Advanced Reasoning Group


Advanced Reasoning Group


Advanced Reasoning

The Advanced Reasoning Group (ARG) aims to conduct innovative research in qualitative and approximative reasoning, including methods of knowledge representation, model generation and refinement, and model-based problem solving.

The ARG has an excellent track record of developing the scientific foundations necessary for building intelligent decision support systems, especially in crime detection and prevention, engineering design analysis, and computer-based diagnosis. In particular, the group is well known for its ground-breaking work on automated diagnostic and failure analysis for circuit design in the automotive industry, and it invention of fuzzy-rough semantics-preserving techniques for explicit knowledge model formulation and simplification. The group's research also includes other advanced computational intelligent techniques, e.g. evolutionary algorithms and meta-heuristics.

Research Topics

  • Multiple failure FMEA and sneak circuit analysis
  • Mode-based whole lifecycle automated system analysis
  • Qualitative model-based learning
  • Knowledge extraction over high dimensional data sets
  • Compositional modeling and preference handling.

Applications of the above techniques are wide-reaching, ranging from laboratory demonstrations (e.g. Metabolic pathway identification and simulation, and crime scenario construction and investigation) to commercial productions (e.g. automotive and aeronautical fault diagnosis, and consumer sensitive data analysis).

Recent Submissions

  • MacParthaláin, Neil Seosamh; Shen, Qiang; Jensen, Richard (2006-09-04)
    Feature Selection (FS) methods based on fuzzy-rough set theory (FRFS) have employed the dependency function to guide the FS process with much success. More recently a method has been developed which uses fuzzy-entropy ...
  • MacParthaláin, Neil Seosamh; Jensen, Richard; Shen, Qiang (2008-06-01)
    Dataset dimensionality is undoubtedly the single most significant obstacle which exasperates any attempt to apply effective computational intelligence techniques to problem domains. In order to address this problem a ...
  • MacParthaláin, Neil Seosamh; Jensen, Richard; Shen, Qiang (2006-07-26)
    Feature Selection (FS) is a dimensionality reduction technique that aims to select a subset of the original features of a dataset which offer the most useful information. The benefits of feature selection include improved ...
  • Shen, Qiang; MacParthaláin, Neil Seosamh; Jensen, Richard (2008-09-10)
    The accuracy of methods for the detection of mammographic abnormaility is heavily related to breast tissue characteristics. A breast with high tissue density will have reduced sensitivity in terms of detection. Also, breast ...
  • Snooke, Neal; Price, Chris (1997-06-03)
    Qualitative reasoning about electrical systems has reached a level of achievement which allows it to be used for applications on realistic automotive circuits. The type of circuits for which it is most effective can be ...

Search Cadair

Advanced Search


My Account

RSS Feeds