Skip to main content

2018 | Book

Developments and Advances in Intelligent Systems and Applications


About this book

This book primarily addresses Intelligent Information Systems (IIS) and the integration of artificial intelligence, intelligent systems and technologies, database technologies and information systems methodologies to create the next generation of information systems.

It includes original and state-of-the-art research on theoretical and practical advances in IIS, system architectures, tools and techniques, as well as “success stories” in intelligent information systems.

Intended as an interdisciplinary forum in which scientists and professionals could share their research results and report on new developments and advances in intelligent information systems, technologies and related areas – as well as their applications – , it offers a valuable resource for researchers and practitioners alike.

Table of Contents

Advanced Classification of Remote Sensing High Resolution Imagery. An Application for the Management of Natural Resources
In the last decades, there has been a decline in ecosystems natural resources. The objective of the study is to develop advanced image processing techniques applied to high resolution remote sensing imagery for the ecosystem conservation. The study area is focused in three ecosystems from The Canary Islands, Teide National Park, Maspalomas Natural Reserve and Corralejo and Islote de Lobos Natural Park. Different pre-processing steps have been applied in order to acquire high quality imagery. After an extensive analysis and evaluation of pansharpening techniques, Weighted Wavelet ‘à trous’ through Fractal Dimension Maps, in Teide and Maspalomas scenes, and Fast Intensity Hue Saturation, in Corralejo scene, are used, then, a RPC (Rational Polymodal Coefficients) model performs the orthorectification and finally, the atmospheric correction is carried out by the 6S algorithm. The final step is to generate marine and terrestrial thematic products using advanced classification techniques for the management of natural resources. Accurate thematic maps have already been obtained in Teide National Park. A comparative study of both pixel-based and object-based (OBIA) approaches was carried out, obtaining the most accurate thematic maps in both of them using Support Vector Machine classifier.
Edurne Ibarrola-Ulzurrun, Javier Marcello, Consuelo Gonzalo-Martin
Analyzing the Impact of Strategic Performance Management Systems and Role Ambiguity on Performance: A Qualitative Approach
This research questions the assumption that strategic performance measurement systems (SPMS) that define strategic goals at the individual job level reduce role ambiguity and ensure desired employee outcomes. Through qualitative research of both white-collar and blue-collar jobs, we seek to determine the types of jobs most amenable to SPMS guidance.
Enoch Asare, Sue Conger
Advanced Radial Approach to Resource Location Problems
This paper deals with the optimal resource location problems used for emergency service system designing. Due to limited budget or other technological restrictions, particular mathematical models usually take the form of the weighted p-median problem, in which the numbers of served users and possible service center locations, from which the associated service is provided, take the value of several hundreds or thousands. A standard objective in such formulation assumes minimization of total disutility, like social costs. The social costs are often proportional to the distance travelled by all system users to the nearest located source of provided service. As the access of population to the service is performed by transportation means operating on the underlying transportation network, the design of suitable deployment of the service centers belongs to hard combinatorial problems. This contribution deals with an approximate approach based on radial formulation with homogenous system of radii. Presented approach enables to solve large instances in admissible time making use of a universal IP-solver. Special attention is paid to possible adjustment of the approximate approach to the exact method based on useful features of the radial formulation.
Marek Kvet
Verbal Decision Analysis Applied to the Prioritization of Influencing Factors in Distributed Software Development
A project manager of distributed software development faces many challenges. Some of them relate to task allocation among remote teams. To assign a task to team, the project manager takes into account several factors such as project manager maturity and team availability. Most of the time, the manager takes the decision subjectively. The verbal decision analysis is an approach to solve problems through multi-criteria qualitative analysis, i.e., it considers the analysis of subjective criteria. This paper describes the application of verbal decision analysis method ZAPROS III-i to prioritize the factors that the project managers should take into account when allocating tasks in projects of distributed software development.
Marum Simão Filho, Plácido Rogério Pinheiro, Adriano Bessa Albuquerque
Agile Documentation Tool Concept
Documentation is often neglected in agile software projects, even if software developers perceive a need for good documentation. One reason can be found in improper documentation tools. This paper provides an overview of the central conceptual ideas for an agile documentation tool.
