University of Twente Student Theses

Login
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.

Exploring Real-Time Acoustic Analysis for Monitoring Welfare in Shelter Cats

Ceban, Anamaria (2025) Exploring Real-Time Acoustic Analysis for Monitoring Welfare in Shelter Cats.

[img] PDF
5MB
Abstract:Animal shelters often exist in resource-poor environments, where staff can barely monitor or identify early signs of stress or illness in certain animals, cats being the experts at concealing stress or signs of being unwell. This project provides a proof-of-concept, realtime, low-cost monitoring solution to identify potential distress or sickness in cats via their vocalizations before an indication of any clinical signs of illness or distress is truly displayed. Specifically, this will be done via finding of cat vocalizations, using a micro- phone set up and a Raspberry Pi as the computational engine of its use. It identifies vocalizations using a system of 2 YAMNet models: a fine-tuned model and the classic YAMNet model. The system achieved an overall clas- sification accuracy of 76%, supporting the feasibility of vocalization-based monitoring in practice. This study aims to assist shelters with inexpensive, non-intrusive, early detection of well-being issues in cats prior to clinical assessment. This study presents whether such a system can credibly improve cat welfare in animal shelters, whilst being computationally efficient, and scalable.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:https://purl.utwente.nl/essays/107774
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page