Neural Processing Letters

, Volume 50, Issue 1, pp 623–643 | Cite as

An Ar2p Deep Learning Architecture for the Discovery and the Selection of Features

  • E. Puerto
  • J. AguilarEmail author
  • R. Vargas
  • J. Reyes


In the context of pattern recognition processes with machine learning algorithms, either through supervised, semi-supervised or unsupervised methods, one of the most important elements to consider are the features that are used to represent the phenomenon to be studied. In this sense, this paper proposes a deep learning architecture for Ar2p, which is based on supervised and unsupervised mechanisms for the discovery and the selection of features for classification problems (called Ar2p-DL). Ar2p is an algorithm of pattern recognition based on the systematic functioning of the human brain. Ar2p-DL is composed of three phases: the first phase, called feature analysis, is supported by two feature-engineering approaches to discover or select atomic features/descriptors. The feature engineering approach used for the discovery, is based on a classical clustering technique, K-means; and the approach used for the selection, is based on a classification technique, Random Forest. The second phase, called aggregation, creates a feature hierarchy (merge of descriptors) from the atomic features/descriptors (it uses as aggregation strategy the DBSCAN algorithm). Finally, the classification phase carries out the classification of the inputs based on the feature hierarchy, using the classical Ar2p algorithm. The last phase of Ar2p-DL uses a supervised learning approach, while the first phases combine supervised and unsupervised learning approaches. To analyze the performance of Ar2p-DL, several tests have been made using different benchmarks (datasets) from the UCI Machine Learning Repository, in order to compare Ar2p-DL with other classification methods.


Deep learning Pattern recognition processes Feature engineering Pattern Recognition Theory of Mind 



