Abstract：In order to fully extract the identifiable information in the image and improve classification accuracy rate, a structure named multiple kernel empirical learning network(MKELN) was proposed. In the feature extraction part, the original image is gradually enhanced by the two-dimensional Gaussian distribution. The local receptive field and the global receptive field are used to fully extract features in the original image and the gradually regional enhancement image, and they are connected in series to form feature vector that represents an image. In the classification part, a multiple kernel empirical algorithm was proposed, and the low rank feature matrix is used as the hidden layer of the network to solve the output weight of the network. To verify the effectiveness of this network, it was tested with USPS, MNIST and NORB data sets. The experiment proves that the proposed MKELN can further extract feature information based on ELM-LRF, effectively improving the classification accuracy.
［1］ Huang G B , Zhu Q Y , Siew C K . Extreme learning machine: Theory and applications［J］. Neurocomputing, 2006, 70(1-3): 489-501.
［2］ 李荣雨, 王立明. 基于ISOMAP-ELM的软测量建模及化工应用［J］. 计量学报, 2016, 37(5): 548-552.
Li R Y, Wang L M. Soft measurement modeling and chemical application based on ISOMAP-ELM neural network［J］. Acta Metrologica Sinica, 2016, 37(5): 548-552.
［3］ 李荣雨, 戚桂洪. 基于CSSE-OSELM算法的软测量建模及其工业应用［J］. 计量学报, 2017, 38(5): 650-655.
Li R Y, Qi G H. Soft sensor modeling based on CSSE-OSELM［J］. Acta Metrologica Sinica, 2017, 38(5): 650-655.
［4］ 牛培峰, 史春见, 刘楠, 等. 基于GSA-PELM的锅炉NOx预测模型［J］. 计量学报, 2018, 39(5): 741-746.
Niu P F, Shi C J, Liu N, et al. Optimization for NOx prediction model from boilers based on GSA-PELM［J］. Acta Metrologica Sinica, 2018, 39(5): 741-746.
［5］ 魏立新, 张宇, 孙浩, 等. 基于改进OS-ELM的冷连轧在线轧制力预报［J］. 计量学报, 2019, 40(1): 111-116.
Wei L X, Zhang Y, Sun H, et al. Online cold rolling prediction based on improved OS-ELM［J］. Acta Metrologica Sinica, 2019, 40(1): 111-116.
［6］ Yu J, Song W, Li M, et al. A novel image classification algorithm based on extreme learning machine［J］. China Communications, 2015, 12(s2): 48-54.
［7］ Zhou Y, Peng J, Chen C L, et al. Extreme learning machine with composite kernels for hyperspectral image classification［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(6): 2351-2360.
［8］ Zhu M, Song Y, Guo J, et al. PCA and kernel-based extreme learning machine for side-scan sonar image classification［C］//IEEE OES International Symposium on Underwater Technology (UT), South Korea, Busan, 2017.
［9］ Krizhevsky A, Sutskever I, Hinton G E, et al. ImageNet classification with deep convolutional neural networks［J］. Neural Information Processing Systems, 2012, 141(5): 1097-1105.
［10］ Huang G B, Bai Z, Kasun L L C, et al. Local receptive fields based extreme learning machine［J］. IEEE Computational Intelligence Magazine, 2015, 10(2): 18-29.
［11］ Shan P, Xinyi Y. Deep Convolutional extreme learning machine and its application in handwritten digit classification［J］. Computational Intelligence and Neuroscience, 2016, 2016(3): 1-10.
［12］ Huang J, Yu Z L, Cai Z, et al. Extreme learning machine with multi-scale local receptive fields for texture classification［J］. Multidimensional Systems and Signal Processing, 2017, 28(3): 995-1011.
［13］ Wu C, Li Y, Zhao Z, et al. Extreme learning machine with autoencoding receptive fields for image classification［J］. Neural Computing and Applications, 2019, 1-17.
［14］ Kasun L L C, Zhou H, Huang G B, et al. Representational Learning with Extreme Learning Machine for Big Data［J］. IEEE Intelligent Systems, 2013, 28(6), 31-34.
［15］ Jia X, Li X, Jin Y, et al. Region-enhanced multi-layer extreme learning machine［J］. Cognitive Computation, 2019, 11(1): 101-109.
［16］ Huang G B, Zhou H, Ding X, et al. Extreme learning machine for regression and multiclass classification［J］. IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 2012, 42(2): 513-529.
［17］ Vong C M, Chen C, Wong P K, et al. Empirical kernel map-based multilayer extreme learning machines for representation learning［J］. Neurocomputing, 2018, 310: 265-276.
［18］ 钱萌, 唐家康. 基于混合核极限学习机的多标签学习研究［J］. 重庆科技学院学报(自然科学版), 2019, 21(2): 79-85.
Qian M, Tang J K. Multi-label learning based on mixed kernel extreme learning machine［J］. Journal of Chongqing University of Science and Technology(Natural Sciences Edition), 2019, 21(2): 79-85.
［19］ Li X, Mao W, Jiang W. Multiple-kernel-learning-based extreme learning machine for classification design［J］. Neural Computing and Applications, 2016, 27(1): 175-184.
［20］ Liu X, Wang L, Huang G B, et al. Multiple kernel extreme learning machine［J］. Neurocomputing, 2015, 149(A): 253-264.
［21］ Cao L, Huang W, Sun F, et al. Optimization-based extreme learning machine with multi-kernel learning approach for classification［C］// 22nd International Conference on Pattern Recognition, Stockholm, Sweden, 2014.
［22］ Xue J, Liu Q, Li M, et al. Incremental multiple kernel extreme learning machine and its application in Robo-advisors［J］. Soft Computing, 2018, 22(11): 3507-3517.
［23］ Ding S, Guo L, Hou Y. Extreme learning machine with kernel model based on deep learning［J］. Neural Computing and Applications, 2017, 28(8): 1975-1984.
［24］ Wang Y, Xie Z, Xu K, et al. An efficient and effective convolutional auto-encoder extreme learning machine network for 3d feature learning［J］. Neurocomputing, 2016, 174(PB): 988-998.
［25］ Tang J, Deng C, Huang G B, et al. Extreme learning machine for multilayer perceptron［J］. IEEE Transactions on Neural Networks, 2016, 27(4): 809-821.
［26］ He B, Song Y, Zhu Y, et al. Local receptive fields based extreme learning machine with hybrid filter kernels for image classification［J］. Multidimensional Systems and Signal Processing, 2019, 30(3): 1149-1169.
2021, Vol. 42 
