Abstract
Powerful deep learning algorithms open an opportunity for solving non-image Machine Learning (ML) problems by transforming these problems into the image recognition problems. The CPC-R algorithm presented in this chapter converts non-image data into images by visualizing non-image data. Then deep learning CNN algorithms solve the learning problems on these images. The design of the CPC-R algorithm allows preserving all high-dimensional information in 2-D images. The use of pair values mapping instead of single value mapping used in the alternative approaches allows encoding each n-D point with 2 times fewer visual elements. The attributes of an n-D point are divided into pairs of its values and each pair is visualized as 2-D points in the same 2-D Cartesian coordinates. Next, grey scale or color intensity values are assigned to each pair to encode the order of pairs. This is resulted in the heatmap image. The computational experiments with CPC-R are conducted for different CNN architectures, and methods to optimize the CPC-R images showing that the combined CPC-R and deep learning CNN algorithms are able to solve non-image ML problems reaching high accuracy on the benchmark datasets. This chapter expands our prior work by adding more experiments to test accuracy of classification, exploring saliency and informativeness of discovered features to test their interpretability, and generalizing the approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dovhalets, D., Kovalerchuk, B., Vajda, S., Andonie, R.: Deep learning of 2-D images representing n-D data in general line coordinates. In: Intern. Symp. on Affective Science and Engineering, pp. 1–6 (2018). https://www.jstage.jst.go.jp/article/isase/ISASE2018/0/ISASE2018_1_18/_pdf
Sharma, A., Vans, E., Shigemizu, D., Boroevich, K.A., Tsunoda, T.: Deep insight: a methodology to transform a non-image data to an image for convolution neural network architecture. Nat. Sci. Rep. 9(1), 1–7 (2019)
Kovalerchuk, B., Agrawal, B., Kalla, D.: Solving non-image learning problems by mapping to images, 24th International Conference Information Visualisation, Melbourne, Victoria, Australia (2020), pp. 264–269, IEEE. https://doi.org/10.1109/IV51561.2020.00050
van der Maaten, L.: Dos and don'ts of using t-SNE to understand vision models, CVPR 2018, Tutorial
Rodrigues, N.M., Batista, J.E., Trujillo, L., Duarte, B., Giacobini, M., Vanneschi, L., Silva, S.: Plotting time: on the usage of CNNs for time series classification (2021). arXiv:2102.04179
Sharma, A., Kumar, D.: Non-image data classification with convolutional neural networks (2020). arXiv:2007.03218
Kovalerchuk, B.: Visual knowledge discovery and machine learning. Springer (2018)
Wolberg, W., Mangasarian, O.: UCI ML repository: Breast Cancer Wisconsin Data Set (1991). https://archive.ics.uci.edu/ml/datasets/breast+cancer+wisconsin+%28original%29
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: 31st AAAI Conference on Artificial Intelligence (2017), https://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/viewPDFInterstitial/14806/14311
LeCun, Y., Bottou, L., Bengio, Y.: Gradient-based learning applied to document recognition. IEEE Proc. 86(11), 2278–2324 (1998)
Balasubramanian, M., Schwartz, E.L.: The isomap algorithm and topological stability. Science 295(5552), 7–7 (2002)
Asuncion, A., Newman, D.: Ionosphere data set (2007). https://archive.ics.uci.edu/ml/datasets/Ionosphere
Spiehler, V.: Glass identification data set (1987). https://archive.ics.uci.edu/ml/datasets/Glass+Identification
Bohanec, M., Zupan, B.: UCI machine learning repository: car evaluation data set (1997). https://archive.ics.uci.edu/ml/datasets/car+evaluation
Ernst, N.: Saliency map. Scholarpedia 2(8), 2675 (2007)
Radhakrishna, A., Sabine, S.: Saliency detection for content-aware image resizing. In: 2009 16th IEEE International Conference on Image Processing (ICIP), pp. 1005–1008. IEEE (2009)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps (2013). arXiv:1312.6034
Seunghoon, H., Tackgeun, Y., Suha, K., Bohyung, H.: Online tracking by learning discriminative saliency map with convolutional neural network. In: International on Conference on Machine Learning, pp. 597–606. PMLR (2015)
Kotikalapudi, Raghavendra and contributors, Keras-vis (2017). https://github.com/raghakot/keras-vis
