亚洲一区欧美在线,日韩欧美视频免费观看,色戒的三场床戏分别是在几段,欧美日韩国产在线人成

基于輕量級(jí)卷積神經(jīng)網(wǎng)絡(luò)的種雞發(fā)聲識(shí)別方法
CSTR:
作者:
作者單位:

作者簡(jiǎn)介:

通訊作者:

中圖分類號(hào):

基金項(xiàng)目:

國(guó)家重點(diǎn)研發(fā)計(jì)劃項(xiàng)目(2016YFD0700204)


Recognition Method of Breeding Birds’ Vocalization Based on Lightweight Convolutional Neural Network
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 圖/表
  • |
  • 訪問(wèn)統(tǒng)計(jì)
  • |
  • 參考文獻(xiàn)
  • |
  • 相似文獻(xiàn)
  • |
  • 引證文獻(xiàn)
  • |
  • 資源附件
  • |
  • 文章評(píng)論
    摘要:

    在種雞養(yǎng)殖和管理過(guò)程中,借助非接觸式、連續(xù)的聲音檢測(cè)手段和智能化設(shè)備,飼養(yǎng)員可以全面了解蛋雞的健康狀況以及個(gè)體需求,為提高生產(chǎn)效率并同時(shí)改善種雞福利化養(yǎng)殖,提出了一種基于輕量級(jí)卷積神經(jīng)網(wǎng)絡(luò)的種雞發(fā)聲分類識(shí)別方法,以海蘭褐種雞為研究對(duì)象,收集種雞舍內(nèi)常見(jiàn)的5類聲音,再將其聲音一維信號(hào)轉(zhuǎn)換為二維圖像信號(hào),利用卷積神經(jīng)網(wǎng)絡(luò)建立輕量級(jí)的深度學(xué)習(xí)模型,80%數(shù)據(jù)進(jìn)行訓(xùn)練,20%數(shù)據(jù)進(jìn)行測(cè)試,該模型實(shí)現(xiàn)了動(dòng)物聲音信號(hào)從輸入端到識(shí)別結(jié)果輸出端的高效檢測(cè)。對(duì)比已有研究,本文方法對(duì)種雞舍內(nèi)常見(jiàn)的5類聲音識(shí)別整體準(zhǔn)確率提高3.7個(gè)百分點(diǎn)。試驗(yàn)結(jié)果表明,該方法平均準(zhǔn)確率為95.7%,模型對(duì)飲水聲、風(fēng)機(jī)噪聲、產(chǎn)蛋叫聲識(shí)別召回率均達(dá)到100%,其中風(fēng)機(jī)噪聲和產(chǎn)蛋叫聲精確率和F1值也均達(dá)到100%,而應(yīng)激叫聲召回率最低,為88.3%。本研究可為規(guī)?;療o(wú)人值守雞舍的智能裝備研發(fā)提供一定理論參考。

    Abstract:

    In the process and management of breeding birds breeding, with the help of noncontact and continuous sound detection as well as some intelligent equipment, the breeder can fully understand the health status and individual needs of breeding birds, which can improve production efficiency as well as animal welfare. A kind of lightweight convolution neural networks for breeding birds voice recognition was proposed. The sound of the Hy-line brown breeding birds was taken as the research object, and five kinds of common sounds in the breeding bird house were collected, then the one-dimensional signal of sound was converted into two-dimensional image signal. Based on the great advantages of convolutional neural network in image recognition, a lightweight deep learning model was established, with 80% data as training and 20% data as testing. This model realized the efficient detection process of animal sound signal from input to output of recognition results. By comparing and analyzing the recognition methods of previous studies, the proposed method greatly improved the overall accuracy rate of recognition of five kinds of common sounds in breeding birds' house by 3.7 percentage points. The experimental results showed that the average accuracy rate of this method was as high as 95.7%. The recall rate of the model for drinking water, fan noise and laying call were all up to 100%, and the precision rate and F1 value of fan noise and laying call were also up to 100%. While, the recall rate of stress call was the lowest value of 88.3%. The research result provided some theoretical reference for the research and development of unmanned intelligent equipment in the future large-scale chicken house.

    參考文獻(xiàn)
    相似文獻(xiàn)
    引證文獻(xiàn)
引用本文

杜曉冬,滕光輝,劉慕霖,趙雨曉,周振宇,祝鵬飛.基于輕量級(jí)卷積神經(jīng)網(wǎng)絡(luò)的種雞發(fā)聲識(shí)別方法[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2022,53(10):271-276. DU Xiaodong, TENG Guanghui, LIU Mulin, ZHAO Yuxiao, ZHOU Zhenyu, ZHU Pengfei. Recognition Method of Breeding Birds’ Vocalization Based on Lightweight Convolutional Neural Network[J]. Transactions of the Chinese Society for Agricultural Machinery,2022,53(10):271-276.

復(fù)制
分享
文章指標(biāo)
  • 點(diǎn)擊次數(shù):
  • 下載次數(shù):
  • HTML閱讀次數(shù):
  • 引用次數(shù):
歷史
  • 收稿日期:2021-11-18
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2021-12-22
  • 出版日期:
文章二維碼