An Animal Behavior State Estimation Method Using CCNN and BN Based System

doi:10.1145/3403746.3403921

	An Animal Behavior State Estimation Method Using CCNN and BN Based System
	Li, Rui; Ren, Yu
	2020-05-22
会议日期	May 22, 2020 - May 24, 2020
会议地点	Beijing, China
关键词	Animals Bayesian networks Convolution Ecology Software engineering Convolutional networks Ecological protection Estimation methods Feature detection Feature location Hierarchical structures Overall accuracies State estimation methods
DOI	10.1145/3403746.3403921
页码	158-163
英文摘要	The study of animal behavior can provide a basis for ecological researchers to help them formulate more reasonable and targeted ecological protection strategies. In this paper, the feature detection method based on cascade convolutional neural network is applied to the detection of animal features. By analyzing the general flow of convolutional neural networks, the researchers designed a cascade convolutional neural network with three hierarchical structures. Each hierarchical structure has multiple convolutional networks, which perform the same or different operations respectively. In order to make up for the defects of neural network in reasoning, this paper uses Bayesian network to infer and estimate in the analysis of features. Through experiments on the proposed method on a self-built data set, the results show that the overall accuracy of the animal behavior estimation method based on CCNN and BN proposed in this paper is more than 85%, and compared with general methods, this method has the advantages of fast learning speed, accurate feature location, and high accuracy of behavior estimation. © 2020 ACM.
会议录	ACM International Conference Proceeding Series
会议录出版者	Association for Computing Machinery
语种	英语
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/118165]
专题	计算机与通信学院
作者单位	School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China
推荐引用方式 GB/T 7714	Li, Rui,Ren, Yu. An Animal Behavior State Estimation Method Using CCNN and BN Based System[C]. 见:. Beijing, China. May 22, 2020 - May 24, 2020.