Informatica Economica Vol. 15 No. 1/2011
Issue Topic: Genetic Algorithms
Issue Editor: Adrian VISOIU, PhD
CONTENTS
An Overview of Vertical Handoff Decision Algorithms in NGWNs and a new
Scheme for Providing Optimized Performance in Heterogeneous Wireless
Networks
Ionut BOSOANCA, Anca VARGATU 5
Because the increasingly development and use of wireless networks and
mobile technologies, was implemented the idea that users of mobile
terminals must have access in different wireless networks simultaneously.
Therefore one of the main interest points of Next Generation Wireless
Networks (NGWNs), refers to the ability to support wireless network access
equipment to ensure a high rate of services between different wireless
networks. To solve these problems it was necessary to have decision
algorithms to decide for each user of mobile terminal, which is the best
network at some point, for a service or a specific application that the
user needs. Therefore to make these things, different algorithms use the
vertical handoff technique. Below are presented a series of algorithms
based on vertical handoff technique with a classification of the different
existing vertical handoff decision strategies, which tries to solve these
issues of wireless network selection at a given time for a specific
application of an user. Based on our synthesis on vertical handoff
decision strategies given below, we build our strategy based on solutions
presented below, taking the most interesting aspect of each one.
Keywords: Vertical Handoff, Genetic Algorithms, Fuzzy Logic, Neural
Networks, AHP
Deriving Trading Rules Using Gene Expression Programming
Adrian VISOIU 22
This paper presents how buy and sell trading rules are generated
using gene expression programming with special setup. Market concepts
are presented and market analysis is discussed with emphasis on
technical analysis and quantitative methods. The use of genetic
algorithms in deriving trading rules is presented. Gene expression
programming is applied in a form where multiple types of operators and
operands are used. This gives birth to multiple gene contexts and
references between genes in order to keep the linear structure of the
gene expression programming chromosome. The setup of multiple gene
contexts is presented. The case study shows how to use the proposed gene
setup to derive trading rules encoded by Boolean expressions, using a
dataset with the reference exchange rates between the Euro and the
Romanian leu. The conclusions highlight the positive results obtained in
deriving useful trading rules.
Keywords: Gene Expression Programming, Trading Rules, Genetic
Algorithms, Exchange Rate
A Genetic Programming Approach to Geometrical Digital Content Modeling in
Web Oriented Applications
Dragos PALAGHITA 31
The paper presents the advantages of using genetic techniques in web
oriented problems. The specific area of genetic programming applications
that paper approaches is content modeling. The analyzed digital content
is formed through the accumulation of targeted geometrical structured
entities that have specific characteristics and behavior. The
accumulated digital content is analyzed and specific features are
extracted in order to develop an analysis system through the use of
genetic programming. An experiment is presented which evolves a model
based on specific features of each geometrical structured entity in the
digital content base. The results show promising expectations with a low
error rate which provides fair approximations related to analyzed
geometrical structured entities.
Keywords: Genetic Algorithm, Genetic Programming, Fitness,
Geometrical Structured Entities, Analysis
Application of Particle Swarm Optimization to Formative E-Assessment in Project Management
Maria-Iuliana DASCALU 48
The current paper describes the application of Particle Swarm
Optimization algorithm to the formative e-assessment problem in project
management. The proposed approach resolves the issue of personalization,
by taking into account, when selecting the item tests in an
e-assessment, the following elements: the ability level of the user, the
targeted difficulty of the test and the learning objectives, represented
by project management concepts which have to be checked. The
e-assessment tool in which the Particle Swarm Optimization algorithm is
integrated is also presented. Experimental results and comparison with
other algorithms used in item tests selection prove the suitability of
the proposed approach to the formative e-assessment domain. The study is
presented in the framework of other evolutionary and genetic algorithms
applied in e-education.
Keywords: Particle Swarm Optimization, Genetic Algorithms,
Evolutionary Algorithms, Formative E-assessment, E-education
Public Transport Route Finding Using a Hybrid Genetic Algorithm
Liviu COTFAS, Andreea DIOSTEANU 62
In this paper we present a public transport route finding solution based
on a hybrid genetic algorithm. The algorithm uses two heuristics that take
into consideration the number of trans-fers and the remaining distance to
the destination station in order to improve the convergence speed. The
interface of the system uses the latest web technologies to offer both
portability and advanced functionality. The approach has been evaluated
using the data for the Bucharest public transport network.
Keywords: Route Finding, Evolutionary Algorithms, Hybrid Genetic
Algorithm
Using Genetic Algorithms in Secured Business Intelligence Mobile
Applications
Silvia TRIF 69
The paper aims to assess the use of genetic algorithms for training
neural networks used in secured Business Intelligence Mobile
Applications. A comparison is made between classic back-propagation
method and a genetic algorithm based training. The design of these
algorithms is presented. A comparative study is realized for determining
the better way of training neural networks, from the point of view of
time and memory usage. The results show that genetic algorithms based
training offer better performance and memory usage than back-propagation
and they are fit to be implemented on mobile devices.
