UWCScholar

This repository serves as a digital archive for the preservation of research outputs from the University of the Western Cape

Communities in UWCScholar

Select a community to browse its collections.

Now showing 1 - 5 of 11

Recent Submissions

Vocal repertoire and acoustic cues to individual identity in the Northern Rockhopper penguin (Eudyptes moseleyi)
(Taylor and Francis Ltd., 2026) Ludynia, Katrin; Turone, Vittoria; Zanoli, Anna
Northern Rockhopper penguins (Eudyptes moseleyi) are highly vocal seabirds. However, detailed descriptions of their vocal repertoire are currently unavailable. Here, we studied the vocal behaviour of this species and assessed the presence of acoustic cues of individuality across different vocal types. We collected audio and video recordings from an ex-situ colony at the Two Oceans Aquarium (Cape Town, South Africa) consisting of wild rescued individuals and their offspring. We combined the visual inspection of spectrograms with spectro-temporal acoustic analyses based on a source-filter theory approach. Our results showed that the vocal repertoire of the Northern Rockhopper penguin is made of three discrete vocal types: agonistic calls, uttered during agonistic interactions, contact calls, produced to maintain acoustic contact among group members when visually isolated, and ecstatic display songs, mediating territorial defence and mate attraction. Moreover, we demonstrated that all vocal types encode acoustic cues to the individual identity of the emitter. Studying the vocal repertoire of penguins is crucial for a deeper understanding of their social behaviour and may ultimately contribute to the conservation of this endangered seabird.
Identifying stakeholder perspectives and priorities for athlete monitoring technology: a mixed-methods study based on interviewing Belgian high-performance sports organisations
(SAGE Publications Inc., 2025) Meeusen, Romain; Aerts, Jean-Marie; Moons, Karen
The rapid growth of technology in managing training processes offers both opportunities and challenges for sports practitioners. This study examines factors influencing technology adoption in four high-performance sports: golf, sprint kayak, freestyle snowboarding, and volleyball. Each discipline reflects distinct physiological and training needs. Using an interview-based approach and including 25 stakeholders (6 athletes, 14 coaches, and 5 high-performance managers), we captured qualitative and quantitative insights into the perceived benefits and challenges of technology in athlete monitoring. The thematic analysis identified key advantages of technology in athlete monitoring, including objective data support, enhanced engagement, real-time feedback, and increased confidence, while also highlighting concerns around misuse, time demands, and technological complexity. Conflicting views on motivation, comfort, and human oversight further emphasized the challenges in integrating technology effectively. To quantify these insights, we applied the Analytic Hierarchy Process (AHP), a structured prioritisation approach that is new within sports science, to rank essential technology features. Findings ranked Reliability (1st; 18.73%) and Validity (2nd; 18.42%) as top priorities, with Interpretability (3rd; 9.95%), Responsiveness (4th; 9.02%), and Complexity (5th; 8.08%) also valued. Key training priorities included monitoring Technique (1st; 15.94%), Performance (2nd; 15.24%), and Benchmarking (3rd; 11.90%). The thematic analysis highlights the importance of balanced use of technology. In a complementary approach, the AHP provides a structured method for assessing stakeholder priorities, enhancing decision-making and helping align technology development with practitioner needs. By introducing a framework that bridges communication between engineers, scientists, and practitioners, this study guides the development of user-centred sports technologies that effectively address real-world challenges in high-performance organisations.
Infection prevention knowledge related to central line infections and ventilator-associated pneumonias: A survey of Finnish intensive care units
(Elsevier Inc., 2025) Salanterä, Sanna; Terho, Kirsi; Löyttyniemi, Eliisa Susanna
Background: Health care-associated infections pose a significant risk for the patients in intensive care due to the use of medical instrumentation required for care. Methods: We conducted a cross-sectional, nationwide survey on awareness of recommended infection prevention practices involving central venous catheters and invasive ventilators in intensive care units. Results: A total of 810 (50% of those surveyed) nurses and physicians participated in the survey. We found that 8% of the respondents had good knowledge of infection prevention in central venous care, while 24% had good knowledge of ventilator-associated pneumonia prevention practices. Discussion: The overall level of knowledge measured with this nationwide survey was suboptimal. The level varied between units, and depending on individual questions for particular professions. The displayed knowledge may have partially been based on tradition rather than on up-to-date evidence-based guidelines. Conclusions: Educational training in evidence-based infection prevention is needed for practical implementation to be improved. © 2025 Association for Professionals in Infection Control and Epidemiology, Inc.
Land use land cover classification in Japanese wetland and agricultural landscapes via machine learning and multi-source sentinel data
(Taylor and Francis Ltd, 2025) Dube, Timothy; Pandit, Santa; Oki, Kazuo
This study assessed land use and land cover (LULC) in the Oze wetland and Hatase agricultural fields using Random Forest (RF) and Support Vector Machine (SVM). Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical data from 2023–2024 were processed into seasonal median composites. Input features included SAR backscatter coefficients (vertical transmit–vertical receive, vertical transmit–horizontal receive, and their ratio), Sentinel-2 bands (10 m resolution), and vegetation indices: Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Bare Soil Index (BSI), and Modified Normalized Difference Water Index (MNDWI). Training and testing data were derived from high-resolution PlanetScope and drone imagery. Models were implemented in Python (Google Colab). Results showed RF consistently outperformed SVM, achieving kappa scores of 81%–83% in Oze and 79%–81% in Hatase, while SVM failed to exceed 80%. RF’s robustness for seasonal LULC mapping highlights its potential to support monitoring and sustainable land management in cloud-prone wetland–agriculture systems.
The algorithmic mine: enhancing managerial effectiveness and organisational agility in the mining industry through artificial intelligence – a spatially aware predictive framework
(AOSIS (pty) Ltd, 2026) Mpundu, Mubanga; Gosho, Talent
Background: This research critically examines the integration of artificial intelligence (AI) within the mining industry, focusing on their capacity to enhance both managerial effectiveness and organisational agility. Aim: This article addresses the existing literature’s limitations by introducing a novel, spatially aware predictive framework tailored to the unique challenges of mining operations. Setting: While existing literature acknowledges the transformative potential of AI in mining, it often lacks concrete strategies for implementation and fails to address the inherent spatial variability of mining operations. This study proposes the spatially aware predictive framework, leveraging AI to optimise resource allocation, predictive maintenance and environmental management. Method: A systematic literature review was conducted, employing Boolean logic across Web of Science, Scopus and IEEE Xplore databases, focusing on publications from 2019 to 2025. Results: Managerial effectiveness and organisational agility are paramount for success in the increasingly complex and dynamic mining industry. The integration of advanced technologies such as AI offers a powerful means to enhance operational efficiency, improve decision-making and achieve sustainable growth. The spatially-aware predictive framework provides a practical roadmap for implementing these technologies, realising their full potential and moving beyond fragmented and spatially unaware applications. Conclusion: This study proposes the spatially aware predictive framework, leveraging AI to optimise resource allocation, predictive maintenance and environmental management creating an AI-circular business model (AI-CBM). Contribution: This study proposes a novel spatially aware predictive framework, leveraging AI to optimise resource allocation, predictive maintenance and environmental management, which creates an AI-CBM.