AAU - Aalborg University
Aalborg University offers education and research within the fields of natural sciences, social sciences, humanities, technical and health sciences. AAU will contribute to the methodological developments in the project. This includes establishing procedures for requirements analysis as well as formal methods for testing and evaluating the developed models.
Furthermore, AAU will provide expertise with regards to the development of the inference and learning components in the AMIDST framework, and will put particular focus on instantiating the framework in relation to oil drilling domains.
On top of the research commitments, AAU will also be responsible for the scientific as well as the general management of the project and general IPR management. Aalborg University will be the project coordinator of the consortium.

UAL - Universidad de Almería
The University of Almeria (UAL) was founded in 1993. Today it has more than 12000 students, including 600 doctorate students. The UAL group contributes to the project through the tasks related to approximate inference, including the specially complex case of the MAP problem, inference and learning in hybrid domains, and classification. It will also be the responsible of the development of the software prototype for risk prediction in credit operations.

HUGIN is a Danish SME established in 1989. The company is a leading provider of tools and services for advanced decision support based on complex statistical models known as probabilistic graphical models (i.e., Bayesian networks and influence diagrams).
HUGIN will contribute to the methodological and software developments in AMIDST. This includes scaling up existing algorithms and implementations for structure learning as well as implementing methods for approximate inference and adaptation in dynamic Bayesian networks. HUGIN is involved in the development of software prototypes for risk prediction in credit operations and recognition of maneuvers in highway traffic situations. HUGIN will also have the role of RTD manager and deputy coordinator of the consortium.

NTNU - Norwegian University of Science and Technology
NTNU is Norway's second largest university with 20.000 students and 51 departments spread out over 7 major campuses. NTNU will contribute towards solving all the methodological challenges in the project, supplying expertise on both inference and learning in probabilistic graphical models. Additionally, NTNU will put particular effort into utilizing the developed methods and framework for pattern recognition in drilling logs.


Daimler AG
Daimler is one of the biggest producers of premium cars and the world’s biggest manufacturer of commercial vehicles with a global reach. As end-user of the project technologies, Daimler will be in charge of providing the real traffic data for test of the developed tools and algorithms. In addition, Daimler will specify the requirements for the automotive use case. The use case is concerned with the recognition of maneuvers in real highway traffic situations, e.g. lane change, cut-in, cut-out, follow maneuvers. The requirements involve, e.g. improvement of memory and time performance of the maneuver recognition, and ensuring earlier predictions and better accuracy. Throughout the project, Daimler will focus on the development and implementation of a software system, based on the principles of dynamic models for recognition of maneuvers.
Additionally, due to the experience of the involved R&D situation analysis team of Daimler AG, critical issues of the implementation will be evaluated with respect to the defined requirements on software application, which operates on a platform with severe constraints on memory and computation time. The prototype will be rigorously tested on realistically complex streaming data.

Verdande Technology
Verdande Technology provides real-time decision management and predictive analytics to enable organizations to minimize risk and make better, faster decisions by turning their data into actionable intelligence. The company’s VTEdge platform is powered by Case-Based Reasoning (CBR) and is based on the principle that similar problems have similar solutions. A continuously learning system, Verdande’s analytics solution maximizes big data performance by identifying, capturing and analyzing patterns in risk and operational data in real time. It uses past events to proactively predict future problems, rapidly diagnose and correct issues to drive business growth and efficiencies.
Verdande Technology AS provides one of the three data sets used in the AMIDST project, and will be a key player in the investigation and testing of this dataset. Further, Verdande Technology AS will also contribute problem-driven research in particular related to quantification and measurements of the quality of the developed framework.


Banco de Crédito Social Cooperativo S.A.
BCC acts as the head of the Cooperative Group Cajamar, which has in Spain more than 1,300 branches and 6,500 employees and is the leading rural savings bank and credit union in Spain. BCC will be responsible of testing AMIDST solution for risk prediction and assessment.  The quality of the developed framework will be checked in a realistically complex data set with massive amounts of information that current techniques cannot deal with.
BCC provides one of the three data sets used in the AMIDST project, and will be a key player in the investigation and testing of this dataset. They will also contribute to problem-driven research in particular related to quantification and measurements of the quality of the developed framework. BCC will use the final results to improve its risk assessment methods for retail clients, minimizing potential losses due to credit risk.



This website uses cookies. Cookies are only used for handling login and identifying registrered users, not for visitor tracking.