Keywords: Genetic Algorithm, Mobile Applications,
Back-propagation, Business Intelligence, Security
Using Genetic Algorithms for Building Metrics of Collaborative Systems
Cristian CIUREA 80
The paper objective is to reveal the importance of genetic algorithms
in building robust metrics of collaborative systems. The main types of
collaborative systems in economy are presented and some characteristics
of genetic algorithms are described. A genetic algorithm was implemented
in order to determine the local maximum and minimum points of the
relative complexity function associated to a collaborative banking
system. The intelligent collaborative systems based on genetic
algorithms, representing the new generation of collaborative systems,
are analyzed and the implementation of auto-adaptive interfaces in a
banking application is described.
Keywords: Collaborative Systems, Genetic Algorithms, Metrics,
Banking, Auto-Adaptive Interfaces
Emergent Frameworks for Decision Support Systems
Ioana Andreea STANESCU, Florin Gheorghe FILIP 92
Knowledge is generated and accessed from heterogeneous spaces. The
recent advances in in-formation technologies provide enhanced tools for
improving the efficiency of knowledge-based decision support systems.
The purpose of this paper is to present the frameworks for developing
the optimal blend of technologies required in order to better the
knowledge acquisition and reuse in large scale decision making
environments. The authors present a case study in the field of clinical
decision support systems based on emerging technologies. They consider
the changes generated by the upraising social technologies and the
challenges brought by the interactive knowledge building within vast
online communities.
Keywords: Knowledge Acquisition, CDDSS, 2D Barcodes, Mobile
Interface
A Process for Engineer Domain Ontology: An Experience in Developing Business Analysis Ontology
Irena ATANASOVA 104
During the last years several works have been aimed to improve
ontology technological as-pects, like representation language and
inference mechanisms. This paper presents a discussion on the process
and product of an experience in developing ontology for the public
sector whose organization requires a strong knowledge management. This
process is applied to engineer and develop ontology for Business
analysis domain.
Keywords: Ontology, Ontology Engineering, Methodology, Protégé,
Business Analysis
Testing the Application for Analyzing Structured Entities
Ion IVAN, Bogdan VINTILA 114
The paper presents the testing process of the application for the
analysis of structured text entities. The structured entities are
presented. Quality characteristics of structured entities are identified
and analyzed. The design and building processes are presented. Rules for
building structured entities are described. The steps of building the
application for the analysis of structured text entities are presented.
The objective of the testing process is defined. Ways of testing the
application on components and as a whole are established. A testing
strategy for different objectives is proposed. The behavior of users
during the testing period is analyzed. Statistical analysis regarding
the behavior of users in processes of infinite resources access are
realized.
Keywords: Structured Entity, Application, Analysis, Testing,
Metrics
Techniques for Representation of Regional Clusters in Geographical Information Systems
Adriana REVEIU 129
This paper provides an overview of visualization techniques adapted
for regional clusters presentation in Geographic Information Systems.
Clusters are groups of companies and insti-tutions co-located in a
specific geographic region and linked by interdependencies in providing
a related group of products and services. The regional clusters can be
visualized by projecting the data into two-dimensional space or using
parallel coordinates. Cluster membership is usually represented by
different colours or by dividing clusters into several panels of a
grille display. Taking into consideration regional clusters requirements
and the multilevel administrative division of the Romania’s territory, I
used two cartograms: NUTS2- regions and NUTS3- counties, to illustrate
the tools for regional clusters representation.
Keywords: Geographic Information Systems, Regional Clusters,
Spatial Statistics, Geographic Data Visualisation
A Bluetooth Solution for Public Information Systems
Nicolae Radu MARSANU, Radu Gabriel CIOBANU 140
This paper gives insights into the opportunities offered by the
Bluetooth technology. Bluetooth advertising proves to be a cheap and
strong tool for enriching and improving the experience offered by a
public transport system, by delivering dense and essential information
about topics of interest. Alongside the Java platform, new applications
can be designed and implemented to make use of the already available
Bluetooth technology incorporated in devices in the target public’s
custody. The paper sets focus on the segment of ready to be made
available content regarding general information about the routes and
timetables of the vehicles integrated in a public transport system.
Keywords: Public Transport, Bluetooth, Java, Mobile Device
Practical Methods for Information Security Risk Management
Cristian AMANCEI 151
The purpose of this paper is to present some directions to perform
the risk man-agement for information security. The article follows to
practical methods through question-naire that asses the internal
control, and through evaluation based on existing controls as part of
vulnerability assessment. The methods presented contains all the key
elements that concurs in risk management, through the elements proposed
for evaluation questionnaire, list of threats, resource classification
and evaluation, correlation between risks and controls and residual risk
computation.
Keywords: Risk Management, Threats, Vulnerabilities, Information
Security
IT Solution for Security Management in the Cadastral Field
Emanuil REDNIC 160
There are presented the particularities of cadastral system which
should be reflected in the software development. It is shown as well the
design of the cadastral software application. The online solution for
the security management in the cadastral field, it is projected in this
way to accomplish all the requirements. Another step is to identify the
risks and vulnerability for the future processes, which gather all the
functionality of the security system. It will be determined all the
functions and new functionalities of the security management solution
for the cadastral system. The future system will assure the security of
the cadastral content which will act as a content management system for
the new cadastral software application. A new evaluation system will be
created in order to track, optimize and define new feature to increase
the security system for the related cadastral system.
