Maximum relevance, minimum redundancy band selection based on neighborhood rough set for hyperspectral data classification
文献类型： 外文期刊
作者： Liu, Yao 1 ; Chen, Yuehua 1 ; Tan, Kezhu 1 ; Xie, Hong 2 ; Wang, Liguo 2 ; Yan, Xiaozhen 3 ; Xie, Wu 2 ; Xu, Zhen 4 ;
作者机构： 1.Northeast Agr Univ, Coll Elect & Informat, Harbin 150030, Peoples R China
2.Harbin Engn Univ, Coll Informat & Commun Engn, Harbin 150001, Peoples R China
3.Harbin Inst Technol WeiHai, Sch Informat & Elect Engn, Weihai 264200, Peoples R China
4.Heilongjiang Acad Agr Sci, Harbin 150086, Peoples R China
关键词： hyperspectral imaging;rough set;band selection;maximal relevance;minimal redundancy
期刊名称：MEASUREMENT SCIENCE AND TECHNOLOGY （ 影响因子：2.046； 五年影响因子：2.11 ）
ISSN： 0957-0233
年卷期： 2016 年 27 卷 12 期
页码：
收录情况： SCI
摘要： Band selection is considered to be an important processing step in handling hyperspectral data. In this work, we selected informative bands according to the maximal relevance minimal redundancy (MRMR) criterion based on neighborhood mutual information. Two measures MRMR difference and MRMR quotient were defined and a forward greedy search for band selection was constructed. The performance of the proposed algorithm, along with a comparison with other methods (neighborhood dependency measure based algorithm, genetic algorithm and uninformative variable elimination algorithm), was studied using the classification accuracy of extreme learning machine (ELM) and random forests (RF) classifiers on soybeans' hyperspectral datasets. The results show that the proposed MRMR algorithm leads to promising improvement in band selection and classification accuracy.
- 相关文献
作者其他论文 更多>>
-
Detection of paralytic shellfish toxins by near-infrared spectroscopy based on a near-Bayesian SVM classifier with unequal misclassification costs
作者：Liu, Yao;Xiong, Jianfang;Qiao, Fu;Qiao, Fu;Xu, Lele;Xu, Zhen;Liu, Yao
关键词：near-infrared spectroscopy; paralytic shellfish toxins; near-Bayesian SVM; unequal misclassification costs; imbalanced classification
-
Identification of Perna viridis contaminated with diarrhetic shellfish poisoning toxins in vitro using NIRS and a discriminative non-negative representation-based classifier
作者：Liu, Yao;Liu, Zhongyan;Qiao, Fu;Qiao, Fu;Xu, Lele;Xu, Zhen
关键词：Near-infrared spectroscopy; Diarrhetic shellfish poisoning; Perna viridis; Discriminative non-negative representation-based classifier; Identification
-
Fast Detection of Diarrhetic Shellfish Poisoning Toxins in Mussels Using NIR Spectroscopy and Improved Twin Support Vector Machines
作者：Liu, Yao;Wang, Runtao;Qiao, Fu;Jiang, Wei;Xu, Lele;Xu, Zhen
关键词：near-infrared spectroscopy; diarrhetic shellfish poisoning toxins; mussels (Mytilidae); waveband selection; twin support vector machines (TWSVM)
-
Study on the detection of heavy metal lead (Pb) in mussels based on near-infrared spectroscopy technology and a REELM classifier
作者：Liu, Yao;Wang, Runtao;Xu, Lele;Qiao, Fu;Xiong, Jianfang;Xu, Zhen
关键词：Near-infrared spectroscopy; Mussels; Heavy metal pollution; Wavelength selection; Residual errors
-
Rapid detection of mussels contaminated by heavy metals using near-infrared reflectance spectroscopy and a constrained difference extreme learning machine
作者：Liu, Yao;Xu, Lele;Zeng, Shaogeng;Qiao, Fu;Jiang, Wei;Xu, Zhen
关键词：Near-infrared reflectance spectroscopy; Heavy metal; Mussel; Wavelength selection; Constrained difference extreme learning; machine
-
Semisupervised classification of hyperspectral images based on tri-training algorithm with enhanced diversity
作者：Cui, Ying;Song, Guojiao;Wang, Xueting;Wang, Liguo;Cui, Ying;Lu, Zhongjun
关键词：hyperspectral image;semisupervised classification;tri-training algorithm;diversification of classifiers;stratified sampling
-
Hyperspectral band selection based on consistency-measure of neighborhood rough set theory
作者：Liu, Yao;Xie, Hong;Wang, Liguo;Liu, Yao;Tan, Kezhu;Chen, Yuehua;Xu, Zhen
关键词：hyperspectral imaging;consistency-measure;neighborhood rough set;band selection
