close
Skip to main content
Springer Nature Link
Log in

Investigation on new Mel frequency cepstral coefficients features and hyper-parameters tuning technique for bee sound recognition

  • Application of soft computing
  • Published:
Save article
View saved research
Soft Computing Aims and scope Submit manuscript

Abstract

Due to the important role of honey bees in life, there have been increasingly advanced techniques introduced to support apiarists in taking the best care of their bees. Recently, machine learning (ML) methods emerge as a powerful tool among these techniques and have great contributions to automated beehive monitoring systems with low cost and better performance. By analyzing the data collected from beehives, ML algorithms are able to solve a number of crucial problems in monitoring the beehives such as early detecting the phenomena of swarming, identifying the bee queen’s absence, and recognizing pest infestations. In this study, we suggest several techniques to enhance the performance of the machine learning models applied to monitoring the honey beehives. Particularly, we apply an advanced technique for tuning hyper-parameters of the ML models and investigate the new Mel frequency cepstral coefficients (MFCCs) features. The obtained results show that our proposed methods can improve significantly the accuracy of these ML-based models in recognizing and classifying the bee buzzing from other ambient noises, making them even better than plural deep learning algorithms suggested in the literature. In addition, we introduce a new dataset of bee sound samples and we verify the efficiency of our proposed models on the new dataset.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+
from $39.99 /Month
  • Starting from 10 chapters or articles per month
  • Access and download chapters and articles from more than 300k books and 2,500 journals
  • Cancel anytime
View plans

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.

Data availability

Enquiries about data availability should be directed to the authors.

Notes

  1. https://www.statista.com/statistics/933928/global-market-value-of-honey/.

  2. https://io-bee.eu/.

  3. https://www.osbeehives.com/pages/about-us.

  4. https://hivemind.nz/

  5. https://www.gobuzzr.com/.

  6. https://usu.app.box.com/v/BeePiAudioData.

  7. https://github.com/doandongnguyen/BeeSoundRecognitions.

References

  • Altman NS (1992) An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat 46:175–185

    MathSciNet  Google Scholar 

  • Alves TS, Pinto MA, Ventura P et al (2020) Automatic detection and classification of honey bee comb cells using deep learning. Comput Electron Agric 170(105):244

    Google Scholar 

  • Aumann HM, Aumann MK, Emanetoglu NW (2021) Janus: a combined radar and vibration sensor for beehive monitoring. IEEE Sens Lett 5(3):1–4

    Article  Google Scholar 

  • Aziz RM (2022a) Application of nature inspired soft computing techniques for gene selection: a novel frame work for classification of cancer. Soft Comput, pp 1–18

  • Aziz RM (2022) Nature-inspired metaheuristics model for gene selection and classification of biomedical microarray data. Med Biol Eng Comput 60(6):1627–1646

    Article  Google Scholar 

  • Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13(1):281–305

    MathSciNet  MATH  Google Scholar 

  • Breeze TD, Bailey AP, Balcombe KG et al (2011) Pollination services in the UK: how important are honeybees? Agric Ecosyst Environ 142(3):137–143

    Article  Google Scholar 

  • Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  MATH  Google Scholar 

  • Cai L, Liu W (2021) Monitoring harmful bee colony with deep learning based on improved grey prediction algorithm. In: 2021 2nd international conference on artificial intelligence and information systems, pp 1–6

  • Cecchi S, Spinsante S, Terenzi A et al (2020) A smart sensor-based measurement system for advanced bee hive monitoring. Sensors 20(9):2726

    Article  Google Scholar 

  • Chen T, Guestrin C (2016) Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 785–794

  • Dreller C, Kirchner WH (1993) Hearing in honeybees: localization of the auditory sense organ. J Comp Physiol A 173(3):275–279

    Article  Google Scholar 

  • Gaikwad SK, Gawali BW, Yannawar P (2010) A review on speech recognition technique. Int J Comput Appl 10(3):16–24

    Google Scholar 

  • Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63(1):3–42

    Article  MATH  Google Scholar 

  • Guo G, Wang H, Bell D, et al (2003) KNN model-based approach in classification. In: OTM confederated international conferences on the move to meaningful internet systems, Springer, pp 986–996

  • Kulyukin V, Mukherjee S, Amlathe P (2018) Toward audio beehive monitoring: deep learning vs. standard machine learning in classifying beehive audio samples. Appl Sci 8(9):1573. https://doi.org/10.3390/app8091573

    Article  Google Scholar 

  • Lavesson N, Davidsson P (2006) Quantifying the impact of learning algorithm parameter tuning. In: In Proceedings of the 21st national conference on artificial intelligence—volume 1 (AAAI’06). AAAI Press, p 6

  • Liao Y, McGuirk A, Biggs B, et al (2020) Noninvasive beehive monitoring through acoustic data using SAS® event stream processing and SAS®Viya®. SAS Global Forum p 24

