Filter by type:

Sort by year:

Open Directory Project based universal taxonomy for Personalization of Online (Re)sources

Jurica Ševa, Markus Schatten, Petra Grd
Journal Paper Expert systems with applications, 42, 17–18; 6306-6314

Abstract

Content personalization reflects the ability of content classification into (predefined) thematic units or information domains. Content nodes in a single thematic unit are related to a greater or lesser extent. An existing connection between two available content nodes assumes that the user will be interested in both resources (but not necessarily to the same extent). Such a connection (and its value) can be established through the process of automatic content classification and labeling. One approach for the classification of content nodes is the use of a predefined classification taxonomy. With the help of such classification taxonomy it is possible to automatically classify and label existing content nodes as well as create additional descriptors for future use in content personalization and recommendation systems. For these purposes existing web directories can be used in creating a universal, purely content based, classification taxonomy. This work analyzes Open Directory Project (ODP) web directory and proposes a novel use of its structure and content as the basis for such a classification taxonomy. The goal of a unified classification taxonomy is to allow for content personalization from heterogeneous sources. In this work we focus on the overall quality of ODP as the basis for such a classification taxonomy and the use of its hierarchical structure for automatic labeling. Due to the structure of data in ODP different grouping schemes are devised and tested to find the optimal content and structure combination for a proposed classification taxonomy as well as automatic labeling processes. The results provide an in-depth analysis of ODP and ODP based content classification and automatic labeling models. Although the use of ODP is well documented, this question has not been answered to date.

Basic Principles and Trends in Hand Geometry and Hand Shape Biometrics

Miroslav Bača, Petra Grd, Tomislav Fotak
Book Chapter New trends and developments in biometrics | 2012 | ISBN:978-953-51-0859-7
image

Researchers in the field of biometrics found that human hand, especially human palm, contains some characteristics that can be used for personal identification. These characteristics mainly include thickness of the palm area and width, thickness and length of the fingers. Large numbers of commercial systems use these characteristics in various applications.

Hand geometry biometrics is not a new technique. It is first mentioned in the early 70’s of 15 the 20th century and it is older than palm print which is part of dactiloscopy. The first known use was for security checks in Wall Street.

Hand geometry is based on the palm and fingers structure, including width of the fingers in different places, length of the fingers, thickness of the palm area, etc. Although these measurements are not very distinctive among people, hand geometry can be very useful for identity verification, i.e. personal authentication. Special task is to combine some non-descriptive characteristics in order to achieve better identification results. This technique is widely accepted and the verification includes simple data processing. Mentioned features make hand geometry an ideal candidate for research and development of new acquisition, preprocessing and verification techniques.

The transportation paths routing semantic description

Markus Schatten, Miroslav Bača, Petra Koruga
Book Chapter Transactions on transport systems telematics & safety | 2011 | ISBN:978-83-7335-824-9
image

This chapter presents a semantic network formalism based on frame logic. Advanced techniques including HiLog extensions, transaction logic and dynamic module creation are applied to the problem of preferential routing and rerouteing. The deductive program is implemented in the FLORA-2 reasoning engine, which allows for scalable query execution. In the end possible extensions to the system and guidelines for future research are presented.

Transportation networks are networks which show linkage relationships among numerous nodes. Routing in transportation network usually deals with questions like: What is the most efficient routing between two locations? What is a reasonable set of alternative routes if a segment of the transportation network is blocked? What are the comparison of costs for routing freight by highway, rail, or waterway? What additional travel times result from increasing traffic congestion along routes? What are the effects of changes in transportation costs, demands, or policies?

Route selection problem is present in various forms in transport networks. In general, to generate alternative routes for transportation many nodes and links which connect location for departure and destination have to be connected. Most common variables taken into consideration are departure location, destination, departure time, arrival time. This chapter takes the routing problem to the next level and adds more variables, for example, type of desired road, landscape type, stores on the way etc.

Introduction to Human Age Estimation Using Face Images

Petra Grd
Journal Paper Research papers Faculty of Materials Science and Technology Slovak University of Technology in Trnava, Special number, 2013, Pages 35-41

Abstract

Age estimation is one of the tasks of facial image classification. It can be defined as determination of a person's age or age group from facial images. This paper gives an overview of recent research in facial age estimation. Along with an overview of previous research on this topic, descriptions of basic age estimation models are given: anthropometric model, active appearance model, aging pattern subspace and age manifold.

