Reliable data quality monitoring is a key asset in delivering collision data suitable for physics analysis in any modern large-scale High Energy Physics experiment. This paper focuses on the use of artificial neural networks for supervised and semi-supervised problems related to the identification of anomalies in the data collected by the CMS muon detectors. We use deep neural networks to analyze LHC collision data, represented as images organized geographically. We train a classifier capable of detecting the known anomalous behaviors with unprecedented efficiency and explore the usage of convolutional autoencoders to extend anomaly detection capabilities to unforeseen failure modes. A generalization of this strategy could pave the way to the automation of the data quality assessment process for present and future high-energy physics experiments.

OATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible. Abstract: Big Data is "things that one can do at a large scale that cannot be done at a small one". Analyzing flows of news events that happen worldwide falls in the scope of Big Data. Twitter has emerged as a valuable source of information where users post their thoughts on news events at a huge scale. At the same time traditional media channels also produce huge amount of data. This paper presents means to compare the propagation of the same news topic through Twitter and news articles, both important yet varied sources. We present visual means based on maps to make it possible to visualize the flow of information at different level of temporal granularity. We also provide an example and how the flow can be interpreted.

No abstract

No abstract