Peter Butka | Technical University of Kosice (original) (raw)

Papers by Peter Butka

Research paper thumbnail of Explainability of deep learning models in medical image classification

Research paper thumbnail of The production of nitric oxide by centimetre-sized meteoroids in the upper atmosphere

European Planetary Science Congress, Sep 1, 2018

Research paper thumbnail of Cueing of Parkinson's Disease Patients by Standard Smart Devices and Deep Learning Approach

Acta Polytechnica Hungarica, 2023

Parkinson's disease is one of the most common neurological diseases. The patients suffer from dif... more Parkinson's disease is one of the most common neurological diseases. The patients suffer from different symptoms, e.g., tremor, bradykinesia, or walk gait disorders. One of the gait disorders which affects Parkinson's disease patients is freezing of gait, which shows as a sudden gait interruption without the ability to take the next step. It is hard to manage this symptom by medication. However, there are ways to address this symptom by applying different visual or vibration aids. This work presents a system for automatic detection and cue of freezing of gait events provided by ordinary smart devices. We used a deep learning approach to detect such events automatically. The test results and the doctors' opinions on the practical experience with the patients suggest the benefits of the provided solution.

Research paper thumbnail of Retrieval of important concepts from generalized one-sided concept lattice

One of the approaches used in data analysis area is related to the theory of concept lattices. It... more One of the approaches used in data analysis area is related to the theory of concept lattices. It is known as formal concept analysis (FCA), which is used for analysis of object-attribute input data models. The output of FCA is represented by concept lattice, which is the hierarchically organized structure of groups of objects with shared attributes (concepts). One of the main issues of FCA is a large number of concepts in generated concept lattice. In this paper, we present a solution based on information retrieval methods, where on the input is user query of what he/she wants to find in concept lattice and on the output we get concepts which best fits input query. Also, some interactive methods for visualization of best concepts are presented. Our approach is applied on concept lattice generated by the model of Generalized One-Side Concept Lattices (GOSCL), which against classical FCA models is suitable to work with different types of attributes used in input data tables. In order to work with this model, the modified Hamming distance was introduced for comparison of values of complex types of attributes.

Research paper thumbnail of The effect of meteoroid impacts on the ozone and nitric oxide budget in the upper Earth's atmosphere

Research paper thumbnail of Interaktívna vizualizácia výsledkov vyhľadávania informácií pomocou konceptových zväzov

Klasický pohľad na výsledky vyhľadávania získaných z vyhľadávača je často vo forme usporiadaného ... more Klasický pohľad na výsledky vyhľadávania získaných z vyhľadávača je často vo forme usporiadaného zoznamu, poznáme však aj systémy poskytujúce štruktúrovanú formu výsledkov. Cieľom tohto príspevku je popísať implementovaný systém pre interaktívnu vizualizáciu výsledkov vyhľadávania vo forme konceptového zväzu. Tento poskytuje štruktúrovanú formu hierarchicky usporiadaných podmnožín vrátených dokumentov na základe metódy známej ako FCA (Formal Concept Analysis). Vytvorený nástroj umožňuje zvoliť dopyt a získať hierarchickú štruktúru zhlukov vrátených výsledkov na základe analýzy obsahu ich krátkych popisovtzv. snippet-ov. Takto vytvorený konceptový zväz sa zobrazuje ako interaktívny graf, na ktorý je následne možné aplikovať redukcie zvyšujúce prehľadnosť výstupnej vizualizácie. Okrem grafickej vizualizácie je možné prehliadať aj jednotlivé výsledky a odkazy na nich, analyzovať ich vzťahy a odlišnosti vzhľadom na ich pozíciu v hierarchickej štruktúre zhlukov, ako aj využiť interaktívne zobrazenie pre rozšírenú navigáciu v sub-doméne odpovedajúcej množine vrátených výsledkov. Kľúčové slová: formálna konceptová analýza, vyhľadávanie informácií, vizualizácia, konceptový zväz Poďakovanie: Tento príspevok vznikol s podporou VEGA projektu č.1/0493/16, KEGA projektu č.025TUKE-4/2015 a APVV projektu č.APVV-16-0213.