Handwritten signature identification using basic concepts of graph theory

Tomislav Fotak, Miroslav Bača, Petra Koruga
Journal Paper WSEAS Transactions on Signal Processing, Volume 7, 2011, Pages 117-129

Abstract

Handwritten signature is being used in various applications on daily basis. The problem arises when someone decides to imitate our signature and steal our identity. Therefore, there is a need for adequate protection of signatures and a need for systems that can, with a great degree of certainty, identify who is the signatory. This paper presents previous work in the field of signature and writer identification to show the historical development of the idea and defines a new promising approach in handwritten signature identification based on some basic concepts of graph theory. This principle can be implemented on both on-line handwritten signature recognition systems and off-line handwritten signature recognition systems. Using graph norm for fast classification (filtration of potential users), followed by comparison of each signature graph concepts value against values stored in database, the system reports 94.25% identification accuracy.

Towards a Formal Conceptualization of Organizational Design Techniques for Large Scale Multi Agent Systems

Markus Schatten, Petra Grd, Mladen Konecki, Robert Kudelić
Conference Papers Conference Proceedings of the 2nd International Conference on System-Integrated Intelligence: Challenges for Product and Production Engineering, 2014, Pages 725-734

Abstract

Computing in the Internet of Things is increasingly pervasive, with everyday items including clothes, smart-phones, cars and various household appliances gaining sophisticated communication and computing capacities. It seems to be just a matter of time before devices have to collaborate and compete mutually as well as with their users, in order to provide better services to mankind. These embedded computers are increasingly autonomous and connected, and can thus be modeled as agents within multi-agent systems (MAS). Only 30 years ago it was science fiction that over a billion of people will exchange billions of e-mails on a daily basis. Today a scenario of millions of collaborating agents embedded in gadgets and appliances, across various networks may also sound futuristic. However given the current rate of development in electronics, we will soon have to manage large scale MAS (LSMAS) where millions of agents exist, collaborate and compete with each other. While a recent study shows that there are at least 50 organizational structure, superstructure and architecture types employed in modern organizations, there is a lack of research that would apply organizational design methods to organizations composed entirely of agents and agent systems in order to achieve alignment of organizational structure, processes, and reward system with the goals and strategy of the organization. Our research is therefore aimed towards enriching formal design methods for the development of LSMAS to foster the development of self-organizing and adaptable networks of devices that will contribute towards a sustainable development of the information society. In this work-in-progress study we apply a collaborative semantic wiki approach towards formalizing organizational design techniques in order to provide a foundation for future studies of automated LSMAS development.

Analysis of Communication of Croatian Faculties through Facebook - Part I

Alen Delić, Petra Grd, Iva Gregurec
Conference Papers Proceedings of the ITI 2013 35th International Conference on Information Technology Interfaces, 2013, Pages 43-48

Abstract

In the 21st century, if a faculty wants to have an effective communication with their fans (for example former, potential or existing students) it must include social networking sites and see them as very important way of communication. With the number of internet, as well as social networking users constantly increasing, it is important and sometimes even vital for faculties to be present on and, consequently, to be proactive. Today social networks facilitate relationship-building since they have become a very powerful communication tool between users, as well as between faculties and their fans. The aim of this paper was to analyse the way Croatian faculties communicate with their fans via Facebook. The paper also shows differences between private and public institutions and their way of communicating with their fans.

Building a framework for the development of biometric forensics

Miroslav Bača, Petra Grd, Tomislav Fotak
Conference Papers MIPRO 2012 Proceedings, 2012, Pages 1904-1906

Abstract

Application of biometric tools today is a major challenge for developers of biometric systems and for users of those systems. A specific application can be seen in systems requiring a certain accuracy in person authentication. A large number of systems is created in a way that the algorithms used are not verified as standardized, thus causing uncertainty in their results and application of those tools in processes which need to confirm obtained results. This paper will describe the basic model necessary to build a framework for the construction of a biometric system applicable in forensics for person authentication in court of law.