Stefan Voigt, Detlef Hüttemann, Andreas Gohr, Michael Große
Pervasive Business Intelligence: A Key Success Factor for Business
Today the strategic significance of information is fundamental to any organization. With the intensification of competition between companies in open markets and often saturated, companies must learn to know themselves and to the market through the collection and analysis of quality information. The strategic information is seen as a key resource for success in the business, which is provided by Business Intelligence systems. A successful business strategy requires an awareness of the surrounding (internal and external) environment of organizations, including customers, competitors, industry structure and competitive forces. Managing the future means not only is able to anticipate what will happen outside the organization, but also be able to represent the events through their own actions timely. To make it possible, Pervasive Business Intelligence arises as a natural evolution of business intelligence applications in organizations, allowing to companies achieve and maintain a sustainable competitive advantage, helping managers react proactively in a timely manner to threats and opportunities.
Teresa Guarda, Marcelo León, Maria Fernanda Augusto, Filipe Mota Pinto, Oscar Barrionuevo, Datzania Villao
Annotated Documents and Expanded CIDOC-CRM Ontology in the Automatic Construction of a Virtual Museum
The Museum of the Person (Museu da Pessoa, MP) is a virtual museum with the purpose of exhibit life stories of common people. Its assets are composed of several interviews involving people whose stories we want to perpetuate. So the museum holds an heterogeneous collection of XML (eXtensible Markup Language) documents that constitute the working repository. The main idea is to extract automatically the information included in the repository in order to build the virtual museum’s exhibition rooms. The goal of this paper is to describe an architectural approach to build a system that will create the virtual rooms from the XML repository to enable visitors to lookup individual life stories and also inter-cross information among them. We adopted the standard for museum ontologies CIDOC-CRM (CIDOC Conceptual Reference Model) refined with FOAF (Friend of a Friend) and DBpedia ontologies to represent OntoMP. That ontology is intended to allow a conceptual navigation over the available information. The approach here discussed is based on a TripleStore and uses SPARQL (SPARQL Protocol and RDF Query Language) to extract the information. Aiming at the extraction of meaningful information, we built a text filter that converts the interviews into a RDF triples file that reflects the assets described by the ontology.
Cristiana Araújo, Ricardo G. Martini, Pedro Rangel Henriques, José João Almeida
Web-Based Decision System for Distributed Process Planning in a Networked Manufacturing Environment
Distributed manufacturing sector is increasingly enabling the Web-enabled services due to the advancements in Information technology and pervasive applications of recently advanced manufacturing systems. In this paper, world wide web (WWW) collaborative model is developed, and architecture with the web enabled service system for effective integration of distributed process planning and scheduling is proposed to assists the geographically distributed enterprises located in the context of networked manufacturing for effective coordination and collaboration. To validate the feasibility of the proposed approach, a case study has been presented and found that the proposed method and developed tool offers some benefits such as high interoperability, openness, cost-efficiency, and production scalability.
V. K. Manupati, P. K. C. Kanigalpula, M. L. R. Varela, Goran D. Putnik, A. F. Araújo, G. G. Vieira
Managing the Lifecycle of Security SLA Requirements in Cloud Computing
One of the major barriers for full adoption of cloud computing is the security issue. As the cloud computing paradigm presents a shared management vision, it is important that security requirements are addressed inside the Service Level Agreements (SLAs) established between cloud providers and consumers, along with the tools and mechanisms necessary to deal with these requirements. This work aims at proposing a framework to orchestrate the management of cloud services and security mechanisms based on the security requirements defined by a SLA, in an automated manner, throughout their lifecycles. In addition, the integration of the framework with a cloud computing solution is presented, in order to demonstrate and validate the framework support throughout SLAs lifecycle phases.
Marco Antonio Torrez Rojas, Fernando Frota Redígolo, Nelson Mimura Gonzalez, Fernando Vilgino Sbampato, Tereza Cristina Melo de Brito Carvalho, Kazi Walli Ullah, Mats Näslund, Abu Shohel Ahmed
Influence of User’s Criteria Preferences for Open Source ITIL Tools Evaluation by Simple MCDM
This paper responds to requirement to improve the orientation between offered SW, as ITIL tools. There are really a lot of offered tools and very often this fact may leads to the poor implementation of ITIL. Main objective of this paper is to provide an overview how users’ preferences change in a short time and primarily the comparison between expert evaluation and evaluation with utilization of simple multi-criterial decision making methods. Simultaneously, the research described in this paper will serve for further work on creating a methodology for evaluation of ITIL tools.
