Abstract
One of the most reliable deep learning approaches for image classification challenges is deep Conventional Conv neural networks (DCNNs); however, identifying the appropriate DCNN architecture for a given application can be quite challenging. This study focuses on finding the optimal DCNN architecture automatically using an improved version of the Chimp Optimization Algorithm (ChOA). Three changes based on the baseline ChOA are developed to accomplish the objectives. As a first step, a digitized-based coding strategy is created, making it easier for chimp vectors to encode DCNN layers. Then, to achieve variable-length DCNNs, a disabled layer is recommended to cover some chimp vector dimensions. As a third contribution, a mechanism is developed to assess the fitness function using only a part of the dataset instead of the whole dataset. In order to assess the developed model’s performance, the comparison is made against 23 classifiers, including the top state-of-the-art approaches, using nine benchmark image datasets. The proposed model presents the best performance in the Fashion dataset with an error percentage of 5.08, while it is the second-best model with 750 k parameters. Also, for other datasets, the experimental findings indicate that the suggested method’s classification accuracy outperforms other benchmarks in 87 out of 95 investigations. This variable-length approach is the first effort of its kind, employing ChOA to evolve the architectures of DCNNs autonomously.
Similar content being viewed by others
Data availability
The resource data and material can be downloaded using the following links and references [52]–[21] https://www.kaggle.com/zalando-research/fashionmnist
Code availability
The source code of the models can be available by official request.
References
Ballester P, Araujo RM (2016) On the performance of GoogLeNet and AlexNet applied to sketches
Ban Y et al (2022) Depth estimation method for monocular camera defocus images in microscopic scenes. Electronics 11(13):2012
Bourlard H, Kamp Y (1988) Auto-association by multilayer perceptrons and singular value decomposition. Biol Cybern. https://doi.org/10.1007/BF00332918
Bruna J, Mallat S (2013) Invariant scattering convolution networks. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/TPAMI.2012.230.
Cao B, Gu Y, Lv Z, Yang S, Zhao J, Li Y (2020) RFID reader anticollision based on distributed parallel particle swarm optimization. IEEE Internet Things J. 8(5):3099–3107
Cao B, Li M, Liu X, Zhao J, Cao W, Lv Z (2021) Many-objective deployment optimization for a drone-assisted camera network. IEEE Trans Netw Sci Eng
Cao B et al (2021) Large-scale many-objective deployment optimization of edge servers. IEEE Trans Intell Transp Syst. 22(6):3841–3849
Chan TH, Jia K, Gao S, Lu J, Zeng Z, Ma Y (2015) PCANet: A simple deep learning baseline for image classification?. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2015.2475625.
Cheng L, Yin F, Theodoridis S, Chatzis S, Chang T-H (2022) Rethinking Bayesian learning for data analysis: The art of prior and inference in sparsity-aware modeling. IEEE Signal Process. Mag. 39(6):18–52
Dai B, Zhang B, Niu Z, Feng Y, Liu Y, Fan Y (2022) A novel ultrawideband branch waveguide coupler with low amplitude imbalance. IEEE Trans Microw Theory Tech
Feng Y, Zhang B, Liu Y, Niu Z, Fan Y, Chen X (2022) A D-band manifold triplexer with high isolation utilizing novel waveguide dual-mode filters. IEEE Trans Terahertz Sci Technol
Fu L et al (2018) Kiwifruit detection in field images using Faster R-CNN with ZFNet. IFAC-PapersOnLine 51(17):45–50
He K, Zhang X, Ren S, Sun J (2016) ResNet Proc IEEE Comput Soc Conf Comput. Vis Pattern Recognit
Hu T, Khishe M, Mohammadi M, Parvizi GR, Taher Karim SH, Rashid TA (2021) Real-time COVID-19 diagnosis from X-Ray images using deep CNN and extreme learning machines stabilized by chimp optimization algorithm. Biomed Signal Process Control 68:102764. https://doi.org/10.1016/j.bspc.2021.102764
Huang N, Wang S, Wang R, Cai G, Liu Y, Dai Q (2023) Gated spatial-temporal graph neural network based short-term load forecasting for wide-area multiple buses. Int J Electr Power Energy Syst. 145:108651
Iandola FN, Moskewicz MW, Ashraf K, Han S, Dally WJ, Keutzer K (2016) “SqueezeNet,” arXiv
Khishe M, Mosavi MR (2020) Chimp optimization algorithm. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2020.113338
Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM. https://doi.org/10.1145/3065386.
