Artificial Intelligence

AI Research has many applications in the real world; from medical diagnosis to expert advices.

An AI system is a knowledge-based system in which knowledge domains are represented and reasoned with. Agent-based systems are systems in which components, called 'agents', reason autonomously with their knowledge and take their own decisions to act, they

ATIA systems

ATIA is developing a system that is knowledge-based and agent-based for applications in, among others, the medical domain. ATIA aims at designing advanced knowledge-based systems that support the use of heterogeneous knowledge sources in which computational and logical reasoning methods are integrated.

This knowledge has to be described explicitly in a format accessible to computers. The facts and the relationships between these facts, the structure of the facts and relations will need to be captured in a formalized manner so that algorithms will have access to the information in this knowledge.
Thus, the domain knowledge will be used to compute new relationships or infer missing or inconsistent "facts". Protégé software has been used by the ATIA developers to construct domain models and knowledge-based applications; Protégé is an open-source platform which implements knowledge-modeling structures and actions that supports the creation, visualization, and manipulation of ontology’s in various representation formats.
Basic structures will have to be defined allowing the integration and/or linking of several domains, and to make it possible to combine different information in a unified and consistent manner.

Heterogeneity

Attention should be given to the aspect of heterogeneity, as well. As the agents may use their own knowledge representation (ontology) and reasoning method, the overall architecture of the HeMAS should be able to connect various different agents in a convenient way. To this end it seems reasonable to design a uniform interface to communicate with the agents.

The main objective of the knowledge representation facet is that this knowledge is described explicitly, yet domain experts will remain in control of the knowledge, i.e. the human experts have the overview of the correctness of it. At least two dimensions can be distinguished: the amount of knowledge to be represented, and the human experts' ability to overview the knowledge.

Applications

AI research at ATIA has many applications, from medical diagnosis to expert advice.
It is an explicit goal for ATIA to work with partners to realize these applications in the real world. For instance, ATIA offers services in wich its tools and expertise are used to analyze medical data sets in order to discover hidden patterns. Other applications involve the use of ATIA components to build intelligent systems.

from 2010 - 2013, ATIA has been participating in a collaborative research program on Individual Differences by ATIA and the Spinoza Centre, University of Amsterdam. This project aims at predicting individual differences in mental, cognitive and affective capacities from the anatomy and functioning of brain systems. From these data,  ATIA is developing decision support systems in the assessment of talents and mental reserve in patient groups. With respect to talented people one might think of employees of all kind like athletes and musicians.

Assessment and utilization of reserve capacities will be helpfull for:

  • patients affected by brain diseases like tumors

  • dementia patients

  • patients with depression. 

Finally, this project will contribute knowledge to the specific programs on obesity and female sexual dysfunction at ATIA.





© 2015 Alan Turing Institute Almere