Classifying Ingestive Behavior of Dairy Cows via Automatic Sound Recognition
Determining ingestive behaviors of dairy cows is critical to evaluate their productivity and health status. The objectives of this research were to (1) develop the relationship between forage species/heights and sound characteristics of three different ingestive behaviors (bites, chews, and chew-bit...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/15/5231 |
| _version_ | 1797525120545193984 |
|---|---|
| author | Guoming Li Yijie Xiong Qian Du Zhengxiang Shi Richard S. Gates |
| author_facet | Guoming Li Yijie Xiong Qian Du Zhengxiang Shi Richard S. Gates |
| author_sort | Guoming Li |
| collection | DOAJ |
| description | Determining ingestive behaviors of dairy cows is critical to evaluate their productivity and health status. The objectives of this research were to (1) develop the relationship between forage species/heights and sound characteristics of three different ingestive behaviors (bites, chews, and chew-bites); (2) comparatively evaluate three deep learning models and optimization strategies for classifying the three behaviors; and (3) examine the ability of deep learning modeling for classifying the three ingestive behaviors under various forage characteristics. The results show that the amplitude and duration of the bite, chew, and chew-bite sounds were mostly larger for tall forages (tall fescue and alfalfa) compared to their counterparts. The long short-term memory network using a filtered dataset with balanced duration and imbalanced audio files offered better performance than its counterparts. The best classification performance was over 0.93, and the best and poorest performance difference was 0.4–0.5 under different forage species and heights. In conclusion, the deep learning technique could classify the dairy cow ingestive behaviors but was unable to differentiate between them under some forage characteristics using acoustic signals. Thus, while the developed tool is useful to support precision dairy cow management, it requires further improvement. |
| first_indexed | 2024-03-10T09:08:12Z |
| format | Article |
| id | doaj.art-71808bc38ab345d5822d2912f62fa7c7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:08:12Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-71808bc38ab345d5822d2912f62fa7c72023-11-22T06:11:22ZengMDPI AGSensors1424-82202021-08-012115523110.3390/s21155231Classifying Ingestive Behavior of Dairy Cows via Automatic Sound RecognitionGuoming Li0Yijie Xiong1Qian Du2Zhengxiang Shi3Richard S. Gates4Department of Agricultural and Biosystems Engineering, Iowa State University, Ames, IA 50011, USADepartment of Animal Science, University of Nebraska-Lincoln, Lincoln, NE 68588, USADepartment of Electrical and Computer Engineering, Mississippi State University, Starkville, MS 39762, USADepartment of Agricultural Structure and Bioenvironmental Engineering, College of Water Resources and Civil Engineering, China Agricultural University, Beijing 100083, ChinaEgg Industry Center, Departments of Agricultural and Biosystems Engineering, and Animal Science, Iowa State University, Ames, IA 50011, USADetermining ingestive behaviors of dairy cows is critical to evaluate their productivity and health status. The objectives of this research were to (1) develop the relationship between forage species/heights and sound characteristics of three different ingestive behaviors (bites, chews, and chew-bites); (2) comparatively evaluate three deep learning models and optimization strategies for classifying the three behaviors; and (3) examine the ability of deep learning modeling for classifying the three ingestive behaviors under various forage characteristics. The results show that the amplitude and duration of the bite, chew, and chew-bite sounds were mostly larger for tall forages (tall fescue and alfalfa) compared to their counterparts. The long short-term memory network using a filtered dataset with balanced duration and imbalanced audio files offered better performance than its counterparts. The best classification performance was over 0.93, and the best and poorest performance difference was 0.4–0.5 under different forage species and heights. In conclusion, the deep learning technique could classify the dairy cow ingestive behaviors but was unable to differentiate between them under some forage characteristics using acoustic signals. Thus, while the developed tool is useful to support precision dairy cow management, it requires further improvement.https://www.mdpi.com/1424-8220/21/15/5231audiodairy cowdeep learningmasticationjaw movementforage management |
| spellingShingle | Guoming Li Yijie Xiong Qian Du Zhengxiang Shi Richard S. Gates Classifying Ingestive Behavior of Dairy Cows via Automatic Sound Recognition Sensors audio dairy cow deep learning mastication jaw movement forage management |
| title | Classifying Ingestive Behavior of Dairy Cows via Automatic Sound Recognition |
| title_full | Classifying Ingestive Behavior of Dairy Cows via Automatic Sound Recognition |
| title_fullStr | Classifying Ingestive Behavior of Dairy Cows via Automatic Sound Recognition |
| title_full_unstemmed | Classifying Ingestive Behavior of Dairy Cows via Automatic Sound Recognition |
| title_short | Classifying Ingestive Behavior of Dairy Cows via Automatic Sound Recognition |
| title_sort | classifying ingestive behavior of dairy cows via automatic sound recognition |
| topic | audio dairy cow deep learning mastication jaw movement forage management |
| url | https://www.mdpi.com/1424-8220/21/15/5231 |
| work_keys_str_mv | AT guomingli classifyingingestivebehaviorofdairycowsviaautomaticsoundrecognition AT yijiexiong classifyingingestivebehaviorofdairycowsviaautomaticsoundrecognition AT qiandu classifyingingestivebehaviorofdairycowsviaautomaticsoundrecognition AT zhengxiangshi classifyingingestivebehaviorofdairycowsviaautomaticsoundrecognition AT richardsgates classifyingingestivebehaviorofdairycowsviaautomaticsoundrecognition |