The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Strategi pemilihan Ciri yang cekap adalah penting dalam pengurangan dimensi data. Usaha penyelidikan sedia ada yang meluas boleh diringkaskan kepada tiga kelas: Kaedah penapis, kaedah pembungkus dan kaedah Terbenam. Dalam kerja ini, kami mencadangkan kaedah pengekstrakan ciri dua peringkat bersepadu, yang dirujuk sebagai FWS, yang menggabungkan kaedah Penapis dan Pembalut untuk mengekstrak ciri penting dengan cekap dalam mod hibrid yang inovatif. FWS menjalankan tahap pemilihan pertama untuk menapis ciri tidak berkaitan menggunakan analisis korelasi dan pemilihan tahap kedua untuk mengetahui subset hampir optimum yang menangkap ciri diskret yang berharga dengan menilai prestasi model ramalan yang dilatih pada sub set tersebut. Berbanding dengan teknologi seperti mRMR dan Relief-F, FWS meningkatkan prestasi pengesanan dengan ketara melalui strategi pengoptimuman bersepadu. Keputusan menunjukkan keunggulan prestasi penyelesaian yang dicadangkan berbanding beberapa kaedah terkenal untuk pemilihan ciri.
Weizhi LIAO
University of Electronic Science and Technology of China
Guanglei YE
University of Electronic Science and Technology of China
Weijun YAN
University of Electronic Science and Technology of China
Yaheng MA
University of Electronic Science and Technology of China
Dongzhou ZUO
University of Electronic Science and Technology of China
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Weizhi LIAO, Guanglei YE, Weijun YAN, Yaheng MA, Dongzhou ZUO, "Improved Hybrid Feature Selection Framework" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 8, pp. 1266-1273, August 2021, doi: 10.1587/transinf.2020BDP0017.
Abstract: An efficient Feature selection strategy is important in the dimension reduction of data. Extensive existing research efforts could be summarized into three classes: Filter method, Wrapper method, and Embedded method. In this work, we propose an integrated two-stage feature extraction method, referred to as FWS, which combines Filter and Wrapper method to efficiently extract important features in an innovative hybrid mode. FWS conducts the first level of selection to filter out non-related features using correlation analysis and the second level selection to find out the near-optimal sub set that capturing valuable discrete features by evaluating the performance of predictive model trained on such sub set. Compared with the technologies such as mRMR and Relief-F, FWS significantly improves the detection performance through an integrated optimization strategy.Results show the performance superiority of the proposed solution over several well-known methods for feature selection.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020BDP0017/_p
Salinan
@ARTICLE{e104-d_8_1266,
author={Weizhi LIAO, Guanglei YE, Weijun YAN, Yaheng MA, Dongzhou ZUO, },
journal={IEICE TRANSACTIONS on Information},
title={Improved Hybrid Feature Selection Framework},
year={2021},
volume={E104-D},
number={8},
pages={1266-1273},
abstract={An efficient Feature selection strategy is important in the dimension reduction of data. Extensive existing research efforts could be summarized into three classes: Filter method, Wrapper method, and Embedded method. In this work, we propose an integrated two-stage feature extraction method, referred to as FWS, which combines Filter and Wrapper method to efficiently extract important features in an innovative hybrid mode. FWS conducts the first level of selection to filter out non-related features using correlation analysis and the second level selection to find out the near-optimal sub set that capturing valuable discrete features by evaluating the performance of predictive model trained on such sub set. Compared with the technologies such as mRMR and Relief-F, FWS significantly improves the detection performance through an integrated optimization strategy.Results show the performance superiority of the proposed solution over several well-known methods for feature selection.},
keywords={},
doi={10.1587/transinf.2020BDP0017},
ISSN={1745-1361},
month={August},}
Salinan
TY - JOUR
TI - Improved Hybrid Feature Selection Framework
T2 - IEICE TRANSACTIONS on Information
SP - 1266
EP - 1273
AU - Weizhi LIAO
AU - Guanglei YE
AU - Weijun YAN
AU - Yaheng MA
AU - Dongzhou ZUO
PY - 2021
DO - 10.1587/transinf.2020BDP0017
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2021
AB - An efficient Feature selection strategy is important in the dimension reduction of data. Extensive existing research efforts could be summarized into three classes: Filter method, Wrapper method, and Embedded method. In this work, we propose an integrated two-stage feature extraction method, referred to as FWS, which combines Filter and Wrapper method to efficiently extract important features in an innovative hybrid mode. FWS conducts the first level of selection to filter out non-related features using correlation analysis and the second level selection to find out the near-optimal sub set that capturing valuable discrete features by evaluating the performance of predictive model trained on such sub set. Compared with the technologies such as mRMR and Relief-F, FWS significantly improves the detection performance through an integrated optimization strategy.Results show the performance superiority of the proposed solution over several well-known methods for feature selection.
ER -