本文選題：肉牛行為 + 姿態(tài)傳感器�。� 參考：《沈陽農(nóng)業(yè)大學(xué)》2017年碩士論文

【摘要】：隨著大規(guī)模、集約化的肉牛養(yǎng)殖業(yè)的發(fā)展,動(dòng)物行為識(shí)別的機(jī)器化實(shí)現(xiàn)表現(xiàn)得尤其重要。現(xiàn)在對肉牛行為特征的觀察主要依賴于飼養(yǎng)員的實(shí)際經(jīng)驗(yàn),即借助自己對牛的了解程度,對肉牛的健康及行為特征作出判斷,這不僅加重飼養(yǎng)員的負(fù)擔(dān),而且工作效率低下,對肉牛個(gè)體行為狀態(tài)的改變不夠快速,不能很好的適應(yīng)大規(guī)模農(nóng)場飼養(yǎng)的需求。最近幾年,信息化技術(shù)不斷發(fā)展,對肉牛精準(zhǔn)飼養(yǎng)提供了技術(shù)支持,各國相關(guān)工作者借助圖像處理技術(shù)對肉牛的行為狀態(tài)進(jìn)行觀察與監(jiān)測,但這種技術(shù)對環(huán)境的要求相對較高。本文以姿態(tài)傳感器為工具,以育肥期肉牛為主體,將肉牛的行為數(shù)據(jù)通過主成分分析進(jìn)行降維,采用卡爾曼濾波器算法、BP神經(jīng)網(wǎng)絡(luò)算法對肉牛行為特征數(shù)據(jù)建立分類模型。主要內(nèi)容包括:(1)本文有針對性的對肉牛的姿態(tài)傳感器數(shù)據(jù)進(jìn)行采集并分析,通過主成分分析算法將肉牛9個(gè)行為特征數(shù)據(jù)集進(jìn)行降維,得到的降維數(shù)據(jù)既可以代表肉牛的所有行為特征,在建模計(jì)算中又可以減少計(jì)算量,增加測量精度。(2)采用卡爾曼濾波器算法對肉牛的行為特征數(shù)據(jù)集展開迭代運(yùn)算,探討其與分類模型之間的關(guān)系及影響程度,這也是采用卡爾曼濾波器在肉牛行為分類方面的初次嘗試。結(jié)合肉牛行為活動(dòng)發(fā)生的時(shí)間,對肉牛的日常行為特征對應(yīng)的姿態(tài)數(shù)據(jù)模型展開研究與分析,經(jīng)過卡爾曼濾波器得到的肉牛行為特征分類模型識(shí)別率為62.5%,識(shí)別率偏低,說明線性系統(tǒng)在肉牛行為識(shí)別領(lǐng)域不能作為理論支持,對肉牛行為分類的研究需要在非線性系統(tǒng)中進(jìn)行進(jìn)一步的研究。(3)由于采用卡爾曼濾波器對肉牛行為分類模型的識(shí)別率過低,不足以作為肉牛行為分類的理論依據(jù),本文還采用BP神經(jīng)網(wǎng)絡(luò)算法對肉牛行為分類進(jìn)行研究,結(jié)果表示:BP神經(jīng)網(wǎng)絡(luò)算法在肉牛行為特征分類方面變現(xiàn)比卡爾曼濾波器要強(qiáng)很多,分類精度在卡爾曼濾波器算法的基礎(chǔ)上提高了近30%,這一結(jié)果表明,肉牛行為特征分類模型的準(zhǔn)確度在采用非線性系統(tǒng)計(jì)算時(shí)取得較大的提升,該方法在肉牛行為識(shí)別領(lǐng)域可以作為理論支持。(4)本文還對傳感器在肉牛身上部署的位置和記錄時(shí)間間隔進(jìn)行了相應(yīng)的研究,研究表明:傳感器安放在肉牛的顳骨位置時(shí),傳感器節(jié)點(diǎn)所測得的數(shù)據(jù)最能符合肉牛的實(shí)際行為活動(dòng);在不影響肉牛行為特征分類精度的情況下,傳感器記錄時(shí)間間隔為2s時(shí)可以減少計(jì)算量,加快數(shù)據(jù)處理的速度。
[Abstract]:With the development of large-scale and intensive beef farming, the realization of machine-based recognition of animal behavior is particularly important. Now the observation of beef cattle behavior characteristics mainly depends on the actual experience of the keeper, that is, with the help of one's own understanding of the cattle, to judge the beef cattle's health and behavior characteristics, which not only increases the burden of the keeper, but also the work efficiency is low. The change of individual behavior of beef cattle is not fast enough to meet the needs of large-scale farms. In recent years, information technology has been developing, which provides technical support for precision feeding of beef cattle. Relevant workers in various countries use image processing technology to observe and monitor the behavior of beef cattle, but this technology requires relatively high environmental requirements. In this paper, the behavior data of beef cattle are reduced by principal component analysis (PCA) with attitude sensor as tool and beef cattle in fattening period as main body. Kalman filter algorithm and BP neural network algorithm are used to establish classification model of beef cattle behavior characteristic data. The main contents include: (1) this paper collects and analyzes the pose sensor data of beef cattle, and reduces the dimension of nine behavioral data sets of beef cattle by principal component analysis (PCA) algorithm. The reduced dimension data can not only represent all the behavioral characteristics of beef cattle, but also reduce the computational cost and increase the measurement accuracy in the modeling calculation. (2) the Kalman filter algorithm is used to iterate the behavioral feature data set of beef cattle. The relationship between the model and the classification model and the degree of influence are discussed. This is also the first attempt to use Kalman filter in beef cattle behavior classification. Combined with the time of beef cattle behavior, the attitude data model corresponding to the daily behavior characteristics of beef cattle was studied and analyzed. The recognition rate of the classification model of beef behavior characteristics obtained by Kalman filter was 62.5 and the recognition rate was on the low side. It shows that the linear system can not be used as theoretical support in beef cattle behavior recognition. The study of beef behavior classification needs further study in nonlinear system. (3) because the recognition rate of beef behavior classification model using Kalman filter is too low, it can not be used as the theoretical basis of beef behavior classification. This paper also uses BP neural network algorithm to study beef cattle behavior classification, the results show that the performance classification of beef cattle behavior is much stronger than Kalman filter. The classification accuracy is improved by nearly 30 percent on the basis of Kalman filter algorithm. The results show that the accuracy of beef behavior feature classification model is greatly improved by using nonlinear system calculation. This method can be used as a theoretical support in the field of Behavioral recognition of Beef cattle. (4) in this paper, the location and recording time interval of the sensor deployed on beef cattle are also studied. The results show that the sensor is placed in the temporal bone position of beef cattle. The measured data of sensor nodes can best accord with the actual behavior of beef cattle. Without affecting the classification accuracy of behavioral characteristics of beef cattle, the sensor recording time interval of 2s can reduce the calculation amount and speed up the data processing.
【學(xué)位授予單位】：沈陽農(nóng)業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：S823;TP212

