
Please use this identifier to cite or link to this item:
https://scholar.dlu.edu.vn/handle/123456789/2711
Title: | A new feature selection approach for optimizing prediction models, applied to breast cancer subtype classification | Authors: | Phạm, Quang Huy Alioune Ngom Luis Rueda |
Keywords: | machine learning;feature selection | Issue Date: | 2016 | Publisher: | IEEE | Conference: | 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) | Abstract: | Feature selection is a useful technique in classification (and regression) problems to find the most informative features for predicting but still preserves the data generality. However, some feature subset searching methods are too exhaustive while others are too greedy. On the other hand, parameter searching is another factor to improve the prediction performance. But, if it is conducted separately after feature selection stage the classification model might not be as optimal as it should. In this study, we propose a new method, called Apriori-like Feature Selection that can overcome those drawbacks. Given a classifier and a dataset, it searches for the optimal parameters and the optimal feature subset in the combined space of features and parameters. Moreover, its greedy search behavior is controllable by running options. When applying this approach on a breast cancer dataset of five subtypes, it yielded the overall classification accuracy of more than 99% but requires only about 12 genes; a significant improvement as compared to another study. |
URI: | https://scholar.dlu.edu.vn/handle/123456789/2711 | DOI: | 10.1109/BIBM.2016.7822749 | Type: | Bài báo đăng trên KYHT quốc tế (có ISBN) |
Appears in Collections: | Kỷ yếu hội thảo (Khoa Toán - Tin học) |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
SSCI16_paper_658.pdf | 253.41 kB | Adobe PDF |
CORE Recommender
SCOPUSTM
Citations
5
7
Last Week
0
0
Last month
checked on Feb 13, 2025
Page view(s)
22
Last Week
0
0
Last month
checked on Feb 18, 2025
Download(s)
15
checked on Feb 18, 2025
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.