Advertisement

Personal and Ubiquitous Computing

, Volume 18, Issue 7, pp 1753–1762 | Cite as

Classifying watermelon ripeness by analysing acoustic signals using mobile devices

  • Wei Zeng
  • Xianfeng Huang
  • Stefan Müller Arisona
  • Ian Vince McLoughlin
Original Article

Abstract

This work addresses the problem of distinguishing between ripe and unripe watermelons using mobile devices. Through analysing ripeness-related features extracted by thumping watermelons, collecting acoustic signals by microphones on mobile devices, our method can automatically identify the ripeness of watermelons. This is possible in real time, making use of machine learning techniques to provide good accuracy. We firstly collect a training dataset comprising acoustic signals generated by thumping both ripe and unripe watermelons. Audio signal analysis on this helps identify features related to watermelon ripeness. These features are then used to construct a classification model for future signals. Based on this, we developed a crowdsourcing application for Android which allows users to identify watermelon ripeness in real time while submitting their results to us allowing continuous improvement of the classification model. Experimental results show that our method is currently able to correctly classify ripe and unripe watermelons with an overall accuracy exceeding 89 %.

Keywords

Mobile and physical computing Real-time signal analysis Machine learning Crowdsourcing 

Notes

Acknowledgments

This work was established at the Singapore-ETH Centre for Global Environmental Sustainability (SEC), co-funded by the Singapore National Research Foundation (NRF) and ETH Zurich. We would also like to thank developers of open libraries like SVM and FFT used in our implementation. Without their work, we would spend much more time on implementing these algorithms.

References

  1. 1.
    Aizerman A, Braverman E, Rozoner L (1964) Theoretical foundations of the potential function method in pattern recognition learning. Autom Remote Control 25:821–837Google Scholar
  2. 2.
    Ay C (1996) Acoustic evaluation of watermelon internal quality-maturity, cavity existence and orientation. J Agric Mech 5(4):57–71Google Scholar
  3. 3.
    Baki S, Annuar Mohd ZM, Yassin IM, Hasliza AH, Zabidi A (2010) Non-destructive classification of watermelon ripeness using Mel-frequency cepstrum coefficients and Multilayer Perceptrons. In: Proceedings of international joint conference on neural networks (IJCNN), IEEE, pp 1–6Google Scholar
  4. 4.
    Balandina E, Trossen D (2006) Nokia remote sensing platform middleware and demo application server: features and user interface. Nokia Research Center, HelsinkiGoogle Scholar
  5. 5.
    Butterworth S (1930) On the theory of filter amplifiers. Wirel Engineer 7:536–541Google Scholar
  6. 6.
    Cantwell M (1996) Case study: quality assurance for melons. Perishables Handling Newsl Iss (85):10–12Google Scholar
  7. 7.
    Diezma-Iglesias B, Ruiz-Altisent M, Barreiro P (2004) Detection of internal quality in seedless watermelon by acoustic impulse response. Biosyst Eng 88(2):221–230CrossRefGoogle Scholar
  8. 8.
    Gouyon F, Pachet F, Delerue O (2000) On the use of zero-crossing rate for an application of classification of percussive sounds. In: Proceedings of the COST G-6 conference on Digital Audio Effects (DAFX-00), Verona, Italy. Helsiniki University of Technology, HelsinikiGoogle Scholar
  9. 9.
    Juillerat N, Müller Arisona S, Schubiger-Banz S (2007) Real-time, low latency audio processing in java. In: Proceedings of the international computer music conference, Copenhagen, DenmarkGoogle Scholar
  10. 10.
    Lu H, Pan W, Lane ND, Choudhury T, Campbell AT (2009) Soundsense: scalable sound sensing for people-centric applications on mobile phones. In: Proceedings of the 7th international conference on mobile systems, applications, and services. ACM, Cumberland, pp 165–178Google Scholar
  11. 11.
    Lu L, Zhang HJ, Li SZ (2003) Content-based audio classification and segmentation by using support vector machines. Multimed Syst 8(6):482–492CrossRefGoogle Scholar
  12. 12.
    McKinney MF, Breebaart J (2003) Features for audio and music classification. In: Proceedings of the third international symposium on music information retrieval (ISMIR), vol 3, pp 151–158Google Scholar
  13. 13.
    McLoughlin IV (2009) Applied speech and audio processing: with Matlab examples. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  14. 14.
    Misra A, Essl G, Rohs M (2008) Microphone as sensor in mobile phone performance. In: Proceedings of the international conference for new interfaces for musical expression (NIME-08), Genova, ItalyGoogle Scholar
  15. 15.
    Mitrović D, Zeppelzauer M, Breiteneder C (2010) Features for content-based audio retrieval. Adv Comput 78:71–150CrossRefGoogle Scholar
  16. 16.
    Pohjalainen J (2007) Methods of automatic audio content classification. Ph.D. thesis, Helsiniki University of TechnologyGoogle Scholar
  17. 17.
    Saunders J (1996) Real-time discrimination of broadcast speech/music. In: Proceedings of international conference on acoustics, speech, and signal processing (ICASSP), vol 2, IEEE, pp 993–996Google Scholar
  18. 18.
    Yamamoto H, Iwamoto M, Haginuma S (1980) Acoustic impulse response method for measuring natural frequency of intact fruits and preliminary applications to internal quality evaluation of apples and watermelons. J Texture Studies 11(2):117–136CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Wei Zeng
    • 1
  • Xianfeng Huang
    • 1
  • Stefan Müller Arisona
    • 1
  • Ian Vince McLoughlin
    • 2
  1. 1.Future Cities Laboratory, Department of ArchitectureETH ZurichZurichSwitzerland
  2. 2.University of Science and Technology of ChinaHefeiChina

Personalised recommendations