【相似文獻(xiàn)】

相關(guān)期刊論文 前3條

1 趙汝祺;趙祚喜;趙汝準(zhǔn);;基于多項(xiàng)式卡爾曼濾波器的車輛定位試驗(yàn)[J];農(nóng)業(yè)工程學(xué)報(bào);2012年18期

2 杜義君;;神經(jīng)網(wǎng)絡(luò)算法在Microsoft SQL Server 2005 Analysis Services中的應(yīng)用[J];塔里木大學(xué)學(xué)報(bào);2007年03期

3 師彪;李郁俠;于新花;閆旺;李鵬;;自適應(yīng)人工魚群-BP神經(jīng)網(wǎng)絡(luò)算法在徑流預(yù)測中的應(yīng)用[J];自然資源學(xué)報(bào);2009年11期

相關(guān)會(huì)議論文 前10條

1 韓德忠;馬深;;多波束測量中姿態(tài)傳感器安裝位置探討[A];第二十一屆海洋測繪綜合性學(xué)術(shù)研討會(huì)論文集[C];2009年

2 談林霞;張福學(xué);趙輝;高幸;;動(dòng)態(tài)水平姿態(tài)傳感器加速度干擾抑制方法[A];微機(jī)電慣性技術(shù)的發(fā)展現(xiàn)狀與趨勢——慣性技術(shù)發(fā)展動(dòng)態(tài)發(fā)展方向研討會(huì)文集[C];2011年

