Bojan Cestnik
University of Nova Gorica, Poslovno Tehniška Fakulteta, Faculty Member
A result-oriented engagement system for performance optimisation (RESPO) has been developed to systematically monitor and improve the competencies of individuals in business, lifelong learning and secondary schools. The RESPO expert... more
A result-oriented engagement system for performance optimisation (RESPO) has been developed to systematically monitor and improve the competencies of individuals in business, lifelong learning and secondary schools. The RESPO expert system was transferred for use in higher education institutions (HEIs) based on successful practical application trials. The architecture and functionality of the original RESPO expert system have been transformed into a new format that will collect information on the required competencies and the available educational programmes to help students effectively develop competencies through formal and non-formal education. First, the initial version of the RESPO system and its functionality were tested on a selected group of students and higher education staff to validate and improve its effectiveness for the needs of HEIs. This paper summarises the key findings and recommendations of the validators for transforming the RESPO application into an application ...
Research Interests:
The estimation of probabilities from empirical data samples has been established as a crucial part of many machine learning and knowledge discovery research projects and applications. In addition to simple probability estimation with... more
The estimation of probabilities from empirical data samples has been established as a crucial part of many machine learning and knowledge discovery research projects and applications. In addition to simple probability estimation with relative frequency, more elaborated probability estimation methods were proposed and applied in practice (e.g. Laplace's rule, m-estimate, Piegat's estimate). In this paper we analyze the role of parameter m in m-estimate. In most practical applications that used m-estimate, m was often set to 2 or, in more complex settings, determined with a cross-validation procedures. In this study we evaluate the impact of various values of m to the absolute error of m-estimate in the context of a carefully designed experimental framework. The results of our analysis suggest that the optimal value of parameter m does not depend only on the size of the observed sample, but also, to a much greater extent, on the difference between hypothetical pa used in m-estimate and the authentic p of the sample.
Research Interests:
Maintaining usability and trust of electronic public services is an important topic of research in e-government field. In this paper, we address the problem of identifying descriptive characteristics of clients that, when offered a choice... more
Maintaining usability and trust of electronic public services is an important topic of research in e-government field. In this paper, we address the problem of identifying descriptive characteristics of clients that, when offered a choice to select between submitting an electronic application form and a paper form, decided not to use the electronic form submission channels due to the lack of trust in the internet technologies. The underlying assumption was that such clients generally perceived electronic services as superfluous digital disruption rather than adding new value. We based our analysis on responses to a survey among the clients of a public service in a tender for buying or renting housing facilities. We demonstrate that the identified characteristics hierarchically organized in the form of a fast and frugal tree can provide classification models for effective real-world decision making to identify delicate citizen groups that might require a more focused communication st...
Research Interests:
Given its immense growth, the scientific literature can be explored to reveal new discoveries, based on as yet undiscovered relations between knowledge from different, relatively isolated fields of specialization. This chapter presents an... more
Given its immense growth, the scientific literature can be explored to reveal new discoveries, based on as yet undiscovered relations between knowledge from different, relatively isolated fields of specialization. This chapter presents an approach to creative knowledge discovery through the mechanism of bisociation. Bisociative reasoning is at the heart of creative, accidental discovery, i.e., serendipity. Bisociative knowledge discovery is focused on finding unexpected links by crossing between different contexts. In this work, bisociative knowledge discovery is explored in the framework of text mining, addressing cross-domain literature-based discovery. Two approaches are briefly outlined: the CrossBee approach to cross-domain bridgingterm detection, and the OntoGen approach to bridging-term detection through outlier document exploration.
Research Interests:
The generalized adoption of Electronic Medical Records (EMR) together with the need to give the patient the appropriate treatment at the appropriate moment at the appropriate cost is demanding solutions to analyze the information on the... more
The generalized adoption of Electronic Medical Records (EMR) together with the need to give the patient the appropriate treatment at the appropriate moment at the appropriate cost is demanding solutions to analyze the information on the EMR automatically. However most of the information on the EMR is non-structured: texts and images. Extracting knowledge from this data requires methods for structuring this information. Despite the efforts made in Natural Language Processing (NLP) even in the biomedical domain and in image processing, medical big data has still to undertake several challenges. The ungrammatical structure of clinical notes, abbreviations used and evolving terms have to be tackled in any Name Entity Recognition process. Moreover abbreviations, acronyms and terms are very much dependant on the language and the specific service. On the other hand, in the area of medical images, one of the main challenges is the development of new algorithms and methodologies that can help the physician take full advantage of the information contained in all these images. However, the large number of imaging modalities used today for diagnosis hinders the availability of general procedures as machine learning is, once again, a good approach for addressing this challenge. In this chapter, which concentrates on the problem of name entity recognition, we review previous approaches and look at future works. We also review the machine leaning approaches for image segmentation and annotation.
