See the published version of this preprint at Journal of Big Data.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research
Mehrdad Rostami
University of Kurdistan
Corresponding Author
ORCiD: https://orcid.org/0000-0001-5710-217X
License:
This work is licensed under a CC BY 4.0 License. Read Full License
The selection of features is an essential data preprocessing stage in data mining. The core principle of feature selection seems to be to pick a subset of possible features by excluding features with almost no predictive information as well as highly associated redundant features. In the past several years, a variety of meta-heuristic methods were introduced to eliminate redundant and irrelevant features as much as possible from high-dimensional datasets. Among the main disadvantages of present meta-heuristic based approaches is that they are often neglecting the correlation between a set of selected features. In this article, for the purpose of feature selection, the authors propose a genetic algorithm based on community detection, which functions in three steps. The feature similarities are calculated in the first step. The features are classified by community detection algorithms into clusters throughout the second step. In the third step, features are picked by a genetic algorithm with a new community-based repair operation. Nine benchmark classification problems were analyzed in terms of the performance of the presented approach. Also, the authors have compared the efficiency of the proposed approach with the findings from four available algorithms for feature selection. The findings indicate that the new approach continuously yields improved classification accuracy.
Keywords
Machine learning, Feature selection, Genetic algorithm, Graph theory, Multi-objective
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at Journal of Big Data.
Version 1
Posted 23 Sep, 2020
No community comments so far
Editorial decision: Major Revision
On 29 Oct, 2020
Review #7 received
Received 25 Oct, 2020
Review #5 received
Received 24 Oct, 2020
Review #10 received
Received 24 Oct, 2020
Reviewer #10 agreed
On 10 Oct, 2020
Reviewer #8 agreed
On 09 Oct, 2020
Reviewer #9 agreed
On 09 Oct, 2020
Review #8 received
Received 09 Oct, 2020
Review #6 received
Received 08 Oct, 2020
Review #2 received
Received 07 Oct, 2020
Review #4 received
Received 07 Oct, 2020
Review #3 received
Received 07 Oct, 2020
Reviewer #7 agreed
On 07 Oct, 2020
Review #1 received
Received 07 Oct, 2020
Reviewers invited
Invitations sent on 06 Oct, 2020
Reviewer #1 agreed
On 06 Oct, 2020
Reviewer #2 agreed
On 06 Oct, 2020
Reviewer #3 agreed
On 06 Oct, 2020
Reviewer #4 agreed
On 06 Oct, 2020
Reviewer #5 agreed
On 06 Oct, 2020
Reviewer #6 agreed
On 06 Oct, 2020
Editor assigned
On 19 Sep, 2020
First submitted
On 18 Sep, 2020
Submission checks complete
On 18 Sep, 2020
Editor invited
On 18 Sep, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Learn more about our company.
See the published version of this preprint at Journal of Big Data.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research
Mehrdad Rostami
University of Kurdistan
Corresponding Author
ORCiD: https://orcid.org/0000-0001-5710-217X
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at Journal of Big Data.
Version 1
Posted 23 Sep, 2020
No community comments so far
Editorial decision: Major Revision
On 29 Oct, 2020
Review #7 received
Received 25 Oct, 2020
Review #5 received
Received 24 Oct, 2020
Review #10 received
Received 24 Oct, 2020
Reviewer #10 agreed
On 10 Oct, 2020
Reviewer #8 agreed
On 09 Oct, 2020
Reviewer #9 agreed
On 09 Oct, 2020
Review #8 received
Received 09 Oct, 2020
Review #6 received
Received 08 Oct, 2020
Review #2 received
Received 07 Oct, 2020
Review #4 received
Received 07 Oct, 2020
Review #3 received
Received 07 Oct, 2020
Reviewer #7 agreed
On 07 Oct, 2020
Review #1 received
Received 07 Oct, 2020
Reviewers invited
Invitations sent on 06 Oct, 2020
Reviewer #1 agreed
On 06 Oct, 2020
Reviewer #2 agreed
On 06 Oct, 2020
Reviewer #3 agreed
On 06 Oct, 2020
Reviewer #4 agreed
On 06 Oct, 2020
Reviewer #5 agreed
On 06 Oct, 2020
Reviewer #6 agreed
On 06 Oct, 2020
Editor assigned
On 19 Sep, 2020
First submitted
On 18 Sep, 2020
Submission checks complete
On 18 Sep, 2020
Editor invited
On 18 Sep, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
License:
This work is licensed under a CC BY 4.0 License. Read Full License
View the published article at Journal of Big Data.
The selection of features is an essential data preprocessing stage in data mining. The core principle of feature selection seems to be to pick a subset of possible features by excluding features with almost no predictive information as well as highly associated redundant features. In the past several years, a variety of meta-heuristic methods were introduced to eliminate redundant and irrelevant features as much as possible from high-dimensional datasets. Among the main disadvantages of present meta-heuristic based approaches is that they are often neglecting the correlation between a set of selected features. In this article, for the purpose of feature selection, the authors propose a genetic algorithm based on community detection, which functions in three steps. The feature similarities are calculated in the first step. The features are classified by community detection algorithms into clusters throughout the second step. In the third step, features are picked by a genetic algorithm with a new community-based repair operation. Nine benchmark classification problems were analyzed in terms of the performance of the presented approach. Also, the authors have compared the efficiency of the proposed approach with the findings from four available algorithms for feature selection. The findings indicate that the new approach continuously yields improved classification accuracy.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Loading...