Larochelle H, Erhan D, Courville A, Bergstra J, Bengio Y (2007) An empirical evaluation of deep architectures on problems with many factors of variation. https://doi.org/10.1145/1273496.1273556
LeCun Y (2015) LeNet-5, convolutional neural networks, URL http//yann.lecun.com/exdb/lenet, 20(5):14
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE. https://doi.org/10.1109/5.726791
Li Q, Song D, Yuan C, Nie W (2022) An image recognition method for the deformation area of open-pit rock slopes under variable rainfall. Measurement 188
Li R, Wu X, Tian H, Yu N, Wang C (2022) Hybrid memetic pretrained factor analysis-based deep belief networks for transient electromagnetic inversion. IEEE Trans Geosci Remote Sens. 60:1–20
Liao X, Li K, Zhu X, Liu KJR (2020) Robust detection of image operator chain with two-stream convolutional neural network. IEEE J Sel Top Signal Process. 14(5):955–968
Liao X, Peng J, Cao Y (2021) GIFMarking: The robust watermarking for animated GIF based deep learning. J Vis Commun Image Represent. 79:103244
Liu R et al (2021) SCCGAN: style and characters inpainting based on CGAN. Mob Networks Appl 26(1):3–12
Liu H, Liu M, Li D, Zheng W, Yin L, Wang R (2022) Recent Advances in Pulse-Coupled Neural Networks with Applications in Image Processing. Electronics 11(20):3264
Liu Y, Xu K-D, Li J, Guo Y-J, Zhang A, Chen Q (2022) Millimeter-Wave E-Plane Waveguide Bandpass Filters Based on Spoof Surface Plasmon Polaritons, IEEE Trans Microw Theory Tech
Piri J, Mohapatra P, Pradhan MR, Acharya B, Patra TK (2021) A binary multi-objective chimp optimizer with dual archive for feature selection in the healthcare domain. IEEE Access 10:1756–1774
Piri J, Mohapatra P, Singh HKR, Acharya B, Patra TK (2022) An Enhanced Binary Multiobjective Hybrid Filter-Wrapper Chimp Optimization Based Feature Selection Method for COVID-19 Patient Health Prediction. IEEE Access 10:100376–100396
Piri J et al (2022) Feature selection using artificial gorilla troop optimization for biomedical data: A case analysis with COVID-19 data. Mathematics 10(15):2742
Postel J (1980) DoD standard internet protocol. ACM SIGCOMM Comput. Commun. Rev. 10(4):12–51
Qin X et al (2022) Improved Image Fusion Method Based on Sparse Decomposition. Electronics 11(15):2321
Rifai S, Vincent P, Muller X, Glorot X, Bengio Y (2011) Contractive auto-encoders: Explicit invariance during feature extraction
Shi Y, Xu X, Xi J, Hu X, Hu D, Xu K (2022) Learning to detect 3D symmetry from single-view RGB-D images with weak supervision, IEEE Trans Pattern Anal Mach Intell
Simonyan K, Zisserman A (2015) “VGGNet,” 3rd Int Conf Learn Represent ICLR 2015 - Conf. Track Proc
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition
Sohn K, Lee H (2012) Learning invariant representations with local transformations
Sohn K, Zhou G, Lee C, Lee H (2013) Learning and selecting features jointly with point-wise gated Boltzmann machines
Stanley KO, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evol. Comput. 10(2):99–127
Suganuma M, Shirakawa S, Nagao T (2017) A genetic programming approach to designing convolutional neural network architectures, in Proceedings of the genetic and evolutionary computation conference, pp. 497–504
Sun Y, Xue B, Zhang M, Yen GG (2020) Evolving Deep Convolutional Neural Networks for Image Classification, IEEE Trans Evol Comput, doi: https://doi.org/10.1109/TEVC.2019.2916183
Sun B, Li Y, Zeng Y, Chen J, Shi J (2022) Optimization planning method of distributed generation based on steady-state security region of distribution network. Energy Rep 8:4209–4222
Szegedy C et al., (2014) “GoogLeNet,” Proc. IEEE Comput Soc Conf Comput Vis Pattern Recognit
