Main Article Content
Use of ensemble convolutional neural networks (CNNs) has become a more robust strategy to improve image classification performance. However, the success of the ensemble method depends on appropriately selecting the optimal weighted parameters. This paper aims to automatically optimize the weighted parameters using the differential evolution (DE) algorithm. The DE algorithm is applied to the weighted parameters and then assigning the optimal weighted to the ensemble method and stacked ensemble method. For the ensemble method, the weighted average ensemble method is applied. For the stacked ensemble method, we use the support vector machine for the second-level classifier. In the experiments, firstly, we experimented with discovering the baseline CNN models and found the best models on the pornographic image dataset were NASNetLarge with an accuracy of 93.63%. Additionally, three CNN models, including EfficientNetB1, InceptionResNetV2, and MobileNetV2, also obtained an accuracy above 92%. Secondly, we generated two ensemble CNN frameworks; the ensemble learning method, called Ensemble-CNN and the stacked ensemble learning method, called StackedEnsemble-CNN. In the framework, we optimized the weighted parameter using the DE algorithm with six mutation strategies containing rand/1, rand/2, best/1, best/2, current to best/1, and random to best/1. Therefore, the optimal weighted was given to classify using ensemble and stacked ensemble methods. The result showed that the Ensemble-3CNN and StackedEnsemble-3CNN, when optimized using the best/2 mutation strategy, surpassed other mutation strategies with an accuracy of 96.83%. The results indicated that we could create the learning method framework with only 3 CNN models, including NASNetLarge, EfficientNetB1, and InceptionResNetV2.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
 Wang W, Yang Y, Wang X, Wang W, Li J. Development of convolutional neural network and its application in image classification: a survey. Opt Eng. 2019;58(4):1-19.
 Majidifard H, Jin P, Adu-Gyamfi Y, Buttlar WG. Pavement image datasets: A new benchmark dataset to classify and densify pavement distresses. arXiv:1910.11123. 2019:1-12.
 Han Y, Chen C, Tang L, Lin M, Jaiswal A, Ding Y, et al. Using radiomics as prior knowledge for abnormality classification and localization in chest x-rays. Transport Res Rec J Transport Res Board. 2020;2674(2):1-11.
 LeCun Y, Matan O, Boser BE, Denker J, Henderson D, Howard R, et al. Handwritten zip code recognition with multilayer networks. 10th International conference on pattern recognition (ICPR); 1990 Aug 16-21; Atlantic, USA. New York: IEEE; 1990. p. 35-40.
 Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inform Process Syst. 2012;25(2):1-9.
 Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. 2017:1-9.
 Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. 2017 IEEE Conference on computer vision and pattern recognition (CVPR); 2017 Jul 21-26; Honolulu, USA. New York: IEEE; 2017. p. 2261-9.
 Tan M, Le QV. EfficientNet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946. 2019:1-11.
 Wu J, Tsai M-H, Huang Y, Islam SH, Hassan M, Alelaiwi A, et al. Applying an ensemble convolutional neural network with Savitzky-Golay filter to construct a phonocardiogram prediction model. Appl Soft Comput J. 2019;78:29-40.
 Vasan D, Alazab M, Wassan S, Safaei B, Zheng Q. Image-based malware classification using ensemble of CNN architectures (IMCEC). Comput Secur. 2020;92:1-13.
 Hospedales TM, Antoniou A, Micaelli P, Storkey A. Meta-learning in neural networks: a survey. arXiv:2004.05439. 2020:1-20.
 Shen S, Gu K, Chen XR, Yang M, Wang R. Movements classification of multi-channel sEMG based on CNN and stacking ensemble learning. IEEE Access. 2019;7:137489-500.
 Zhang Y, Zhang H, Cai J, Yang B. A weighted voting classifier based on differential evolution. Abstr Appl Anal. 2014;2014:1-6.
 Wang M, Lu S, Zhu D, Lin J, Wang Z. A high-speed and low-complexity architecture for softmax function in deep learning. 2018 IEEE asia pacific conference on circuits and systems (APCCAS); 2018 Oct 26-30; Chengdu, China. New York: IEEE; 2018. p. 223-6.