Research Interests:
Purpose – The increase of prevalence of autism spectrum disorders (ASD) has been accompanied by much new research. The amount and the speed of growth of scientific information available online have strongly influenced the way of work in... more
Purpose – The increase of prevalence of autism spectrum disorders (ASD) has been accompanied by much new research. The amount and the speed of growth of scientific information available online have strongly influenced the way of work in the research community which calls for new methods and tools to support it. The purpose of this paper is to present ontology-based text mining in the field of autism trend analysis that may help to understand the broader picture of the disorder since its discovery. Design/methodology/approach – The data sets consisted of abstracts of more than 18,000 articles on ASD published from 1943 to the end of 2012 found in MEDLINE and of the documents’ titles for all those articles where the abstracts were not available. Findings – In this way, the authors demonstrated a steeper exponential curve of ASD publications compared with all publications in MEDLINE. In addition, the main research topics over time were identified using the “open discovery” approach. Fi...
Research Interests:
Research Interests:
This chapter presents two methods that combine data mining and decision support techniques in marketing. The first method deals with targeting a direct mailing campaign and the second one with selecting the target consumer segment for a... more
This chapter presents two methods that combine data mining and decision support techniques in marketing. The first method deals with targeting a direct mailing campaign and the second one with selecting the target consumer segment for a marketing campaign. Both methods are applied on the results of completed questionnaires about brand name recognition in Slovenia. First, we give a motivation for the task. Then, we briefly describe the data and explain the preprocessing steps. In the main part of the paper we highlight the two methods that first use data mining to elicit knowledge from the data and then apply the knowledge in a system for decision support to help solving a difficult task. The chapter concludes with lessons learned and directions for further work
Research Interests:
Research Interests:
At the University of Nova Gorica we introduced game playing as a didactical approach for learning the role of information support in supply chain management. We implemented a well-known beer distribution game developed at MIT Sloan School... more
At the University of Nova Gorica we introduced game playing as a didactical approach for learning the role of information support in supply chain management. We implemented a well-known beer distribution game developed at MIT Sloan School of Management more than fifty years ago. The game is regularly used in the Business information systems course in the Engineering and Management study programme at University of Nova Gorica. The supporting computer program that enables the game to be played using mobile devices was developed by the course teacher. The game playing in this course has proved to be very efficient for learning the importance of relevant information flows for better decision making.
Research Interests:
Research Interests:
A general framework of the Sequential Diagnosis Tool that is currently under development in the Computer Systems Department at the Jo#ef Stefan Institute is presented in this paper. The tool can be used as an experimental environment for... more
A general framework of the Sequential Diagnosis Tool that is currently under development in the Computer Systems Department at the Jo#ef Stefan Institute is presented in this paper. The tool can be used as an experimental environment for the analysis of solutions of the test sequencing problem. For example, changes of decision trees and their costs as a function of system failure data can be studied. The tool also represents the basis of system diagnosis software package for a system maintenance and repair. V #lanku je opisan splo#ni koncept orodja za sekven#no diagnosticiranje, ki ga razvijamo v Odseku za ra#unalni#ke sisteme na Institutu Jo#ef Stefan. Orodje lahko slu#i kot eksperimentalno okolje za analiziranje re#itev problema generiranja testnih sekvenc. Tako lahko na primer prou#ujemo spremembe odlo #itvenih dreves in njihovih cen v odvisnosti od podatkov o odpovedi sistema. Obenem je opisano orodje osnova programskega okolja za sekven#no diagnosticiranje v okviru si...
Research Interests:
A system of computerized estimation of compatibility of stressors at work and worker's health characteristics is presented. Each characteristic is defined and scored on a specific scale. Incompatible workplace characteristics as... more
A system of computerized estimation of compatibility of stressors at work and worker's health characteristics is presented. Each characteristic is defined and scored on a specific scale. Incompatible workplace characteristics as related to worker's characteristics are singled out and offered to the user for an ergonomic solution. Work on the system started in 1987. This paper deals with the system's further development, which involves a larger number of topics, changes of the algorithm and presentation of an applicative case. Comparison of the system's results with those of medical experts shows that the use of the system tends to improve the thoroughness and consistency of incompatibility evaluations and consequently to make working ability assessment more objective.
