Modelling behavior of Crested gecko (Correlophus ciliatus) using classification algorithms

IF 2.2 2区农林科学 Q1 AGRICULTURE, DAIRY & ANIMAL SCIENCE

Applied Animal Behaviour Science Pub Date : 2024-11-04 DOI:10.1016/j.applanim.2024.106436

Jakub Pacoń, Barbara Kosińska-Selbi, Jarosław Wełeszczuk, Joanna Kochan, Wojciech Kruszyński

{"title":"Modelling behavior of Crested gecko (Correlophus ciliatus) using classification algorithms","authors":"Jakub Pacoń, Barbara Kosińska-Selbi, Jarosław Wełeszczuk, Joanna Kochan, Wojciech Kruszyński","doi":"10.1016/j.applanim.2024.106436","DOIUrl":null,"url":null,"abstract":"<div><div>Animal behavior plays a crucial role in evolution of many species. Many studies focused on animal behavior enhance the ability to collect large and detailed data. However, this kind of data is surpassing the capability of traditional statistical methods for analysis. In this study we propose to use artificial intelligence (AI) with machine learning models (ML) as tools to study animal behavior and potentially assumed evolution patterns in their behavior. For the Crested gecko (<em>Correlophus ciliatus</em>), some guidelines have been published regarding the breeding of these reptiles, focusing on their behavior. However, little is known about moderating their behavior using AI and advanced ML algorithms. In this study, based on information collected from twenty individuals, we proposed building a supervised classifier model using simple Decision Tree classifier (DT), Gradient Boosting classifier (GB) and Extreme Gradient Boosting classifier (XGBoost). Our results show that the highest accuracy (above 60 %) was achieved for variables which were not complex in terms of animal behavior. The analysis presented in this study, demonstrates that it is possible to model Crested Gecko behavior using ML models.</div></div>","PeriodicalId":8222,"journal":{"name":"Applied Animal Behaviour Science","volume":"281 ","pages":"Article 106436"},"PeriodicalIF":2.2000,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Animal Behaviour Science","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0168159124002843","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, DAIRY & ANIMAL SCIENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Animal behavior plays a crucial role in evolution of many species. Many studies focused on animal behavior enhance the ability to collect large and detailed data. However, this kind of data is surpassing the capability of traditional statistical methods for analysis. In this study we propose to use artificial intelligence (AI) with machine learning models (ML) as tools to study animal behavior and potentially assumed evolution patterns in their behavior. For the Crested gecko (Correlophus ciliatus), some guidelines have been published regarding the breeding of these reptiles, focusing on their behavior. However, little is known about moderating their behavior using AI and advanced ML algorithms. In this study, based on information collected from twenty individuals, we proposed building a supervised classifier model using simple Decision Tree classifier (DT), Gradient Boosting classifier (GB) and Extreme Gradient Boosting classifier (XGBoost). Our results show that the highest accuracy (above 60 %) was achieved for variables which were not complex in terms of animal behavior. The analysis presented in this study, demonstrates that it is possible to model Crested Gecko behavior using ML models.

查看原文本刊更多论文

利用分类算法模拟凤头壁虎（Correlophus ciliatus）的行为

动物行为在许多物种的进化过程中发挥着至关重要的作用。许多关注动物行为的研究都提高了收集大量详细数据的能力。然而，这类数据已经超出了传统统计方法的分析能力。在这项研究中，我们建议使用人工智能（AI）和机器学习模型（ML）作为研究动物行为的工具，并假设动物行为的潜在进化模式。对于凤头壁虎（Correlophus ciliatus），已经发布了一些关于这些爬行动物繁殖的指南，重点关注它们的行为。然而，人们对利用人工智能和先进的 ML 算法来调节它们的行为却知之甚少。在本研究中，基于从 20 个个体收集到的信息，我们建议使用简单的决策树分类器（DT）、梯度提升分类器（GB）和极端梯度提升分类器（XGBoost）建立一个监督分类器模型。我们的结果表明，对于动物行为并不复杂的变量，准确率最高（超过 60%）。本研究中的分析表明，可以使用 ML 模型对冠壁虎的行为进行建模。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Applied Animal Behaviour Science 农林科学-行为科学

CiteScore

4.40

自引率

21.70%

发文量

191

审稿时长

18.1 weeks

期刊介绍： This journal publishes relevant information on the behaviour of domesticated and utilized animals. Topics covered include: -Behaviour of farm, zoo and laboratory animals in relation to animal management and welfare -Behaviour of companion animals in relation to behavioural problems, for example, in relation to the training of dogs for different purposes, in relation to behavioural problems -Studies of the behaviour of wild animals when these studies are relevant from an applied perspective, for example in relation to wildlife management, pest management or nature conservation -Methodological studies within relevant fields The principal subjects are farm, companion and laboratory animals, including, of course, poultry. The journal also deals with the following animal subjects: -Those involved in any farming system, e.g. deer, rabbits and fur-bearing animals -Those in ANY form of confinement, e.g. zoos, safari parks and other forms of display -Feral animals, and any animal species which impinge on farming operations, e.g. as causes of loss or damage -Species used for hunting, recreation etc. may also be considered as acceptable subjects in some instances -Laboratory animals, if the material relates to their behavioural requirements