Editorial The 17 Artificial Intelligence and Cognitive Science Conference (AICS-06)

bigskymanΤεχνίτη Νοημοσύνη και Ρομποτική

24 Οκτ 2013 (πριν από 3 χρόνια και 7 μήνες)

57 εμφανίσεις


The 17

Artificial Intelligence and Cognitive Science Conference

This special issue of AI Review

is devoted to papers selected from those presented at
the 17

Irish Conference on Artificial Intelligence and Cognitive Science (AICS
hosted by the School of Electronics, Electrical Engineering and Computer Science,
Queen’s University Belfast, Northern Ireland.

The AICS Conference is Ireland’s
foremost gathering of minds for those involved in the fields of Artificial Intelligence
nd Cognitive Science. The conference


taken place (almost a
nnually) since
1988 and provide

a forum for the exchange of ideas and the presentation of results
relating to research conducted both in Ireland and worldwide. AICS conferences
support the pre
sentation and discussion of original research in the areas of Artificial
Intelligence, Cognitive Science and related disciplines. In recent years papers have
been presented in the areas of: Genetic Algorithms, Connectionist Models, Case
Based Reasoning, In
formation Retrieval, Learning, Robotics, Planning and
Scheduling, Natural Language Processing and Cognitive Linguistics.

This year
authors were invited to submit extended and
enhanced versions of their papers for consideration
for incl
usion in this

special issue.

The initial selection was made on
the basis of the original reviewers’ comments and
feedback fr
om the conference.

a second
review process
resulted in
the identification of
the papers that appe
ar in this issue
eleven papers selected for
publication are introduced below. They cover a broad range of topics and were
selected on the bas
is of quality of research

in terms of
contribution to the subject


papers discuss research in the area o
f Information R
and O’Riordan

describe an attempt to improve information retrieval. They propose a
system based on the development of user profiles. An approach is described that
attempts to learn a user’s short term interests. At the first query a profi
le is created
which is modified during all subsequent queries. The system will then use this profile
in an attempt to improve
all future queries.
Lillis et al.


the application of their

algorithm to a large document collection.


a data fusion
algorithm that uses the history of underlying information retrieval algorithms to
estimate the probability of result sets containing relevant documents in particular
positions. They demonstrate that their approach outperforms the common Comb

Cummins and O’Riordan

consider the problems associated with the use of
genetic programming based solutions within information retrieval. In particular they
consider the problem of analyzing the solutions produced by this non
ocess. They introduce two different distance measures which are used to show how
solutions are distributed within a given solution space.

The area of Machine Learning is represented through two contributions.
Horgan and Cummins

compare and contrast two co
mputational models of dopamine
activity in the brain. Both models employ reinforcement learning using the method of
emporal differences. They

note that to deal with problems in earlier models both new
approaches employ ‘internal models’ which differ in th
e degree to which they
implement prop
erties of the environment. Nugent et al. describe

a framework that
applies flexible machine vision techniques to microscope analysis. Their system
utilizes active learning to help overcome data acquisition and adaptabil
ity problems.
The value of their framework is investigated by its application to a real world
problem, the recognition of parasite eggs.

The next two papers concentrate on the area of Case
Based Reasoning. Delan
and Bridge

consider the problem of filterin
g spam e
mails. They describe the ECUE
system which classifies e
mails using a fea
ture based form of textual case
reasoning. Then they describe an alternative classification model that computes the
distance between cases in a feature free manner. Bot
h systems are evaluated and
mechanisms to improve the classification time are considered. Hassan et al. consider
the topic of self
healing within autonomic computing. They present an approach to
self healing, informed by environment knowledge, base
d on the

use of case

and rule based reasoning. Case
based reasoning is used in fault diagnosis
and rule based reasoning as the base for fault remediation, recovery and repair.

The area of

Reasoning is represented through two pieces of work.

consider problems associated with multi
agent systems where the
objective is to build robust intelligent systems capable of existing in complex


note that such systems are often characterized as being uncertain
and open to c
hange partly as a result of agents being able to enter and le
ave the
system freely. They examine

this form of population change in a game theoretic

Qi et al. address

the problems associated with handling inconsistencies in
description logi
cs. They

introduce new revision operators for description logics and
demonstrate an algorithm for handling inconsistency in a stratified description logic
knowledge base.

Finally, t
wo papers discuss work in the field of Cognitive Science.
and O’Donoghue

describe an instance
based reasoning solution to a variety of spatial
reasoning problems. The solution centres on identifying an isomorphic mapping
between labelled graphs that represent some problem data and a know
n solution
instance. They

present results

derived from the application of their algorithm to
different categories of spatial reasoning tasks from the domain of geographical
information science. Jackson e
t al.

present the results of a study into the potential
interaction between those brain region
s involved in the control and execution of
movement and those regions activated during the perception of another’s movements.
In particular, the

study set out to determine which aspects of the observed motion
are crucial to this interference effect.

hope that the papers presented in this special issue will prove to be
informative and useful to a wide reader audience. In addition, we hope that the


will create interest in the work of
the Artificial Intelligence Association of

(AIAI) and

encourage readers to join in the

of AIAI and

to submit

to a forthcoming AICS conference.

Finally, we would like to thank the anonymous reviewers for their help
reviewing these papers

the Springer Desk Editor,

Fiona Routley, the Spring
Computer Science Editor, Ronan Nugent and Professor Paul Mc

Kevitt, AI Review
Chief, for their help and advice in preparing this publication.

David Bell, Peter Milligan

and Paul Sage


{da.bell, p.milligan,


School of

, Electrical Engineering

and Computer Science

Queen’s University Belfast
, Northern Ireland