Dr. Ahmad Abdollahzadeh
Barforoush
Artificial Intelligent Systems
Laboratory
Dr. Ahmad Abdollahzadeh Barforoush is the
professor of Software Engineering and Artificial
Intelligent Systems. He joined Amirkabir university of
Technology in October -1991. He received his Ph.D.
in computer science from University of Bristol,
England, in 1990. He is currently serving, as a head
of software engineering group in Department of
Computer Engineering at Amirkabir University of
Technology.
Abbas
Rasoolzadegan
2007
Shiva
Vafadar
Formal specification
Analysis Patterns for Agent's
Intelligence Engineering
Mining Frequent Pattern in Large Active View Prediction, to Store
Databases Using divide and
Aggregated Data in order to
conquer approach
Efficient OLAP System
We are interested to research
about formal specification and its
open problems. It is generally
hoped that formal methods can
prove that a system satisfies its
requirements in a mathematically
rigorous way. If this is the goal,
there are two weak links in a chain
of inferences that threaten this aim:
1. The specification may not be
rigorous
enough
to
support
mathematical proof or may be too
incomplete to imply the desired
properties, 2. The implementation
may be too complicated or not
mathematical enough to allow a
proof that the specification is
satisfied.
In this research, I work on the field
of
Agent-Oriented
Software
Engineering (AOSE). Specifically,
I try to improve requirement
engineering of agent based
systems by introducing a new
concept;
"Intelligence
Engineering".
Intelligence
engineering adapts a requirements
engineering approach to elicit,
analysis, specify and validate
agent’s
intelligence.
This
intelligence engineering approach
helps us to benefit from the more
specific assumptions on structures
and capabilities expected for
agents as intelligent entities.
Frequent pattern mining is an
important data mining problem with
broad applications. It is challenging
since one may need to examine a
combinatorial explosive number of
possible patterns. This is a Time
and space consuming task with
exponential order. This thesis aims
to represent a good method to
compress the datasets and apply
its new efficient pattern mining
algorithms on the compressed
structure.
The
represented
algorithms use divide and conquer
approach to reduce the size of
datasets and mine them.
In this thesis, we research on
designing
and
modeling
aggregated
data
in
data
warehouses and present an
efficient technique based on data
mining techniques to calculate and
select proper views to materialize.
These views decrease query
response time and improve OLAP
systems. Our technique is dynamic
and depends on the type of online
analytical queries, their frequency,
view maintenance cost, query
response time, and available space
to store views.
Besat
Zardosht
2007
Elham
Moazzen
2007
Reza
Gorgan
Mohammadi,
2008
Ali
Rahnama
2008
A New Method of Machine
Translation Evaluation Using NGrams and Pos based on BLUE
Method
Using Aspect-Oriented
Approach in Evaluation and
Modeling of NFRs in Web-based
Systems Design
Requirements Engineering
Ontology Engineering
In every part of the science, it is
necessary to prove what you are
claiming with numbers. The
problem with language is that
language is not exact. Language
has some degree of vagueness,
which makes it hard in Natural
Language Processing to put
objective numbers to it. The central
idea is that the closer a machine
translation is to a professional
human translation, the better it is.
To check how close a candidate
translation is to a reference
translation, an n-gram comparison
is done between both translations.
In this research, We focus on the
design phase of AOSD which
stands
for
Aspect-Oriented
Software Development. AOSD
deals with crosscutting concerns
during all software development life
cycle. We have focused on the
explicit design of non-functional
requirements (NFRs) which are
mostly crosscutting concerns. We
investigate the use of aspectoriented techniques to model and
evaluate those NFRs in the design
of web-based systems which have
their own particular NFRs.
As a PhD student, I am currently
working to prepare my PhD
proposal. My research field of
interest is Software Requirements
Engineering. I received two BSc.
degrees in both software &
hardware
engineering
from
Amirkabir University of Technology
in 2006. I also got my MSc. in
Software Engineering from the
same university in 2008.
I am currently a PhD student
working on Ontology Engineering. I
have not revised my PhD proposal
yet but hope it will be ready soon. I
got my BSc in computer hardware
engineering from Shahid Bahonar
University in 1382. And I got my
MSc
in
computer
software
engineering from Sharif University
in 1384. Also I have been an
instructor at Shahid Bahonar
University since 1384.
2007
Mohammad
Karim Sohrabi
2005
Negin
Daneshpour
2004
Elham
Nikooie
2008
Agent-based human computer
interaction for visually disabled
people
The growth in Human-Computer
Interaction (HCI) field has not only
been in quality of interaction, it has
experienced different branching in
its history. Instead of designing
regular interfaces, the different
research branches have had
different focus on the concepts of
multimodality
rather
than
unimodality, intelligent adaptive
interfaces
rather
than
command/action based ones, and
finally active rather than passive
interfaces. In this research we want
to focus on visually impaired
people and after review the
existing systems for them, we will
model a system for interaction of
these peoples with computer
(based on visual, audio or haptic
methods) and finally we test our
suggested system with the others.
Sima
Salmani
2008
Sajjad
Zare
2008
Esmaeel
Rezaee
2007
Using Dynamic Ontologies for
Web Personalization
Mapping Business Process
Model to Formal Model
Student Modeling in Intelligent
Tutoring System.
In Semantic Web environment,
user access behavior models can
be shared as ontology. Ontology
has
become
an
important
component for Semantic Web, as it
allows the description of the
semantics
of
web
content.
However, majority of works have
focused on generating concept
hierarchy for building ontology from
text
documents.
Recently,
semantic web personalization has
become an active research area.
However, the current research
works create ontology manually
and are unable to deal with
temporal access behavior.
Researchers have tried to model
the business process using many
analytical tools, such as finite state
machine, process algebra, petri net
and many more. The aim of my
research is defining a formalism to
transform BPEL to Petri net, which
enables property verification. BPEL
is a language for describing the
behavior of business processes
based on web services. BPEL
lacks formal semantics as it has
been defined informally. We chose
Petri net as our analytical model
because of its powerful modeling
capability and its nice graphic
interface.
Intelligent Tutoring System use
methods for making educational
system more adaptive. Student
model is the most important feature
in ITS’s. By better model, we can
improve system’s adaptive ability
and students’ learning process. In
our approach we want to use
students’ experiences as their
model to help new students to
improving their learning process. In
this approach, we want to
recommend best study fragments
to
new
students.
In
this
recommendation we use data
mining techniques to discover the
best links for recommend. This
recommendation helps students to
achieve necessary knowledge as
soon as possible. In the other word
helps them to save time in
situations that choosing the best
sequence of resources is time
consuming.
Mostafa
Etemadian
2008
Indexing scientific, investigative
and applied reports with agent
Indexing text documents refers to
selecting
some
words
that
represent the content of a
document. The selected words are
referred to as index words. Manual
indexing of text documents is
considered to be a cumbersome
task in information retrieval. The
people who perform indexing are
usually well trained and have
reasonable linguistic background.
Manual indexing requires intensive
human effort, since it requires
people to read the whole document
before selecting the candidate
index words for that document.
Now, finding the keywords of a text
document is a challenge in
indexing text documents. Also, we
should pay attention to the
conceptual and semantic relation
between words and sentences. We
want to design and implement an
automatic indexing system to
perform this.