Szegedy C et al. (2015) Going deeper with convolutions, doi: https://doi.org/10.1109/CVPR.2015.7298594
Tan J, Liao X, Liu J, Cao Y, Jiang H (2021) Channel attention image steganography with generative adversarial networks. IEEE Trans. Netw. Sci. Eng. 9(2):888–903
Tomkins J, Bergman J (2012) Genomic monkey business—estimates of nearly identical human–chimp DNA similarity re-evaluated using omitted data. J. Creat. 26(1):94–100
Wang B, Sun Y, Xue B, Zhang M (2018) Evolving deep convolutional neural networks by variable-length particle swarm optimization for image classification, in 2018 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8
Wang W, Chen Z, Yuan X (2022) Simple low-light image enhancement based on Weber-Fechner law in logarithmic space. Signal Process Image Commun.:116742
Webb GI, Keogh E, Miikkulainen R, Miikkulainen R, Sebag M (2011) No-Free-Lunch Theorem, in Encyclopedia of Machine Learning
Wu C, Khishe M, Mohammadi M, Karim SHT, Rashid TA (2021) Evolving deep convolutional neutral network by hybrid sine–cosine and extreme learning machine for real-time COVID19 diagnosis from X-ray images, Soft Comput, pp. 1–20
Xiao H, Rasul K, Vollgraf R (2017) Fashion-mniST: A novel image dataset for benchmarking machine learning algorithms, arXiv
Xiao S et al. (2022) Influence of the distributed grounding layout for intercity trains on the ‘train-rail’circumflux, IEEE Trans. Circuits Syst. II Express Briefs
Xu K-D, Guo Y-J, Liu Y, Deng X, Chen Q, Ma Z (2021) 60-GHz compact dual-mode on-chip bandpass filter using GaAs technology. IEEE Electron Device Lett. 42(8):1120–1123
Xu S, He Q, Tao S, Chen H, Chai Y, Zheng W (2022) Pig Face Recognition Based on Trapezoid Normalized Pixel Difference Feature and Trimmed Mean Attention Mechanism, IEEE Trans Instrum Meas
Yang M, Wang H, Hu K, Yin G, Wei Z (2022) IA-Net $: $ An inception–attention-module-based network for classifying underwater images from others. IEEE J Ocean Eng 47(3):704–717
Ye DH, Zikic D, Glocker B, Criminisi A, Konukoglu E. [SqueezeNet] SQUEEZENET: ALEXNET-LEVEL ACCURACY WITH 50X FEWER PARAMETERS AND <0.5MB MODEL SIZE,” ICLR17, 2013.
Zhang H, Luo G, Li J, Wang F-Y (2021) C2FDA: Coarse-to-Fine Domain Adaptation for Traffic Object Detection, IEEE Trans Intell Transp Syst
Zhang Z, Wang L, Zheng W, Yin L, Hu R, Yang B (2022) Endoscope image mosaic based on pyramid ORB. Biomed. Signal Process. Control 71
Zhou X, Zhang L (2022) SA-FPN: An effective feature pyramid network for crowded human detection. Appl. Intell. 52(11):12556–12568
Zhou W, Yu L, Zhou Y, Qiu W, Wu M-W, Luo T (2018) Local and global feature learning for blind quality evaluation of screen content and natural scene images. IEEE Trans. Image Process. 27(5):2086–2095
Zhou W, Lv Y, Lei J, Yu L (2019) Global and local-contrast guides content-aware fusion for RGB-D saliency prediction, IEEE Trans. Syst. Man, Cybern Syst
Zhou W, Wang H, Wan Z (2022) Ore Image Classification Based on Improved CNN. Comput. Electr. Eng. 99
Funding
This work was supported by the open research fund program of state key laboratory of hydroscience and engineering of Tsinghua university (Grant No: sklhse-2020-A-01)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest/Competing interests
The authors declare that there is 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
Khishe, M., Azar, O.P. & Hashemzadeh, E. Variable-length CNNs evolved by digitized chimp optimization algorithm for deep learning applications. Multimed Tools Appl 83, 2589–2607 (2024). https://doi.org/10.1007/s11042-023-15411-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15411-z