Lukas Kralik, Roman Jasek, Petr Zacek
E-consultation as a Tool for Participation in Teachers’ Unions
In the 2000s, the Internet became the preferred mean for the citizens to communicate. The YouTube, Twitter, Facebook, LinkedIn, i.e., the social networks in general appeared together with the Web 2.0, which allows an extraordinary interaction between citizens and the democratic institutions. The trade unions constantly fight governments’ decisions, especially in periods of crisis like the one that the world, Europe and, in particular, Portugal are facing. In this regard, the use of e-participation platforms is expected to strengthen the relationship between trade unions and the education community. This paper reports the research about the planning and driving of a series of experiments of online public consultation, launched by teachers’ trade unions. These experiments are compared with those of other countries, such as Australia, United Kingdom and United States of America. A quantitative analysis of the results regarding hits, subscriptions, and response rates is presented, and it is compared with the 90-9-1 rule, the ASCU model and data from government agencies. The experiments performed used the Liberopinion, an online platform that supports bidirectional asynchronous communication. A better understanding of the benefits of these collaborative environments is expected by promoting quality of interaction between actors.
Carlos Quental, Luis Borges Gouveia
A Method for Quality Assurance for Business Process Modeling with BPMN
Within the development of computer systems, the goal of business process mapping is to understand, improve, and organize the process activities to ensure efficient and correct implementation for releasing important firsthand inputs for requirements engineering. These inputs can be improved by process modeling. The quality of business process modeling can decisively influence the software quality. Internal quality analysis is done in-house, for the development process, while external quality analysis is done for the final product and satisfaction of the end consumer. Therefore, process modeling contributes to the production of consistent artifacts inorder to improve communications within the project. A way to assure quality comes from quality attributes verified with checklists in iterative cycles. Process mapping, then, contributes both to producing consistent artifacts and to improving communications within the project.
Waldeyr Mendes C. da Silva, Aletéia P. F. Araújo, Maristela T. Holanda, Rafael T. de Sousa Júnior
Performance Analysis on Voluntary Geographic Information Systems with Document-Based NoSQL Database
With the advent of Web 2.0 and mobile technology, including, smartphones equipped with GPS (Global Positioning System) receptors, there has been an increase in the number of individuals who create and share spatial data. Consequently, the ability to store a large quantity of data, in diverse formats is made possible by Geographic Information Systems (GIS) that use voluntary data. This study presents a performance analysis of data storage architecture of a Voluntary Geographic Information System (VGIS) that uses a document-based NoSQL database and a relational database for comparison. To carry out the performance analysis it was necessary to remodel the application database from a relational database to a non-relational model. Furthermore, insertion and reading tests were needed, and performed in local and clustered environments using a simulator that generates random data on a large scale. The test results have sought to analyze the performance and feasibility of using a document-based database from data storage architecture for VGIS.
Daniel Cosme Mendonça Maia, Breno D. C. Camargos, Maristela Holanda
Adding the Third Dimension to Urban Networks for Electric Mobility Simulation: An Example for the City of Porto
Elevation data is important for precise electric vehicle simulation. However, traffic simulators are often strictly two-dimensional and do not offer the capability of modelling urban networks taking elevation into account. In particular, SUMO—Simulation of Urban Mobility, a popular microscopic traffic simulation platform, relies on urban networks previously modelled with elevation data in order to use this information during simulations. This work tackles the problem of how to add this elevation data to urban network models—in particular for the case of the Porto urban network, in Portugal. With this goal in mind, a comparison between altitude information retrieval approaches is made and a tool to annotate network models with altitude data is proposed. This paper starts by describing the methodological approach followed to develop the work, then describing and analysing its main findings, including an in-depth explanation of the proposed tool.
Diogo Santos, José Pinto, Rosaldo J. F. Rossetti, Eugénio Oliveira
Parallel Remote Servers for Scientific Computing Over the Web: Random Polygons Inscribed in a Circle
