Abstract
Based on the network structure and training methods of extreme learning machines, extreme learning machine combining hidden-layer feature weighting and batch training (ELM-WB) is proposed to make full use of representation-level features for object images and human action videos classification. To solve the problem of insufficient fusion of multiple representation-level features in most classification methods, a double hidden layer structure in which the input layer and the second hidden layer are directly connected is designed. A loop training method of weighting coefficients and output weights is proposed based on the advantages of this structure. The proposed network structure and training method are combined to construct an extreme learning machine combining hidden-layer feature weighting (ELM-W), which can effectively fuse representation-level features to enhance the classification ability of representation-level features. On this basis, the principle of online sequential ELM (OS-ELM) is introduced to update the loop training formula of the two weights to reduce the memory consumption during the operation of the overall algorithm. ELM-WB is proposed by combining the loop training formula of two weight matrices with batch training. In order to test the feasibility of ELM-WB, experiments are conducted on Caltech 101, MSRC, UCF11 and UCF101 databases. Experimental results prove that the proposed ELM-WB can improve classification accuracy by fusing representation-level features. At the same time, ELM-WB can be used to perform classification tasks on databases of any size in a general-purpose computer without specific hardware.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data Availability
The Caltech 101 [34], MSRC [35], UCF11 [36] and UCF101 [27] databases that are used to support the findings of this study could be found freely here: https://data.caltech.edu/records/mzrjq-6wc02https://www.microsoft.com/en-us/download/details.aspx?id=52644https://www.crcv.ucf.edu/data/UCF_YouTube_Action.php and https://www.crcv.ucf.edu/data/UCF101.php, respectively.
References
Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In: IEEE International Joint Conference on Neural Networks, Budapest, Hungary, pp 985–990. https://doi.org/10.1109/IJCNN.2004.1380068.
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1/3):489–501. https://doi.org/10.1016/j.neucom.2005.12.126
Huang GB, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B Cybern 42(2):513–529. https://doi.org/10.1109/TSMCB.2011.2168604
Deng WY, Ong YS, Zheng QH (2016) A fast reduced kernel extreme learning machine. Neural Netw 76:29–38
Albtoush A, Fernández-Delgado M, Cernadas E, Barro S (2022) Quick extreme learning machine for large-scale classification. Neural Comput Appl 34(8):5923–5938. https://doi.org/10.1007/s00521-021-06727-8
Preeti BR, Dagar A et al (2021) A novel online sequential extreme learning machine with L2,1-norm regularization for prediction problems. Appl Intell 51(3):1669–1689. https://doi.org/10.1007/s10489-020-01890-2
Zhang Z, Cai Y, Gong W (2023) Semi-supervised learning with graph convolutional extreme learning machines. Expert Syst Appl 213:119164
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, USA, pp 2169–2178. https://doi.org/10.1109/CVPR.2006.68.
Jégou H, Douze M, Schmid C, Pérez P (2010) Aggregating local descriptors into a compact image representation. In: Computer Vision and Pattern Recognition. CVPR. pp 3304–3311
Sánchez J, Perronnin F, Mensink T, Verbeek J (2013) Image classification with the fisher vector: theory and practice. Int J Comput Vis 105(3):222–245
Xing HJ, Wang XM (2013) Training extreme learning machine via regularized correntropy criterion. Neural Comput Appl 23(7–8):1977–1986. https://doi.org/10.1007/s00521-012-1184-y
Chen L, Paul H, Qu H et al (2018) Correntropy-based robust multilayer extreme learning machines. Pattern Recogn 84:357–370
Chen M, Li Y, Luo X et al (2018) A novel human activity recognition scheme for smart health using multilayer extreme learning machine. IEEE Internet Things J 6(2):1410–1418
