Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion
To improve the classification of pig vocalization using vocal signals and improve recognition accuracy, a pig vocalization classification method based on multi-feature fusion is proposed in this study. With the typical vocalization of pigs in large-scale breeding houses as the research object, short...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/2/313 |
| _version_ | 1797339437894467584 |
|---|---|
| author | Yuting Hou Qifeng Li Zuchao Wang Tonghai Liu Yuxiang He Haiyan Li Zhiyu Ren Xiaoli Guo Gan Yang Yu Liu Ligen Yu |
| author_facet | Yuting Hou Qifeng Li Zuchao Wang Tonghai Liu Yuxiang He Haiyan Li Zhiyu Ren Xiaoli Guo Gan Yang Yu Liu Ligen Yu |
| author_sort | Yuting Hou |
| collection | DOAJ |
| description | To improve the classification of pig vocalization using vocal signals and improve recognition accuracy, a pig vocalization classification method based on multi-feature fusion is proposed in this study. With the typical vocalization of pigs in large-scale breeding houses as the research object, short-time energy, frequency centroid, formant frequency and first-order difference, and Mel frequency cepstral coefficient and first-order difference were extracted as the fusion features. These fusion features were improved using principal component analysis. A pig vocalization classification model with a BP neural network optimized based on the genetic algorithm was constructed. The results showed that using the improved features to recognize pig grunting, squealing, and coughing, the average recognition accuracy was 93.2%; the recognition precisions were 87.9%, 98.1%, and 92.7%, respectively, with an average of 92.9%; and the recognition recalls were 92.0%, 99.1%, and 87.4%, respectively, with an average of 92.8%, which indicated that the proposed pig vocalization classification method had good recognition precision and recall, and could provide a reference for pig vocalization information feedback and automatic recognition. |
| first_indexed | 2024-03-08T09:48:04Z |
| format | Article |
| id | doaj.art-c868ce417eab43259882e7bff32c7906 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T09:48:04Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c868ce417eab43259882e7bff32c79062024-01-29T14:12:39ZengMDPI AGSensors1424-82202024-01-0124231310.3390/s24020313Study on a Pig Vocalization Classification Method Based on Multi-Feature FusionYuting Hou0Qifeng Li1Zuchao Wang2Tonghai Liu3Yuxiang He4Haiyan Li5Zhiyu Ren6Xiaoli Guo7Gan Yang8Yu Liu9Ligen Yu10Research Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaSchool of Science, China University of Geosciences (Beijing), Beijing 100083, ChinaCollege of Computer and Information Engineering, Tianjin Agricultural University, Tianjin 300384, ChinaCollege of Computer and Information Engineering, Tianjin Agricultural University, Tianjin 300384, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaTo improve the classification of pig vocalization using vocal signals and improve recognition accuracy, a pig vocalization classification method based on multi-feature fusion is proposed in this study. With the typical vocalization of pigs in large-scale breeding houses as the research object, short-time energy, frequency centroid, formant frequency and first-order difference, and Mel frequency cepstral coefficient and first-order difference were extracted as the fusion features. These fusion features were improved using principal component analysis. A pig vocalization classification model with a BP neural network optimized based on the genetic algorithm was constructed. The results showed that using the improved features to recognize pig grunting, squealing, and coughing, the average recognition accuracy was 93.2%; the recognition precisions were 87.9%, 98.1%, and 92.7%, respectively, with an average of 92.9%; and the recognition recalls were 92.0%, 99.1%, and 87.4%, respectively, with an average of 92.8%, which indicated that the proposed pig vocalization classification method had good recognition precision and recall, and could provide a reference for pig vocalization information feedback and automatic recognition.https://www.mdpi.com/1424-8220/24/2/313pig vocalizationmulti-feature fusionprincipal component analysisclassification recognition |
| spellingShingle | Yuting Hou Qifeng Li Zuchao Wang Tonghai Liu Yuxiang He Haiyan Li Zhiyu Ren Xiaoli Guo Gan Yang Yu Liu Ligen Yu Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion Sensors pig vocalization multi-feature fusion principal component analysis classification recognition |
| title | Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion |
| title_full | Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion |
| title_fullStr | Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion |
| title_full_unstemmed | Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion |
| title_short | Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion |
| title_sort | study on a pig vocalization classification method based on multi feature fusion |
| topic | pig vocalization multi-feature fusion principal component analysis classification recognition |
| url | https://www.mdpi.com/1424-8220/24/2/313 |
| work_keys_str_mv | AT yutinghou studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT qifengli studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT zuchaowang studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT tonghailiu studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT yuxianghe studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT haiyanli studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT zhiyuren studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT xiaoliguo studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT ganyang studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT yuliu studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion AT ligenyu studyonapigvocalizationclassificationmethodbasedonmultifeaturefusion |