Themenangebote

Anforderungen an Abschlussarbeiten

Die Anforderungen an Abschlussarbeiten sind für alle studentischen Ausarbeitungen (d.h. Abschlussarbeiten, Projektseminararbeiten, Seminararbeiten, etc.) an unserem Lehrstuhl verbindlich und MÜSSEN eingehalten werden! Etwaige Abweichungen MÜSSEN mit dem Betreuer der Arbeit abgesprochen werden! Nicht-abgesprochene Abweichungen von den Anforderungen an studentischen Ausarbeitungen führen in der Regel zu einer Bewertung der Arbeit mit "nicht ausreichend".

Bitte beachten Sie unbedingt die folgenden

Hinweise zu unseren Lehrveranstaltungen
(Moodle-Login erforderlich; ggf. als Gast)!

Concept and Design of a Learning/Teaching Component for Disease Specialists Agents in a Holonic Medical Diagnostic System

Art der Arbeit:
  • Masterarbeit Informatik
  • Diplomarbeit Informatik
Status:
Themenangebot
Ansprechpartner:

Kurzfassung

At the University Duisburg-Essen, a holonic medical diagnostic system based on multi-agents technology  and swarm intelligence is developed through the last years.
The system combines the advantages of the holonic paradigm, multi-agent technologies and swarm intelligence in building a highly adaptive, scalable, flexible, reliable and robust Internet-based medical diagnostic system.
The medical diagnostic system is compound of three type of agents: a mediator agent, many diagnosis specialist agents and disease representative agents.
The mediator agent represents the diagnostic system interface to the diagnosis requester and to the physician/specialist evaluator. Several diagnosis specialist agents are becoming part of the ad-hoc holonic structure in order to provide a suitable diagnostic. The disease representative agents are related to each defined disease that can be a diagnosis result. A disease representative agent determines if a set of symptoms matches its own symptom pattern. 
In diagnosis retrieval process, the agents follow a specific swarm intelligence method to build a holonic structure that provides one or more possible diagnostics. Each diagnostic returned by the system has a probability to match the true diagnostic that, in common way, is determined by the physician. The diagnosis specialist agent of a certain level is forwarding the symptoms description data as computer readable patient pattern to other diagnosis specialist agents of a lower level in order to receive from them later on a diagnostic that can satisfy the symptoms constraints. Any 
diagnosis specialist agent encapsulates a learning/teaching component and a disease specific component that are determining the agent capability to adapt or to adopt a new disease as representative.
This thesis has to contribute to the diagnosis specialist agent development by introducing the design and implementation of a learning/teaching component and of a disease specific module required by such an agent.
The following milestones have to be reached by the thesis:
1.
Realization of a Learning Component for acquiring of new disease data from another agent or from a special system;
2.
Realization of a Teaching Component for publishing of description data for actual disease that the diagnosis specialist agent contains.
3.
Implementation of a Disease Specific Component to operate with standard format of the disease data and with operations that the disease specialist agent can perform on that data; standardization of the disease data has to be handled;

For implementation, one of the most common object oriented programming languages,   Java and C++ have to be used.