Pattern discovery and disentanglement on relational datasets

Abstract Machine Learning has made impressive advances in many applications akin to human cognition for discernment. However, success has been limited in the areas of relational datasets, particularly for data with low volume, imbalanced groups, and mislabeled cases, with outputs that typically lack...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Andrew K. C. Wong, Pei-Yuan Zhou, Zahid A. Butt
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/64083eccb74443dabb0c1fcdff51dc8b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:64083eccb74443dabb0c1fcdff51dc8b
record_format	dspace
spelling	oai:doaj.org-article:64083eccb74443dabb0c1fcdff51dc8b2021-12-02T13:20:04ZPattern discovery and disentanglement on relational datasets10.1038/s41598-021-84869-42045-2322https://doaj.org/article/64083eccb74443dabb0c1fcdff51dc8b2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-84869-4https://doaj.org/toc/2045-2322Abstract Machine Learning has made impressive advances in many applications akin to human cognition for discernment. However, success has been limited in the areas of relational datasets, particularly for data with low volume, imbalanced groups, and mislabeled cases, with outputs that typically lack transparency and interpretability. The difficulties arise from the subtle overlapping and entanglement of functional and statistical relations at the source level. Hence, we have developed Pattern Discovery and Disentanglement System (PDD), which is able to discover explicit patterns from the data with various sizes, imbalanced groups, and screen out anomalies. We present herein four case studies on biomedical datasets to substantiate the efficacy of PDD. It improves prediction accuracy and facilitates transparent interpretation of discovered knowledge in an explicit representation framework PDD Knowledge Base that links the sources, the patterns, and individual patients. Hence, PDD promises broad and ground-breaking applications in genomic and biomedical machine learning.Andrew K. C. WongPei-Yuan ZhouZahid A. ButtNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Andrew K. C. Wong Pei-Yuan Zhou Zahid A. Butt Pattern discovery and disentanglement on relational datasets
description	Abstract Machine Learning has made impressive advances in many applications akin to human cognition for discernment. However, success has been limited in the areas of relational datasets, particularly for data with low volume, imbalanced groups, and mislabeled cases, with outputs that typically lack transparency and interpretability. The difficulties arise from the subtle overlapping and entanglement of functional and statistical relations at the source level. Hence, we have developed Pattern Discovery and Disentanglement System (PDD), which is able to discover explicit patterns from the data with various sizes, imbalanced groups, and screen out anomalies. We present herein four case studies on biomedical datasets to substantiate the efficacy of PDD. It improves prediction accuracy and facilitates transparent interpretation of discovered knowledge in an explicit representation framework PDD Knowledge Base that links the sources, the patterns, and individual patients. Hence, PDD promises broad and ground-breaking applications in genomic and biomedical machine learning.
format	article
author	Andrew K. C. Wong Pei-Yuan Zhou Zahid A. Butt
author_facet	Andrew K. C. Wong Pei-Yuan Zhou Zahid A. Butt
author_sort	Andrew K. C. Wong
title	Pattern discovery and disentanglement on relational datasets
title_short	Pattern discovery and disentanglement on relational datasets
title_full	Pattern discovery and disentanglement on relational datasets
title_fullStr	Pattern discovery and disentanglement on relational datasets
title_full_unstemmed	Pattern discovery and disentanglement on relational datasets
title_sort	pattern discovery and disentanglement on relational datasets
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/64083eccb74443dabb0c1fcdff51dc8b
work_keys_str_mv	AT andrewkcwong patterndiscoveryanddisentanglementonrelationaldatasets AT peiyuanzhou patterndiscoveryanddisentanglementonrelationaldatasets AT zahidabutt patterndiscoveryanddisentanglementonrelationaldatasets
_version_	1718393215136038912

Pattern discovery and disentanglement on relational datasets

Ejemplares similares