PoS - Proceedings of Science
Volume 429 - The 6th International Workshop on Deep Learning in Computational Physics (DLCP2022) - Track3. Machine Learning in Natural Sciences
Application of a neural network approach to the task of arena marking for the ”Open Field” behavioral test
A.I. Anikina*, D. Podgainy, A. Stadnik, O. Streltsova, I. Kolesnikova, Y. Severiukhin and D. Savvateev
Full text: pdf
Pre-published on: November 23, 2022
Published on:
Abstract
Within the joint project of MLIT and LRB JINR, aimed to the creation of an information system for the tasks of radiation biology, a module to study the behavioral patterns of small laboratory animals exposed to radiation is being developed. The module for behavioral analysis automates the analysis of video data obtained by testing laboratory animals in different test systems. The ”Open Field” behavioral test is one of the systems. The considered behavioral test has a form of round arena with chequered-marked sectors and holes. The observation procedure on laboratory animals takes 3-6 minutes. The ”Open Field” test system allows one to register the exploratory and general motor activities, orienting-exploratory reaction and emotional status of the animal. To this aim, we fix the number of crossed sectors together with the number of intersections of the marked center. In addition, the actions the animal performed, i.e., hole dipping, rearing/climbing, freezing and shifting, is taken into account.
Therefore, one of our tasks is to develop an algorithm for behavioral test arena marking. The paper presents algorithms for arena marking of the ”Open Field” test system on the basis of computer vision methods together with the method of key points within a neural network approach.
DOI: https://doi.org/10.22323/1.429.0017
How to cite

Metadata are provided both in "article" format (very similar to INSPIRE) as this helps creating very compact bibliographies which can be beneficial to authors and readers, and in "proceeding" format which is more detailed and complete.

Open Access
Creative Commons LicenseCopyright owned by the author(s) under the term of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.