Research Interests:
... top of page AUTHORS. Search for Maja Bračič Lotrič Search for Bojan Cestnik. ... 1. Bernjak A., Clarkson PBM, McClintock PV E, Stefanovska A., Low-frequency blood flow oscillations in congestive heart failure and after β1-blockade... more
... top of page AUTHORS. Search for Maja Bračič Lotrič Search for Bojan Cestnik. ... 1. Bernjak A., Clarkson PBM, McClintock PV E, Stefanovska A., Low-frequency blood flow oscillations in congestive heart failure and after β1-blockade treatment. Microvascular Res. ...
Research Interests:
Research Interests:
In this paper, we derived competences from previously developed competence models, ensuring the effective use of advanced technologies in future factories to improve the sustainability of their business models and strategies. Based on the... more
In this paper, we derived competences from previously developed competence models, ensuring the effective use of advanced technologies in future factories to improve the sustainability of their business models and strategies. Based on the analysis of the Hogan competence model and competence models for sustainability and leadership, we compiled a selection of competences for digitalisation, automation, robotics, artificial intelligence, and soft competences such as emotional intelligence and cultural literacy. We also included competences required for sustainability, corporate social responsibility, and circular economy. The selected competences formed the core for the conceptual development of a decision support tool for the individualised selection of training for employees. The concept was tested in customised training to improve employees’ skills and motivation for lifelong learning at the selected industrial partner. The developed assessment algorithm was used to monitor the pr...
Research Interests:
Studying relations between customer characteristics and usability requirements for online services remains a challenging task in e-government services development. In this paper we present the findings from a survey conducted among the... more
Studying relations between customer characteristics and usability requirements for online services remains a challenging task in e-government services development. In this paper we present the findings from a survey conducted among the users of an e-government service in public housing tender for buying housing facilities, where citizens were allowed to choose between two application submission channels: electronic submission and paper submission. Our aim was to detect the user characteristics that can be used to differentiate between the users that deliberately decide for the electronic form submission channel and those that prefer using the paper one. We show that such factors can be used to identify citizen groups that might require a more focused communication strategy to reduce the risks of potential e-government services dropouts. Our approach is aligned with the user centricity principle used in related studies, where the focus is on the ease and speed of using digital services online as perceived by the users.
Research Interests:
In this paper we analyze an easy-to-use and non-expensive educational mobile application called QTvity from the viewpoint of its scalability and its potential to be used in different educational settings. The tool allows the lecturer to... more
In this paper we analyze an easy-to-use and non-expensive educational mobile application called QTvity from the viewpoint of its scalability and its potential to be used in different educational settings. The tool allows the lecturer to interactively display questions on students' mobile devices during the lecture and to project the answers on the screen, enabling immediate feedback and providing guidelines for discussion needed to improve students' understanding of the topics to be learned. QTvity has already proved to have a very positive effect on the quality of educational process in small groups. To use it effectively in larger classes, originally implemented presentations of answers are not sufficient. To overcome this problem, aggregations of answers and their suitable visualizations, such as word cloud, descriptive statistics and histograms were suggested. In addition to this, new suggested features include anonymity of answers for public discussion, evaluation of st...
Business Analysis (BA) is a modern discipline that is involved in most projects where efficiency is to be improved. The tendency of BA is to improve value for a customer, which in turn brings more revenue to an organization [1].... more
Business Analysis (BA) is a modern discipline that is involved in most projects where efficiency is to be improved. The tendency of BA is to improve value for a customer, which in turn brings more revenue to an organization [1]. Historically, BA share common roots with system analysis. For example, business analysts are typically hired to investigate, analyze, design, and evaluate organization's business needs. However, business requirements are elicited and analyzed at a much more detailed level than traditionally done during systems analysis. BA also puts more emphasis on understanding user groups and business environments and designing highly usable applications. The discipline of BA is useful for solving business problems and taking advantage of opportunities by helping business people design procedures, structures, and technology to support and enhance their work. Similar requirements and needs are well known within effective and innovative approaches to e-learning. Therefo...
Open Educational Resources (OER) are gaining importance in design of course materials and study plans in different disciplines, especially in those developing very fast and demanding frequent updates of study materials. Although they... more
Open Educational Resources (OER) are gaining importance in design of course materials and study plans in different disciplines, especially in those developing very fast and demanding frequent updates of study materials. Although they affect also face-to-face learning, their biggest impact is on e-learning and blended learning. With their accessibility and diversity, OER promise to bridge the gap between big needs for new contents at one hand, and limited resources on the other. OER can become an important element on a way towards accessible and sustainable education, providing that appropriate mechanisms for supporting teachers in making, sharing, finding, selecting and reusing these materials are provided. It is important to take care that wide accessibility and big quantity of available materials will not decrease the quality of education, but rather contribute to its enhancement. We present ExplorEdu, a project that develops a web service for acquisition, structuring and analysis...