Computing over the Web can be applied to solve problems of many types of users, namely companies, which can thus benefit from the service of remote collaborators, e.g., from academia, without the user’s awareness, namely if the user is the customer. An illustration of scientific computing over the Web is described, based on remote servers in parallel, as fits separable time consuming tasks. The illustrative problem chosen was the probabilistic behaviour of the perimeter of random polygons inscribed in a circle, because: it is simple to state; its Monte Carlo resolution suits the type of computing considered; and each polygon to be simulated (with 3, 4, etc., sides) can be assigned to multiple servers, only two servers for demonstration purposes. Our objectives are: to emphasize the pertinence of the Web for scientific or other computing; and to show the use of parallel, possibly heterogeneous remote servers. The problem shown can be freely solved on the authors’ webpage. We think the benefits of scientific computing over the Web, despite the ubiquity of this environment, have lagged behind most of the other uses of the Internet.
Marco Cunha, Miguel Casquilho
webQDA 2.0 Versus webQDA 3.0: A Comparative Study About Usability of Qualitative Data Analysis Software
Communication and Information Technology (ICT) applied to qualitative research has proved to be an asset for quality, improvement and innovation of this research area. Having emerged in 2010 webQDA is an online software that has supported the data analysis of several areas of research such as education, health, sociology, psychology, social sciences and others fields that need qualitative analysis. This study presents an assessment of the usability of the qualitative data analysis software webQDA® (version 2.0) in comparison with its new version webQDA 3.0. To assess its usability, the System Usability Scale (SUS) was used. The results indicate that there is still room and potential for improvement of webQDA 3.0, as expected‚ once it is still being improved. It is encouraging to know that more and more researchers find it not only useful but easy to use, even if demanding (which is positive from our point of view)‚ in the way it “forces” researchers to adopt a more inquisitive approach to the data they deal with in their qualitative studies. Suggestions for future studies and improvement of the software are put forward.
António Pedro Costa, Francislê Neri de Souza, António Moreira, Dayse Neri de Souza
Location Privacy Concerns in Mobile Applications
Privacy is a ubiquitous topic in research nowadays, specially in mobile application scenarios. Users are seldom aware of the privacy hazards they are under when using mobile applications. In this paper we compare two privacy studies and present development strategies that can be employed to favour the awareness of privacy and security issues with a strong focus on location data. Results show that developers should play an increasingly important role in the assurance of privacy since users of mobile apps, although concerned with privacy issues, are not fully prepared for making the right decisions in every situation as a rerun of an old study shows.
Luis Marcelino, Catarina Silva
Towards a New Approach of Learning: Learn by Thinking Extending the Paradigm Through Cognitive Learning and Artificial Intelligence Methods to Improve Special Education Needs
Cognitive theorists believe that the learning process involves the integration of events into actives organizational structures termed schemata. Schemata serve a number of functions in human cognition: schemata regulates attention, organizes searches of the environment and “fill the gaps” during information processing. Thus, the mind uses schemata to selectively organize and processes all the information individuals receive from the world. This perspective fits e.g. in teaching blind and deaf people alongside of children with special education needs. The aim of the research developed until the moment was to prove that the full integration of the concept of teaching and learning in the light of cognitive theories.
Jorge Pires, Manuel Pérez Cota, Álvaro Rocha, Ramiro Gonçalves
On Feature Weighting and Selection for Medical Document Classification
Medical document classification is still one of the popular research problems inside text classification domain. In this study, the impact of feature selection and feature weighting on medical document classification is analyzed using two datasets containing MEDLINE documents. The performances of two different feature selection methods namely Gini index and distinguishing feature selector and two different term weighting methods namely term frequency (TF) and term frequency-inverse document frequency (TF-IDF) are analyzed using two pattern classifiers. These pattern classifiers are Bayesian network and C4.5 decision tree. As this study deals with single-label classification, a subset of documents inside OHSUMED and a self-constructed dataset is used for assessment of these methods. Due to having low amount of documents for some categories in self-compiled dataset, only documents belonging to 10 different disease categories are used in the experiments for both datasets. Experimental results show that the better result is obtained with combination of distinguishing feature selector, TF feature weighting, and Bayesian network classifier.
Bekir Parlak, Alper Kursat Uysal
Developments and Advances in Intelligent Systems and Applications
Álvaro Rocha
Luís Paulo Reis
Copyright Year
Electronic ISBN
Print ISBN

Premium Partner