  • Mac Aodha O, Gibb R, Barlow KE et al (2018) Bat detective-deep learning tools for bat acoustic signal detection. PLoS Comput Biol 14(3):e1005,995

    Article  Google Scholar 

  • Mantovani RG, Rossi ALD, Vanschoren J, et al (2015) To tune or not to tune: Recommending when to adjust SVM hyper-parameters via meta-learning. In: 2015 International joint conference on neural networks (IJCNN), pp 1–8, ISSN: 2161-4407

  • Marstaller J, Tausch F, Stock S (2019) Deepbees-building and scaling convolutional neuronal nets for fast and large-scale visual monitoring of bee hives. In: Proceedings of the IEEE/CVF international conference on computer vision workshops, p 0

  • Maurya NS, Kushwaha S, Chawade A et al (2021) Transcriptome profiling by combined machine learning and statistical R analysis identifies TMEM236 as a potential novel diagnostic biomarker for colorectal cancer. Sci Rep 11(1):1–11

    Article  Google Scholar 

  • Mercadier M, Lardy JP (2019) Credit spread approximation and improvement using random forest regression. Eur J Oper Res 277(1):351–365

    Article  MathSciNet  MATH  Google Scholar 

  • Metlek S, Kayaalp K (2021) Detection of bee diseases with a hybrid deep learning method. J Fac Eng Arch Gazi Univ 36(3):1716–1731

    Google Scholar 

  • Mittal K, Khanduja D, Tewari PC (2017) An insight into ‘decision tree analysis’’’. World Wide J Multidiscip Res Dev 3(12):111–115

    Google Scholar 

  • Murty KSR, Yegnanarayana B (2005) Combining evidence from residual phase and MFCC features for speaker recognition. IEEE Signal Process Lett 13(1):52–55

    Article  Google Scholar 

  • Narkhede S (2018) Understanding AUC-ROC curve: towards data. Science 26:220–227

    Google Scholar 

  • Ngo TN, Rustia DJA, Yang EC et al (2021) Automated monitoring and analyses of honey bee pollen foraging behavior using a deep learning-based imaging system. Comput Electron Agric 187(106):239

    Google Scholar 

  • Nguyen HD, Nguyen DD, Vu TL et al (2020) Audio beehive monitoring based on IoT-AI techniques: a survey and perspective. Tap chi Khoa hoc Nong nghiep Viet Nam/Vietnam Journal of Agricultural Sciences 3(1):530–540

    Google Scholar 

  • Nolasco I, Benetos E (2018) To bee or not to bee: investigating machine learning approaches for beehive sound recognition

  • Nolasco I, Terenzi A, Cecchi S et al (2019) Audio-based identification of beehive states. In: ICASSP 2019–2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 8256–8260

  • Orlowska A, Fourer D, Gavini JP, et al (2022) Honey bee queen presence detection from audio field recordings using summarized spectrogram and convolutional neural networks. In: International conference on intelligent systems design and applications, Springer, pp 83–92

  • Osei-Bryson KM (2004) Evaluation of decision trees: a multi-criteria approach. Comput Oper Res 31(11):1933–1945

    Article  MathSciNet  MATH  Google Scholar 

  • Oshiro TM, Perez PS, Baranauskas JA (2012) How many trees in a random forest? In: International workshop on machine learning and data mining in pattern recognition, Springer, pp 154–168

  • Pashaei E, Pashaei E (2022) An efficient binary chimp optimization algorithm for feature selection in biomedical data classification. Neural Comput Appl 34(8):6427–6451

    Article  Google Scholar 

  • Picone J (1993) Signal modeling techniques in speech recognition. Proc IEEE 81(9):1215–1247 (Conference Name: Proceedings of the IEEE)

    Article  Google Scholar 

  • Probst P, Bischl B, Boulesteix AL (2018) Tunability: importance of hyperparameters of machine learning algorithms. arXiv:1802.09596 [stat]

  • Rabiner L (1989) A tutorial on hidden Markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286. https://doi.org/10.1109/5.18626 (conference Name: Proceedings of the IEEE)

    Article  Google Scholar 

  • Ribeiro AP, da Silva NFF, Mesquita FN et al (2021) Machine learning approach for automatic recognition of tomato-pollinating bees based on their buzzing-sounds. PLoS Comput Biol 17(9):e1009,426

    Article  Google Scholar 

  • Robles-Guerrero A, Saucedo-Anaya T, González-Ramérez E et al (2017) Frequency analysis of honey bee buzz for automatic recognition of health status: a preliminary study. Res Comput Sci 142(1):89–98

    Article  Google Scholar 

  • Robles-Guerrero A, Saucedo-Anaya T, Qonzalez Ramirez E et al (2019) Analysis of a multiclass classification problem by Lasso Logistic Regression and Singular Value Decomposition to identify sound patterns in queenless bee colonies. Comput Electron Agric 159:69–74