 Dixit A, Mani A, Bansal R. Feature selection for text and image data using differential evolution with SVM and Naive bayes classifiers. Eng J. 2020;24(5):161-72.
 Gour M, Jain S. Stacked convolutional neural network for diagnosis of COVID-19 disease from x-ray images. arXiv:2006.13817. 2020:1-26.
 Omran MGH, Engelbrecht A, Salman A. Differential evolution methods for unsupervised image classification. 2005 IEEE congress on evolutionary computation; 2005 Sep 2-5; Edinburgh, UK. New York: IEEE; 2005. p. 966-97.
 Wang B, Sun Y, Xue B, Zhang M. A hybrid differential evolution approach to designing deep convolutional neural networks for image classification. 31st Australasian joint conference; 2018 Dec 11-14; Wellington, New Zealand. Berlin: Springer; 2018. p. 237-50.
 Yazdizadeh A, Patterson Z, Farooq B. Ensemble convolutional neural networks for mode inference in smartphone travel survey. IEEE Trans Intell Transport Syst. 2020;21(6):2232-9.
 Vapnik VN. Statistical learning theory. New Jersey: Wiley; 1998.
 Storn R, Price K. Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. J Global Optim. 1997;11(4):341-59.
 Penunuri F, Peon-Escalante R, Solis-Perales G, Villanueva C, Acosta C. A differential evolutionary method for solving a class of differential equations numerically. 2012 IFAC conference on analysis and control of chaotic system; 2012 Jun 20-22; Cancun, Mexico. Switzerland: IFAC; 2012. p. 45-50.
 Harangi B. Skin lesion classification with ensembles of deep convolutional neural networks. J Biomed Informat. 2018;86:25-32.
 Frazao X, Alexandre LA. Weighted convolutional neural network ensemble. In: Bayro-Corrochano E, Hancock E, Editors. Iberoamerican congress on pattern recognition (ICARP); 2014 Nov 2-5; Mexico. Berlin: Springer; 2014. p. 674-81.
 Gao B, Pavel L. On the properties of the softmax function with application in game theory and reinforcement learning. arXiv:1704.00805. 2017:1-10.
 Deepika S, Geetha TV. A meta-learning framework using representation learning to predict drug-drug interaction. J Biomed Informat. 2018;84:136-47.
 Liu X, Wang X, Matwin S. Interpretable deep convolutional neural networks via meta-learning. arXiv:1802.00560. 2018:1-9.
 Codreanu V, Droge B, Williams D, Yasar B, Yang P, Liu B, et al. Evaluating automatically parallelized versions of the support vector machine. Concurrency Comput Pract Ex. 2016;28:2274-94.
 Wijaya IS, Widiartha I, Arjarwani SE. Pornographic image recognition based on skin probability and eigenporn of skin ROIs images. TELKOMNIKA (Telecomm Comput Electron Contr). 2015;13(3):985-95.
 Wijaya IS, Widiartha I, Uchimura K, Koutaki G. Phonographic image recognition using fusion of scale invariant descriptor. 21st Korea-Japan Joint Workshop on Forntiers of Computer Vision (FCV); 2015 Jan 28-30; Mokpo, South Korea. New York: IEEE; 2015. p. 1-5.
 Surinta O, Khamket T. Recognizing pornographic images using deep convolutional neural networks. Joint international conference on digital arts media and technology with ECTI northern section conference on electrical electronics computer and telecommunications engineering (ECTI DAMT-NCON); 2019 Jan 30-Feb 2; Nan, Thailand. New York: IEEE; 2019. p. 150-4.
 Darwish A. Bio-inspired computing: algorithms review, deep analysis, and the scope of applications. Future Comput Informat J. 2018;3(2):231-46.
 Ma T, Liu S, Xiao H. Location of natural gas leakage sources on offshore platform by a multi-robot system using particle swarm optimization algorithm. J Nat Gas Sci Eng. 2020;84(2020):1-15.
 Fan X, Sayers W, Zhang S, Han Z, Ren L, Chizari H. Review and classification of bio-inspired algorithms and their applications. J Bionic Eng. 2020;17:611-31.