Abstract
Class-specific cost regulation extreme learning machine (CCR-ELM) can effectively deal with the class imbalance problems. However, its key parameters, including the number of hidden nodes, the input weights, the biases and the tradeoff factors are normally generated randomly or preset by human. Moreover, the number of input weights and biases depend on the size of hidden layer. Inappropriate quantity of hidden nodes may lead to the useless or redundant neuron nodes, and make the whole structure complex, even cause the worse generalization and unstable classification performances. Based on this, an adaptive CCR-ELM with variable-length brain storm optimization algorithm is proposed for the class imbalance learning. Each individual consists of all above parameters of CCR-ELM and its length varies with the number of hidden nodes. A novel mergence operator is presented to incorporate two parent individuals with different length and generate a new individual. The experimental results for nine imbalance datasets show that variable-length brain storm optimization algorithm can find better parameters of CCR-ELM, resulting in the better classification accuracy than other evolutionary optimization algorithms, such as GA, PSO, and VPSO. In addition, the classification performance of the proposed adaptive algorithm is relatively stable under varied imbalance ratios. Applying the proposed algorithm in the fault diagnosis of conveyor belt also proves that ACCR-ELM with VLen-BSO has the better classification performances.
Similar content being viewed by others
References
Cheng S, Qin QD, Chen JF et al (2014) Maintaining population diversity in brain storm optimization algorithm. Proc IEEE Congr Evolut Comput 4(3):3230–3237
Cheng S, Qin QD, Chen JF et al (2015) Brain storm optimization algorithm: a review. Artif Intell Rev 6728:1–14
Ertam F, Avci E (2017) A new approach for internet traffic classification: GA-WK-ELM. Measurement 95:135–142
Frank A, Asuncion A (2010) UCI machine learning repository. University of California, Irvine, School of Information and Computer Sciences. http://archive.ics.uci.edu/mlS
Gao M, Hong X, Chen S et al (2011) A combined smote and PSO based RBF classifier for two-class imbalanced problems. Neurocomputing 74(17):3456–3466
Guo XP, Wu YL, Xie LX et al (2015) An adaptive brain storm optimization algorithm for multiobjective optimization problems. Lect Notes Comput Sci 9140(4):365–372
Guo YN, Zhen Y, Wang C et al (2016) Cultural particle swarm optimization algorithms for uncertain multi-objective problems with interval parameters. Nat Comput 16(4):1–22
Guo YN, Zhang P, Cheng J et al (2017) An improved weighted ELM with krill herd algorithm for imbalanced learning. In: Advances in swarm intelligence Springer, pp 371–378
Guo YN, Cheng J, Luo S, Gong DW, Xue Y (2018) Robust dynamic multi-objective vehicle routing optimization method. IEEE/ACM Trans Comput Biol Bioinform 15(6):1891–1903
Han F, Yao HF, Ling QH (2013) An improved evolutionary extreme learning machine based on particle swarm optimization. Neurocomputing 116:87–93
He HB, Ma YQ (2013) Imbalanced learning: foundations, algorithms, and applications. Wiley, New York
Huang GB, Zhu QY, and Siew CK (2005) Extreme learning machine: a new learning scheme of feed forward neural networks. In: IEEE international joint conference on neural networks, vol 2, pp 985–990
Huang GB, Zhou HM, Ding XJ et al (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B 42(2):513–529
Huang GB, Song SJ, Gupta JND et al (2014) Semi-supervised and unsupervised extreme learning machines. IEEE Trans Cybern 44(12):2405–2417
Li QJ, Mao YB (2014) A review of boosting methods for imbalanced data classification. Pattern Anal Appl 17(4):679–693
Li D, Zhang W (2014) Stock price prediction based on ELM and FOA. Comput Eng Appl 50(18):14–18
Liu XY, Wu JX, Zhou ZH (2009) Exploratory undersampling for class-imbalance learning. IEEE Trans Syst Man Cybern Part B 39(2):539–550
Mirza B, Lin ZP, Toh KA (2013) Weighted online sequential extreme learning machine for class imbalance learning. Neural Process Lett 38(3):465–486
Mirza B, Lin ZP, Liu N (2015) Ensemble of subset online sequential extreme learning machine for class imbalance and concept drift. Neurocomputing 149(Part A):316–329
Nitesh VC, Bowyer KW, Lawrence OH et al (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16(1):321–357
Ramentol E (2012) SMOTE-RS: a hybrid preprocessing approach based on oversampling and undersampling for high imbalanced data-sets using smote and rough sets theory. Knowl Inf Syst 33(2):245–265
Rong HJ, Huang GB, Narasimhan S et al (2009) Online sequential fuzzy extreme learning machine for function approximation and classification problems. IEEE Trans Syst Man Cybern Part B 39(4):1067
Shen F, Liu J, Wu P (2018) Double complete D-LBP with extreme learning machine auto-encoder and cascade forest for facial expression analysis. In: 25th IEEE international conference on image processing (ICIP), pp 1947–1951
Wang B, Sun YN, Xue B et al (2018) Evolving deep convolutional neural networks by variable-length particle swarm optimization for image classification. In: IEEE congress on evolutionary computation
Wu G, Chang EY (2005) KBA: kernel boundary alignment considering imbalanced data distribution. IEEE Trans Knowl Data Eng 17(6):786–795
Wu DH, Wang ZL, Ye C et al (2016) Mixed-kernel based weighted extreme learning machine for inertial sensor based human activity recognition with imbalanced dataset. Neurocomputing 190:35–49
Xiao WD, Zhang J, Li Y et al (2017) Class-specific cost regulation extreme learning machine for imbalanced classification. Neurocomputing 261:70–82
Yang LX, Yang SY, Li SJ et al (2017) Incremental laplacian regularization extreme learning machine for online learning. Appl Soft Comput 59:546–555
Yu HL, Sun CY, Yang XB et al (2016) ODOC-ELM: optimal decision outputs compensation-based extreme learning machine for classifying imbalanced data. Knowl Based Syst 92:55–70
Zeng ZQ, Qun WU, Liao BS et al (2009) A classfication method for imbalance data set based on kernel smote. Acta Electron Sin 37(11):2489–2495
Zhao JW, Wang ZH, Dong SP (2012) Online sequential extreme learning machine with forgetting mechanism. Neurocomputing 87(15):79–89
Zong WW, Huang GB, Chen YQ (2013) Weighted extreme learning machine for imbalance learning. Neurocomputing 101(3):229–242
Acknowledgements
This work is supported by National Natural Science Foundation of China under Grant 61573361, Research Program of Frontier Discipline of China University of Mining and Technology under Grant 2015XKQY19, Six Talent Peak Project in Jiangsu Province under Grant 2017-DZXX-046 and National Key Research and Development Program under Grant 2016YFC0801406.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cheng, J., Chen, J., Guo, Yn. et al. Adaptive CCR-ELM with variable-length brain storm optimization algorithm for class-imbalance learning. Nat Comput 20, 11–22 (2021). https://doi.org/10.1007/s11047-019-09735-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11047-019-09735-9