The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지
DOI QR코드

DOI QR Code

Sound Noise-Robust Porcine Wasting Diseases Detection and Classification System Using Convolutional Neural Network

CNN 기반의 소리 잡음에 강인한 돼지 호흡기 질병 탐지 및 식별 시스템

  • 이종욱 (고려대학교 컴퓨터융합소프트웨어학과) ;
  • 최용주 (고려대학교 컴퓨터정보학과) ;
  • 박대희 (고려대학교 컴퓨터융합소프트웨어학과) ;
  • 정용화 (고려대학교 컴퓨터융합소프트웨어학과)
  • Received : 2018.02.22
  • Accepted : 2018.03.29
  • Published : 2018.05.31
⟨ Previous Next ⟩

Abstract

Failure to detect pig wasting disease in a timely and accurate manner in the commercial pig farm can be a serious factor in achieving efficient livestock management. In this paper, we propose a noise-robust porcine wasting diseases detection and classification method in piglet farm monitoring system using sound data. First, we extract a spectrogram of sound signals and convert it into noise-robust features by a convolutional neural network (CNN), and lastly, use the multi-layer perceptron (MLP) as an early anomaly detector and classifier. On the basis of the experimental results, we confirmed that the proposed method could detect and classify the porcine wasting diseases with acceptable accuracy even under noise-environmental conditions. In particular, as a result of comparing the discrimination performance of the proposed method in this research and the MFCC-SVM method, it was confirmed that the f-score was improved by 15.1%.

