The promises of Big Data very often come with the disillusion that, while data from multiple sources is increasingly easy to access, it is hard to formulate the adequate questions to be asked against that data. Additionally, data integration at very large scale is costly, so decisions to integrate need to be well informed. Which data from which components of an engineering asset needs to be taken into account when tracing down an error to its source? Which situation in a complex interconnected ecosystem may occur in the future that causes critical problems? To find the answers to such questions, by taking into account the adequate selection from vast amounts of dynamically growing and changing data sources is hard.
Transcendental Information Cascades have been proposed as an innovative method for exploratory data analysis that addresses such cases. Based on the concept of tracing the co-occurrence of information patterns in joined data streams from multiple sources, it allows to detect activity bursts that indicate complex underlying events, which are hidden when looking at all data individually or when drawing the wrong samples.
The RECOIN project will develop scalable algorithms and investigate use cases, for which data at significant scale is already available and which allow demonstrating the potential of the approach to reduce risks and enhance security in scenarios of greater societal impact. Further use cases will be developed as additional data becomes available as a result of the dissemination and outreach activities of the RECOIN project.
Principal investigator (PI)
Dr Markus Luczak-Roesch is a senior research fellow at the Web and Internet Science Group (WAIS) at the University of Southampton, Electronics and Computer Science (ECS), currently working on the prestigious EPSRC-funded project SOCIAM – The Theory and Practice of Social Machines (http://sociam.org). SOCIAM researches into pioneering methods of supporting purposeful human interaction on the World Wide Web, of the kind exemplified by phenomena such as Wikipedia and Galaxy Zoo. These collaborations are empowering, as communities identify and solve their own problems, harnessing their commitment, local knowledge and embedded skills, without having to rely on remote experts or governments. In this context Markus works on analyzing citizen science platforms as well as information-centric theories of Social Machines. His research is generally focused on macro- and micro-scale information architectures. This encompasses information systems, their users, and the data, which is either managed for any particular application purpose or results from various forms of interactions. At the core of this work stands the investigation of the natural flow of information on the World Wide Web that results from coincidental information sharing activities of individuals.
Markus Luczak-Roesch obtained his doctoral degree at Freie Universität Berlin where he held a lecturer position. He published peer-reviewed articles and papers in the area of intelligent information systems, social media analysis and mining, and information theory. Recently, Markus was one of the principal investigators (together with Dr. Silke Roth, University of Southampton) of the project INCROWD – Inclusiveness in Crowdsourced Disaster Management, which was funded under the ESRC/NERC/DFID Big Data for resilience call in 2015.
Dr Ramine Tinati is a Research Fellow in the Web and Internet Science group at the University of Southampton working on the SOCIAM project. His work in the project involves the investigation of methods and analytics to understand the development and connectivity of the Web and the exploration of metrics to measure different forms of community-driven social machines, such as the popular citizen science project, Zooniverse, and the collective-knowledge platform, Wikipedia.
Ramine Tinati has also performed research the diffusion of information in the context of social networking services, and has been involved in the development of methods for identifying inter- and cross-system information cascades. Ramine has worked with industry partners to develop new methods for identifying and classifying different categories of entities in real-time. He is part of the development team responsible for the Web Observatory, working on developing the necessary infrastructure to support real-time Big Data stream processing and querying. Ramine Holds a PhD in Web Science from the University of Southampton, an MSc in Web Science, and a BSc (Hons) in Computer Science.
Dr Markus Luczak-Roesch
Senior Research Fellow
Department of Electronics and Computer Science
University of Southampton
Highfield Campus, Building 32, Room 3001
Southampton, SO17 1BJ
The RECOIN project is funded by the Lloyd’s Register Foundation.