Domain Reduction Techniques for Sequential Fuzzy Indexing Tables – A Case Study

  • B. TusorEmail author
  • J. Bukor
  • L. Végh
  • O. Takáč
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 101)


In recent years, single-board computers have been gaining popularity because they make it possible to use low cost, low energy consumption devices to solve complex tasks that would be much harder to solve with microcontrollers. However, these devices have much more limited capabilities both computation and memory-wise compared to traditional computers, which in turn limits the options available to use them for classification problems. One of the available options is using Lookup Table-based classifiers that require minimal computation, although in return they require more memory space. Sequential Fuzzy Indexing Tables are improved versions of Lookup Tables that require less memory, but for large problem spaces their storage cost is still very high. This is due to the size of its structure, which can be reduced with suitable domain conversion techniques. In this paper, multiple options are investigated, analyzed and compared in order to solve this problem.


Data hashing Text processing Machine learning Domain reduction 



The publication was prepared with the financial support of Pallas Athéné Domus Educationis Foundation, project number: PADE-0117-5.


  1. 1.
    Gay, W.W.: Raspberry Pi Hardware Reference (2014). Scholar
  2. 2.
    Campbell-Kelly, M., Croarken, M., Robson, E.: The History of Mathematical Tables from Sumer to Spreadsheets. NY, USA (2003)Google Scholar
  3. 3.
    Tusor, B., Várkonyi-Kóczy, A.R., Tóth, J.T.: Active problem workspace reduction with a fast fuzzy classifier for real-time applications. In: IEEE International Conference on Systems, Man, and Cybernetics, pp. 4423–4428, Budapest, Hungary (2016)Google Scholar
  4. 4.
    Várkonyi-Kóczy, A.R., Tusor, B., Tóth, J.T.: Robust variable length data classification with extended sequential fuzzy indexing tables. In: 2017 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), pp. 1881–1886, Torino, Italy (2017)Google Scholar
  5. 5.
    Konheim, A.G.: Hashing in Computer Science: fifty Years of Slicing and Dicing, p. 393. Wiley-Intersciencem (2010)Google Scholar
  6. 6.
    Minsky, M., Papert, S.: Perceptrons: an Introduction to Computational Geometry. MIT Press (1969)Google Scholar
  7. 7.
    Tapson, J., van Schaik, A.: Learning the pseudoinverse solution to network weights. Neural Netw. 45, 94–100 (2013)CrossRefGoogle Scholar
  8. 8.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)CrossRefGoogle Scholar
  9. 9.
    Kamwa, I., Grondin, R., Sood, V.K., Gagnon, C., Nguyen, V.T., Mereb, J.: Recurrent neural networks for phasor detection and adaptive identification in power system control and protectio. IEEE Trans. Instr. Meas. 45(2), 657–664 (1996)CrossRefGoogle Scholar
  10. 10.
    Mikolov, T., Karafiát, M., Burget, L., Černocký, J., Khudanpur, S.: Recurrent neural network based language model. In: INTERSPEECH-2010, pp. 1045–1048 (2010)Google Scholar
  11. 11.
    Mozer, M.C., Chauvin, Y., Rumelhart, D.: A Focused Backpropagation Algorithm for Temporal Pattern Recognition, pp. 137–169. Lawrence Erlbaum Associates, Hillsdale, NJ (1995)Google Scholar
  12. 12.
    Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)CrossRefGoogle Scholar
  13. 13.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  14. 14.
    Zarit, B.D., Super, B.J., Quek, F.K.H.: Comparison of five color models in skin pixel classification. In: Proceedings International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, Corfu, Greece, pp. 58–63 (1999)Google Scholar
  15. 15.
    Tusor, B., Simon-Nagy, G., Várkonyi-Kóczy, A.R., Tóth, J.T.: Personalized dietary assistant-an intelligent space application. In: 21st IEEE International Conference on Intelligent Engineering Systems (INES 2017), pp. 27–32 (2017)Google Scholar
  16. 16.
    Tusor, B., Várkonyi-Kóczy, A.R., Bukor, J.: An ISpace-based dietary advisor. In: 2018 IEEE International Symposium on Medical Measurements and Applications (MeMeA), pp. 1–6 (2018)Google Scholar
  17. 17.
    Fonollosa, J., Sheik, S., Huerta R., Marco S.: Reservoir computing compensates slow response of chemosensor arrays exposed to fast varying gas concentrations in continuous monitoring. Sens. Actuators B: Chem 215, 618–629 (2015)CrossRefGoogle Scholar
  18. 18.
    Tshitoyan, V.: Simple Neural Network., GitHub. Accessed 10 August 2019
  19. 19.
    Cass, S.: Taking AI to the edge: Google’s TPU now comes in a maker-friendly package. IEEE Spectr. 56(5), 16–17 (2019)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Mathematics and InformaticsJ. Selye UniversityKomárnoSlovakia

Personalised recommendations