According to the World Health Report (World Health Organization, 2000), a health-care system (HCS) is a system composed of organizations, institutions and resources that are devoted to producing a health action. Human resources are one of... more
According to the World Health Report (World Health Organization, 2000), a health-care system (HCS) is a system composed of organizations, institutions and resources that are devoted to producing a health action. Human resources are one of the main parts of this system. This paper is focused on the model for monitoring and planning of human resources in the
Research Interests:
Research Interests:
The field of bisociative literature-based discovery aims at mining scientific literature to reveal yet uncovered connections between different fields of specialization. This paper outlines several outlier-based literature mining... more
The field of bisociative literature-based discovery aims at mining scientific literature to reveal yet uncovered connections between different fields of specialization. This paper outlines several outlier-based literature mining approaches to bridging term detection and the lessons learned from selected biomedical literature-based discovery applications. The paper addresses also new prospects in bisociative literature-based discovery, proposing an advanced embeddings-based technology for cross-domain literature mining.
Research Interests:
Literature-based discovery tools have been often used to overcome the problem of fragmentation of science and to assist researchers in their process of cross-domain knowledge discovery. In this paper we propose a methodology for... more
Literature-based discovery tools have been often used to overcome the problem of fragmentation of science and to assist researchers in their process of cross-domain knowledge discovery. In this paper we propose a methodology for cross-domain literature-based discovery that focuses on outlier documents to reduce the search space of potential cross-domain links and to improve search efficiency. In a previous study, literature mining tools OntoGen for document clustering and CrossBee for cross-domain bridging term exploration were combined to search for hidden relations in scientific papers from two different domains of interest, where the utility of the approach was demonstrated in a study involving PubMed papers about Alzheimer’s disease and gut microbiome. This paper extends the approach by proposing a methodology, implemented as a repeatable workflow in a web-based text mining platform TextFlows, which enables easy access and execution of the methodology for the interested researcher.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Our aim was to motivate and support more active student-teacher collaboration by using the students' mobile devices in class activities. We designed a mobile application called QTvity that can be used by the lecturer to prepare... more
Our aim was to motivate and support more active student-teacher collaboration by using the students' mobile devices in class activities. We designed a mobile application called QTvity that can be used by the lecturer to prepare questions related to the lecture contents. During the lectures, the application allows the lecturer to interactively display each question on the students' mobile devices and to designate the time period in which the students can submit their answers. The answers are then projected on the screen and discussed by the lecturer and students. Our experience of using QTvity indicates that the majority of students accept it as a motivating challenge, especially when their participation is stimulated with additional scoring that can improve their final grades. Among many benefits of such lectures compared to traditional ones we found out that the students not only pay more attention to the topics discussed during the lectures, but also tend to use their devices less for other distracting purposes (e.g. browsing social networks and writing messages to their friends). While both students and lecturers reported about improved student-teacher interaction, students appreciated also better peer-to-peer communication in the learning process. Analysis of students' feed-back revealed some subtle issues that contribute to better understanding of students' behaviour and indicate directions for further improvements of the system.
Research Interests:
Research Interests:
ABSTRACT Social networks foster information exchange and situation monitoring by offering new interpersonal communication means within a group of actively engaged concerned citizens. The hypothesis investigated in this article is that the... more
ABSTRACT Social networks foster information exchange and situation monitoring by offering new interpersonal communication means within a group of actively engaged concerned citizens. The hypothesis investigated in this article is that the citizens included in social computing are more likely to engage and participate in other services offered by public sector. Popularity of social computing seems to improve the confidence as well as the ICT literacy and awareness of its users. As a case study we selected a project for distributing housing subventions for young families and selling flats under favourable terms in Slovenia. With respect to a broader housing field we have observed that a group of concerned citizens even started a web forum documenting and analysing the activities of a public housing institution on a project of constructing residential dwellings for the market.
Research Interests:
Research Interests:
Research Interests:
ABSTRACT This paper present methods of data presentations that enable performance and activity monitoring of a health care system. The methods enable visual discovery of typical and atypical patterns, anomalies and outliers in the data.... more
ABSTRACT This paper present methods of data presentations that enable performance and activity monitoring of a health care system. The methods enable visual discovery of typical and atypical patterns, anomalies and outliers in the data. The methods were successfully implemented in a monitoring system developed for monitoring the primary healthcare system of Slovenia, to be used by the national Ministry of Health.