Trends in Hand Geometry Biometrics

Tomislav Fotak, Petra Grd, Miroslav Bača
Conference Papers Central European Conference on Information and Intelligent Systems 23rd International Conference, 2012, Pages 319-324

Abstract

Researchers in the field of biometrics found that human hand contains some characteristics that can be used for personal identification. Some of these are hand geometry and hand shape. These biometric characteristics are more than 30 years old and are very popular and widely accepted among people. That makes them suitable for development of various acquisition and authentication methods. So far, many contact-based and contact-less systems have been developed in the academy and commercial sector. Contact-less biometrics is becoming more important in this field, thus making the researchers to concentrate their efforts in this direction.

ebXML and Interoperability: A Systematic Review

Petra Grd, Miroslav Bača
Conference Papers The Proceedings of the 4th International Conference on Information Technologies and Information Society ITIS, 2012

Abstract

In this paper, ebXML standard and its architecture will be described. A systematic review of current research on ebXML will be given. At the end, ebXML will be connected with interoperability. Research question to which an answer will be given is: In which countries is ebXML registry implemented outside the laboratory, and is used as such?

Search Engine Optimization (SEO): Website analysis of selected faculties in Croatia

Iva Gregurec, Petra Grd
Conference Papers Central European Conference on Information and Intelligent Systems 23rd International Conference, 2012, Pages 211-218

Abstract

Search engine optimization is an Internet marketing strategy, and as such, very important in building websites. Websites need to be optimized in order to atract users and to sell products and services. This paper will give an overview of selected SEO elements, and analyse websites of Croatian faculties related to computer science and engineering.

Communication of political parties on Twitter: Comparison of political parties in Serbia, Croatia, Slovenia and BiH

Petra Koruga, Miroslav Bača
Conference Papers SYMORG Inovative management and business performance, 2012, Pages 408-416

Abstract

In the past decades, information and communication technologies affect all aspects of our lives, including politics. Political parties use the Internet to communicate with their potential voters. This paper will give a short introduction to communication over the Internet in general, description of political parties in question, and the main part of the paper is the analysis and comparison of communication of Slovenian and Croatian political parties over the Internet. Special attention will be payed to communication using social networks, such as Facebook or Twitter.

Knowledge Visualization in Biometric Face Recognition on Two-dimensional Images

Petra Koruga, Miroslav Bača, Tomislav Fotak
Conference Papers Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces, 2012, Pages 349-353

Abstract

Biometric face recognition is one of the fields of computer vision. The part of biometric person identification has been extensivly researched. This resulted in a large number of algorithms used for person identification. This paper gives an overview and classification of those algorithms. Because of large number of algorithms, knowledge visualization is used for easier understanding of structure and connections between those algorithms.

An Outlook to Security and Trust in Internet Communications

Robert Logožar, Petra Koruga
Conference PapersProceedings of the 22nd Central European Conference on Information and Intelligent Systems, 2011

Abstract

In this paper we address the key questions on security and trust in communication over Internet, in a synthetic approach aimed to connect the technological and human aspects of the subject. As first, a brief outline of the Internet security technology is given. This serves as a ground for the exposition of the general security concepts and principles, its pillars and threats. The achieved security provides the basis for building of the user trust. The trust is then proportional to the user’s perception of the achieved security level. The omnipresence of Internet in all human activities today, including financial transactions, e-commerce, trade, auctioning, and other, proves by itself that the trust of majority of online users is won. Legal support and especially the mechanisms of the user protection initiated by the service providers are improving, as well as the general efforts to educate the online community.

Basic on-line handwriten signature features for personal biometric authentication

Miroslav Bača, Petra Koruga, Tomislav Fotak
Conference Papers 34th international convention on information and communication technology, electronics and microelectronics, 2011, Pages 116-121

Abstract

On-line handwritten signature-based personal authentication is still a challenging research topic. Although great efforts have been achieved in developing and defining a framework that systems for on-line authentication based on the handwritten signature of a person should adhere, these frameworks are still not enough because they do not include all the features that handwritten signature as a biometric feature has. In addition, there is a range of features that current system for capturing a signature posses by which it is possible to further and better define the characteristics of signatures required to be in the process of authentication of entities, but can be used not only for authentication but also for identification. The paper provides an overview of the differences between off-line and on-line mode of authentication system based on the handwritten signature as well as surveys of some properties that these features can have, supported with the latest systems to "capture" handwritten signatures.

