Monitoring foraging behavior in grazing ruminants in a semi-natural grassland
| Project/Area Number |
17K08062
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Animal production science
|
|---|
| Research Institution | Gifu University |
|---|
Principal Investigator |
Yayota Masato 岐阜大学, 応用生物科学部, 教授 (30324289)
|
|---|
| Project Period (FY) |
2017-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2017: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 放牧 / 精密畜産 / 採食行動 / バイオロギング |
|---|
| Outline of Final Research Achievements |
This study aimed to monitor and identify characteristics bite pattern when animals ingest plant species with different morphology, using a multi axis logger and machine learning technique. Six goats, which were attached a multi axis acceleration and gyro sensor to their forehead, ingested four plant species with different morphology (tufted type, creeper type, rosette type, and erect type). We used oscillation data in each axis and body weight of goats as explanatory variables and compared decision tree, random forest, support vector machine and neural network technique to identify ingested plant species. The results suggested that using random forest technique with acceleration of left-right and up-down directions and body weight can clearly identify the ingested plant species with over 95% accuracy.
|
| Academic Significance and Societal Importance of the Research Achievements |
多種多様な植物で構成される半自然草地は，家畜生産の場としてだけでなく，生態系サービスを提供する場としても重要である。半自然草地の利用および保全には，放牧した家畜がいつ，どこで，なにを，どれだけ摂取したかを知ることが，植物の種構成および量に直接影響するため，大きな役割を果たす。本研究は，加速度センサと機械学習を用いることで，これまで技術的に難しかった放牧家畜の採食植物の種類を採食行動から識別可能であることを初めて示した。本研究の成果とGPS/GISを組み合わせることで，放牧家畜による半自然草地の利用状況を経時的にモニタリングする可能性が高まり，利用と保全をより効果的に行うことが期待できる。
|
Report
(5 results)
Research Products
(1 results)
