Analysis of community based on information about interactions between cows

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K12099
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Intelligent informatics
• Research Institution: Kobe University
• Principal Investigator: OHKAWA TAKENAO 神戸大学, システム情報学研究科, 教授 (30223738)
• Co-Investigator(Kenkyū-buntansha): 大山 憲二 神戸大学, 農学研究科, 教授 (70322203) ; 太田 能 神戸大学, 科学技術イノベーション研究科, 教授 (10272254)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: インタラクション情報 / 時系列データ / スマート農業 / ネットワーク分析 / 放牧牛

Outline of Final Research Achievements

In this study, we presented several new methods of detecting estrus and monitoring health condition of cows through extraction and analysis of interaction between cows by focusing on cows' sociality. In order to extract various types of information about interaction, we developed some methods of tracking a cow and classifying its behavior based on the data obtained from an active BLE (Bluetooth Low Energy) tag attached on the neck of each cow and bird's eye videos. In addition, we proposed a method of predicting condition of the cow by analyzing temporal change of interactions and/or communities of cows and confirmed experimentally that the proposed method obtained accurate results of estrus detection.

Free Research Field

情報工学