Selvaraju Ramprasaath, R., Michael, C., Abhishek, D., Ramakrishna, V., Devi, P., Dhruv, B.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Schreiber, A.: Saliency maps for deep learning, Part 1: Vanilla Gradient (2019). https://andrewschrbr.medium.com/saliency-maps-for-deep-learning-part-1-vanilla-gradient-1d0665de3284
Kim, B., Seo, J., Jeon, S., Koo, J., Choe, J., Jeon, T.: Why are saliency maps noisy? Cause of and solution to noisy saliency maps. In: IEEE CVF International Conference on Computer Vision Workshop, pp. 4149–4157 (2019)
He, S., Lau, R.W., Liu, W., Huang, Z., Yang, Q.: SuperCNN: a superpixelwise convolutional neural network for salient object detection. Int. J. Comput. Vision 115(3), 330–344 (2015)
Kovalerchuk, B., Gharawi, A.: Decreasing occlusion and increasing explanation in interactive visual knowledge discovery. In: International Conference on Human Interface and the Management of Information, pp. 505–526. Springer (2018)
Van Der Maaten, L., Postma, E., Van den Herik, J.: Dimensionality reduction: a comparative. J Mach Learn Res. 10(66–71), 13 (2009)
Smilkov, D., Carter, S., Sculley, D., Viégas, F.B., Wattenberg, M.: Direct-manipulation visualization of deep networks (2017). arXiv:1708.03788
Aldayel, M.S.: K-Nearest Neighbor classification for glass identification problem. In: 2012 International Conference on Computer Systems and Industrial Informatics, pp. 1–5. IEEE (2012)
Khan, M.M., Arif, R.B., Siddique, M.A., Oishe, M.R.: Study and observation of the variation of accuracies of KNN, SVM, LMNN, ENN algorithms on eleven different datasets from UCI machine learning repository. In: 2018 4th International Conference on iCEEiCT, pp. 124–129. IEEE (2018)
Mohit, R.R., Katoch, S., Vanjare, A., Omkar, S.N.: Classification of complex UCI datasets using machine learning algorithms using hadoop. In: IJCSSE, vol. 4, pp. 190–198 (2015)
Prachuabsupakij, W., Soonthornphisaj, N.: Clustering and combined sampling approaches for multi-class imbalanced data classification. In: Advances in IT and Industry Applications, pp. 717–724. Springer (2012)
Becker, S., Marcon, M., Ghafoor, S., Wurnig, C., Frauenfelder, T., Boss, A.: Deep learning in mammography: diagnostic accuracy of a multipurpose image analysis software in the detection of breast cancer. Invest. Radiol. 52(7), 434–440 (2017)
Junbao, L., Tingting, W., Huayou, S.: Dws-mkl: Depth-width-scaling multiple kernel learning for data classification. Neurocomputing 411, 455–467 (2020)
Eklund, P., Hoang, A.: A performance survey of public domain supervised machine learning algorithms. Austr. J. Intell. Inform. Syst. 9(1), 1–47 (2002)
Ding, S., Zhang, N., Xu, X., Guo, L., Zhang, J.: Deep extreme learning machine and its application in EEG classification. Math. Probl. Eng. (2015)
El-Khatib, M.J., Abu-Nasser, B.S., Abu-Naser, S.S.: Glass Classification using Artificial Neural Network (2019). http://dstore.alazhar.edu.ps/xmlui/bitstream/handle/123456789/144/ELKGCUv1.pdf?sequence=1&isAllowed=y
Arora, R.: Comparative analysis of classification algorithms on different datasets using Weka. Int. J. Comp. Appl. 54(13) (2012)
Awwalu, J., Ghazvini, A., Bakar, A.A.: Performance comparison of data mining algorithms: a case study on car evaluation dataset. Int. J. Comput. Trends Technol. 13(2) (2014)
Yang, L., Luo, P., Change Loy, C., Tang, X.: A large-scale car dataset for fine-grained categorization and verification. In: Proceedings of the IEEE CVPR Conference, pp. 3973–3981 (2015)
Braun J.: On Kolmogorov's Superposition Theorem and its Applications, p. 192. SVH Verlag (2010)
Lou, Y., Caruana, R., Gehrke, J., Hooker, G.: Accurate intelligible models with pairwise interactions. In: 19th SIGKDD, pp. 623–631. ACM (2013)
Kovalerchuk, B., Phan, H.: Full interpretable machine learning in 2D with inline coordinates. In: 25th International Conference Information Visualisation, Australia (2021) Vol. 1, pp. 189-196, IEEE, https://doi.org/10.1109/IV53921.2021.00038
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Kovalerchuk, B., Kalla, D.C., Agarwal, B. (2022). Deep Learning Image Recognition for Non-images. In: Kovalerchuk, B., Nazemi, K., Andonie, R., Datia, N., Banissi, E. (eds) Integrating Artificial Intelligence and Visualization for Visual Knowledge Discovery. Studies in Computational Intelligence, vol 1014. Springer, Cham. https://doi.org/10.1007/978-3-030-93119-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-93119-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93118-6
Online ISBN: 978-3-030-93119-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)