Handling missing data problems with sampling methods

Rima Houari; Ahcène Bounceur; A. Kamel Tari; M. Tahar Kecha

doi:10.1109/INDS.2014.25

Handling missing data problems with sampling methods

Rima Houari
, Ahcène Bounceur
, A. Kamel Tari
, M. Tahar Kecha

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

36 Scopus citations

Abstract

Missing data cases are a problem in all types of statistical analyses and arise in almost all application domains. Several schemes have been studied in this paper to overcome the drawbacks produced by missing values in data mining tasks, one of the most well known is based on pre processing, formerly known as imputation. In this work, we propose a new multiple imputation approach based on sampling techniques to handle missing values problems, in order to improving the quality and efficiency of data mining process. The proposed method is favourably compared with some imputation techniques and outperforms the existing approaches using an experimental benchmark on a large scale, waveform dataset taken from machine learning repository and different rate of missing values (till 95%).

Original language	English
Title of host publication	Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	99-104
Number of pages	6
ISBN (Electronic)	9781479951789
DOIs	https://doi.org/10.1109/INDS.2014.25
State	Published - 26 Nov 2014
Externally published	Yes
Event	2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014 - Bejaia, Algeria Duration: 17 Jun 2014 → 19 Jun 2014

Publication series

Name	Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014

Conference

Conference	2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014
Country/Territory	Algeria
City	Bejaia
Period	17/06/14 → 19/06/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Keywords

Copula
Data Pre-Processing
Data mining
Missing values
Multidimensional Sampling

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Information Systems

Access to Document

10.1109/INDS.2014.25

Cite this

Houari, R., Bounceur, A., Tari, A. K., & Kecha, M. T. (2014). Handling missing data problems with sampling methods. In Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014 (pp. 99-104). Article 6969065 (Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INDS.2014.25

Houari, Rima ; Bounceur, Ahcène ; Tari, A. Kamel et al. / Handling missing data problems with sampling methods. Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 99-104 (Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014).

@inproceedings{2dbbb69b712d438eac690c73314557e7,

title = "Handling missing data problems with sampling methods",

abstract = "Missing data cases are a problem in all types of statistical analyses and arise in almost all application domains. Several schemes have been studied in this paper to overcome the drawbacks produced by missing values in data mining tasks, one of the most well known is based on pre processing, formerly known as imputation. In this work, we propose a new multiple imputation approach based on sampling techniques to handle missing values problems, in order to improving the quality and efficiency of data mining process. The proposed method is favourably compared with some imputation techniques and outperforms the existing approaches using an experimental benchmark on a large scale, waveform dataset taken from machine learning repository and different rate of missing values (till 95\%).",

keywords = "Copula, Data Pre-Processing, Data mining, Missing values, Multidimensional Sampling",

author = "Rima Houari and Ahc{\`e}ne Bounceur and Tari, \{A. Kamel\} and Kecha, \{M. Tahar\}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014 ; Conference date: 17-06-2014 Through 19-06-2014",

year = "2014",

month = nov,

day = "26",

doi = "10.1109/INDS.2014.25",

language = "English",

series = "Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "99--104",

booktitle = "Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014",

address = "United States",

}

Houari, R, Bounceur, A, Tari, AK & Kecha, MT 2014, Handling missing data problems with sampling methods. in Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014., 6969065, Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014, Institute of Electrical and Electronics Engineers Inc., pp. 99-104, 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014, Bejaia, Algeria, 17/06/14. https://doi.org/10.1109/INDS.2014.25

Handling missing data problems with sampling methods. / Houari, Rima; Bounceur, Ahcène; Tari, A. Kamel et al.
Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 99-104 6969065 (Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Handling missing data problems with sampling methods

AU - Houari, Rima

AU - Bounceur, Ahcène

AU - Tari, A. Kamel

AU - Kecha, M. Tahar

PY - 2014/11/26

Y1 - 2014/11/26

N2 - Missing data cases are a problem in all types of statistical analyses and arise in almost all application domains. Several schemes have been studied in this paper to overcome the drawbacks produced by missing values in data mining tasks, one of the most well known is based on pre processing, formerly known as imputation. In this work, we propose a new multiple imputation approach based on sampling techniques to handle missing values problems, in order to improving the quality and efficiency of data mining process. The proposed method is favourably compared with some imputation techniques and outperforms the existing approaches using an experimental benchmark on a large scale, waveform dataset taken from machine learning repository and different rate of missing values (till 95%).

AB - Missing data cases are a problem in all types of statistical analyses and arise in almost all application domains. Several schemes have been studied in this paper to overcome the drawbacks produced by missing values in data mining tasks, one of the most well known is based on pre processing, formerly known as imputation. In this work, we propose a new multiple imputation approach based on sampling techniques to handle missing values problems, in order to improving the quality and efficiency of data mining process. The proposed method is favourably compared with some imputation techniques and outperforms the existing approaches using an experimental benchmark on a large scale, waveform dataset taken from machine learning repository and different rate of missing values (till 95%).

KW - Copula

KW - Data Pre-Processing

KW - Data mining

KW - Missing values

KW - Multidimensional Sampling

UR - https://www.scopus.com/pages/publications/84919372456

U2 - 10.1109/INDS.2014.25

DO - 10.1109/INDS.2014.25

M3 - Conference contribution

AN - SCOPUS:84919372456

T3 - Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014

SP - 99

EP - 104

BT - Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014

Y2 - 17 June 2014 through 19 June 2014

ER -

Houari R, Bounceur A, Tari AK, Kecha MT. Handling missing data problems with sampling methods. In Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 99-104. 6969065. (Proceedings - 2014 International Conference on Advanced Networking Distributed Systems and Applications, INDS 2014). doi: 10.1109/INDS.2014.25

Handling missing data problems with sampling methods

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this