Deep Learning Algorithms for Complex Pattern Recognition in Ultrasonic Sensors Arrays

  • Vittorio MazziaEmail author
  • Angelo Tartaglia
  • Marcello Chiaberge
  • Dario Gandini
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11943)


Nowadays, applications of ultrasonic proximity sensors are limited to a post-processing of the acquired signals with a pipeline of filters and threshold comparators. This article proposes two different and novel processing methodologies, based on machine learning algorithms, that outperform classical approaches. Indeed, noisy signals and presence of thin or soundproofing objects are likely sources of false positive detections that can make traditional approaches useless and unreliable. In order to take advantage of correlations among the data, multiple parallel signals, coming from a cluster of ultrasonic sensors, have been exploited, producing a number of different features that allowed to achieve more accurate and precise predictions for object detection. Firstly, model-based learning as well as instance-based learning systems have been investigated for an independent time correlation analysis of the different signals. Particular attention has been given to the training and testing of the deep fully connected network that showed, since the beginning, more promising results. In the second part, a recurrent neural network, based on long short term memory cells, has been devised. As a result of its intrinsic nature, time correlations between successive samples are not more overlooked, further improving the overall prediction capability of the system. Finally, cutting edge training methodologies and strategies to find the different hyperparameters have been adopted in order to obtain the best results and performance from the available data.


Deep learning Ultrasound sensors Industrial security 



This work has been developed with the contribution of the Politecnico di Torino Interdepartmental Centre for Service Robotics PIC4SeR ( and SmartData@Polito (


  1. 1.
    Shrivastava, A.K., Verma, A., Singh, S.P.: Distance measurement of an object or obstacleby ultrasound sensors using P89C51RD2. Int. J. Comput. Theory Eng. 2(1), 1793–8201 (2010)Google Scholar
  2. 2.
    Houghton, R., DeLuca, F.: Ultrasonicensordevice. Patentinspiration (1964)Google Scholar
  3. 3.
    Li, S.-H.: Ultrasound sensor for distance measurement. Google Patents (2002)Google Scholar
  4. 4.
    Wu, K., Chen, X., Ding, M.: Deep learning based classification of focal liver lesions with contrast-enhanced ultrasound. Optik-Int. J. Light Electron Opt. 125(15), 4057–4063 (2014) CrossRefGoogle Scholar
  5. 5.
    Carneiro, G., Nascimento, J.C., Freitas, A.: The segmentation of the left ventricle of the heart from ultrasound data using deep learning architectures and derivative-based search methods. IEEE Trans. Image Process. 21(3), 968–982 (2012)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Farias, G., et al.: A neural network approach for building an obstacle detection model by fusion of proximity sensors data. Sensors 18(3), 683 (2018)CrossRefGoogle Scholar
  7. 7.
    De Simone, M., Rivera, Z., Guida, D.: Obstacle avoidance system for unmanned ground vehicles by using ultrasonic sensors. Machines 6(2), 18 (2018)CrossRefGoogle Scholar
  8. 8.
    Lee, D., Kim, S., Tak, S., Yeo, H.: Real-time feed-forward neural network-based forward collision warning system under cloud communication environment. IEEE (2018)Google Scholar
  9. 9.
    Parrilla, M., Anaya, J.J., Fritsch, C.: Digital signal processing techniques for high accuracy ultrasonic range measurements. IEEE Trans. Instrum. Meas. 40(4), 759–763 (1991) CrossRefGoogle Scholar
  10. 10.
    Cover, T., Hart, P.: Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13(1), 21–27 (1967)CrossRefGoogle Scholar
  11. 11.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar
  12. 12.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  13. 13.
    Tharwat, A.: Classification assessment methods. Appl. Comput. Inf. (2018) Google Scholar
  14. 14.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  15. 15.
    Reddi, S.J., Kale, S., Kumar, S.: On the convergence of adam and beyond (2018)Google Scholar
  16. 16.
    Lipton, Z.C., Berkowitz, J., Elkan, C.: A critical review of recurrent neural networks for sequence learning, arXiv preprint arXiv:1506.00019 (2015)
  17. 17.
    Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam, arXiv preprint arXiv:1711.05101 (2017)
  18. 18.
    Smith, L.N.: Cyclical learning rates for training neural networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Vittorio Mazzia
    • 1
    • 2
    • 3
    Email author
  • Angelo Tartaglia
    • 1
    • 2
  • Marcello Chiaberge
    • 1
    • 2
  • Dario Gandini
    • 1
    • 2
  1. 1.Department of Electronic and Telecommunications Engineering (DET)Politecnico di TorinoTurinItaly
  2. 2.PIC4SeR - Politecnico Interdepartmental Centre for Service RoboticTurinItaly
  3. 3.SmartData@PoliTo - Big Data and Data Science LaboratoryTurinItaly

Personalised recommendations