  1. 1.
    Guyon I, Gunn S, Nikravesh M, Zadeh LA (2006) Feature extraction foundations and applications. Springer, BerlinCrossRefzbMATHGoogle Scholar
  2. 2.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444CrossRefGoogle Scholar
  3. 3.
    Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 6:85–117CrossRefGoogle Scholar
  4. 4.
    LeCun Y, Bengio Y (1998) Convolutional networks for images, speech, and time series. In: Arbib MA (ed) The handbook of brain theory and neural networks. MIT Press, Cambridge, MA, pp 255–258Google Scholar
  5. 5.
    Salakhutdinov R, Hinton G (2010) Efficient learning of deep Boltzmann machines. In: Proc. intl conference on artificial intelligence and statistics, pp 693–700Google Scholar
  6. 6.
    Hua Y, Guo J, Hua Z (2015) Deep belief networks and deep learning. In: Proc. int. conf. intel. comput. internet things, pp 1–4Google Scholar
  7. 7.
    Ester M, Kriegel H, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proc. 2nd intl conf on knowledge discovery and data mining, pp 226–231Google Scholar
  8. 8.
    Aguilar J (2001) Learning algorithm and retrieval process for the multiple classes random neural network model. Neural Process Lett 13(1):81–91CrossRefzbMATHGoogle Scholar
  9. 9.
    Aguilar J (1998) Definition of an energy function for the random neural to solve optimization problems. Neural Netw 11(4):731–738CrossRefGoogle Scholar
  10. 10.
    Gelenbe E, Yin Y (2016) Deep learning with random neural networks. In: Proc. international joint conference on neural networks (IJCNN), pp 1633–1638Google Scholar
  11. 11.
    Aguilar J (2004) A color pattern recognition problem based on the multiple classes random neural network model. Neurocomputing 61:71–83CrossRefGoogle Scholar
  12. 12.
    Zhang J, Yu J, Tao D (2018) Local deep-feature alignment for unsupervised dimension reduction. IEEE Trans Image Process 27(5):2420–2432MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Yu H, Sun D, Xi X, Yang X, Zheng S, Wang Q (2018) Fuzzy one-class extreme auto-encoder. Neural Process Lett. Google Scholar
  14. 14.
    Hong J, Yu J, Zhang X, Jin K, Lee K (2018) Multi-modal face pose estimation with multi-task manifold deep learning. Accessed 1 July 2019
  15. 15.
    Kumar G, Bhatia PK (2014) A detailed review of feature extraction in image processing systems. In: Proc. fourth international conference on advanced computing & communication technologies. IEEE, pp 5–12Google Scholar
  16. 16.
    Pacheco F, Exposito E, Gineste M, Budoin C, Aguilar J (2019) Towards the deployment of machine learning solutions in traffic network classification: a systematic survey. IEEE Commun Surv Tutor 21(2):1988–2014CrossRefGoogle Scholar
  17. 17.
    Chang M, Buš P, Schmitt G (2017) Feature extraction and K-means clustering approach to explore important features of urban identity. In: 16th IEEE international conference on machine learning and applications (ICMLA), pp 1139–1144Google Scholar
  18. 18.
    Puerto E, Aguilar J (2017) Un algoritmo recursivo de reconocimiento de patrones. Revista Técnica de la Facultad de Ingeniería Universidad del Zulia 40(2):95–104Google Scholar
  19. 19.
    Puerto E, Aguilar J, Chavez D (2017) A new recursive patterns matching model inspired in systematic theory of human mind. Int J Adv Comput Technol (IJACT) 9(1):28–39Google Scholar
  20. 20.
    Puerto E, Aguilar J (2016) Formal description of a pattern for a recursive process of recognition. In: Proc IEEE Latin American conference on computational intelligence, pp 1–2Google Scholar
  21. 21.
    Puerto E, Aguilar J (2016) Learning algorithm for the recursive pattern recognition model. Appl Artif Intell 30(7):662–678CrossRefGoogle Scholar
  22. 22.
    Kurzweil R (2013) How to make mind. The Futurist 47(2):14–17Google Scholar
  23. 23.
    Puerto E, Aguilar J, Chávez D (2018) A recursive patterns matching model for the dynamic pattern recognition problem. Appl Artif Intell 32(4):419–432CrossRefGoogle Scholar
  24. 24.
    Liu H, Motoda H (1998) Feature extraction, construction and selection: a data mining perspective, vol 453. Springer, BerlinCrossRefzbMATHGoogle Scholar
  25. 25.
    Khalid S, Khalil T, Nasreen S (2014) A survey of feature selection and feature extraction techniques in machine learning. In: Proc. IEEE science and information conference (SAI), pp 372–378Google Scholar
  26. 26.
    Motoda H, Liu H (2002) Feature selection, extraction and construction. Commun IICM 5:67–72Google Scholar
  27. 27.
    Yu J, Kuang Z, Zhang B, Zhang W, Lin D, Fan J (2018) Leveraging content sensitiveness and user trustworthiness to recommend fine-grained privacy settings for social image sharing. IEEE Trans Inf Forensics Secur 13(5):1317–1332CrossRefGoogle Scholar
  28. 28.
    Yu J, Liu D, Tao D, Seah H (2012) On combining multiple features for cartoon character retrieval and clip synthesis. IEEE Trans Syst Man Cybern 42(5):1413–1427CrossRefGoogle Scholar
  29. 29.
    Lausser L, Szekely R, Schirra L, Kestler H (2018) The influence of multi-class feature selection on the prediction of diagnostic phenotypes. Neural Process Lett 48(2):863–880CrossRefGoogle Scholar
  30. 30.
