Classifying Flies Based on Reconstructed Audio Signals

  • Michael FlynnEmail author
  • Anthony Bagnall
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11872)


Advancements in sensor technology and processing power have made it possible to create recording equipment that can reconstruct the audio signal of insects passing through a directed infrared beam. The widespread deployment of such devices would allow for a range of applications previously not practical. A sensor net of detectors could be used to help model population dynamics, assess the efficiency of interventions and serve as an early warning system. At the core of any such system is a classification problem: given a segment of audio collected as something passes through a sensor, can we classify it? We examine the case of detecting the presence of fly species, with a particular focus on mosquitoes. This gives rise to a range of problems such as: can we discriminate between species of fly? Can we detect different species of mosquito? Can we detect the sex of the insect? Automated classification would significantly improve the effectiveness and efficiency of vector monitoring using these sensor nets. We assess a range of time series classification (TSC) algorithms on data from two projects working in this area. We assess our prior belief that spectral features are most effective, and we remark on all approaches with respect to whether they can be considered “real-time”.


Insect classification Time series classification Spectral features 



This work is supported by the Biotechnology and Biological Sciences Research Council [grant number BB/M011216/1], and the UK Engineering and Physical Sciences Research Council (EPSRC) [grant number EP/M015807/1]. The experiments were carried out on the High Performance Computing Cluster supported by the Research and Specialist Computing Support service at the University of East Anglia and using a Titan X Pascal donated by the NVIDIA Corporation.


  1. 1.
    Chadwick, L.E.: A simple stroboscopic method for the study of insect flight. Psyche 46(1), 1–8 (1939)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Chen, Y., Why, A., Batista, G., Mafra-Neto, A., Keogh, E.: Flying insect classification with inexpensive sensors. J. Insect Behav. 27(5), 657–677 (2014)CrossRefGoogle Scholar
  3. 3.
    Deng, H., Runger, G., Tuv, E., Vladimir, M.: A time series forest for classification and feature extraction. Inf. Sci. 239, 142–153 (2013)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Greven, H., Kaya, M., Junker, K., Akyuz, L., Amemiya, C.T.: Characterization of tongue worm (pentastomida) chitin supports \(\alpha \)-rather than \(\beta \)-chitin. Zoologischer Anzeiger 279, 111–115 (2019)CrossRefGoogle Scholar
  5. 5.
    Large, J., Lines, J., Bagnall, A.: A probabilistic classifier ensemble weighting scheme based on cross-validated accuracy estimates. Data Min. Knowl. Discov., 1–36 (2019) Google Scholar
  6. 6.
    Li, Z., Zhou, Z., Shen, Z., Yao, Q.: Automated identification of mosquito (diptera: culicidae) wingbeat waveform by artificial neural network. In: Li, D., Wang, B. (eds.) AIAI 2005. ITIFIP, vol. 187, pp. 483–489. Springer, Boston, MA (2005). Scholar
  7. 7.
    Lines, J., Taylor, S., Bagnall, A.: Time series classification with HIVE-COTE: the hierarchical vote collective of transformation-based ensembles. ACM Trans. Knowl. Discov. Data 12(5), 1041–1046 (2018)CrossRefGoogle Scholar
  8. 8.
    Lines, J., Davis, L.M., Hills, J., Bagnall, A.: A shapelet transform for time series classification. In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 289–297. ACM (2012)Google Scholar
  9. 9.
    Moore, A.: Development of a data acquisition system for long-term outdoor recording of insect flight activity using a photosensor. In: 13th Conference on Aerobiology and Biometeorology, American Meteorological Society, Albuquerque, New Mexico (1998)Google Scholar
  10. 10.
    Moore, A., Miller, J.R., Tabashnik, B.E., Gage, S.H.: Automated identification of flying insects by analysis of wingbeat frequencies. J. Econ. Entomol. 79(6), 1703–1706 (1986)CrossRefGoogle Scholar
  11. 11.
    Moore, A., Miller, R.H.: Automated identification of optically sensed aphid (homoptera: Aphidae) wingbeat waveforms. Ann. Entomol. Soc. Am. 95(1), 1–8 (2002)CrossRefGoogle Scholar
  12. 12.
    Potamitis, I.: Classifying insects on the fly. Ecol. Inform. 21, 40–49 (2014)CrossRefGoogle Scholar
  13. 13.
    Potamitis, I., Rigakis, I.: Novel noise-robust optoacoustic sensors to identify insects through wingbeats. IEEE Sens. J. 15(8), 4621–4631 (2015)CrossRefGoogle Scholar
  14. 14.
    Potamitis, I., Rigakis, I.: Large aperture optoelectronic devices to record and time-stamp insects’ wingbeats. IEEE Sens. J. 16(15), 6053–6061 (2016)CrossRefGoogle Scholar
  15. 15.
    Reed, S., Williams, C., Chadwick, L.: Frequency of wing-beat as a character for separating species races and geographic varieties of drosophila. Genetics 27(3), 349 (1942)Google Scholar
  16. 16.
    Sarpola, M., et al.: An aquatic insect imaging system to automate insect classification. Trans. ASABE 51(6), 2217–2225 (2008)CrossRefGoogle Scholar
  17. 17.
    Schäfer, P.: Bag-of-SFA-Symbols in Vector Space (BOSS VS) (2015)Google Scholar
  18. 18.
    Unwin, D., Ellington, C.: An optical tachometer for measurement of the wing-beat frequency of free-flying insects. J. Exp. Biol. 82(1), 377–378 (1979)Google Scholar
  19. 19.
    Wen, C., Guyer, D.: Image-based orchard insect automated identification and classification method. Comput. Electron. Agric. 89, 110–115 (2012)CrossRefGoogle Scholar
  20. 20.
    Zhang, C., Wang, P., Guo, H., Fan, G., Chen, K., Kämäräinen, J.K.: Turning wingbeat sounds into spectrum images for acoustic insect classification. Electron. Lett. 53(25), 1674–1676 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.The University of East AngliaNorwichUK

Personalised recommendations