On-line Handwritten Signature Identification: The Basics

Tomislav Fotak, Petra Koruga, Miroslav Bača
Conference Papers Proceedings of the 22nd Central European Conference on Information and Intelligent Systems, 2011, Pages 139-145

Abstract

Handwritten signature is widely accepted and collectable biometric characteristic. Great entropy makes this characteristic suitable for research and development of new methods for personal authentication and identification. While development of authentication methods based on this biometric characteristic is common thing in academic and research community, there are only few attempts of developing personal identification system based on handwritten signature. This paper presents basic difeerences between authentication and identification methods, followed by previous work in the field of handwritten signature identification and main directions in developing an on-line personal identification system based on handwritten signature. This work can be considered as the theoretic base for the further development of an on-line handwritten signature identification system.

Comparison of Communication of Political Parties over the Internet in Slovenia and Croatia

Petra Koruga, Miroslav Bača, Tomislav Fotak
Conference Papers Proceedings of International Conference on Information Society, 2011, Pages 31-36

Abstract

In the past decades, information and communication technologies affect all aspects of our lives, including politics. Political parties use the Internet to communicate with their potential voters. This paper will give a short introduction to communication over the Internet in general, description of political parties in question, and the main part of the paper is the analysis and comparison of communication of Slovenian and Croatian political parties over the Internet. Special attention will be payed to communication using social networks, such as Facebook or Twitter.

Analysis of Craniofacial Morphology Changes during Aging and their Connection with Facial Age Estimation

Petra Koruga, Miroslav Bača, Markus Schatten
Conference Papers Proceedings of the ITI 2011 33rd International Conference on INFORMATION TECHNOLOGY INTERFACES, 2011, Pages 481-485

Abstract

The aging process affects the structure and appearance of people in different ways. One of such is the change in craniofacial morphology (CM) of individuals. The subject of a person's CM and age estimation is by itself insufficiently researched. Especially on the analysis of children's CM at different ages, because it hasn't been considered thoroughly. This paper will analyse certain characteristics of the CM and their changes during aging from a biometrics perspective, and will also give an overview of previous work on this subject.

Application of Modified Anthropometric Model in Facial Age Estimation

Petra Koruga, Jurica Ševa, Miroslav Bača
Conference Papers Proceedings of the 53rd International Symposium ELMAR, 2011, Pages 17-20

Abstract

Aging process affects the appearance of people in different ways. One of the changes caused by aging are changes in craniofacial morphology of individuals. Different models of facial aging exist and this paper will apply anthropometric model of facial aging on pictures of 20 people at different ages of their lives to show the similarities between craniofacial morphology of people at the same age. FGNet database that contains two-dimensional faces of people from childhood to adulthood will be used for analysis.

A Review of Face Recognition Algorithms and Their Application in Age Estimation

Petra Koruga, Jurica Ševa, Miroslav Bača
Conference Papers Proceedings of the 22nd Central European Conference on Information and Intelligent Systems, 2011, Pages 127-132

Abstract

Age estimation of humans is one of the problems in the field of computer vision which is insufficiently researched. To efficiently estimate the age of an individual based on his/her face image, characteristic points of the face have to be determined. In this paper, the most common face recognition algorithms, like Principal Component Analysis (PCA), Independent Component Analysis (ICA), Linear Discriminant Analysis (LDA) and Elastic Bunch Graph Matching (EBGM) will be described. These algorithms will then be compared, and the application in age estimation will be given. At the end of the paper, ideas for future research will be stated.

Analysis of B-tree data structure and its usage in computer forensics

Petra Koruga, Miroslav Bača
Conference Papers Proceedings of the 21st Central European Conference on Information and Intelligent Systems, 2010, Pages 423-428

Abstract

The idea behind this article is to give an overview of B-tree data structure and show the connection between B-tree indexing technique and computer forensics. B-tree is a fast data indexing method that organizes indexes into a multi-level set of nodes, where each node contains indexed data. This technique is most commonly used in databases and file systems where it is important to retrieve records stored in a file when data is to large to fit in main memory. In that case, Btrees are used to reduce the number of disk accesses.