Abstract
Convolutional Neural Networks (CNN) have revolutionized image recognition technology, and has found uses in various non-image related fields. When dealing with non-natural data, where the ordering of various parts of a data sample is not dictated by nature, it is known that a model trained on certain orderings of the data performs better than models trained on other orderings. Understanding how to best order the training data for improving CNN performance is not well-studied. In this paper, we investigate this problem by examining several different CNN models. We define a functional algorithm for ordering, show that order importance in CNNs is model dependent and that depending on the model, statistical relationships are an important tool in establishing order with better performance.
This work is partially supported by NSF grants HRD-1736209 and CNS-1553696.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abdelsalem, M., Krishnan, R., Huang, Y., Sandu, R.: Malware detection in cloud infrastructure using convolutional neural networks. In: IEEE 11th International Conference on Cloud Computing (2018)
Avula, S.B., Badri, S.J., Reddy P, G.: A novel forest fire detection system using fuzzy entropy optimized thresholding and STN-based CNN. In: 2020 International Conference on COMmunication Systems NETworkS (COMSNETS), pp. 750–755 (2020). https://doi.org/10.1109/COMSNETS48256.2020.9027347
Chollet, F.: Xception: Deep learning with depthwise separable convolutions (2017)
Deng, L., Hinton, G., Kingsbury, B.: New types of deep neural network learning for speech recognition and related applications: an overview. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8599–8603 May (2013). https://doi.org/10.1109/ICASSP.2013.6639344
Elhassouny, A., Smarandache, F.: Trends in deep convolutional neural networks architectures: a review. In: 2019 International Conference of Computer Science and Renewable Energies (ICCSRE), pp. 1–8 (2019). https://doi.org/10.1109/ICCSRE.2019.8807741
Golinko, E., Sonderman, T., Zhu, X.: Learning convolutional neural networks from ordered features of generic data. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 897–900, December 2018. https://doi.org/10.1109/ICMLA.2018.00145
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 http://arxiv.org/abs/1512.03385 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: The IEEE International Conference on Computer Vision (ICCV), December 2015
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications (2017)
Hu, Y., Zhang, D., Cao, G., Pan, Q.: Network data analysis and anomaly detection using CNN technique for industrial control systems security. In: 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 593–597 (2019). https://doi.org/10.1109/SMC.2019.8913895
Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. CoRR abs/1608.06993 http://arxiv.org/abs/1608.06993 (2016)
Jiang, W., Bruton, L.: Lossless color image compression using chromatic correlation. In: Proceedings DCC 1999 Data Compression Conference (Cat. No. PR00096), pp. 533 (1999). https://doi.org/10.1109/DCC.1999.785690
Kimmel, J.C., Mcdole, A.D., Abdelsalam, M., Gupta, M., Sandhu, R.: Recurrent neural networks based online behavioural malware detection techniques for cloud infrastructure. IEEE Access 9, 68066–68080 (2021). https://doi.org/10.1109/ACCESS.2021.3077498
Lee, J.Y., Dernoncourt, F.: Sequential short-text classification with recurrent and convolutional neural networks. CoRR abs/1603.03827 http://arxiv.org/abs/1603.03827 (2016)
Lihao, W., Yanni, D.: A fault diagnosis method of tread production line based on convolutional neural network. In: 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS), pp. 987–990, November 2018. https://doi.org/10.1109/ICSESS.2018.8663824
Liu, C., Dai, L., Cui, W., Lin, T.: A byte-level CNN method to detect DNS tunnels. In: 2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC), pp. 1–8 (2019). https://doi.org/10.1109/IPCCC47392.2019.8958714
Liu, G., Zhao, F.: An efficient compression algorithm for hyperspectral images based on correlation coefficients adaptive three dimensional wavelet zerotree coding. In: 2007 IEEE International Conference on Image Processing, vol. 2, pp. II - 341-II - 344 (2007). https://doi.org/10.1109/ICIP.2007.4379162
McDole, A., Abdelsalam, M., Gupta, M., Mittal, S.: Analyzing CNN based behavioural malware detection techniques on cloud IaaS. In: Zhang, Q., Wang, Y., Zhang, L.-J. (eds.) CLOUD 2020. LNCS, vol. 12403, pp. 64–79. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59635-4_5
Milton-Barker, A.: Inception v3 deep convolutional architecture for classifying acute (2019). https://software.intel.com/content/www/us/en/develop/articles/inception-v3-deep-convolutional-architecture-for-classifying-acute-myeloidlymphoblastic.html
Mobadersany, P., et al.: Predicting cancer outcomes from histology and genomics using convolutional networks. Proc. Nat. Acad. Sci. 115(13), E2970–E2979 (2018). https://doi.org/10.1073/pnas.1717139115, https://www.pnas.org/content/115/13/E2970
Wang, Q., Shen, Y.: A jpeg2000 and nonlinear correlation measurement based method to enhance hyperspectral image compression. In: 2005 IEEE Instrumentationand Measurement Technology Conference Proceedings, vol. 3, pp. 2009–2011 (2005). https://doi.org/10.1109/IMTC.2005.1604524
van Wyk, F., Wang, Y., Khojandi, A., Masoud, N.: Real-time sensor anomaly detection and identification in automated vehicles. IEEE Trans. Intell. Transp. Syst. 21(3), 1264–1276 (2020). https://doi.org/10.1109/TITS.2019.2906038
Zhang, Y., Chen, X., Jin, L., Wang, X., Guo, D.: Network intrusion detection: based on deep hierarchical network and original flow data. IEEE Access 7, 37004–37016 (2019). https://doi.org/10.1109/ACCESS.2019.2905041
Zhao, X., Gao, L., Chen, Z., Zhang, B., Liao, W., Yang, X.: An entropy and MRF model-based CNN for large-scale landsat image classification. IEEE Geosci. Remote Sens. Lett. 16(7), 1145–1149 (2019). https://doi.org/10.1109/LGRS.2019.2890996
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Klepetko, R., Krishnan, R. (2022). Analyzing CNN Models’ Sensitivity to the Ordering of Non-natural Data. In: Krishnan, R., Rao, H.R., Sahay, S.K., Samtani, S., Zhao, Z. (eds) Secure Knowledge Management In The Artificial Intelligence Era. SKM 2021. Communications in Computer and Information Science, vol 1549. Springer, Cham. https://doi.org/10.1007/978-3-030-97532-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-97532-6_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97531-9
Online ISBN: 978-3-030-97532-6
eBook Packages: Computer ScienceComputer Science (R0)