The world is increasingly being represented by data
Rich intelligence is there, ready to be discovered
Persistently monitoring and analysing information becomes increasingly difficult for humans as the duration, diversity and volume of data increases. Humans find it hard to maintain concentration for extended periods of time, to provide continuity between work-shifts, or to process big data streams and large varieties of data.
Cyberupt systems are designed to fulfill this role and allow the human to focus on that which is most interesting, most threatening or which specifically need human insight. Our systems augment human judgement by avoiding confirmation bias and potential under- or overreaction to events; attributes which are highly important for operations in complex environments.
Multi-source intelligence creation
Cyberupt systems uses multi-source enriched data which is fused to create a single view of the observed domain, virtual of physical. This enables real-time insight into behaviour, activities or transactions based on a broad range of inputs, over extended periods of time, persistently and with the ability to react immediately. Through the use of statistical modeling new observations can be tested against an expectation, which allows the discovery of patterns, anomalies, trends and developing threats. The system can automatically learn from observations to “understand” what is normal using Model-Based Machine Learning, so as to detect that which is unexpected or indicative of a threat, even in a potentially fluid environment. Contrary to learning methods used by other Artificial Intelligence approaches, Model-Based Machine Learning is well suited to the detection of rare events and anomalies.
Flexible, Scalable, Robust, Distributable
Information to the Right people, at the Right time, in the Right format
Data is ingested from any connected sensor and information source, which is then enriched and probabilistically fused to provide a comprehensive, mutidimensional view on the entity, transation or event being observed. Human input (HUMINT) is incorporated where available to further enrich information, add new information or to aid classification or ranking. Statistical modelling and Model-based Machine Learning services use this fused data to discover intelligence, which is then in turn made available to the user at the edge.
The System comprises of an Info-Structure which uses interconnected Data Centres as building blocks. The Data Centres are located in the most convenient location for access to sensors, information sources and tools for intelligence creation. The system uses a Service Oriented Architecture (SOA) which enables seamless extension with new services and information sources and to scale from small to very large deployments. The Data Centres are connected using robust, encrypted links and data is transparently made available across the entire network, enabling users to connect to the most convenient node while accessing any information they need. The information is presented on the desired user device or geospatial platform, to the dismounted person, in connected vehicles or aircraft and in operations centres.
Solutions in many domains
Cyberupt BV is wholly based in The Netherlands and provides solutions for UN recognised government agencies around the world.
Our engineers and data scientists has an extensive track record in the development of own technology and products. Our skills include the mining of massive data sets, machine learning, natural language processing and the design, development and deployment of very large distributed systems.
Cyberupt has an operating philosophy of partnering with its customers and key suppliers to maximise operational benefits of its systems.