| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Search the digital library catalog Help

Query: search in
search in
search in
search in
* old and bologna study programme

Options:
  Reset


41 - 50 / 64
First pagePrevious page1234567Next pageLast page
41.
Group decision making
Vladislav Rajkovič, 2011, original scientific article

Abstract: The paper discusses group decision making as a way of managing decision knowledge. Described are pros and cons of group decision making. Special emphasis is given to the leveraging of different interests and possibilities of formulating a joint decision. Available methods and techniques together with a properly organized group work can make a substantial contribution.
Keywords: decision making, groups, conflict of interest, leveraging interests, hierarchical modelling
Published: 10.07.2015; Views: 882; Downloads: 84
.pdf Full text (646,93 KB)
This document has many files! More...

42.
Comparative analysis of collaborative and simulation based learning in the management environment
Mirjana Kljajić Borštnar, 2012, original scientific article

Abstract: Purpose of the study is to compare two different approaches to the collaborative problem solving one in a highly controlled laboratory experiment: Optimisation of business politics using business simulator at different experimental condition which reflect different feedback information structure and one in a collaborative environment of the social media, characterised by non-structured, rule-free and even chaotic feedback information. Comparative analyses of participant’s opinion who participate in experiments have been considered in order to find common characteristics relevant for group/collaborative problem solving. Based on these findings a general explanatory causal loop model of collaborative learning during problem solving was built.
Keywords: group decision support, information structure, collaborative learning, simulation model
Published: 10.07.2015; Views: 867; Downloads: 292
.pdf Full text (325,88 KB)
This document has many files! More...

43.
Computer aided decision support in product design engineering
Marina Novak, 2012, original scientific article

Abstract: Product design engineering is a complex discipline, which is undergoing a transformation from informal and largely experience-based domain to scientific oriented domain. Computational intelligence can contribute greatly to product design process, as it is becoming more and more evident that adding intelligence to existing computer aids, such as computer aided design systems, can lead to significant improvements in terms of effectiveness and reliability of various tasks within product design engineering. Providing computer aided decision support is one of the computational intelligence methods that proved to be effective in enabling more intelligent and less experience-dependent design performance. In this paper, some of the most crucial areas of product design engineering process that require additional computational intelligence in terms of computer aided decision support are presented together with some examples of intelligent knowledge-based modules applied to this areas.
Keywords: product development, design engineering, design for X, computational intelligence, decision support, knowledge-based modules
Published: 10.07.2015; Views: 1072; Downloads: 56
.pdf Full text (1,73 MB)
This document has many files! More...

44.
VTJ48 - Visually Tuned J48
Gregor Štiglic, 2012, software

Keywords: decision trees, comprehensible classifiers, machine learning
Published: 10.07.2015; Views: 1390; Downloads: 34
URL Link to full text

45.
46.
47.
TOWARDS A SUSTAINABLE SYSTEM FOR NON-BUREAUCRATIC GOVERNMENT
Aloisius Paulin, 2015, doctoral dissertation

Abstract: The present doctoral thesis develops a pioneering system for the self-management of jural eligibilities by means of ICTs as the basis for a novel form of government of juropolitical societies. By means of this system we aim to contribute towards a form of government that would not require a dedicated civil service for the creation, storage, change, and deletion of jural eligibilities in the context of the res publica. In the thesis we explore the concept of jural relations as the atomic links of governmental systems, the composition of the jural relations as such, as well as the role of the jural subjectivity as a crucial component for creating complex systems of jural relations that serve as the underlying structures of juropolitical systems. We then walk through the history of the civil service – the bureaucratic machine, as Banfield called it, to understand its role and implications on the course of civilization, up till present time, where we discuss the impacts of ICTs on the development of the bureaucratic machine as such. We argue that the changes which ICTs so far brought to the government sector through what is known as e-government, e-democracy, and e-governance respectively, are based on unsustainable artefacts and hence there are strong reasons for them to be considered more of a burden to future generations, rather than a source of relief. Based on the implications of the so explored context we describe a model for an information system that would enable self-managed creation and determination of jural eligibilities, and thus self-managed government of juropolitical societies as such. We call this model Sustainable Non-Bureaucratic Government (SNBG). SNBG bases on a network of electronic registries, which store jural facts, from which eligibilities can be derived through a dedicated mechanism, which we call constellation-based reasoning (CBR). CBR bases on a purposely developed fine-grained data access control mechanism, which does not rely on predefined accessor roles, but dynamically enables / disables access to data based on the context of the request and the context of the data stored in the accessed registry. As such, CBR is purposely designed to support changing the rules of access to the stored data by means of collaborative decision making, as such is required in the political legislative context, whereby the rules that regulate such decision making, are again governed by the very same system, which ensures full flexibility of the SNBG system to fluidly undergo at design-time unpredictable transitions that would happen through time. This feature amongst others then, assures the system’s sustainability. We describe the architecture and the stakeholders of SNBG, as well as auxiliary constructs for planning and communicating regulations which make-up the CBR rules. We define the functional characteristics that instances of the electronic registries must satisfy in order to assure sustainability and to be applicable in the juropolitical context in accordance with core jural principles (and in order to avoid the mistakes as conducted in the course of development of e-government artefacts). Then, we describe the instantiation of a prototype SNBG system, i.e. the instantiation of a respective electronic registry that provides CBR-based access to the underlying data stored in a relational database. We evaluate this prototype instantiation based on three demo applications, which prove its technical feasibility in different scenarios. Finally, we evaluate the SNBG model in four different real-world scenarios to argue for its feasibility in crucial governance situations.
Keywords: unsustainability of e-government, self-management of jural relations, computability of jural eligibilities, non-bureaucratic government, collaborative decision making, liquid democracy, fine-grained data access control, fair non-repudiation, digital identity
Published: 04.06.2015; Views: 1182; Downloads: 31
.pdf Full text (11,06 MB)

