Paul Murray

Paul Murray

Auto-generated profile, based on publicly available information

Paul Murray

University of Strathclyde

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 January 2020 in IEEE Access
Verified
Journal Article
Open access
SFSamson Damilola Fabiyi
Samson Damilola Fabiyi
HVHai Vu
Hai Vu
Christos TachtatzisChristos Tachtatzis
Christos Tachtatzis
PMPaul Murray
Paul Murray
DHDavid Harle
David Harle
Stephen MarshallStephen Marshall
Stephen Marshall

23 November 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
SFSamson Damilola Fabiyi
Samson Damilola Fabiyi
PMPaul Murray
Paul Murray
Jaime ZabalzaJaime Zabalza
Jaime Zabalza
Jinchang RenJinchang Ren
Jinchang Ren
The rich spectral information provided by hyperspectral imaging has made this technology very useful in the classification of remotely sensed data. However, classification of hyperspectral data is typically affected by noise and the Hughes phenomenon due to the presence of hundreds of spectral bands and correlation among them, with usually a limited number of samples for training. Linear discriminant analysis (LDA) is a well-known technique that has been widely used for supervised dimensionality reduction of hyperspectral data. However, the use of LDA in hyperspectral remote sensing is limited due to its poor performance on small training datasets and the limited number of features that can be selected i.e., $c - 1$ , where $c$ is the number of classes in the data. To solve these problems, this article presents a folded LDA (F-LDA) for dimensionality reduction of remotely sensed HSI data in small sample size scenarios. The proposed approach allows many more discriminant features to be selected in comparison to the conventional LDA since the selection is no longer bound by the limiting factor, leading to significantly higher accuracy in the classification of pixels under SSS restrictions. The proposed approach is evaluated on five different datasets, where the experimental results demonstrate the superiority of the F-LDA to the conventional LDA in terms of not only higher classification accuracy but also reduced computational complexity, and reduced contiguous memory requirements.

24 October 2019 in International Journal of Sustainability in Higher Education
Verified
Journal Article
Open access
SSScott Munro Strachan
Scott Munro Strachan
Stephen MarshallStephen Marshall
Stephen Marshall
PMPaul Murray
Paul Murray
ECEdward J. Coyle
Edward J. Coyle
JSJulia Sonnenberg-Klein
Julia Sonnenberg-Klein
Purpose: This paper aims to share the University of Strathclyde’s experience of embedding research-based education for sustainable development (RBESD) within its undergraduate curricula through the use of an innovative pedagogy called Vertically Integrated Projects (VIP), originated at Georgia Institute of Technology.Design/methodology/approach: This paper discusses how aligning VIP with the SDG framework presents a powerful means of combining both research-based education (RBE) and education for sustainable development (ESD), and in effect embedding RBESD in undergraduate curricula.Findings: The paper reports on the University of Strathclyde’s practice and experience of establishing their VIP for Sustainable Development programme and presents a reflective account of the challenges faced in the programme implementation and those envisaged as the programme scales up across a higher education institution (HEI).Research limitations/implications: The paper is a reflective account of the specific challenges encountered at Strathclyde to date after a successful pilot, which was limited in its scale. While it is anticipated these challenges may resonate with other HEIs, there will also be some bespoke challenges that may not be discussed here.Practical implications: This paper offers a practical and scalable method of integrating SDG research and research-based education within undergraduate curricula.Social implications: The paper has the potential to deliver SDG-related impact in target communities by linking research-based teaching and learning with community outreach.Originality/value: The alignment of VIP with the SDG research area is novel, with no other FE institutions currently using this approach to embed SDG research-based teaching within their curricula. Furthermore, the interdisciplinary feature of the VIP programme, which is critical for SDG research, is a Strathclyde enhancement of the original model.

3 March 2023 in IEEE Access
Verified
Journal Article
Open access
EBEfstathios Branikas
Efstathios Branikas
PMPaul Murray
Paul Murray
GWGraeme West
Graeme West
Condition monitoring and inspection are core activities for assessing and evaluating the health of critical infrastructure spanning from road networks to nuclear power stations. Defect detection on visual inspections of such assets is a field that enjoys increasing attention. However, data-based models are prone to a lack of available data depicting cracks of various modalities and present a great data imbalance. This paper introduces a novel data augmentation technique by deploying the CycleGan Generative Adversarial Network (GAN). The proposed model is deployed between different image datasets depicting cracks, with a nuclear application as the main industrial example. The aim of this network is to improve the segmentation accuracy on these datasets using deep convolutional neural networks. The proposed GAN generates realistic images that are challenging to segment and under-represented in the original datasets. Different deep networks are trained with the augmented datasets while introducing no labelling overhead. A comparison is drawn between the performance of the different neural networks on the original data and their augmented counterparts. Extensive experiments suggest that the proposed augmentation method results in superior crack detection in challenging cases across all datasets. This is reflected by the respective increase in the quantitative evaluation metrics.

8 August 2016 in Cognitive Computation
Verified
Journal Article
Closed access
PDF file
YZYan Zhou
Yan Zhou
FZFan-Zhi Zeng
Fan-Zhi Zeng
HZHui-Min Zhao
Hui-Min Zhao
PMPaul Murray
Paul Murray
Jinchang RenJinchang Ren
Jinchang Ren

25 November 2020 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
PMPing Ma
Ping Ma
Jinchang RenJinchang Ren
Jinchang Ren
HZHuimin Zhao
Huimin Zhao
GSGenyun Sun
Genyun Sun
PMPaul Murray
Paul Murray
JZJiangbin Zheng
Jiangbin Zheng
In hyperspectral images (HSI), most feature extraction and data classification methods rely on corrected dataset, in which the noisy and water absorption bands are removed. This can result in not only extra working burden but also information loss from removed bands. To tackle these issues, in this article, we propose a novel spatial-spectral feature extraction framework, multiscale 2-D singular spectrum analysis (2-D-SSA) with principal component analysis (PCA) (2-D-MSSP), for noise-robust feature extraction and data classification of HSI. First, multiscale 2-D-SSA is applied to exploit the multiscale spatial features in each spectral band of HSI via extracting the varying trends within defined windows. Taking the extracted trend signals at each scale level as the input features, the PCA is employed to the spectral domain for dimensionality reduction and spatial-spectral feature extraction. The derived spatial-spectral features in each scale are separately classified and then fused at decision-level for efficacy. As our 2-D-MSSP method can extract features and simultaneously remove noise in both spatial and spectral domains, which ensures it to be noise-robust for classification of HSI, even the uncorrected dataset. Experiments on three publicly available datasets have fully validated the efficacy and robustness of the proposed approach, when benchmarked with 10 state-of-the-art classifiers, including six spatial-spectral methods and four deep learning classifiers. In addition, both quantitative and qualitative assessment has validated the efficacy of our approach in noise-robust classification of HSI even with limited training samples, especially in classifying uncorrected data without filtering noisy bands.