  • Soares BS, Luz JS, de Macêdo VF et al (2022) Mfcc-based descriptor for bee queen presence detection. Expert Syst Appl 201(117):104

    Google Scholar 

  • Spiesman BJ, Gratton C, Hatfield RG et al (2021) Assessing the potential for deep learning and computer vision to identify bumble bee species from images. Sci Rep 11(1):1–10

    Article  Google Scholar 

  • Stastny J, Munk M, Juranek L (2018) Automatic bird species recognition based on birds vocalization. EURASIP J Audio, Speech Music Process 2018:19

    Article  Google Scholar 

  • Tashakkori R, Hamza AS, Crawford MB (2021) Beemon: An IoT-based beehive monitoring system. Comput Electron Agric 190(106):427

    Google Scholar 

  • Terenzi A, Cecchi S, Spinsante S (2020) On the importance of the sound emitted by honey bee hives. Vet Sci 7(4):168

    Article  Google Scholar 

  • Tiwari A (2018) A deep learning approach to recognizing bees in video analysis of bee traffic

  • van Rijn JN, Hutter F (2018) Hyperparameter importance across datasets. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining. Association for Computing Machinery, New York, NY, USA, KDD ’18, pp 2367–2376

  • Vapnik VN (1995) The nature of statistical learning theory. Springer, Berlin

    Book  MATH  Google Scholar 

  • Wakjira K, Negera T, Zacepins A et al (2021) Smart apiculture management services for developing countries-the case of SAMS project in Ethiopia and Indonesia. PeerJ Comput Sci 7:e484

    Article  Google Scholar 

  • Wehmann HN, Gustav D, Kirkerud NH et al (2015) The sound and the fury-bees hiss when expecting danger. PLoS ONE 10(3):e0118,708

    Article  Google Scholar 

  • Zgank A (2019) Bee swarm activity acoustic classification for an IoT-based farm service. Sensors 20(1):21

    Article  Google Scholar 

  • Zgank A (2021) Iot-based bee swarm activity acoustic classification using deep neural networks. Sensors 21(3):676

    Article  Google Scholar 

  • Zheng F, Zhang G, Song Z (2001) Comparison of different implementations of MFCC. J Comput Sci Technol 16(6):582–589

    Article  MATH  Google Scholar 

Download references

Acknowledgements

This research was funded by the Vietnam national research project titled “Study and application on industry 4.0 technologies in management of honey bee production for export and national consumption,” Grant Number: KC4.0-20/19-25. The funders had no role in designing experiment, collecting and processing data, deciding to publish, or preparing the manuscript.

Funding

The funding is supported by Ministry of Science and Technology of Vietnam, KC4.0 program.

Author information

Authors and Affiliations

  1. Department of Information Technology, FPT University, Da Nang, Vietnam

    Thi-Thu-Hong Phan

  2. Department of Natural Sciences and Technology, International School - Vietnam National University Hanoi, Hanoi, Vietnam

    Dong Nguyen-Doan

  3. School of Applied Mathematics and Informatics, Hanoi University of Sciences and Technology, Hanoi, Vietnam

    Du Nguyen-Huu & Hanh Nguyen-Van

  4. Research Center for Tropical Bees and Beekeeping, Vietnam National University of Agriculture, Hanoi, Vietnam

    Thai Pham-Hong

Authors
  1. Thi-Thu-Hong Phan
    View author publications

    Search author on:PubMed Google Scholar

  2. Dong Nguyen-Doan
    View author publications

    Search author on:PubMed Google Scholar

  3. Du Nguyen-Huu
    View author publications

    Search author on:PubMed Google Scholar

  4. Hanh Nguyen-Van
    View author publications

    Search author on:PubMed Google Scholar

  5. Thai Pham-Hong
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Thi-Thu-Hong Phan contributed to conceptualization, methodology, writing—original draft, writing—review and editing, investigation, and data curation and provided software; Huu Du Nguyen was involved in conceptualization, writing—original draft, and writing—review and editing; Doan Dong Nguyen contributed to conceptualization, data curation, writing—original draft, and writing–review and editing, and provided software; Van Hanh Nguyen was involved in conceptualization; and Hong Thai Pham contributed to resources.

Corresponding author

Correspondence to Thi-Thu-Hong Phan.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Phan, TTH., Nguyen-Doan, D., Nguyen-Huu, D. et al. Investigation on new Mel frequency cepstral coefficients features and hyper-parameters tuning technique for bee sound recognition. Soft Comput 27, 5873–5892 (2023). https://doi.org/10.1007/s00500-022-07596-6

Download citation

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1007/s00500-022-07596-6

Keywords

Profiles

  1. Thi-Thu-Hong Phan View author profile