3 宋佳;樸林華;劉玉潔;李言杰;張福學(xué);;微機(jī)械氣流式全方位水平姿態(tài)傳感器氣體擺特性的三維有限元分析[A];中國電子學(xué)會(huì)第十五屆電子元件學(xué)術(shù)年會(huì)論文集[C];2008年

4 樸林華;李言杰;李白華;;氣流式水平姿態(tài)傳感器的敏感機(jī)理[A];2009年中國智能自動(dòng)化會(huì)議論文集（第五分冊）[東南大學(xué)學(xué)報(bào)（增刊）][C];2009年

5 李明;楊洪耕;劉立生;;新型自適應(yīng)卡爾曼濾波器作動(dòng)態(tài)諧波估計(jì)[A];2004年電力電容器學(xué)會(huì)論文集[C];2004年

6 苑薇薇;王建輝;;采用推廣卡爾曼濾波器估計(jì)入射波參數(shù)[A];1997中國控制與決策學(xué)術(shù)年會(huì)論文集[C];1997年

7 姜義德;鐘潁秀;張帆人;;以限制型卡爾曼濾波器估測位置與姿態(tài)(英文)[A];第七屆海峽兩岸工程力學(xué)研討會(huì)論文摘要集[C];2011年

8 馬馳州;楊亦春;李曉東;;多模型卡爾曼濾波器在聲定位中的應(yīng)用[A];中國聲學(xué)學(xué)會(huì)2006年全國聲學(xué)學(xué)術(shù)會(huì)議論文集[C];2006年

9 張勇軍;李小占;楊志剛;;動(dòng)態(tài)優(yōu)化漸消因子的強(qiáng)跟蹤卡爾曼濾波器研究[A];中國自動(dòng)化學(xué)會(huì)控制理論專業(yè)委員會(huì)C卷[C];2011年

10 房媛媛;李亞安;李曉花;白曉娟;;Cubature-Kalman濾波及性能分析[A];中國聲學(xué)學(xué)會(huì)第九屆青年學(xué)術(shù)會(huì)議論文集[C];2011年

相關(guān)博士學(xué)位論文 前3條

1 王思思;自適應(yīng)容積卡爾曼濾波器及其在雷達(dá)目標(biāo)跟蹤中的應(yīng)用[D];大連海事大學(xué);2015年

2 陸詩遠(yuǎn);基于WSN的分布式傳感器系統(tǒng)關(guān)鍵技術(shù)研究[D];浙江大學(xué);2016年

3 方旭明;基于自適應(yīng)卡爾曼濾波器的WSN定位算法研究[D];南京大學(xué);2017年

相關(guān)碩士學(xué)位論文 前10條

1 姜美曦;基于姿態(tài)傳感器的肉牛行為特征識(shí)別研究[D];沈陽農(nóng)業(yè)大學(xué);2017年

2 何思銳;姿態(tài)傳感器中基于遺傳算法的小波去噪研究[D];西安工業(yè)大學(xué);2015年

3 馬燕妮;三維姿態(tài)傳感器的研制[D];西安工業(yè)大學(xué);2015年

4 荊波;姿態(tài)傳感器檢測平臺(tái)的設(shè)計(jì)[D];西安工業(yè)大學(xué);2016年

5 李明哲;姿態(tài)傳感器的運(yùn)動(dòng)特性研究[D];西安工業(yè)大學(xué);2016年

6 王沛;野外文物遠(yuǎn)程實(shí)時(shí)監(jiān)測系統(tǒng)設(shè)計(jì)與實(shí)現(xiàn)[D];西安工業(yè)大學(xué);2016年

7 趙傳超;基于姿態(tài)傳感器的虛擬儀器的研究和應(yīng)用[D];西安工業(yè)大學(xué);2017年

8 胡鈴;高精度姿態(tài)傳感器的研制[D];西安工業(yè)大學(xué);2014年

9 張銘;高精度姿態(tài)傳感器的可靠性設(shè)計(jì)[D];西安工業(yè)大學(xué);2013年

10 徐冰;基于下肢姿態(tài)傳感器檢測的人體防摔策略研究[D];吉林大學(xué);2013年

，

本文編號：1839373