Keywords: Cadastral, Management, Security, Performance, Software
metrics
Implementing a Decision-Aware System for Loan Contracting Decision Process
Razvan PETRUSEL, Daniel MICAN, Cristina Claudia DOLEAN 167
The paper introduces our work related to the design and
implementation of a decision-aware system focused on the loan
contracting decision process. A decision-aware system is a software that
enables the user to make a decision in a simulated environment and logs
all the actions of the decision maker while interacting with the
software. By using a mining algorithm on the logs, it creates a model of
the decision process and presents it to the user. The main design issue
introduced in the paper is the possibility to log the mental actions of
the user. The main implementation issues are: user activity logging
programming and technologies used. The first section of the paper
introduces the state-of-the-art research in process mining and the
framework of our research; the second section argues the design of the
system; the third section introduces the actual implementation and the
fourth section shows a running example.
Keywords: Decision-Aware Systems, Decision Activity Logs,
Decision Mining, Codeigniter, JSON
A Stock Trading Algorithm Model Proposal, based on Technical Indicators Signals
Darie MOLDOVAN, Mircea MOCA, Stefan NITCHI 183
The algorithmic stock trading has developed exponentially in the past
years, while the automatism of the technical analysis was the main
research are for implementing the algorithms. This paper proposes a
model for a trading algorithm that combines the signals from different
technical indicators in order to provide more accurate trading signals.
Keywords: Decision Support System, Trading Algorithm, Technical
Analysis
The SGIA and the Common Growing Language
Laurentiu CIOVICA, Liviu CIOVICA, Marian-Pompiliu CRISTESCU, Corina-Ioana CRISTESCU 189
Human or virtual agents are presented in our lives daily. They serve
our purposes and represent us in different many situations. Nowadays the
number of virtual agents is increasing daily because they are cheaper,
faster and more accurate than human agents. Our aim in this article is
to define a new type of intelligent agent called SGIA – Self Growing
Intelligent Agent and a new defining language for it. The SGIA agent is
an intelligent agent with all the common agents’ characteristics and
with other special one: that to learn and grow by itself in knowledge
and size.
Keywords: Software Agent, Knowledge Management, Education
Process, Language Development
Open Source Approach to Project Management Tools
Romeo MARGEA, Camelia MARGEA 196
Managing large projects involving different groups of people and
complex tasks can be challenging. The solution is to use Project
management software, which allows a more efficient management of
projects. However, famous project management systems can be costly and
may require expensive custom servers. Even if free software is not as
complex as Microsoft Project, is noteworthy to think that not all
projects need all the features, amenities and power of such systems.
There are free and open source software alternatives that meet the needs
of most projects, and that allow Web access based on different platforms
and locations. A starting stage in adopting an OSS in-house is finding
and identifying existing open source solution. In this paper we present
an overview of Open Source Project Management Software (OSPMS) based on
articles, reviews, books and developers’ web sites, about those that
seem to be the most popular software in this category.
Keywords: Project Management Software, Microsoft Project
alternatives, Open Source Project Management Software
Multiagent-Based Model for ESCM
Delia MARINCAS 207
Web based applications for Supply Chain Management (SCM) are now a
necessity for every company in order to meet the increasing customer
demands, to face the global competition and to make profit. Multiagent-based
approach is appropriate for eSCM because it shows many of the
characteristics a SCM system should have. For this reason, we have
proposed a multiagent-based eSCM model which configures a virtual SC,
automates the SC activities: selling, purchasing, manufacturing,
planning, inventory, etc. This model will allow a better coordination of
the supply chain network and will increase the effectiveness of Web and
intel-ligent technologies employed in eSCM software.
Keywords: Multiagent System, eSCM, Ontologies, Knowledge, ACL,
KQML
The Place of e-Learning in Romanian Universities’ Strategies
Ramona LACUREZEANU, Robert BUCHMANN, Paul BRESFELEAN, Valerica MARES 220
The educational policy documents at European level reaffirm
professors’ status as key players of strategies aimed to stimulate
socio-economic development. In a powerful knowledge-based society, the
e-Learning system has the capacity to transform education, creating
major initiatives required to identify new skills and behaviors. In this
paper we try to outline the position of this new educational system in
the Romanian higher education strategy.
Keywords: e-Learning, Portals, ICT, Universities
Security Risk Management - Approaches and Methodology
Elena Ramona STROIE, Alina Cristina RUSU 228
In today’s economic context, organizations are looking for ways to
improve their business, to keep head of the competition and grow
revenue. To stay competitive and consolidate their position on the
market, the companies must use all the information they have and process
their information for better support of their missions. For this reason
managers have to take into consideration risks that can affect the
organization and they have to minimize their impact on the organization.
Risk management helps managers to better control the business practices
and improve the business process.
Keywords: Risk Management, Security, Methodology
The Tenth International Conference on Informatics in Economy IE 2011 241
Publishing Guide for Authors 242
Inforec Association 244
|