Clustering of Remote Sensing Imagery Using a Social Recognition-Based Multi-objective Gravitational Search Algorithm
Clustering of Remote Sensing Imagery Using a Social Recognition-Based Multi-objective Gravitational Search Algorithm
复制标题
使用基于社会识别的多目标引力搜索算法对遥感图像进行聚类
DOI：
10.1007/s12559-018-9582-9
复制
发表时间：
2018-07
影响因子：
5.4
通讯作者：
Zhenjie Wang
中科院分区：
文献类型：
--
作者：
Aizhu Zhang;Sihan Liu;Genyun Sun;Hui Huang;Ping Ma;Jun Rong;Hongzhang Ma;Chengyan Lin;Zhenjie Wang
认知启发的群智能算法（SIAs）由于能够赋予机器自学习能力以获得更好的分类结果而在聚类研究领域受到广泛关注。近年来，基于SIA的多目标优化（MOO）方法在数据聚类中显示出了其优越性。然而，它们的性能是有限的，当应用于遥感图像（RSI）的聚类。为了构造一个优秀的基于MOO的聚类方法，本文提出了一种基于社会约束的多目标引力搜索算法（SMGSA），以实现两个冲突的聚类有效性指标，即，Xie-Beni（XB）指数和Jmindex.在SMGSA中，搜索粒子不仅通过引力被存储在外部档案中的精英粒子引导，而且还通过位置差异从整个种群的社会认知中学习。从而形成了具有突出开发能力的SMGSA。通过对两个公开的遥感影像数据集的对比实验，验证了基于MOO的聚类方法比基于单一有效性指数的方法能获得更准确的结果。此外，基于SMGSA的方法可以获得比不具有社会识别能力的多目标引力搜索算法更上级的结果。建议SMGSA之间的两个冲突的聚类有效性指标进行了有利的平衡，并实现了更好的分类RSI。此外，本研究还表明，基于群体智能的认知计算在复杂遥感场景的智能解译和理解方面具有很大的潜力。
Cognitively inspired swarm intelligence algorithms (SIAs) have attracted much attention in the research area of clustering since it can give machine the ability of self-learning to achieve better classification results. Recently, the SIA-based multi-objective optimization (MOO) methods have shown their superiorities in data clustering. However, their performances are limited when applying to the clustering of remote sensing imagery (RSI). To construct an excellent MOO-based clustering method, this paper presents a social recognition-based multi-objective gravitational search algorithm (SMGSA) to achieve simultaneous optimization of two conflicting cluster validity indices, i.e., the Xie-Beni (XB) index and theJmindex. In the SMGSA, searching particles not only are guided by those elite particles stored in an external archive by the gravitational force but also learn from the social recognition of the whole population through the position difference. SMGSA thereby formed with outstanding exploitation ability. Comparison experiments on two public RSI data sets, including a moderate aerial image and a hyperspectral, validated that the MOO-based clustering methods could obtain more accurate results than the single validity index-based method. Moreover, the SMGSA-based method can achieve superior results than that of the multi-objective gravitational search algorithm without social recognition ability. The proposed SMGSA performs favorable balance between the two conflicting cluster validity indices and achieves preferable classification for the RSI. In addition, this study indicates that the swarm intelligence-based cognitive computing is potential for the intelligent interpretation and understanding of complicated remote sensing scene.
登录
查看更多内容
基于多目标生物地理学的优化迁移模型的数值比较
影响因子：
8.1
作者：
Guo Weian;Wang Lei;Wu Qidi
通讯作者：
Wu Qidi
DOI：
10.1016/j.compeleceng.2017.06.001
发表时间：
2017-06
期刊：
Comput. Electr. Eng.
影响因子：
--
作者：
Baoyong Yin;Zhaolu Guo;Zhengping Liang;Xuezhi Yue
通讯作者：
Baoyong Yin;Zhaolu Guo;Zhengping Liang;Xuezhi Yue
影响因子：
8.5
作者：
Mirjalili, Seyedali;Saremi, Shahrzad;Coelho, Leandro dos S.
通讯作者：
Coelho, Leandro dos S.
DOI：
10.1109/tpami.2002.1114856
发表时间：
2002-12-01
影响因子：
23.6
作者：
Maulik, U;Bandyopadhyay, S
通讯作者：
Bandyopadhyay, S
影响因子：
5.4
作者：
Siddique N;Adeli H
通讯作者：
Adeli H