Skip to main content

Research Repository

Advanced Search


Welcome to OpenAIR@RGU

OpenAIR@RGU is the open access institutional repository of Robert Gordon University. It contains examples of research outputs produced by staff and research students, as well as related information about the university's funded projects and staff research interests. Further information is available in the repository policy. Any questions about submissions to the repository or problems with access to any of its content should be sent to the Publications Team at publications@rgu.ac.uk



Latest Additions

MDDNet: multilevel difference-enhanced denoise network for unsupervised change detection in SAR images. (2025)
Presentation / Conference Contribution
ZONG, H., ZHANG, E., LI, X., ZHANG, H. and REN, J. 2025. MDDNet: multilevel difference-enhanced denoise network for unsupervised change detection in SAR images. In Proceedings of the 50th IEEE (Institute of Electrical and Electronics Engineers) International conference on acoustics, speech and signal processing 2025 (ICASSP 2025), 06-11 April 2025, Hyderabad, India. Piscataway: IEEE [online], article number 576. Available from: https://doi.org/10.1109/icassp49660.2025.10887943

Change detection in synthetic aperture radar (SAR) images is a hot yet highly challenging task in remote sensing. Existing unsupervised SAR change detection methods often struggle with inherent speckle noise and insufficiently utilize pseudo-labels,... Read More about MDDNet: multilevel difference-enhanced denoise network for unsupervised change detection in SAR images..

Group proceedings, negligence and res judicata in Scotland. (2024)
Journal Article
MANTE, J. and ARNELL, P. 2024. Group proceedings, negligence and res judicata in Scotland. Journal of professional negligence [online], 40(4), pages 177-183. Available from: https://www.bloomsburyprofessionalonline.com/view/journal_prof_negl/b-17466709_40-4-0000558.xml

This article discusses McCluskey v Scott Wilson Scotland Ltd (OH) on the extent to which an individual in a group action, which had sought personal injury damages against a civil engineering company for alleged negligence in the inspection and remedi... Read More about Group proceedings, negligence and res judicata in Scotland..

Why we must stop assuming and estimating menstrual cycle phases in laboratory and field-based sport related research. (2025)
Journal Article
ELLIOTT-SALE, K.J., ALTINI, M., DOYLE-BAKER, P. et al. 2025. Why we must stop assuming and estimating menstrual cycle phases in laboratory and field-based sport related research. Sports medicine [online], Latest Articles. Available from: https://doi.org/10.1007/s40279-025-02189-3

The increased growth, popularity, and media interest in women's sport has led to calls for greater prioritisation of female-specific research and innovation. In response, science and medicine researchers have increased the volume of sport-related stu... Read More about Why we must stop assuming and estimating menstrual cycle phases in laboratory and field-based sport related research..

Unsupervised similarity-aligned ensemble metrics for evaluating legal Q&A LLM responses. [Dataset] (2025)
Data
ABEYRATNE, R. 2025. Unsupervised similarity-aligned ensemble metrics for evaluating legal Q&A LLM responses(LINK ONLY). Hosted on GitHub [online]. Available from: https://github.com/RAbeyratne/aligned_ensemble_judge

This repository contains code and datasets related to the paper titled "Unsupervised Similarity-Aligned Ensemble Metrics for Evaluating Legal Q&A LLM Responses".

AlignLLM: alignment-based evaluation using ensemble of LLMs-as-judges for Q &A. (2025)
Presentation / Conference Contribution
ABEYRATNE, R., WIRATUNGA, N., MARTIN, K., NKISI-ORJ, I. and JAYAWARDENA, L. [2025]. AlignLLM: alignment-based evaluation using ensemble of LLMs-as judges for Q&A. In Case-based reasoning research and development: proceedings of the 33rd International conference on case-based reasoning 2025 (ICCBR 2025), 30 June - 03 July 2025, Biarritz, France. Lecture notes in computer science (LNCS), TBC. Cham: Springer [online], (forthcoming).

Evaluating responses generated by large language models (LLMs) is challenging in the absence of ground-truth knowledge, particularly in specialised domains such as law. Increasingly, LLMs themselves are used to evaluate the responses they generate; h... Read More about AlignLLM: alignment-based evaluation using ensemble of LLMs-as-judges for Q &A..