Research paper thumbnail of Meteor activities within the BigSkyEarth COST Action: enabling new approaches in modeling and observations

European Planetary Science Congress, Sep 1, 2018

Research paper thumbnail of Retrieval of important concepts from generalized one-sided concept lattice

2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES), 2017

One of the approaches used in data analysis area is related to the theory of concept lattices. It... more One of the approaches used in data analysis area is related to the theory of concept lattices. It is known as formal concept analysis (FCA), which is used for analysis of object-attribute input data models. The output of FCA is represented by concept lattice, which is the hierarchically organized structure of groups of objects with shared attributes (concepts). One of the main issues of FCA is a large number of concepts in generated concept lattice. In this paper, we present a solution based on information retrieval methods, where on the input is user query of what he/she wants to find in concept lattice and on the output we get concepts which best fits input query. Also, some interactive methods for visualization of best concepts are presented. Our approach is applied on concept lattice generated by the model of Generalized One-Side Concept Lattices (GOSCL), which against classical FCA models is suitable to work with different types of attributes used in input data tables. In order to work with this model, the modified Hamming distance was introduced for comparison of values of complex types of attributes.

Research paper thumbnail of Experimental study on reduction of one-sided concept lattice based on subsets quality measure

2015 IEEE 10th Jubilee International Symposium on Applied Computational Intelligence and Informatics, 2015

The methods from the area of Formal Concept Analysis (or FCA) are usually used for conceptual-bas... more The methods from the area of Formal Concept Analysis (or FCA) are usually used for conceptual-based exploratory data-mining tasks. One of the methods used in this area is based on one-sided fuzzification of standard approach, which provides the clusters of objects structured in concept hierarchy according to the specified set of fuzzy attributes. The limiting problem of FCA-based approaches is that they produce large set of concepts, which can be problematic for the interpretability of results and practical usage of the method. We have designed a method for evaluation of concepts from so-called generalized one-sided concept lattice, which is based on the quality measure of objects subsets. This method selects most relevant concepts and therefore leads to reduction of concept lattice. In this paper we will provide experimental study on the reduction, which can be achieved according to different settings of randomly generated data sets.

Research paper thumbnail of Reduction ratio for GOSCL constrained by Moore co-families on object set

2015 IEEE 13th International Symposium on Applied Machine Intelligence and Informatics (SAMI), 2015

Generalized one-sided concept lattices (GOSCL) represent an FCA-like method for analysis of objec... more Generalized one-sided concept lattices (GOSCL) represent an FCA-like method for analysis of object-attribute models with different types of attributes. Since the number of concepts can be exponential with respect to the number of objects in a model, study of various reduction methods represents one of the most recognized problems in FCA. One of such reduction is possible, provided that a Moore co-family on object set is considered as some kind of parameter. In order to investigate the efficiency of such reduction method, we experimentally study a reduction ratio for randomly generated contexts.

Research paper thumbnail of Social-Media Data Analysis Using Tessera Framework in the Hadoop Cluster Environment

Advances in Intelligent Systems and Computing, 2016

The presented paper describes the design and implementation of R functions for twitter feeds anal... more The presented paper describes the design and implementation of R functions for twitter feeds analysis and visualization based on a combination of analytical technologies with big data processing tools. The main idea was to utilize the Hadoop processing framework and its storage and computational capabilities in analytical tasks designed and implemented in R language. For such purposes, we decided to use the Hadoop HDFS and MapReduce v2 for storage and handling of the processing logic connected via Tessera framework to analytical functions written in R. The results of the analysis were presented as the graph visualizations. Visualizations were implemented using the Trelliscope framework for flexible visualizations of large complex data in R environment in fast and effective fashion.

Research paper thumbnail of Interaktívna vizualizácia hierarchických štruktúr

V súčasnosti existuje množstvo dát v digitálnej podobe. Tieto dáta obsahujú informácie, ktoré môž... more V súčasnosti existuje množstvo dát v digitálnej podobe. Tieto dáta obsahujú informácie, ktoré môžu byť potencionálne užitočné napr. pre spoloč-nosti pri podpore rozhodovania. Na extrakciu informácií z dát je možné použiť širokú škálu metód analýzy dát. Problémom pri analýze dát je interpretácia jej výsledkov koncovým používateľom, tak aby získané informácie dokázali po-chopiť a následne vhodným spôsobom využiť. Jednou z možností ako čo naj-rýchlejšie porozumieť výsledkom je ich transformácia do grafickej podoby. Preto sa v tomto článku zameriame na prezentáciu rozličných vizualizačných techník určených na vizualizáciu výsledkov získaných z hierarchických metód analýzy dát akou je napr. formálna konceptová analýza

Research paper thumbnail of Automatic detection of atmospherics and tweek atmospherics in radio spectrograms based on a deep learning approach