Research Interests:
The exploration of new forms of teaching that improve learning ability is often motivated by its positive influence on economic growth and social prosperity. In this paper we present a set of IT tools which can empower small nations to... more
The exploration of new forms of teaching that improve learning ability is often motivated by its positive influence on economic growth and social prosperity. In this paper we present a set of IT tools which can empower small nations to contribute to the treasure of widely accessible educational resources, and at the same time enhance their ability for using these resources with no fears of endangering their identity, so tightly attached to culture, tradition and language. The context of our study is a national initiative to develop and apply technological as well as pedagogical solutions to serve teachers and learners at all levels of education in Slovenia. We demonstrate the post-processing abilities such as automatic translation on a case study video lecture. The preliminary evaluation of the results indicates that the used tools can typically improve both the quality and the speed of the process of automatic transcription and translation.
Research Interests:
Research Interests:
Research Interests:
ABSTRACT In literature-based creative knowledge discovery the goal is to identify interesting terms or concepts which relate different domains. We propose to support this cross-context link discovery process by inspecting outlier... more
ABSTRACT In literature-based creative knowledge discovery the goal is to identify interesting terms or concepts which relate different domains. We propose to support this cross-context link discovery process by inspecting outlier documents which are not in the mainstream domain literature. We have explored the utility of outlier documents, discovered by combining three classification-based outlier detection methods, in terms of their potential for bridging concept discovery in the migraine-magnesium cross-domain discovery problem and in the autism-calcineurin domain pair. Experimental results prove that outlier documents present a small fraction of a domain pair dataset that is rich on concept bridging terms. Therefore, by exploring only a small subset of documents, where a great majority of bridging terms are present and more frequent, the effort needed for finding cross-domain links can be substantially reduced. Keywordstext mining–creative knowledge discovery–outlier detection
Research Interests:
Research Interests:
Research Interests:
Knowledge discovery in biomedicine is a time-consuming process starting from the basic research, through preclinical testing, towards possible clinical applications. Crossing of conceptual boundaries is often needed for groundbreaking... more
Knowledge discovery in biomedicine is a time-consuming process starting from the basic research, through preclinical testing, towards possible clinical applications. Crossing of conceptual boundaries is often needed for groundbreaking biomedical research that generates highly inventive discoveries. We demonstrate the ability of a creative literature mining method to advance valuable new discoveries based on rare ideas from existing literature. When emerging ideas from scientific literature are put together as fragments of knowledge in a systematic way, they may lead to original, sometimes surprising, research findings. If enough scientific evidence is already published for the association of such findings, they can be considered as scientific hypotheses. In this chapter, we describe a method for the computer-aided generation of such hypotheses based on the existing scientific literature. Our literature-based discovery of NF-kappaB with its possible connections to autism was recently...
Research Interests:
Research Interests:
Research Interests:
In the field of autism, an enormous increase in available information makes it very difficult to connect fragments of knowledge into a more coherent picture. We present a literature mining method, RaJoLink, to search for matched themes in... more
In the field of autism, an enormous increase in available information makes it very difficult to connect fragments of knowledge into a more coherent picture. We present a literature mining method, RaJoLink, to search for matched themes in unrelated literature that may contribute to a better understanding of complex pathological conditions, such as autism. 214 full text articles on autism, published in PubMed, served as a source of data. Using ontology construction, we identified the main concepts of what is already known about autism. Then, the RaJoLink method, based on Swanson's ABC model, was used to reveal potentially interesting, but not yet investigated, connections between different concepts in research. Among the more interesting concepts identified with RaJoLink in our study were calcineurin and NF-kappaB. Both terms can be linked to neuro-immune abnormalities in the brain of patients with autism. Further research is needed to provide stronger evidence about calcineurin ...
Research Interests:
Research Interests:
ABSTRACT Business analytics (BA) involves defining organization's capabilities and requirements in order to understand how it functions to accomplish its purposes. BA is typically performed to define and validate solutions that... more
ABSTRACT Business analytics (BA) involves defining organization's capabilities and requirements in order to understand how it functions to accomplish its purposes. BA is typically performed to define and validate solutions that are designed to meet organization's business needs, goals or objectives. To pursue this mission, analysts have to collect, analyse and synthesise huge amount of information. In this paper we demonstrate how constructing semantic ontologies can increase the level of automation of BA methods and techniques. This can be achieved by sophisticated semantic data analysis that can help us structure information and obtain birds-eye overview of a given domain. For the case study we take a set of abstracts from the articles presented on CompSysTech'09 conference and use OntoGen tool to semi-automatically construct ontology for the domain. The obtained results indicate that the proposed approach can be effectively used to digest textual information and present it in a more operational form of topic ontology. We argue that such approach can be useful also to generate domain knowledge in the field of BA.