Vong CM, Du J, Wong CM et al (2018) Postboosting using extended G-mean for online sequential multiclass imbalance learning. IEEE Trans Neural Netw Learn Syst 29(12):6163–6177
Du J, Vong CM (2019) Robust online multilabel learning under dynamic changes in data distribution with labels. IEEE Trans Cybern 50(1):374–385
Chen C, Gan Y, Vong CM (2020) Extreme semi-supervised learning for multiclass classification. Neurocomputing 376:103–118
Wang C, Peng G, De Baets B (2022) Embedding metric learning into an extreme learning machine for scene recognition. Expert Syst Appl 203:117505
Wu Q, Fu YL, Cui DS, Wang E (2023) C-loss-based doubly regularized extreme learning machine. Cognit Comput 15(2):496–519
Kasun LLC, Zhou H, Huang GB, Vong CM (2013) Representational learning with extreme learning machine for big data. IEEE Intell Syst 28(6):31–34
Chen C, Vong CM, Wong CM et al (2018) Efficient extreme learning machine via very sparse random projection. Soft Comput 22:3563–3574
Deeb H, Sarangi A, Mishra D et al (2022) Human facial emotion recognition using improved black hole based extreme learning machine. Multimed Tools Appl 81(17):24529–24552
Zha L, Ma K, Li G et al (2022) An improved extreme learning machine with self-recurrent hidden layer. Adv Eng Inform 54:101736
Peng X, Li H, Yuan F et al (2022) An extreme learning machine for unsupervised online anomaly detection in multivariate time series. Neurocomputing 501:596–608
Zhou X, Huang J, Lu F et al (2023) A novel compound fault-tolerant method based on online sequential extreme learning machine with cycle reservoir for turbofan engine direct thrust control. Aerosp Sci Technol 132:108059
Shi M, Ding C, Que H et al (2023) Multilayer-graph-embedded extreme learning machine for performance degradation prognosis of bearing. Measurement 207:112299
Ghalyan IF (2023) Capacitive empirical risk function-based bag-of-words and pattern classification processes. Pattern Recogn 139:109482
Zou J, Li W, Chen C, Du Q (2016) Scene classification using local and global features with collaborative representation fusion. Inf Sci 348:209–226
Xiong W, Zhang L, Du B, Tao D (2017) Combining local and global: rich and robust feature pooling for visual recognition. Pattern Recogn 62:225–235
Ahmed KT, Irtaza A, Iqbal MA (2017) Fusion of local and global features for effective image extraction. Appl Intell 47(2):526–543
Mansourian L, Abdullah MT, Abdullah LN, Azman A, Mustaffa MR (2018) An effective fusion model for image retrieval. Multimed Tools Appl 77(13):16131–16154
Shekhar S, Patel VM, Nasrabadi NM et al (2014) Joint sparse representation for robust multimodal biometrics recognition. IEEE Trans Pattern Anal Mach Intell 36(1):113–126
Yan J, Zheng W, Xu Q et al (2016) Sparse kernel reduced-rank regression for bimodal emotion recognition from facial expression and speech. IEEE Trans Multimed 18(7):1319–1329
Bai S, Bai X (2016) Sparse contextual activation for efficient visual re-ranking. IEEE Trans Image Process 25(3):1056–1069
Pan PZ, Huang CL, Technology S et al (2016) Human action recognition based on dense trajectories analysis and random forest. J Electr Sci Technol 14(4):370–376
Xu W, Miao Z, Tian Y (2016) A novel mid-level distinctive feature learning for action recognition via diffusion map. Neurocomputing 218(19):185–196
Giveki D (2021) Scale-space multi-view bag of words for scene categorization. Multimed Tools Appl 80:1223–1245
Li FF, Fergus R, Perona P (2007) Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. Comput Vis Image Underst 106(1):59–70
Wu C, Li YQ, Zhao ZB, Liu B (2019) Image classification method rationally utilizing spatial information of the image. Multimed Tools Appl 78:19181–19199
Liu J, Luo J, Shah M (2009) Recognizing realistic actions from videos “in the wild”. In: IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, pp 1996–2003. https://doi.org/10.1109/CVPR.2009.5206744
Soomro K, Zamir AR, Shah M (2012) UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv Preprint arXiv:1212.0402
Wu C, Li Y, Zhang Y et al (2021) Double constrained bag of words for human action recognition. Signal Process Image Commun 98:116399
