深層学習を用いた乳牛の分娩時「いきみ」検知技術の開発

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2024/09/01

タイトル(英語): Development of a Technology for Detecting Straining in Cows During Labor Using Deep Learning

著者名: 井出　達樹（静岡県工業技術研究所富士工業技術支援センター／日本工業大学），小熊　亜津子（静岡県西部家畜保健衛生所），荒川　俊也（日本工業大学）

著者名(英語): Tatsuki Ide (Industrial Research Institute of Shizuoka Prefecture Fuji Technical Support Center/Nippon Institute of Technology), Atsuko Oguma (Seibu Livestock Disease Diagnostic Center of Shizuoka Prefecture), Toshiya Arakawa (Nippon Institute of Technology)

キーワード: 乳牛，いきみ，無拘束，検知，畳み込みニューラルネットワーク（CNN）　　cows，straining，non-restraint，detection，convolutional neural network (CNN)

要約(英語): In the dairy farming sector, the need for efficient individual cow management via ICT has intensified owing to a declining workforce in the industry and a simultaneous increase in livestock numbers. To address challenges such as reducing night-time cow-monitoring hours for workers and preventing calving accidents, we developed a system capable of automatically detecting straining during labor (a key indicator of impending cow calving). Our approach involved collecting waveform data on cow movements from an unrestrained cow positioned on a sensor sheet. The collected data were subsequently analyzed using deep learning techniques. Employing a sample of 40 cows, veterinarians correlated data collected using the sensor sheet with those collected using a video camera, classifying the data into straining and other movements unrelated to calving. This curated dataset was then used to train a staining detection model using a convolutional neural network, the accuracy of which was verified. Consequently, we successfully used the staining detection model to predict cow calving with a high accuracy rate of > 95%.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.144 No.9 （2024） 特集：知能メカトロニクス分野と連携する知覚情報技術

本誌掲載ページ: 918-925 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/144/9/144_918/_article/-char/ja/