abstract = "The study of host pathogen protein-protein interactions (PPIs) is essential to understand the disease-causing mechanisms of human pathogens. A large number of scientific findings about PPIs are generated in the biomedical literatures. Building a document classification system can accelerate the process of mining and curation of PPI knowledge. With more and more imbalanced dataset appearing, how to handle the imbalanced classification problem is becoming a hot topic in machine learning field. In this paper, we propose an Active Learning algorithm for Threshold of Decision Probability (ALTDP) to solve problem of misclassifying the minority class based on imbalanced host pathogen PPIs data set. The results demonstrate the proposed approach is significant to improve the accuracy of classification on imbalanced data set.",

keywords = "Imbalanced text classification, Machine learning, Protein-protein interaction",

author = "Guixian Xu and Zhendong Niu and Xu Gao and Yujuan Cao and Yumin Zhao",

year = "2010",

doi = "10.1109/DSDE.2010.28",

language = "English",

isbn = "9780769539584",

series = "DSDE 2010 - International Conference on Data Storage and Data Engineering",

pages = "78--82",

booktitle = "DSDE 2010 - International Conference on Data Storage and Data Engineering",

note = "2010 International Conference on Data Storage and Data Engineering, DSDE 2010 ; Conference date: 09-02-2010 Through 10-02-2010",

}

TY - GEN

T1 - Active learning algorithm for threshold of decision probability on imbalanced text classification based on protein-protein interaction documents

AU - Xu, Guixian

AU - Niu, Zhendong

AU - Gao, Xu

AU - Cao, Yujuan

AU - Zhao, Yumin

PY - 2010

Y1 - 2010

N2 - The study of host pathogen protein-protein interactions (PPIs) is essential to understand the disease-causing mechanisms of human pathogens. A large number of scientific findings about PPIs are generated in the biomedical literatures. Building a document classification system can accelerate the process of mining and curation of PPI knowledge. With more and more imbalanced dataset appearing, how to handle the imbalanced classification problem is becoming a hot topic in machine learning field. In this paper, we propose an Active Learning algorithm for Threshold of Decision Probability (ALTDP) to solve problem of misclassifying the minority class based on imbalanced host pathogen PPIs data set. The results demonstrate the proposed approach is significant to improve the accuracy of classification on imbalanced data set.

AB - The study of host pathogen protein-protein interactions (PPIs) is essential to understand the disease-causing mechanisms of human pathogens. A large number of scientific findings about PPIs are generated in the biomedical literatures. Building a document classification system can accelerate the process of mining and curation of PPI knowledge. With more and more imbalanced dataset appearing, how to handle the imbalanced classification problem is becoming a hot topic in machine learning field. In this paper, we propose an Active Learning algorithm for Threshold of Decision Probability (ALTDP) to solve problem of misclassifying the minority class based on imbalanced host pathogen PPIs data set. The results demonstrate the proposed approach is significant to improve the accuracy of classification on imbalanced data set.

KW - Imbalanced text classification

KW - Machine learning

KW - Protein-protein interaction

UR - https://www.scopus.com/pages/publications/77952638249

U2 - 10.1109/DSDE.2010.28

DO - 10.1109/DSDE.2010.28

M3 - Conference contribution

AN - SCOPUS:77952638249

SN - 9780769539584

T3 - DSDE 2010 - International Conference on Data Storage and Data Engineering

SP - 78

EP - 82

BT - DSDE 2010 - International Conference on Data Storage and Data Engineering

T2 - 2010 International Conference on Data Storage and Data Engineering, DSDE 2010

Y2 - 9 February 2010 through 10 February 2010

ER -

Xu G, Niu Z, Gao X, Cao Y, Zhao Y. Active learning algorithm for threshold of decision probability on imbalanced text classification based on protein-protein interaction documents. In DSDE 2010 - International Conference on Data Storage and Data Engineering. 2010. p. 78-82. 5452631. (DSDE 2010 - International Conference on Data Storage and Data Engineering). doi: 10.1109/DSDE.2010.28