    Singaravel S, Suykens J, Geyer P (2018) Deep-learning neural-network architectures and methods: using component based models in building-design energy prediction. Adv Eng Inform 38:81–90CrossRefGoogle Scholar
  31. 31.
    Pham D, Dimov S, Nguyen C (2005) Selection of K in K-means clustering. In: Proc. inst. mech. eng., pp 103–119Google Scholar
  32. 32.
    Pham D, Dimov S, Nguyen C (2004) An incremental K-means algorithm. J Mech Eng Sci 218(7):783–795CrossRefGoogle Scholar
  33. 33.
    Pelleg D, Moore A (2000) X-means: extending K-means with efficient estimation of the number of clusters. In: Proc. of the 17th international conf. on machine learning, pp 727–734Google Scholar
  34. 34.
    Kass R, Wasserman L (1995) A reference Bayesian test for nested hypotheses and its relationship to the Schwarz criterion. J Am Stat Assoc 90(431):928–934MathSciNetCrossRefzbMATHGoogle Scholar
  35. 35.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRefzbMATHGoogle Scholar
  36. 36.
    Balakrishnama A, Ganapathiraju S (1998) Linear discriminant analysis-a brief tutorial. Inst Signal Inf Process 18:1–8Google Scholar
  37. 37.
    Ester M, Kriegel H-P, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proc. 2nd int conf on knowledge discovery and data mining, pp 226–231Google Scholar
  38. 38.
    Wagner P, Peres S, Lima C, Freitas F, Barros R (2014) Gesture unit segmentation using spatial-temporal information and machine learning. In: Proc. twenty-seventh international Florida artificial intelligence research society conference, pp 101–106Google Scholar
  39. 39.
    Lichman M (2013) UCI machine learning repository. University of California, IrvineGoogle Scholar
  40. 40.
    El Kessab B, Daoui C, Boukhalene B, Salouan R (2014) A comparative study between the K-nearest neighbors and the multi-layer perceptron for cursive handwritten arabic numerals recognition. Int J Comput Appl 107(21):25–30Google Scholar
  41. 41.
    Keith MJ et al (2010) The high time resolution universe pulsar survey—I. System configuration and initial discoveries. Mon Not R Astron Soc 409(2):619–627CrossRefGoogle Scholar
  42. 42.
    Lyon RJ, Stappers BW, Cooper S, Brooke JM, Knowles JD (2016) Fifty years of pulsar candidate selection: from simple filters to a new principled real-time classification approach. Mon Not R Astron Soc 459(1):1104–1123CrossRefGoogle Scholar
  43. 43.
    Charytanowicz M et al. (2010) A complete gradient clustering algorithm for features analysis of X-ray images. In: Proc. information technologies in biomedicine. Springer, pp 15–24Google Scholar
  44. 44.
    Altay H, Acar B, Demiroz G, Cekin A (1997) A supervised machine learning algorithm for arrhythmia analysis. In: Proceedings of the computers in cardiology conferenceGoogle Scholar
  45. 45.
    Bareiss E, Ray E, Porter B (1987) Protos: an exemplar-based learning apprentice. In: Proceedings 4th international workshop on machine learning, pp 12–23Google Scholar
  46. 46.
    Puerto E, Aguilar J, Reyes J, Sarkar D (2018) Deep learning architecture for the recursive patterns recognition model. J Phys Conf Ser 1126:012035CrossRefGoogle Scholar
  47. 47.
    Van M, Van L (2011) Combining RGB and ToF cameras for real-time 3D hand gesture interaction. In: Proc. IEEE workshop on applications of computer vision, pp 66–72Google Scholar
  48. 48.
    Nguyen A, Yosinski J, Clune J (2015) Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Proc. IEEE conference on computer vision and pattern recognition, pp 427–436Google Scholar
  49. 49.
    Niu X, Suen C (2012) A novel hybrid CNN–SVM classifier for recognizing handwritten digits. Pattern Recogn 45(4):1318–1325CrossRefGoogle Scholar
  50. 50.
    Liu L, Wu Y, Wei W, Cao W, Sahin S, Zhang Q (2018) Benchmarking deep learning frameworks: design considerations, metrics and beyond. In: IEEE 38th international conference on distributed computing systems (ICDCS), pp 1258–1269Google Scholar
  51. 51.
    Wu D, Pigou L, Kindermans P, Do-Hoang N, Shao L, Dambre J, Odobez J (2016) Deep dynamic neural networks for multimodal gesture segmentation and recognition. IEEE Trans Pattern Anal Mach Intell 38(8):1583–1597CrossRefGoogle Scholar
  52. 52.
    Wang P, Li W, Liu S, Zhang Y, Gao Z, Ogunbona P (2016) Large-scale continuous gesture recognition using convolutional neural networks. In: 23rd International conference on pattern recognition, pp 13–18Google Scholar
  53. 53.
    Chen F, Chen N, Mao H, Hu H (2018) Assessing four neural networks on handwritten digit recognition dataset (MNIST). Chuangxinban J Comput. arXiv:1811.08278v1 [cs.CV]
  54. 54.
    Köpüklü O, Gunduz A, Kose N, Rigoll G (2019) Real-time hand gesture detection and classification using convolutional neural networks. arXiv preprint arXiv:1901.10323
  55. 55.
    Strezoski G, Stojanovski D, Dimitrovsk I, Madjarov G (2016) Hand gesture recognition using deep convolutional neural networks. In: International conference on ICT innovations, pp 49–58Google Scholar
  56. 56.
    Hossein A (2018) Implementing VGG13 for MNIST dataset in TensorFlow. Accessed 1 July 2019

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.GIDISUniversidad Francisco de Paula SantanderCúcutaColombia
  2. 2.CEMISIDUniversidad de Los AndesMéridaVenezuela
  3. 3.Laboratorio de PrototiposUniversidad UNETSan CristóbalVenezuela

Personalised recommendations