Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations
Failure to quickly and accurately detect abnormal situations, such as the occurrence of infectious diseases, in pig farms can cause significant damage to the pig farms and the pig farming industry of the country. In this study, we propose an economical and lightweight sound-based pig anomaly detecti...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/19/6991 |
| _version_ | 1827704796808740864 |
|---|---|
| author | Minki Hong Hanse Ahn Othmane Atif Jonguk Lee Daihee Park Yongwha Chung |
| author_facet | Minki Hong Hanse Ahn Othmane Atif Jonguk Lee Daihee Park Yongwha Chung |
| author_sort | Minki Hong |
| collection | DOAJ |
| description | Failure to quickly and accurately detect abnormal situations, such as the occurrence of infectious diseases, in pig farms can cause significant damage to the pig farms and the pig farming industry of the country. In this study, we propose an economical and lightweight sound-based pig anomaly detection system that can be applicable even in small-scale farms. The system consists of a pipeline structure, starting from sound acquisition to abnormal situation detection, and can be installed and operated in an actual pig farm. It has the following structure that makes it executable on the embedded board TX-2: (1) A module that collects sound signals; (2) A noise-robust preprocessing module that detects sound regions from signals and converts them into spectrograms; and (3) A pig anomaly detection module based on MnasNet, a lightweight deep learning method, to which the 8-bit filter clustering method proposed in this study is applied, reducing its size by 76.3% while maintaining its identification performance. The proposed system recorded an F1-score of 0.947 as a stable pig’s abnormality identification performance, even in various noisy pigpen environments, and the system’s execution time allowed it to perform in real time. |
| first_indexed | 2024-03-10T15:48:15Z |
| format | Article |
| id | doaj.art-e1beca53416b4e2da323355c9200787d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:48:15Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e1beca53416b4e2da323355c9200787d2023-11-20T16:16:38ZengMDPI AGApplied Sciences2076-34172020-10-011019699110.3390/app10196991Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board ImplementationsMinki Hong0Hanse Ahn1Othmane Atif2Jonguk Lee3Daihee Park4Yongwha Chung5Department of Computer Information Science, Korea University, Sejong Campus, Sejong City 30019, KoreaDepartment of Computer Information Science, Korea University, Sejong Campus, Sejong City 30019, KoreaDepartment of Computer Information Science, Korea University, Sejong Campus, Sejong City 30019, KoreaDepartment of Computer Convergence Software, Korea University, Sejong Campus, Sejong City 30019, KoreaDepartment of Computer Convergence Software, Korea University, Sejong Campus, Sejong City 30019, KoreaDepartment of Computer Convergence Software, Korea University, Sejong Campus, Sejong City 30019, KoreaFailure to quickly and accurately detect abnormal situations, such as the occurrence of infectious diseases, in pig farms can cause significant damage to the pig farms and the pig farming industry of the country. In this study, we propose an economical and lightweight sound-based pig anomaly detection system that can be applicable even in small-scale farms. The system consists of a pipeline structure, starting from sound acquisition to abnormal situation detection, and can be installed and operated in an actual pig farm. It has the following structure that makes it executable on the embedded board TX-2: (1) A module that collects sound signals; (2) A noise-robust preprocessing module that detects sound regions from signals and converts them into spectrograms; and (3) A pig anomaly detection module based on MnasNet, a lightweight deep learning method, to which the 8-bit filter clustering method proposed in this study is applied, reducing its size by 76.3% while maintaining its identification performance. The proposed system recorded an F1-score of 0.947 as a stable pig’s abnormality identification performance, even in various noisy pigpen environments, and the system’s execution time allowed it to perform in real time.https://www.mdpi.com/2076-3417/10/19/6991agriculture ITpig anomaly detectionembedded boardlight-weight deep learning8-bit filter clustering |
| spellingShingle | Minki Hong Hanse Ahn Othmane Atif Jonguk Lee Daihee Park Yongwha Chung Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations Applied Sciences agriculture IT pig anomaly detection embedded board light-weight deep learning 8-bit filter clustering |
| title | Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations |
| title_full | Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations |
| title_fullStr | Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations |
| title_full_unstemmed | Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations |
| title_short | Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations |
| title_sort | field applicable pig anomaly detection system using vocalization for embedded board implementations |
| topic | agriculture IT pig anomaly detection embedded board light-weight deep learning 8-bit filter clustering |
| url | https://www.mdpi.com/2076-3417/10/19/6991 |
| work_keys_str_mv | AT minkihong fieldapplicablepiganomalydetectionsystemusingvocalizationforembeddedboardimplementations AT hanseahn fieldapplicablepiganomalydetectionsystemusingvocalizationforembeddedboardimplementations AT othmaneatif fieldapplicablepiganomalydetectionsystemusingvocalizationforembeddedboardimplementations AT jonguklee fieldapplicablepiganomalydetectionsystemusingvocalizationforembeddedboardimplementations AT daiheepark fieldapplicablepiganomalydetectionsystemusingvocalizationforembeddedboardimplementations AT yongwhachung fieldapplicablepiganomalydetectionsystemusingvocalizationforembeddedboardimplementations |