A hybrid scheme for feature selection of high dimensional educational data

Usman Ali; Khawaja Sarmad Arif; Usman Qamar

doi:10.1109/COMTECH.2019.8737829

A hybrid scheme for feature selection of high dimensional educational data

Usman Ali
, Khawaja Sarmad Arif
, Usman Qamar

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

6 Scopus citations

Abstract

Now a days, in educational data sets, the gigantic amounts of records can be the problem in generating good quality data. Lately, a lot of educational researchers are using the data mining methodology to analyze the data. But, several research studies focus on the selection of right learning algorithm rather than carrying out the feature selection on data. Therefore, the dataset has problem like high computational complexity and performing classification on such data requires a lot of computational time. This paper will give a summary of the feature selection methods which are being used for analysis of features of data. The proposed hybrid methodology is a combination of both feature selection and wrapper based technique, which helps to enhance the quality of students' data set.

Original language	English
Title of host publication	2019 International Conference on Communication Technologies, ComTech 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	71-75
Number of pages	5
ISBN (Electronic)	9781538651063
DOIs	https://doi.org/10.1109/COMTECH.2019.8737829
State	Published - Mar 2019
Externally published	Yes
Event	2019 International Conference on Communication Technologies, ComTech 2019 - Rawalpindi, Pakistan Duration: 20 Mar 2019 → 21 Mar 2019

Publication series

Name	2019 International Conference on Communication Technologies, ComTech 2019

Conference

Conference	2019 International Conference on Communication Technologies, ComTech 2019
Country/Territory	Pakistan
City	Rawalpindi
Period	20/03/19 → 21/03/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Classification
Data mining
Dimensionality reduction
Feature selection
High-dimensional data
Machine Learning

ASJC Scopus subject areas

Computer Networks and Communications
Hardware and Architecture
Signal Processing
Safety, Risk, Reliability and Quality
Instrumentation

Access to Document

10.1109/COMTECH.2019.8737829

Cite this

Ali, U., Arif, K. S., & Qamar, U. (2019). A hybrid scheme for feature selection of high dimensional educational data. In 2019 International Conference on Communication Technologies, ComTech 2019 (pp. 71-75). Article 8737829 (2019 International Conference on Communication Technologies, ComTech 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/COMTECH.2019.8737829

@inproceedings{368c6ffffb234fce848fbcf202533cc2,

title = "A hybrid scheme for feature selection of high dimensional educational data",

abstract = "Now a days, in educational data sets, the gigantic amounts of records can be the problem in generating good quality data. Lately, a lot of educational researchers are using the data mining methodology to analyze the data. But, several research studies focus on the selection of right learning algorithm rather than carrying out the feature selection on data. Therefore, the dataset has problem like high computational complexity and performing classification on such data requires a lot of computational time. This paper will give a summary of the feature selection methods which are being used for analysis of features of data. The proposed hybrid methodology is a combination of both feature selection and wrapper based technique, which helps to enhance the quality of students' data set.",

keywords = "Classification, Data mining, Dimensionality reduction, Feature selection, High-dimensional data, Machine Learning",

author = "Usman Ali and Arif, \{Khawaja Sarmad\} and Usman Qamar",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 International Conference on Communication Technologies, ComTech 2019 ; Conference date: 20-03-2019 Through 21-03-2019",

year = "2019",

month = mar,

doi = "10.1109/COMTECH.2019.8737829",

language = "English",

series = "2019 International Conference on Communication Technologies, ComTech 2019",

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

pages = "71--75",

booktitle = "2019 International Conference on Communication Technologies, ComTech 2019",

address = "United States",

}

Ali, U, Arif, KS & Qamar, U 2019, A hybrid scheme for feature selection of high dimensional educational data. in 2019 International Conference on Communication Technologies, ComTech 2019., 8737829, 2019 International Conference on Communication Technologies, ComTech 2019, Institute of Electrical and Electronics Engineers Inc., pp. 71-75, 2019 International Conference on Communication Technologies, ComTech 2019, Rawalpindi, Pakistan, 20/03/19. https://doi.org/10.1109/COMTECH.2019.8737829

A hybrid scheme for feature selection of high dimensional educational data. / Ali, Usman; Arif, Khawaja Sarmad; Qamar, Usman.
2019 International Conference on Communication Technologies, ComTech 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 71-75 8737829 (2019 International Conference on Communication Technologies, ComTech 2019).

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

TY - GEN

T1 - A hybrid scheme for feature selection of high dimensional educational data

AU - Ali, Usman

AU - Arif, Khawaja Sarmad

AU - Qamar, Usman

PY - 2019/3

Y1 - 2019/3

N2 - Now a days, in educational data sets, the gigantic amounts of records can be the problem in generating good quality data. Lately, a lot of educational researchers are using the data mining methodology to analyze the data. But, several research studies focus on the selection of right learning algorithm rather than carrying out the feature selection on data. Therefore, the dataset has problem like high computational complexity and performing classification on such data requires a lot of computational time. This paper will give a summary of the feature selection methods which are being used for analysis of features of data. The proposed hybrid methodology is a combination of both feature selection and wrapper based technique, which helps to enhance the quality of students' data set.

AB - Now a days, in educational data sets, the gigantic amounts of records can be the problem in generating good quality data. Lately, a lot of educational researchers are using the data mining methodology to analyze the data. But, several research studies focus on the selection of right learning algorithm rather than carrying out the feature selection on data. Therefore, the dataset has problem like high computational complexity and performing classification on such data requires a lot of computational time. This paper will give a summary of the feature selection methods which are being used for analysis of features of data. The proposed hybrid methodology is a combination of both feature selection and wrapper based technique, which helps to enhance the quality of students' data set.

KW - Classification

KW - Data mining

KW - Dimensionality reduction

KW - Feature selection

KW - High-dimensional data

KW - Machine Learning

UR - https://www.scopus.com/pages/publications/85068561578

U2 - 10.1109/COMTECH.2019.8737829

DO - 10.1109/COMTECH.2019.8737829

M3 - Conference contribution

AN - SCOPUS:85068561578

T3 - 2019 International Conference on Communication Technologies, ComTech 2019

SP - 71

EP - 75

BT - 2019 International Conference on Communication Technologies, ComTech 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Conference on Communication Technologies, ComTech 2019

Y2 - 20 March 2019 through 21 March 2019

ER -

A hybrid scheme for feature selection of high dimensional educational data

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this