48.
Contrasting temporal trend discovery for large healthcare databases
Goran Hrovat, Gregor Štiglic, Peter Kokol, Milan Ojsteršek, original scientific article

Abstract: With the increased acceptance of electronic health records, we can observe theincreasing interest in the application of data mining approaches within this field. This study introduces a novel approach for exploring and comparingtemporal trends within different in-patient subgroups, which is basedon associated rule mining using Apriori algorithm and linear model-based recursive partitioning. The Nationwide Inpatient Sample (NIS), Healthcare Costand Utilization Project (HCUP), Agency for Healthcare Research and Qualitywas used to evaluate the proposed approach. This study presents a novelapproach where visual analytics on big data is used for trend discovery in form of a regression tree with scatter plots in the leaves of the tree. Thetrend lines are used for directly comparing linear trends within a specified time frame. Our results demonstrate the existence of opposite trendsin relation to age and sex based subgroups that would be impossible to discover using traditional trend-tracking techniques. Such an approach can be employed regarding decision support applications for policy makers when organizing campaigns or by hospital management for observing trends that cannot be directly discovered using traditional analytical techniques.
Keywords: data mining, decision support, trend discovery
Published: 27.11.2014; Views: 1267; Downloads: 395
.pdf Full text (1013,97 KB)
This document has many files! More...

49.
ACQUIRING TEMPORAL KNOWLEDGE FOR MAKING DECISIONS IN MEDICAL PROCESSES
Aida Kamišalić Latifić, 2014, doctoral dissertation

Abstract: A medical process is a set of medical actions performed by healthcare professionals while making observations about signs and symptoms, ordering interventions, prescriptions, tests, and any other actions in order to solve a health problem that is affecting a particular patient. The objective is to offer a curative, chronic, palliative and/or symptomatic treatments. The capability of a physician to propose an appropriate treatment depends on his/her knowledge of similar clinical cases and by following advances in the treatment of particular diseases. Time is an important concept of the real world that has to be considered in regard to medical processes. Clinical Practice Guidelines (CPGs) are a narrative set of recommendations for treating patients suffering from a particular disease. By constantly referring to CPGs physicians can stay up to date with the best evidence-based medical care and with the recommendations of experts. The time dimension is, however, often omitted or only partially covered in CPGs. Some CPGs do contain certain recommendations considering time but often there are huge gaps that are supposed to be overcome by physicians’ own knowledge and experience. At the same time, healthcare centres hold healthcare records and information systems that register medical processes and patients data, including information about the times of any encounters, prescriptions, and other medical actions. Therefore healthcare records and information systems data can be a source for detecting temporal medical knowledge and sound evidence regarding healthcare. This thesis is centred on temporal knowledge acquisition and representation for the purposes of decision-making during medical processes. CPGs were analysed to obtain procedural knowledge models and Extended Timed Transition Diagrams defined for representations of the obtained knowledge. The data about the treatments of patients were analysed in order to detect temporal medical knowledge models that represented those medical procedures that were carried out while the data was being generated. These models thus provided an explicit representation of the time dimensions of past medical procedures. They could be used for complementing the knowledge provided by CPGs, for studying adherences to the CPGs and for representing a basic framework for medical procedural decision support systems development.
Keywords: knowledge acquisition, knowledge representation, temporal knowledge, decision-making, medical processes, procedural knowledge modelling
Published: 25.02.2014; Views: 1302; Downloads: 110
.pdf Full text (2,91 MB)

50.
Comprehensive decision tree models in bioinformatics
Gregor Štiglic, Simon Kocbek, Igor Pernek, Peter Kokol, 2012, original scientific article

Abstract: Purpose Classification is an important and widely used machine learning technique in bioinformatics. Researchers and other end-users of machine learning software often prefer to work with comprehensible models where knowledge extraction and explanation of reasoning behind the classification model are possible. Methods This paper presents an extension to an existing machine learning environment and a study on visual tuning of decision tree classifiers. The motivation for this research comes from the need to build effective and easily interpretable decision tree models by so called one-button data mining approach where no parameter tuning is needed. To avoid bias in classification, no classification performance measure is used during the tuning of the model that is constrained exclusively by the dimensions of the produced decision tree. Results The proposed visual tuning of decision trees was evaluated on 40 datasets containing classical machine learning problems and 31 datasets from the field of bioinformatics. Although we did notexpected significant differences in classification performance, the resultsdemonstrate a significant increase of accuracy in less complex visuallytuned decision trees. In contrast to classical machine learning benchmarking datasets, we observe higher accuracy gains in bioinformatics datasets. Additionally, a user study was carried out to confirm the assumptionthat the tree tuning times are significantly lower for the proposed method in comparison to manual tuning of the decision tree. Conclusions The empirical results demonstrate that by building simple models constrained by predefined visual boundaries, one not only achieves good comprehensibility, but also very good classification performance that does not differ from usually more complex models built using default settings of the classical decision tree algorithm. In addition, our study demonstrates the suitability of visually tuned decision trees for datasets with binary class attributes anda high number of possibly redundant attributes that are very common in bioinformatics.
Keywords: decision tree models, machine learning technique, visual tuning, bioinformatics
Published: 05.06.2012; Views: 1324; Downloads: 258
.pdf Full text (524,39 KB)
This document has many files! More...

Search done in 0.3 sec.
Back to top
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica