Flotation performance recognition based on dual-modality multiscale CNN features and adaptive deep learning KELM

Yi-peng LIAO; Jin ZHANG; Zhi-gang WANG; Wei-xing WANG

doi:10.3788/OPE.20202808.1785

您当前的位置：

首页 >

文章列表页 >

Flotation performance recognition based on dual-modality multiscale CNN features and adaptive deep learning KELM

Information Sciences | 更新时间：2020-08-14

- Flotation performance recognition based on dual-modality multiscale CNN features and adaptive deep learning KELM
- Optics and Precision Engineering Vol. 28, Issue 8, Pages: 1785-1798(2020)
- 作者机构：
  
  1.福州大学物理与信息工程学院, 福建福州 350108
  2.福建金东矿业股份有限公司, 福建三明 365101
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20202808.1785
  CLC： TP391
- Received：12 March 2020，
  
  Revised：20 April 2020，
  
  Accepted：20 April 2020，
  
  Published：25 August 2020
- 稿件说明：
移动端阅览
Yi-peng LIAO, Jin ZHANG, Zhi-gang WANG, et al. Flotation performance recognition based on dual-modality multiscale CNN features and adaptive deep learning KELM[J]. Optics and precision engineering, 2020, 28(8): 1785-1798.
DOI：

Yi-peng LIAO, Jin ZHANG, Zhi-gang WANG, et al. Flotation performance recognition based on dual-modality multiscale CNN features and adaptive deep learning KELM[J]. Optics and precision engineering, 2020, 28(8): 1785-1798. DOI： 10.3788/OPE.20202808.1785.

摘要

针对可见光图像特征驱动的浮选工况识别方法的不足，提出一种基于双模态图像多尺度CNN特征及自适应深度自编码核极限学习机（Kernel Extreme Learning Machine，KELM）的浮选工况识别方法。先对泡沫的可见光、红外图像进行非下采样剪切波多尺度分解，设计双通道CNN网络对双模态多尺度图像进行特征提取及融合，将多个双隐层自编码极限学习机串联成深度学习网络对CNN特征逐层抽象提取，然后通过核极限学习机映射到更高维空间进行决策，最后改进量子细菌觅食算法并应用于深度自编码KELM识别模型参数优化。实验结果表明：采用双模多尺度CNN特征较单模多尺度、双模单尺度CNN特征的识别精度提高了2.65%，自适应深度自编码KELM模型具有较好的分类精度和泛化性能，各工况识别的平均准确率达到95.98%，识别精度和稳定性较现有方法有较大提升。

Abstract

To address the limitations of visible image feature-driven flotation performance recognition method

a new flotation performance recognition method based on dual-modality multiscale images CNN features and adaptive deep autoencoder kernel extreme learning machine was proposed.First

the visible and infrared images of foam were decomposed by nonsubsampled shearlet multiscale transform

and a two-channel CNN network was developed to extract and fuse the features of the dual-modality multiscale images.Then

the CNN features were abstracted layer-by-layer in the deep learning network

which was connected by a series of two hidden layer autoencoder extreme learning machine.Then

the decision was made by mapping to a higher dimensional space through the kernel extreme learning machine.Finally

the quantum bacterial foraging algorithm was improved and applied to optimize the recognition model parameters. The experimental results show that the recognition accuracy using dual-modality multiscale CNN features is clearly better than that of single modality multiscale and dual-modality single scale CNN features at a confidence level of 2.65%. Further

the adaptive deep autoencoder kernel extreme learning machine has better classification accuracy and generalization performance. The average recognition accuracy of each working condition reaches 95.98%. The accuracy and stability of flotation performance recognition is considerably improved compared with the existing methods.

关键词

Keywords

references

J ZHANG , Z H TANG , M X AI , 等 . Nonlinear modeling of the relationship between reagent dosage and flotation froth surface image by Hammerstein-Wiener model . Minerals Engineering , 2018 . 120 ( 5 ): 19 - 28 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=72ba9e3a3c52118b8e6f70b94569dc0f http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=72ba9e3a3c52118b8e6f70b94569dc0f .

黄凌霄 , 廖一鹏 . 浮选气泡NSCT域多尺度等效形态特征提取及识别 . 光学精密工程 , 2020 . 28 ( 3 ): 704 - 716 . http://ope.lightpublishing.cn/thesisDetails?columnId=2127181&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2127181&Fpath=&index=-1&l=zh .

L X HUANG , Y P LIAO . Recognition and multiscale equivalent morphological features extraction of flotation bubbles in NSCT domain . Opt. Precision Eng. , 2020 . 28 ( 3 ): 704 - 716 . http://ope.lightpublishing.cn/thesisDetails?columnId=2127181&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2127181&Fpath=&index=-1&l=zh .

A JAHEDSARAVANI , MARHABAN , H M , 等 . Prediction of the metallurgical performances of a batch flotation system by image analysis and neural networks . Minerals Engineering , 2014 . 69 ( 8 ): 137 - 145 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=3420220a8e831426311c3aec3329b7c2 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=3420220a8e831426311c3aec3329b7c2 .

Y L WANG , B SUN , R Q ZHANG , 等 . Sulfur flotation performance recognition based on hierarchical classification of local dynamic and static froth features . IEEE Access , 2018 . 6 ( 3 ): 14019 - 14029 . http://ieeexplore.ieee.org/document/8289360 http://ieeexplore.ieee.org/document/8289360 .

王建林 , 付雪松 , 黄展超 , 等 . 改进YOLOv2卷积神经网络的多类型合作目标检测 . 光学精密工程 , 2020 . 28 ( 1 ): 251 - 260 . http://ope.lightpublishing.cn/thesisDetails?columnId=1496735&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1496735&Fpath=&index=-1&l=zh .

J L WANG , X S FU , ZH CH HUANG , 等 . Multi-type cooperative targets detection using improved YOLOv2 convolutional neural network . Opt. Precision Eng. , 2020 . 28 ( 1 ): 251 - 260 . http://ope.lightpublishing.cn/thesisDetails?columnId=1496735&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1496735&Fpath=&index=-1&l=zh .

Y FU , C ALDRICH . Froth image analysis by use of transfer learning and convolutional neural networks . Minerals Engineering , 2018 . 115 68 - 78 . DOI: 10.1016/j.mineng.2017.10.005 http://doi.org/10.1016/j.mineng.2017.10.005 .

Y FU , C ALDRICH . Flotation froth image recognition with convolutional neural networks . Minerals Engineering , 2019 . 132 183 - 190 . DOI: 10.1016/j.mineng.2018.12.011 http://doi.org/10.1016/j.mineng.2018.12.011 .

X L WANG , S CHEN , C H YANG , 等 . Process working condition recognition based on the fusion of morphological and pixel set features of froth for froth flotation . Minerals Engineering , 2018 . 128 17 - 26 . DOI: 10.1016/j.mineng.2018.08.017 http://doi.org/10.1016/j.mineng.2018.08.017 .

王运兰 . 基于极限学习机和离散小波变换的视频水印算法 . 液晶与显示 , 2020 . 35 ( 2 ): 180 - 188 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs202002012 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs202002012 .

Y L WANG . Video watermarking algorithm based on extreme learning machine and discrete wavelet transform . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 2 ): 180 - 188 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs202002012 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs202002012 .

Z X YANG , L L TANG , K ZHANG , 等 . Multi-view CNN feature aggregation with ELM auto-encoder for 3D shape recognition . Cognitive Computation , 2018 . 10 908 - 921 . DOI: 10.1007/s12559-018-9598-1 http://doi.org/10.1007/s12559-018-9598-1 .

N ZHANG , S F DING , J ZHANG . Multi-layer ELM-RBF for multi-label learning . Applied Soft Computing , 2016 . 43 535 - 545 . DOI: 10.1016/j.asoc.2016.02.039 http://doi.org/10.1016/j.asoc.2016.02.039 .

S SINGH , R S ANAND , D GUPTA . CT and MR image information fusion scheme using a cascaded framework in ripplet and NSST domain . IET Image Processing , 2018 . 12 ( 5 ): 696 - 707 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=64b854c6b18a7e4f888024982309b0ab http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=64b854c6b18a7e4f888024982309b0ab .

H Y GAO , C W LI . Quantum-inspired bacterial foraging algorithm for parameter adjustment in green cognitive radio . Journal of Systems Engineering and Electronics , 2015 . 26 ( 5 ): 897 - 907 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xtgcydzjs-e201505001 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xtgcydzjs-e201505001 .

S H MORAR , D J BRADSHAW , M C HARRIS . The use of the froth surface lamellae burst rate as a flotation froth stability measurement . Minerals Engineering , 2012 . 36 ( 4 ): 152 - 159 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9067b532c2d7e038cc23ca9b4ddd221f http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9067b532c2d7e038cc23ca9b4ddd221f .

廖一鹏 , 王卫星 . 基于Shearlet多尺度边界检测及融合的浮选气泡提取 . 光学学报 , 2018 . 38 ( 3 ): 0315004 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201803036 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201803036 .

Y P LIAO , W X WANG . Flotation bubble delineation based on Shearlet multiscale boundary detection and fusion . Acta Optica Sinica , 2018 . 38 ( 3 ): 0315004 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201803036 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201803036 .

Y S CHENG , D W ZHAO , Y B WANG , 等 . Multi-label learning with kernel extreme learning machine autoencoder . Knowledge-Based Systems , 2019 . 178 1 - 10 . http://cn.bing.com/academic/profile?id=d622360be342de39104eb9952d8f1902&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=d622360be342de39104eb9952d8f1902&encoded=0&v=paper_preview&mkt=zh-cn .

J KIM , B LEE . Identification of Alzheimer's disease and mild cognitive impairment using multimodal sparse hierarchical extreme learning machine . Hum Brain Mapp , 2018 . 39 ( 9 ): 3728 - 3741 . DOI: 10.1002/hbm.24207 http://doi.org/10.1002/hbm.24207 .

K M PASSINO . Biomimicry of bacterial foraging for distributed optimization and control . IEEE Control Systems Magazine , 2002 . 22 ( 3 ): 52 - 67 . DOI: 10.1109/MCS.2002.1004010 http://doi.org/10.1109/MCS.2002.1004010 .

V TKACHUK . Quantum genetic algorithm based on qutrits and its application . Mathematical Problems in Engineering , 2018 . 4 8614073 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=8a812ce0da16a98945c35c5fa2a652a2 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=8a812ce0da16a98945c35c5fa2a652a2 .

A LAYEB . A hybrid quantum inspired harmony search algorithm for 0-1 optimization problems . Journal of Computational and Applied Mathematics , 2013 . 253 14 - 25 . DOI: 10.1016/j.cam.2013.04.004 http://doi.org/10.1016/j.cam.2013.04.004 .

L LIU , L SHAN , Y W DAI , 等 . A modified quantum bacterial foraging algorithm for parameters identification of fractional-order system . IEEE Access , 2018 . 6 ( 11 ): 6610 - 6619 . http://cn.bing.com/academic/profile?id=c176c0ca64dba5ce7264d1b5952aedd7&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=c176c0ca64dba5ce7264d1b5952aedd7&encoded=0&v=paper_preview&mkt=zh-cn .

Views

659

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Secret key extraction from atmospheric wireless optical channels by combing with generative adversarial network

Progressive CNN-transformer semantic compensation network for polyp segmentation

Cascade residual-optimized image super-resolution reconstruction in Transformer network

Real-time urban street view semantic segmentation based on cross-layer aggregation network

Collaborative classification of hyperspectral and LiDAR data based on CNN-transformer

Related Author

WANG Fang

LI Yanfeng

YU Haiyang

HU Xiaojuan

CHEN Chunyi

TIAN Zhuozhan

LI Denghui

LI Daxiang

Related Institution

Chongqing Research Institute， Changchun University of Science and Technology

School of Computer Science and Technology， Changchun University of Science and Technology

College of Communication and Information Engineering，Xi′an University of Posts and Telecommunication，Xi′an

College of Physics and Telecommunication Engineering， Fuzhou University

Fujian Science and Technology Innovation Laboratory for Optoelectronic Information of China

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