基于深度学习的实验鼠行为识别关键技术研究  

Research on Key Technologies of Laboratory Rat Behavior Recognition Based on Deep Learning

作　　者：徐涌霞[1] XU Yong-xia(Department of Computer, Huaibei Vocational and Technical College, Huaibei Anhui 235000, China)

机构地区：[1]淮北职业技术学院计算机系,安徽淮北235000

出　　处：《佳木斯大学学报（自然科学版）》2020年第2期66-69,共4页Journal of Jiamusi University：Natural Science Edition

基　　金：安徽省高校自然科学研究项目(KJ2019A0603)。

摘　　要：实验鼠的行为识别和分析对于脑神经等学科的研究进展很重要,因此将深度学习模型应用于实验鼠的行为识别中。首先结合多纤维神经网络和合适的数据增强策略以实现高效的行为识别。然后使用视频剪切和动态亮度变化过滤器来实现视频增强。最后使用大量实验来评估本模型的识别性能。结果显示,与最先进的老鼠行为识别(RBR)系统相比,模型具有更好的识别性能。The behavior recognition and analysis of laboratory rats is very important for the research progress of pharmacology and other disciplines.Therefore,this paper applies deep learning models to the behavior recognition of laboratory mice.This paper first combines MF neural network and appropriate data enhancement strategies to achieve efficient behavior recognition.Video enhancement is then implemented using video cropping and dynamic brightness change filters.Finally,a large number of experiments were used to evaluate the recognition performance of the model in this paper.The results show that compared with the most advanced rat behavior recognition(RBR)system,our model has better recognition performance.

关 键 词：深度学习 多纤维神经网络 实验鼠行为识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]