S
Stephen Marshall
Researcher at University of Strathclyde
Publications - 240
Citations - 5657
Stephen Marshall is an academic researcher from University of Strathclyde. The author has contributed to research in topics: Hyperspectral imaging & Image processing. The author has an hindex of 36, co-authored 222 publications receiving 4358 citations.
Papers
More filters
Posted Content
Activation Functions: Comparison of trends in Practice and Research for Deep Learning
TL;DR: This paper will be the first, to compile the trends in AF applications in practice against the research results from literature, found in deep learning research to date.
Journal ArticleDOI
Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging
Jaime Zabalza,Jinchang Ren,Jiangbin Zheng,Huimin Zhao,Chunmei Qing,Zhijing Yang,Peijun Du,Stephen Marshall +7 more
TL;DR: Segmented SAE (S-SAE) is proposed by confronting the original features into smaller data segments, which are separately processed by different smaller SAEs, which has resulted in reduced complexity but improved efficacy of data abstraction and accuracy of data classification.
Journal ArticleDOI
Biocatalytic induction of supramolecular order
Andrew R. Hirst,Sangita Roy,Meenakshi Arora,Apurba K. Das,Nigel Hodson,Paul Murray,Stephen Marshall,Nadeem Javid,Jan Sefcik,Job Boekhoven,Jan H. van Esch,Stefano Santabarbara,Stefano Santabarbara,Neil T. Hunt,Rein V. Ulijn +14 more
TL;DR: By combining biocatalysis and molecular self-assembly, supramolecular gels have shown the ability to more quickly access higher-ordered structures by simply increasing enzyme concentration, and gels that assembled faster showed fewer defects.
Journal ArticleDOI
Breast cancer detection using deep convolutional neural networks and support vector machines
TL;DR: A new methodology for classifying breast cancer using deep learning and some segmentation techniques are introduced and the highest area under the curve (AUC) achieved was 0.88, which is the highest AUC value compared to previous work using the same conditions.
Journal ArticleDOI
Novel Folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensing
TL;DR: Comprehensive results have indicated that the proposed Folded-PCA approach not only outperforms the conventional PCA but also the baseline approach where the whole feature sets are used.