Smart Media Journal (스마트미디어저널)

THE KOREAN INSTITUTE OF SMART MEDIA (한국스마트미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of Livestock Vocal Data using Lightweight MobileNet

경량화 MobileNet을 활용한 축산 데이터 음성 분석

  • 정세연 (전북대학교 부설 지능형 로봇연구소 ) ;
  • 김상철 (전북대학교 부설 지능형 로봇연구소)
  • Received : 2024.02.27
  • Accepted : 2024.03.19
  • Published : 2024.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

Pigs express their reactions to their environment and health status through a variety of sounds, such as grunting, coughing, and screaming. Given the significance of pig vocalizations, their study has recently become a vital source of data for livestock industry workers. To facilitate this, we propose a lightweight deep learning model based on MobileNet that analyzes pig vocal patterns to distinguish pig voices from farm noise and differentiate between vocal sounds and coughing. This model was able to accurately identify pig vocalizations amidst a variety of background noises and cough sounds within the pigsty. Test results demonstrated that this model achieved a high accuracy of 98.2%. Based on these results, future research is expected to address issues such as analyzing pig emotions and identifying stress levels.

돼지는 꿀꿀거림, 기침, 비명과 같은 다양한 소리로 환경에 대한 반응과 건강 상태를 나타낸다. 돼지 음성의 중요성으로 최근 들어 돼지의 음성은 축산업 종사자에게 매우 중요한 데이터로 활발하게 연구되고 있다. 이를 위해 돼지의 음성 패턴을 분석하여 농장 소음 속에서 돼지의 음성을 구분하고 음성과 기침 소리를 구분하는 경량화 MobileNet 모델을 제안한다. 이 MobileNet은 돈사 내에서 다양한 배경 잡음, 기침 소리 등의 다양한 소리 속에서 돼지의 음성만을 정밀하게 구분하고 분석할 수 있었다. 테스트 결과, 이 모델은 98.2%의 높은 정확도를 보여주었다. 이러한 결과를 바탕으로 향후 연구에서는 돼지의 감정 분석, 스트레스 파악 등의 문제 해결을 기대한다.

Keywords

Acknowledgement

본 논문은 한국연구재단 대학중점연구소지원사업(NRF-2019R1A6A1A09031717)과 2023년도 정부(농림축산식품부, 과학기술정보통신부, 농촌진흥청 공동)의 재원으로 스마트팜연구개발사업단의 지원을 받아 수행된 연구임(No. 421023-04)

References

  1. 돼지고기 연간 소비량과 소비 트렌드(2023.).https://www.pignpork.com/news/articleView.html?idxno=6954 (accessed Jan., 16, 2024).
  2. Jonguk Lee, Yongju Choi, Daihee Park, and Yongwha Chung, "Sound Noise-Robust Porcine Wasting Diseases Detection and Classification System Using Convolutional Neural Network," Journal of Korean Institute of Information Technology (JKIIT), vol. 16, no. 5, pp. 1-13, 2018. https://doi.org/10.14801/jkiit.2018.16.5.1
  3. E. Sasmaz and F. В. Tek, "Animal Sound Classification Using A Convolutional Neural Network," 2018 3rd International Conference on Computer Science and Engineering (UBMK), Sarajevo, Bosnia and Herzegovina, pp. 625-629, 2018.
  4. Min Kyoung Jin, Min Kyoung Eun, Kim Na Yeon, Jeong Sang Wook, Moon Sang Ho, Kim Dong Jun, & Lee Jeong Hwan, "A Study on the Classificatio Method of Livestock Vocal Sound by Situation for Animal Welfare," The Korean Institute of Electrical Engineers(KIEE) Conference, pp. 1,968 - 1,969, 2020.
  5. Nan Ji, Weizheng Shen, Yarding Yin, Jun Bao, Baisheng Dai, Handan Hou, Shengli Kou, Yize Zhao, Investigation of acoustic and visual features for pig cough classification, Biosystems Engineering, Vol. 219, pp. 281-293, 2022. https://doi.org/10.1016/j.biosystemseng.2022.05.010
  6. Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam, "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications", arXiv:1704.04861, 2017.
  7. Y.W. Lim and S.U. Lee, "On the color image segmentation algorithm based on the thresholding and the fuzzy c-means techniques, Pattern Recognition, vol. 23,no. 9, pp. 935-952, 1990. https://doi.org/10.1016/0031-3203(90)90103-R
  8. Young Eon Kim and Gooman Park, "Recognition of Overlapped Sound and Influence Analysis Based on Wideband Spectrogram and Deep Neural Networks," JOURNAL OF BROADCAST ENGINEERING, vol. 23, no. 3, pp. 421-430, 2018. https://doi.org/10.5909/JBE.2018.23.3.421
  9. Minkyung Kim, Gunwoo Kim, Keunho Choi, "A COVID-19 Diagnosis Model based on Various Transformations of Cough Sounds," Journal of Intelligence and Information Systems, vol. 29. no. 3, pp.57-78, 2023.
  10. Jaeseung Lee, Eunbeen Kim, Jaeuk Moon, Eenjun Hwang, "Focal Loss-based Animal Sound Classification Scheme using Ensemble," Proceedings of the Korean Information Science Society Conference, pp. 860-862, 2023.
  11. Min-Ji Seo, and Myung Ho Kim, "Ensemble Method of Emotion Classifier for Speech Emotion Recognition," Journal of The Korea Society of Information Technology Policy & Management (ITPM), vol. 11, no. 2, pp. 1187-1193, 2019.
  12. Moung Ho Yi, Myung Jin Lim, Ju Hyun Shin, "Multi-Emotion Regression Model for Recognizing Inherent Emotions in Speech Data," Smart Media Journal, pp. 81-88, 2023.
  13. Heegon Kim, Dohyun Mun, Yongwha Chung, & Daihee Park, "Cough Detection of Individual Pigs using Video Information," Conference of The Institute of Electronics and Information Engineers(IEIE), pp. 696 - 699, 2016.
  14. Kim Seung Jae, Yoe Hyun, Lee Meong Hun, Yang Kwang Ho, & Ryu Jong Kil, "A Study on the Data Collection of Korean Beef in Smart Livestock", Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp. 583-584, 2020
  15. Jeong HeeHyeon, Jungyeol Hong, & Park Dongjoo, Assessment of Livestock Infectious Diseases Exposure by Analyzing the Livestock Transport Vehicle"s Trajectory Using Big Data," The Journal of The Korea Institute of Intelligent Transportation Systems, vol. 19, no. 6, pp. 134-143, 2020. https://doi.org/10.12815/kits.2020.19.6.134
  16. Kyeongjun In, Jonguk Lee, Yongwha Chung, & Daihee Park, "Porcine Sound Aquisition Process in a Noisy Pigsty," Proceedings of the Korean Information Science Society Conference, pp. 1441-1443, 2013.
  17. Dong Kyu Lee, Bong Kuk Lee, You-Jin Kim, Jae-Young Jung, Jee-Sook Eun, & Dae Hoe Km, "CNN-Based Swine Cough Audio Sensing System for Early Disease Detection in Bams," Journal of Digital Contents Society, vol. 24, no. 10, pp. 2569-2577, 2023. https://doi.org/10.9728/dcs.2023.24.10.2569