Han HG, Wang LD, Qiao JF (2014) Hierarchical extreme learning machine for feedforward neural network. Neurocomputing 128(27):128–135
Ghalyan IFJ, Chacko SM, Kapila V (2018) Simultaneous robustness against random initialization and optimal order selection in bag-of-words modeling. Pattern Recogn Lett 116:135–142
Ghalyan IFJ (2020) Estimation of ergodicity limits of bag-of-words modeling for guaranteed stochastic convergence. Pattern Recogn 99:107094
Li J, Han Y, Zhang M et al (2022) Multi-scale residual network model combined with global average pooling for action recognition. Multimed Tools Appl. https://doi.org/10.1007/s11042-021-11435-5
Zhang C, Xu Y, Xu Z et al (2022) Hybrid handcrafted and learned feature framework for human action recognition. Appl Intell 52(11):12771–12787
Lin B, Fang B, Yang W, Qian J (2018) Human action recognition based on spatio-temporal three-dimensional scattering transform descriptor and an improved vlad feature encoding algorithm. Neurocomputing 348(5):145–157. https://doi.org/10.1016/j.neucom.2018.05.121
Sun Y, Zhang Z, Jiang W et al (2020) Discriminative local sparse representation by robust adaptive dictionary pair learning. IEEE Trans Neural Netw Learn Syst 31(10):4303–4317
Koniusz P, Yan F, Gosselin PH et al (2016) Higher-order occurrence pooling for bags-of-words: visual concept detection. IEEE Trans Pattern Anal Mach Intell 39(2):313–326
Kiruba K, Shiloah ED, Sunil RRC (2019) Hexagonal volume local binary pattern (H-VLBP) with deep stacked autoencoder for human action recognition. Cogn Syst Res 58:71–93. https://doi.org/10.1016/j.cogsys.2019.03.001
Quan Y, Chen Y, Xu R, Ji H (2019) Attention with structure regularization for action recognition. Comput Vis Image Understand 187:102794. https://doi.org/10.1016/j.cviu.2019.102794
Afza F, Khan MA, Sharif M et al (2021) A framework of human action recognition using length control features fusion and weighted entropy-variances based feature selection. Image Vis Comput 106:104090. https://doi.org/10.1016/j.imavis.2020.104090
Liu M, Yin M, Han K et al (2023) Algorithm and hardware co-design co-optimization framework for LSTM accelerator using quantized fully decomposed tensor train. Internet of Things. https://doi.org/10.1016/j.iot.2023.100680
Zhen P, Yan X, Wang W et al (2023) A Highly compressed accelerator with temporal optical flow feature fusion and tensorized LSTM for video action recognition on terminal device. IEEE Trans Comput Aid Des Integr Circuits Syst. https://doi.org/10.1109/TCAD.2023.3241113
Leyva R, Sanchez V, Li CT (2019) Compact and low-complexity binary feature descriptor and Fisher vectors for video analytics. IEEE Trans Image Process 28(12):6169–6184. https://doi.org/10.1109/TIP.2019.2922826
Yang G, Zou W (2022) Deep learning network model based on fusion of spatiotemporal features for action recognition. Multimed Tools Appl 81(7):9875–9896. https://doi.org/10.1007/s11042-022-11937-w
Zong M, Wang R, Chen X, Chen Z, Gong Y (2021) Motion saliency based multi-stream multiplier ResNets for action recognition. Image Vis Comput 107:104108. https://doi.org/10.1016/j.imavis.2021.104108
Liu T, Ma Y, Yang W, Ji W, Wang R, Jiang P (2022) Spatial-temporal interaction learning based two-stream network for action recognition. Inf Sci 606:864–876. https://doi.org/10.1016/j.ins.2022.05.092
Zhao H, Liu J, Wang W (2023) Research on human behavior recognition in video based on 3DCCA. Multimed Tools Appl. https://doi.org/10.1007/s11042-023-14355-8
Acknowledgements
This work is supported by High-Level Talent Scientific Research Start-up Foundation of Henan Institute of Technology of China (KQ2109)
Author information
Authors and Affiliations
Contributions
CW wrote the main manuscript text. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wu, C., Sang, Y. & Gao, Y. Extreme Learning Machine Combining Hidden-Layer Feature Weighting and Batch Training for Classification. Neural Process Lett 55, 10951–10973 (2023). https://doi.org/10.1007/s11063-023-11358-2
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-023-11358-2