PoachNet: Predicting poaching using an ontology-based knowledge graph

Hamed, Naeima ORCID: https://orcid.org/0000-0002-2998-5056, Rana, Omer ORCID: https://orcid.org/0000-0003-3597-2646, Orozco Ter Wengel, Pablo ORCID: https://orcid.org/0000-0002-7951-4148, Goossens, Benoit ORCID: https://orcid.org/0000-0003-2360-4643 and Perera, Charith ORCID: https://orcid.org/0000-0002-0190-3346 2024. PoachNet: Predicting poaching using an ontology-based knowledge graph. Sensors 24 (24) , 8142. 10.3390/s24248142

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (2MB) | Preview

Abstract

Poaching poses a significant threat to wildlife and their habitats, necessitating advanced tools for its prediction and prevention. Existing tools for poaching prediction face challenges such as inconsistent poaching data, spatiotemporal complexity, and translating predictions into actionable insights for conservation efforts. This paper presents PoachNet, a novel predictive system that integrates deep learning with Semantic Web reasoning to infer poaching likelihood. Using elephant GPS data extracted from an ontology-based knowledge graph, PoachNet employs a sequential neural network to predict future movements, which are semantically modelled and incorporated into the graph. Semantic Web Rule Language (SWRL) is applied to infer poaching risk based on these geo-location predictions and poaching rule-based logic. By addressing spatiotemporal complexity and integrating predictions into an actionable semantic rule, PoachNet advances the field, with its geo-location prediction model outperforming state-of-the-art approaches.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Biosciences Computer Science & Informatics
Publisher:	MDPI
ISSN:	1424-8220
Date of First Compliant Deposit:	20 December 2024
Date of Acceptance:	19 December 2024
Last Modified:	03 Jan 2025 15:18
URI:	https://orca.cardiff.ac.uk/id/eprint/174886

Actions (repository staff only)

Edit Item