MFCC-Based Sound Classification of Honey Bees

• Autorzy: Libal Urszula , Biernacki Pawel

Identyfikatory

DOI

10.24425/ijet.2024.152069

• Języki publikacji: EN

Abstrakty

EN

Smart beekeeping is a rapidly developing field. Automated detection and classification of honey bees opens many new opportunities for studies on their behavior. In this paper, we focus on distinguishing between two classes of bees: female workers and male drones. The classification is performed on mel-frequency cepstral coefficients obtained for audio recordings of their flights in a close proximity to an entrance to a beehive. We compare the classification accuracy for several classifiers. We investigate how partitioning of the frequency spectrum influences the classification results. The study involves series of experiments performed for different cepstral representations in the form of 5, 10, 15, 20 and 40 mel-frequency cepstral coefficients.

Słowa kluczowe

EN

internet of things; IoT; smart beekeeping; pattern recognition; signal processing; mel-frequency cepstral coefficients; MFCC

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2024
• Tom: Vol. 70, No. 4
• Strony: 849--853
• Opis fizyczny: Bibliogr. 21 poz., rys.

Twórcy

autor

Libal Urszula

• Wroclaw University of Science and Technology Department of Acoustics Multimedia and Signal Processing

• https://orcid.org/0000-0002-3348-510X

autor

Biernacki Pawel

• Wroclaw University of Science and Technology Department of Acoustics Multimedia and Signal Processing

• https://orcid.org/0000-0002-0818-5981

Bibliografia

• [1] S. Kontogiannis, ”An Internet of Things-Based Low-Power Integrated Beekeeping Safety and Conditions Monitoring System”, Inventions 4(3):52 (2019). [Online]. Available: https://doi.org/10.3390/inventions4030052
• [2] G. Voudiotis, S. Kontogiannis and C. Pikridas, ”Proposed Smart Monitoring System for the Detection of Bee Swarming”, Inventions 6(4):87 (2021). [Online]. Available: https://doi.org/10.3390/inventions6040087
• [3] E. Ntawuzumunsi, S. Kumaran and L. Sibomana, ”Self-Powered Smart Beehive Monitoring and Control System (SBMaCS)”, Sensors (Basel) 21, 3522 (2021). [Online]. Available: https://doi.org/10.3390/s21103522
• [4] S.M. Williams, S. Bariselli, C. Palego, R. Holland nad P. Cross, ”A comparison of machine-learning assisted optical and thermal camera systems for beehive activity counting”, Smart Agricultural Technology 2, 100038 (2022). [Online]. Available: https://doi.org/10.1016/j.atech.2022.100038
• [5] U. Libal and P. Biernacki, ”Detecting drones at an entrance to a beehive based on audio signals and autoencoder neural networks”, in Proc. IEEE Signal Processing Symposium (SPSympo), Karpacz, Poland, 26-28 September 2023; pp. 99-104. [Online]. Available: https://doi.org/10.23919/SPSympo57300.2023.10302687
• [6] U. Libal and P. Biernacki, ”MFCC Selection by LASSO for Honey Bee Classification”, Appl. Sci. 14(2):913 (2024). [Online]. Available: https://doi.org/10.3390/app14020913
• [7] A.S. Hamza, R. Tashakkori, B. Underwood, W. O’Brien, C. Campell, ”BeeLive: The IoT platform of Beemon monitoring and alerting system for beehives”, Smart Agricultural Technology 6, 100331 (2023). [On-line]. Available: https://doi.org/10.1016/j.atech.2023.100331
• [8] H. Hadjur, D. Ammar and L. Lefèvre, ”Toward an intelligent and efficient beehive: a survey of precision beekeeping systems and services”, Comput. Electron. Agric. 192, 106604 (2022). [Online]. Available: https://doi.org/10.1016%2Fj.compag.2021.106604
• [9] P. Nunes-Silva, M. Hrncir, J.T.F. Guimarães, et al. ”Applications of RFID technology on the study of bees”, Insect. Soc. 66, 15-24 (2019). [Online]. Available: https://doi.org/10.1007/s00040-018-0660-5
• [10] Abdul, Z. K., Al-Talabani, A. K. Mel Frequency Cepstral Coefficient and its Applications: A Review”, IEEE Access 10: 122136-122158 (2022). [Online]. Available: https://doi.org/10.1109/ACCESS.2022.3223444
• [11] B.S. Soares, J.S. Luz, V.F. de Macêdo, R.R.V. e Silva, F.H.D. de Araújo, D.M.V. Magalhães, ”MFCC-based descriptor for bee queen presence detection”, Expert Syst. Appl. 201, 117104 (2022). [Online]. Available: https://doi.org/10.1016/j.eswa.2022.117104
• [12] A. Terenzi, N. Ortolani, I. Nolasco, E. Benetos, S. Cecchi, ”Comparison of Feature Extraction Methods for Sound-Based Classification of Honey Bee Activity”, IEEE/ACM Trans. Audio Speech Lang. Process. 30: 112-122 (2022). [Online]. Available: https://doi.org/10.1109/TASLP.2021.3133194
• [13] P. Biernacki, ”Dataset for Honey Bee Audio Detection” [Dataset], Zenodo. 2023. [Online]. Available: https://zenodo.org/doi/10.5281/zenodo.10359685 (accessed on 13 December 2023).
• [14] C. Cortes and V. Vapnik, ”Support-vector networks”, Mach. Learn. 20(3): 273-297 (1995). [Online]. Available: https://doi.org/10.1007/BF00994018
• [15] R.O. Duda, P.E. Hart and D.H. Stork, ”Pattern Classification”, Wiley Interscience (2000).
• [16] C.M. Bishop, ”Pattern Recognition and Machine Learning”, Information Science and Statistics, Springer-Verlag New York (2006).
• [17] T.K. Ho, ”Random Decision Forests”, in Proc. the 3rd Int. Conf. on Document Analysis and Recognition (ICDAR), Montreal, QC, 14-16 August 1995, pp. 278-282. [Online]. Available: https://doi.org/10.1109/ICDAR.1995.598994
• [18] T.K. Ho, ”The Random Subspace Method for Constructing Decision Forests”, IEEE Trans. Pattern Anal. Mach. Intell. 20(8): 832-844 (1998). [Online]. Available: https://doi.org/10.1109/34.709601
• [19] L. Devroye, ”On the asymptotic probability of error in nonparametric discrimination”, Ann. Stat. 9: 1320-1327 (1981). [Online]. Available: https://doi.org/10.1214/aos/1176345648
• [20] T. Cover and P. Hart, ”Nearest neighbor pattern classification”, IEEE Trans. Inf. Theory 13: 21-27 (1967). [Online]. Available: https://doi.org/10.1109/TIT.1967.1053964
• [21] L. Devroye, L. Gy¨orfi and G. Lugosi, ”A Probabilistic Theory of Pattern Recognition”, Stochastic Modelling and Applied Probability, Springer-Verlag, New York (1996).

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).