期刊文献+

三种记录间隔时间对山羊行为分类精度的影响

Effects of Three Recording Intervals Time on the Classification Accuracy of Goats Behaviors
下载PDF
导出
摘要 引入三轴加速度传感器对山羊的行为特征进行监测,按照三种不同的记录间隔时间(1 s、2 s、3 s)分批次获取山羊的三轴加速度数据。同时,利用全程的视频监控结合动作发生的时间分析山羊的3种典型日常行为。试验结果显示:1 s和2 s的记录间隔时间对山羊行为模型的分类精度分别为87.75%和86.73%,无统计学差异(P>0.05);而3 s的记录间隔时间相比较前两种记录间隔显著性差异明显(P<0.05),且分类精度明显下降为74.32%。总体来说,在不影响分类模型精度的前提下,记录间隔时间可延长至2 s,这样既可以减少数据样本量与数据处理的压力,同时也可以减少人为干预对动物正常行为的应激影响。 Tri-axial accelerometer could be used to monitor goats daily behavior, the devices collect the three- dimensional acceleration data based on pre-defined recording intervals (1 s, 2 s, 3 s). Meanwhile, the video-re- corded observations also be used to identify the goats typical daily behavior. The experiment results showed that dif- ferent recording intervals of 1 s and 2 s corresponding classification accuracy of 87.75% and 86.73% respectively in goats activity model, but the influences were not remarkable ( P 〉 0.05 ) ; However, classification accuracy in the 3 s recording interval was lower compared to the former two recording intervals, and the classification accuracy reduced to 74.32% , the influences were remarkable (P 〈 0.05 ). Overall, the time of recording interval can be extended to 2 s under the premise that didn't affect the accuracy of classification model, in this way, it can not only to reduce the pressure of data sizes and data processing, but also reduces the stress influence by the human inter- vention on animals normal behaviors.
出处 《科学技术与工程》 北大核心 2015年第2期254-258,共5页 Science Technology and Engineering
基金 国家高技术研究发展计划(863计划)(2012AA101905)资助
关键词 记录间隔时间 山羊 三轴加速度传感器 行为活动 分类精度 recording interval goats tri-axial accelerometer activity classification accuracy
  • 相关文献

参考文献19

  • 1韩志国,江燕,高腾云,吕超.从行为学角度思考奶牛福利[J].家畜生态学报,2011,32(6):6-11. 被引量:11
  • 2吴宝明,卓豫,王禾.动物行为检测技术进展及展望[J].中国行为医学科学,2001,10(3):278-280. 被引量:12
  • 3章书声,鲍毅新,王艳妮,方平福,叶彬.不同相机布放模式在古田山兽类资源监测中的比较[J].生态学杂志,2012,31(8):2016-2022. 被引量:46
  • 4Muller R, Schrader L. A new method to measure behavioral activity levels in dairy cows. Applied Animal Behavior Science, 2003; 83 (4) :247-258.
  • 5White B J, Coetzee J F, et al. Evaluation of two-dimensional acceler- ometers to monitor beef eattle behavior post-castration. American Journal of Veterinary Research,2008 ;69(9) :1005-1012.
  • 6温长吉,王生生,赵昕,王忞,马丽,刘依婷.基于视觉词典法的母牛产前行为识别[J].农业机械学报,2014,45(1):266-274. 被引量:16
  • 7刘龙申,沈明霞,姚文,陆明洲,杨晓静,柏广宇.基于加速度传感器的母猪产前行为特征采集与分析[J].农业机械学报,2013,44(3):192-196. 被引量:45
  • 8Karantonis D M,Narayanan M R, Mathie M, et al. Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. IEEE transactions on information technolo- gy in biomedicine,2006 ; 10( 1 ) :156-167.
  • 9Keegan K G, Yonezawa Y, et al. Evaluation of a sensor-based system of motion analysis for detection and quantification of forelimb and hind limb lameness in horses. American Journal of Veterinary Research, 2004; 65(5) :665-670.
  • 10Robert B, White B J, Renter D G, et al. Evaluation of three-di- mensional accelerometers to monitor and classify behavior patterns in cattle. Computers and Electronics in Agriculture, 2009; 6 (67): 80 -84.

二级参考文献185

共引文献275

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部