“…For scientific visualisation, ParaView [1] and VTK [41] have been used to create high-quality large-volume isosurface, and flow data visualisation. While successful in medical and engineering applications, they do not facilitate the simple creation of information visualisations such as scatterplots, matrices, and trajectories.…”
Section: Immersive Applications and Visualisation Toolkitsmentioning
Figure 4: The rendering pipeline of IATK. Each stage represents a data transformation. Computational expensive stages, such as normalisation and animation, are performed on the GPU.
“…For scientific visualisation, ParaView [1] and VTK [41] have been used to create high-quality large-volume isosurface, and flow data visualisation. While successful in medical and engineering applications, they do not facilitate the simple creation of information visualisations such as scatterplots, matrices, and trajectories.…”
Section: Immersive Applications and Visualisation Toolkitsmentioning
Figure 4: The rendering pipeline of IATK. Each stage represents a data transformation. Computational expensive stages, such as normalisation and animation, are performed on the GPU.
“…The VTK library enables the creation of virtual and augmented reality environments. The developers themselves explain in the paper [19] which are the guidelines to follow in order to avoid problems in development. It is also a library widely used by the scientific community to visualise virtual reality simulations [20].…”
Anomaly detection is the identification of events or observations that deviate from the expected behaviour of a given set of data. Its main application is the prediction of possible technical failures. In particular, anomaly detection on supercomputers is a difficult problem to solve due to the large scale of the systems and the large number of components. Most research works in this field employ machine learning methods and regression models in a supervised fashion, which implies the need for a large amount of labelled data to train such systems. This work proposes the use of autoencoder models, allowing the problem to be approached with semi-supervised learning techniques. Two different model training approaches are compared. The former is a model trained with data from all the nodes of a supercomputer. In the latter approach, observing significant differences between nodes, one model is trained for each node. The results are analysed by evaluating the positive and negative aspects of each approach. On the other hand, a replica of the Marconi 100 supercomputer is developed in a virtual reality environment that allows the data from each node to be visualised at the same time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.