상업적 시설에서 키우고 있는 돼지의 호흡기 질병을 초기에 정확하게 탐지하지 못한다면 해당 농가의 생산성에 문제를 발생시키는 심각한 요인이 된다. 본 논문에서는 돼지의 소리 데이터를 이용하여 현장에서 발생하는 소음에도 강인한 호흡기 질병 탐지 및 식별 시스템을 제안한다. 제안된 시스템은 먼저, 소리 신호에서 스펙트로그램 정보를 추출하고, 이를 CNN에 적용하여 돼지 호흡기 질병을 탐지 및 식별에 효과적인 특징 정보로 변환한다. 마지막으로, 변환된 정보는 MLP에 적용되어 해당 호흡기 질병을 탐지 및 식별과정을 수행한다. 본 연구의 실험 결과, 다양한 잡음 환경에서도 돼지 호흡기 질병 탐지 및 식별 성능이 안정적임을 확인하였다. 특히, 본 연구에서 제안한 방법과 MFCC와 SVM을 이용한 방법의 식별 성능을 비교한 결과 f-score 수치가 15.1% 향상됨을 확인하였다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. Ministry of Agriculture, Food and Rural Affairs. http://www.mifaff.go.kr [Accessed Oct. 24, 2017]
  2. B. Kim, Y. Lee, Y. Kim, T. Kim, J. Park, and S. Lee et al., "Top 10 Agriculture Issues in 2017", Korea Rural Economic Institute, Focus on Agricultural Affairs, Vol. 142, pp. 1-27, Jan. 2017.
  3. K. S. Chu, M. S. Kang, Y. S. Jo, and J. W. Lee, “Detection of Porcine Circovirus 2, Porcine Reproductive and Respiratory Syndrome Virus and Mycoplasma Hyopneumoniae from Swine Lungs with Lesions by PCR,” Korean Journal of Veterinary Service, Vol. 31, No. 1, pp. 71-77, Mar. 2008.
  4. L. Lee, L. Jin, D. Park, and Y. Chung, "Automatic Recognition of Aggressive Behavior in Pigs using a Kinect Depth Sensor," Sensors, Vol. 16, No. 5, 631, Nov. 2016. https://doi.org/10.3390/s16050631
  5. M. Ju, H. Baek, J. Sa, H. Kim, Y. Chung, and D. Park, “Real-Time Pig Segmentation for Individual Pig Monitoring in a Weaning Pig Room,” Journal of Korea Multimedia Society, Vol. 19, No. 2, pp. 215-223, Feb. 2016. https://doi.org/10.9717/kmms.2016.19.2.215
  6. J. Choi, L. Lee, Y. Chung, and D. Park, “Individual Pig Detection using Fast Region-based Convolution Neural Network,” Journal of Korea Multimedia Society, Vol. 20, No. 2, pp. 216-224, Feb. 2017. https://doi.org/10.9717/kmms.2017.20.2.216
  7. J. Choi, L. Lee, Y. Chung, and D. Park, “Individual Pig Detection using Kinect Depth Information,” KIPS Transactions on Computer and Communication Systems, Vol. 5, No. 10, pp. 319-326, Aug. 2016. https://doi.org/10.3745/KTCCS.2016.5.10.319
  8. J. Lee, B. Noh, S. Jang, D. Park, Y. Chung, and H.H. Chang, "Stress Detection and Classification of Laying Hens by Sound Analysis," Asian-Australasian Journal of Animal Sciences, Vol. 28, No. 4, 592, Apr. 2015. https://doi.org/10.5713/ajas.14.0654
  9. M. Rizwan, B. T. Carroll, D. V. Anderson, W. Daley, S. Harbert, and D. F. Britton et al., "Identifying Rale Sounds in Chickens using Audio Signals for Early Disease Detection in Poultry," Proceeding of Global Conference on Signal and Information Processing, pp. 55-59, Dec. 2016.
  10. Y. Chung, J. Lee, S. Oh, D. Park, H. H. Chang, and S. Kim, “Automatic Detection of Cow’s Oestrus in Audio Surveillance System,” Asian-Australasian Journal of Animal Sciences, Vol. 26, No. 7, pp. 1030-037, Jul. 2013. https://doi.org/10.5713/ajas.2012.12628
  11. J. Vandermeulen, C. Bahr, D. Johnston, B. Earley, E. Tullo, and I. Fontana et al., "Early Recognition of Bovine Respiratory Disease in Calves using Automated Continuous Monitoring of Cough Sounds," Computers and Electronics in Agriculture, Vol. 129, pp. 15-26, Nov. 2016. https://doi.org/10.1016/j.compag.2016.07.014
  12. M. Guarino, P. Jans, A. Costa, J. M. Aerts, and D. Berckmans, “Field Test of Algorithm for Automatic Cough Detection in Pig Houses,” Computers and Electronics in Agriculture, Vol. 62, No. 1, pp. 22-28, Feb. 2008. https://doi.org/10.1016/j.compag.2007.08.016
  13. Y. Chung, S. Oh, J. Lee, D. Park, H. H. Chang, and S. Kim, “Automatic Detection and Recognition of Pig Wasting Diseases using Sound Data in Audio Surveillance,” Sensors, Vol. 13, No. 10, pp. 12929-12942, Sep. 2013. https://doi.org/10.3390/s131012929
  14. J. Lee, L. Jin, D. Park, Y. Chung, and H. H. Chang, “Acoustic Features for Pig Wasting Disease Detection,” International Journal of Information Processing and Management, Vol. 6, No. 1, pp. 37-46, Apr. 2015.
  15. J. Salamon and J. P. Bello, “Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification,” Signal Processing Letters, Vol. 24, No. 3, pp. 279-283, Jan, 2017. https://doi.org/10.1109/LSP.2017.2657381
  16. W. Zhang, G. Peng, C. Li, Y. Chen, and Z. Zhang, "A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals," Sensors, Vol. 17, No. 2, 425, Feb. 2017. https://doi.org/10.3390/s17020425
  17. T. L. Nwe, H. D. Tran, W. Z. T. Ng, and B. Ma, "An Integrated Solution for Snoring Sound Classification Using Bhattacharyya Distance based GMM Supervectors with SVM, Feature Selection with Random Forest and Spectrogram with CNN", Processing of Interspeech, pp. 3467-3471, Aug. 2017.
  18. A. Krizhevsky, I., Sutskever, and G. E. Hinton, "Imagenet Classification with Deep Convolutional Neural Networks," Advances in Neural Information Processing Systems, pp. 1097-1105, Dec. 2012.
  19. I. S. Kim and S. Y. Hwang, “A Effective Online Training Algorithm by Partitioning Bounding Box for Visual Object Tracking using Convolutional Neural Network,” The Journal of Korean Institute of Communications and Information Sciences, Vol. 42, No. 6, pp. 1117-1128, Jul. 2017. https://doi.org/10.7840/kics.2017.42.6.1117
  20. K. H. Kong and D. S. Kang, “A Study of Face Detection Algorithm Using CNN with Mixed-LGP and Hippocampus Structure,” Journal of KIIT, Vol. 16, No. 1, pp. 11-17, Jan. 2018.
  21. K. K. Yeo and D. S. Kang, “CNN-based Alzheimer’s Disease Image Learning and Accuracy Measurement Using 18F-Florbetaben PET Image Editted Database,” Journal of KIIT, Vol. 15, No. 10, pp. 1-8, Oct. 2017.
  22. TensorFlow ver.1.02. http://www.tensorflow.org [Accessed: Apr. 09, 2017]
  23. L.V.D. Maaten and G. Hinton, "Visualizing Data using t-SNE," Journal of Machine Learning Research, Vol. 9, pp. 2579-2605, Nov. 2008.

Cited by

  1. 향상된 음향 신호 기반의 음향 이벤트 분류 vol.8, pp.5, 2018, https://doi.org/10.3745/ktsde.2019.8.5.193
  2. 반려묘의 상황인지형 행동 캡셔닝 시스템 vol.24, pp.1, 2018, https://doi.org/10.9717/kmms.2020.24.1.021