Machine Learning Models for Behavioural Diversity of Asian Elephants Prediction Using Satellite Collar Data

Aug 3, 2026

Upload by Anda

Analysis of animal movement data using statistical applications and machine learning has accelerated with advances in tracking devices and data collection systems. Location and movement data are obtained at temporal and spatial scales, often via GPS, while satellite collars enable continuous monitoring by transmitting received records to electronic systems. Accurately extracting stable elephant activity patterns from satellite collar data remains difficult. This study proposes machine learning models to predict the behavioural diversity of Asian elephants.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages36

Reading Time1 h 31 min

AccessFree to download

Abstract

Introduction

Wildlife movement and forecasting

Satellite collar monitoring in Malaysia

Asian elephant background and protection

Satellite collar technology used

JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGY [https://e-journal.uum.edu.my/index.php/jict](https://e-journal.uum.edu.my/index.php/jict) How to cite this article: Ahmad Radzali, N. S., Abu Bakar, A., & Zamahsasri, A. I. (2023). Machine learning models for behavioral diversity of asian elephants prediction using satellite collar data. Journal of Information and Communication Technology, 22(3), 363-398. [https://](https://)[ ](https://)[doi.org/10.32890/jict2023.22.3.3](doi.org/10.32890/jict2023.22.3.3) Machine Learning Models for Behavioural Diversity of Asian Elephants Prediction Using Satellite Collar Data *1Nurul Su’aidah Ahmad Radzali, 2Azuraliza Abu Bakar & 3Amri Izaffi Zamahsasri 1Department of Information System and Communication, Politeknik Sultan Idris Shah, Selangor, Malaysia 2Centre for Artificial Intelligence Technology (CAIT), Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Selangor, Malaysia 3 Supritendent’s Office, Kelantan National Park, Kelantan, Malaysia * [1](1 nurulsuaidah@psis.edu.my)[ nurulsuaidah@psis.edu.my](1 nurulsuaidah@psis.edu.my) [2](2 azuraliza@ukm.edu.my)[ azuraliza@ukm.edu.my](2 azuraliza@ukm.edu.my) [3](3 amriizaffi@gmail.com)[ amriizaffi@gmail.com](3 amriizaffi@gmail.com) *Corresponding author Received: 22/9/2022 Revised: 20/12/2022 Accepted: 6/4/2023 Published: 24/7/2023 ABSTRACT Analysis of animal movement data using statistical applications and machine learning has developed rapidly in line with the development and use of various tracking devices. Location and movement data at temporal and spatial scales are collected using the Global Positioning System (GPS) to estimate the location of animals. In contrast, installing a satellite collar can ensure continuous monitoring, as the received data will be sent directly to the electronic mailbox. Nevertheless, identifying an exact pattern of elephant activity from satellite collar data is still challenging. This study aimed to propose a machine learning model to predict the behavioural diversity of Asian elephants. The study involved four main phases, including two levels of model development, to produce initial and primary classification models. The phases were data collection and preparation, data labelling and initial classification model development, all data classification, and primary classification model development. The elephant behaviour data were collected from the satellite collars attached to five elephants, three males and two females, in forest reserves from 2018 to 2020 by the Department of Wildlife and National Parks, Malaysia. The study’s outcome was a novel classification model that can predict the behaviour of the Asian elephant movement. The findings showed that the XGBoost method could produce the predictive model to classify Asian elephants’ behaviour with 100 percent accuracy. This study revealed the capability of machine learning to identify behaviour classes and decision-making in setting initiatives to preserve this species in the future. Keywords: Machine learning, XGBoost algorithm, Satellite collar data, Behaviour classification. INTRODUCTION Wild animals live in the wild and do not interact with humans, and consist of thousands of mammals, birds, reptiles, fish, amphibians, and insects (Chandrakar, 2018) . Wildlife refers to an animal that is not tame and has its habitat, such as forests, mountains, deserts, and even the ocean. It has a vital role in maintaining the balance of the environment because it can provide stability to different natural processes. The revolution of animal movement analysis is in line with improved positional accuracies and temporal frequency detection devices, such as ARGOS, Radio Frequency Identification (RFID), IDentification (Tag), Geotag, and Global Navigation2 Satellite System (GNSS) (Cooke et al., 2004) . Cargnelutti et al. (2007) and Mattisson et al. (2010) used mobile collars to test the performance of the Gl

FAQs

What data sources are used to analyze elephant behaviour in this study?

The study uses satellite collar data collected from Asian elephants over 2018 to 2020. The collars provide continuous location and movement information for behavioural analysis.

What modelling approach does the study propose?

The research proposes machine learning models developed through multiple phases, including data collection and preparation, labelling, and iterative classification model development to produce initial and primary classifiers.

How effective is the final predictive model for behaviour classification?

The findings report that the XGBoost method produced a predictive model that classifies Asian elephants’ behaviour with 100 percent accuracy.

Aug 3, 2026

Upload by Anda