[1]温晓红,刘华平,阎高伟,等.基于超限学习机的非线性典型相关分析及应用[J].智能系统学报,2018,13(04):633-639.[doi:10.11992/tis.201703034]
 WEN Xiaohong,LIU Huaping,YAN Gaowei,et al.Nonlinear canonical correlation analysis and application based on extreme learning machine[J].CAAI Transactions on Intelligent Systems,2018,13(04):633-639.[doi:10.11992/tis.201703034]
点击复制

基于超限学习机的非线性典型相关分析及应用(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第13卷
期数:
2018年04期
页码:
633-639
栏目:
出版日期:
2018-07-05

文章信息/Info

Title:
Nonlinear canonical correlation analysis and application based on extreme learning machine
作者:
温晓红1 刘华平23 阎高伟1 孙富春23
1. 太原理工大学 电气与动力工程学院, 山西 太原 030600;
2. 清华大学 计算机科学与技术系, 北京 100084;
3. 智能技术与系统国家重点实验室, 北京 100084
Author(s):
WEN Xiaohong1 LIU Huaping23 YAN Gaowei1 SUN Fuchun23
1. College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030600, China;
2. Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China;
3. State Key Laboratory of Intelligent Technology and Systems, Beijing 100084, China
关键词:
典型相关分析超限学习机特征提取多模态融合机器抓取目标识别RGB-D数据神经网络
Keywords:
canonical correlation analysisextreme learning machinefeature extractionmulti-modal fusionrobotic graspingobject recognitionRGB-D dataneural networks
分类号:
TP391.4
DOI:
10.11992/tis.201703034
摘要:
典型相关分析是目前常用的研究两个变量间相关性的统计方法。针对线性典型相关分析难以准确揭示变量之间复杂关系的问题,提出一种基于超限学习机的非线性典型相关分析多模态特征提取方法。首先,采用超限学习机分别的对每个模态进行无监督特征学习,得到抽象的深度特征表示;然后将这些深度抽象特征通过典型相关分析极大化模态之间的相关性,同时得到两组相关变量,实现多模态数据的复杂非线性和高相关性表示。最后在康奈尔大学机器抓取公开数据集上进行实验验证,结果表明,所提出的方法与其他相关算法相比,训练速度得到显著提升。
Abstract:
Canonical correlation analysis (CCA) is a statistical technique commonly used to determine the correlativity of two variables. It is difficult to accurately identify the complex underlying relationship between variables using linear CCA, so we propose a nonlinear CCA based on an extreme learning machine (ELM) for multi-modal feature extraction. First, to obtain abstract-depth feature representation, we use the ELM to perform unsupervised feature learning for each modality. Then, we use CCA to maximize the correlation between the nonlinear representations, thereby simultaneously obtaining two groups of related variables, and realize complex nonlinear and high-correlation representations of multi-modality data. Lastly, we conducted an experiment using the Cornell grasping dataset. The results show that, in comparison with other related algorithms, the proposed method significantly increases the training speed.

参考文献/References:

[1] HOTELLING H. Relations between two sets of variates[J]. Biometrika, 1936, 28(3/4):321-377.
[2] SARGIN M E, YEMEZ Y, ERZIN E, et al. Audiovisual synchronization and fusion using canonical correlation analysis[J]. IEEE transactions on multimedia, 2007, 9(7):1396-1403.
[3] 侯书东, 孙权森. 稀疏保持典型相关分析及在特征融合中的应用[J]. 自动化学报, 2012, 38(4):659-665. HOU Shudong, SUN Quansen. Sparsity preserving canonical correlation analysis with application in feature fusion[J]. Acta automatica sinica, 2012, 38(4):659-665.
[4] YUAN Yunhao, SUN Quansen, GE Hongwei. Fractional-order embedding canonical correlation analysis and its applications to multi-view dimensionality reduction and recognition[J]. Pattern recognition, 2014, 47(3):1411-1424.
[5] XING Xianglei, WANG Kejun, YAN Tao, et al. Complete canonical correlation analysis with application to multi-view gait recognition[J]. Pattern recognition, 2016, 50:107-117.
[6] RASIWASIA N, PEREIRA J C, COVIELLO E, et al. A new approach to cross-modal multimedia retrieval[C]//Proceedings of the 18th ACM International Conference on Multimedia. New York, NY, USA, 2010:251-260.
[7] HARDOON D R, SZEDMAK S, SHAWE-TAYLOR J. Canonical correlation analysis:an overview with application to learning methods[J]. Neural computation, 2004, 16(12):2639-2664.
[8] ANDREW G, ARORA R, BILMES J, et al. Deep canonical correlation analysis[C]//Proceedings of the 30th International Conference on Machine Learning. Atlanta, Georgia, USA, 2013:Ⅲ-1247-Ⅲ-1255.
[9] WANG Weiran, ARORA R, LIVESCU K, et al. On deep multi-view representation learning[C]//Proceedings of the 32nd International Conference on Machine Learning. Lille, France, 2015:1083-1092.
[10] HUANG Guang, ZHU Qinyu, SIEW C K. Extreme learning machine:theory and applications[J]. Neurocomputing, 2006, 70(1/2/3):489-501.
[11] CAMBRIA E, HUANG Guangbin, KASUN L L C, et al. Extreme learning machines:trends and controversies[J]. IEEE intelligent systems, 2013, 28(6):30-59. (请核对标题信息)
[12] YU Wenchao, ZHUANG Fuzhen, HE Qing, et al. Learning deep representations via extreme learning machines[J]. Neurocomputing, 2015, 149:308-315.
[13] SUN Kai, ZHANG Jiangshe, ZHANG Chunxia, et al. Generalized extreme learning machine autoencoder and a new deep neural network[J]. Neurocomputing, 2017, 230:374-381.
[14] UZAIR M, SHAFAIT F, GHANEM B, et al. Representation learning with deep extreme learning machines for efficient image set classification[M]//MACINTYRE J. Neural Computing and Applications. London:Springer, 2015:1-13.
[15] WEI Jie, LIU Huaping, YAN Gaowei, et al. Robotic grasping recognition using multi-modal deep extreme learning machine[J]. Multidimensional systems and signal processing, 2017, 28(3):817-833.
[16] WANG Weiran, ARORA R, LIVESCU K, et al. Unsupervised learning of acoustic features via deep canonical correlation analysis[C]//Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing. Brisbane, Australia, 2015:4590-4594.
[17] LENZ I, LEE H, SAXENA A. Deep learning for detecting robotic grasps[J]. The international journal of robotics research, 2015, 34(4/5):705-724.
[18] JIANG Yun, MOSESON S, SAXENA A. Efficient grasping from RGBD images:learning using a new rectangle representation[C]//Proceedings of 2011 IEEE International Conference on Robotics and Automation. Shanghai, China, 2011:3304-3311.
[19] 韩峥, 刘华平, 黄文炳, 等. 基于Kinect的机械臂目标抓取[J]. 智能系统学报, 2013, 8(2):149-155. HAN Zheng, LIU Huaping, HUANG Wenbing, et al. Kinect-based object grasping by manipulator[J]. CAAI transactions on intelligent systems, 2013, 8(2):149-155.
[20] 温有福, 贾彩燕, 陈智能. 一种多模态融合的网络视频相关性度量方法[J]. 智能系统学报, 2016, 11(3):359-365. WEN Youfu, JIA Caiyan, CHEN Zhineng. A multi-modal fusion approach for measuring web video relatedness[J]. CAAI transactions on intelligent systems, 2016, 11(3):359-365.
[21] 姬晓飞, 秦宁丽, 刘洋. 多特征的光学遥感图像多目标识别算法[J]. 智能系统学报, 2016, 11(5):655-662. JI Xiaofei, QIN Ningli, LIU Yang. Research on multi-feature based multi-target recognition algorithm for optical remote sensing image[J]. CAAI transactions on intelligent systems, 2016, 11(5):655-662.
[22] CAMPLANI M, PAIEMENT A, MIRMEHDI M, et al. Multiple human tracking in RGB-D data:a survey[J]. arXiv:1606.04450, 2016.

相似文献/References:

[1]倪怀发,沈肖波,孙权森.基于低秩分解的鲁棒典型相关分析[J].智能系统学报,2017,12(04):491.[doi:10.11992/tis.201607024]
 NI Huaifa,SHEN Xiaobo,SUN Quansen.Robust canonical correlation analysis based onlow rank decomposition[J].CAAI Transactions on Intelligent Systems,2017,12(04):491.[doi:10.11992/tis.201607024]

备注/Memo

备注/Memo:
收稿日期:2017-03-24。
基金项目:国家自然科学基金重点项目(U1613212);国家高技术研究发展计划项目(2015AA042306).
作者简介:温晓红,女,1993年生,硕士研究生,主要研究方向为智能控制、模式识别、多模态融合;刘华平,男,1976年生,副教授,博士生导师,主要研究方向为机器人感知、学习与控制,多模态信息融合;阎高伟,男,1970年生,教授,主要研究方向为复杂工业控制系统、智能控制理论及其应用、机器学习与软测量建模。
通讯作者:刘华平.E-mail:hpliu@tsinghua.edu.cn.
更新日期/Last Update: 2018-08-25