Presentation 2009-07-13
Estrus Detection of Cattle by Activity using Neural Network
Ryosuke KAWAKAMI, Toru WATANABE, Makoto DOHI, Motoi NAKASHIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Cattle breeders in Japan are facing problem of declining productivity by missing estrous sign of maternal cows with resulting economical losses damaging the management of them. As the estrous sign includes increasing activities, allowing mounting, mucus discharge and elevated body temperature, there are many enterprises recently working on to research and develop a system that detect estrous cows with monitoring activities and body temperature of those cows. The Researchers in this study proposed a method to detect estrous cows by analyzing activity data exploiting the typical expression of increasing activity as one of the estrous sign. First, indicators representing increase of each activity are extracted from the activity data. Then, each indicator was learned in a multi-layer neural network and the outputs were compared and evaluated by each indicator to show validity of utilizing multi-layer neural network in detecting estrus. It was also identified that each indicator has its best targeting period.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Cattle / Estrus detection / Activity / Multi-layer neural network
Paper # NLP2009-21,NC2009-14
Date of Issue

Conference Information
Committee NLP
Conference Date 2009/7/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estrus Detection of Cattle by Activity using Neural Network
Sub Title (in English)
Keyword(1) Cattle
Keyword(2) Estrus detection
Keyword(3) Activity
Keyword(4) Multi-layer neural network
1st Author's Name Ryosuke KAWAKAMI
1st Author's Affiliation Faculty of Information Engineering, Matsue College of Technology()
2nd Author's Name Toru WATANABE
2nd Author's Affiliation Faculty of Information Engineering, Matsue College of Technology
3rd Author's Name Makoto DOHI
3rd Author's Affiliation Faculty of Life and Environmental Science, Shimane University
4th Author's Name Motoi NAKASHIMA
4th Author's Affiliation Innovit Corporation
Date 2009-07-13
Paper # NLP2009-21,NC2009-14
Volume (vol) vol.109
Number (no) 124
Page pp.pp.-
#Pages 6
Date of Issue