Earth and Space Science, 2021

Lightning strikes can be routinely observed by the radio receivers that measure electromagnetic s... more Lightning strikes can be routinely observed by the radio receivers that measure electromagnetic signals in the very low frequency range. The acquired pulses called atmospherics provide valuable details about source lightning discharges and also about the Earth‐ionosphere waveguide where they can propagate thousands of kilometers. The automatic acquisition of the events requires also automatic methods for extraction of atmospherics' details to confirm the observed trends with statistical significance. For this purpose, we have developed a method based on a deep learning approach to automatically obtain the type of atmospherics, their exact time, and the frequency range from the frequency‐time spectrograms. The method that employs convolutional neural networks is designed to be adaptable to scientific needs and provide reliable results according to the requirements on the sensitivity to events, computation performance, and precision of extracted details. The efficiency and specific steps of our method are demonstrated for data recorded by the ELMAVAN‐G instrument. The comprehensive description of the method allows its usage for regular characterization of the ionospheric D‐layer or for other similar applications in the future.

Research paper thumbnail of Comparison of experimental identification methods using measured data from a turbojet engine

2016 IEEE 14th International Symposium on Applied Machine Intelligence and Informatics (SAMI), 2016

In this work, we compare nine methods of experimental identification (polynomial models, artifici... more In this work, we compare nine methods of experimental identification (polynomial models, artificial neural networks and deterministic methods). We use measured data from the small turbojet engine iSTC-21v to create experimental models through programming environment MATLAB/Simulink. Comparing the output of these calculated models with the real measured data, we get the amount of the mean absolute error (MAE) and mean absolute percentage error (MAPE) on the basis of which we determine the accuracy of each method.

Research paper thumbnail of Design and integration of ICT tools for OCOPOMO policy modelling approach

2012 7th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI), 2012

This paper describes design and integration of several tools for ICT-based support of knowledge i... more This paper describes design and integration of several tools for ICT-based support of knowledge intensive activities within the process of collaborative policy modelling proposed by the project OCOPOMO. This process combines collaborative creation and analysis of narrative scenarios with agent-based simulation models. The policy model for a given domain is created iteratively using cooperation of several stakeholder groups (decision makers, analysts, companies, civic societies, and the general public). Integration of scenario generation module, annotation module, model preparing phases and simulation tool (with the visualization tools) makes the whole OCOPOMO platform. The main focus of the paper is on the presentation of design and integration aspects of the architecture. Therefore, we describe software components, functionality, as well as some integration details. I.

Research paper thumbnail of Semantic Support for Educational IT Services

Acta Electrotechnica et Informatica, 2012

Technology enhanced learning is one of the intensively researched domains, because it promises in... more Technology enhanced learning is one of the intensively researched domains, because it promises interesting contribution to educational processes at various levels, in particular in higher education. This paper presents our approach to design and implementation of semantic-based electronic services, which will support selected educational processes, especially in mathematical and computer science disciplines. The resulting, semantically enhanced electronic services will provide powerful means to educators at the university, for preparation and running of their courses. Added semantics will make it possible to integrate various parts of the educational processes and help educators to minimize their efforts when preparing and running a new instance of a course, as well as effectively analyse the whole process and the students' performance.

Research paper thumbnail of Distributed task-based execution engine for support of text-mining processes

SAMI 2009 - 7th International Symposium on Applied Machine Intelligence and Informatics, Proceedings, 2009

This paper describes design and implementation aspects for extension of our original software sys... more This paper describes design and implementation aspects for extension of our original software system developed in Java for support of information retrieval and text mining with specialized execution engine for different type of tasks. Some of our experiences and specific requirements of the real applications lead us to idea give the system possibility to run the tasks in distributive way. The result of the idea is task-based execution engine, which represents middleware-like transparent layer (mostly for programmers who want to re-use functionality of our package) for running of different tasks in multi-thread environment. The original system is being developed as open source with the intention to provide an easy extensible, modular framework for pre-processing, indexing and further exploration of large text collections. This specialized execution engine has been implemented within APVV project called PoZnaŤ (Support for knowledge creation processes) in order to extend proposed text-mining platform for educational and experimental purposes. Conceptual architecture of the system is provided as well as details regarding our extension of library like usage of content repository paradigm, representation and encapsulation of tasks, implementation of the engine itself and its role within PoZnaŤ platform. I. II.

Research paper thumbnail of Design of a system architecture for support of collaborative policy modelling processes

2011 6th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI), 2011

The paper describes a design of system architecture for support of collaborative policy modelling... more The paper describes a design of system architecture for support of collaborative policy modelling processes in electronic governance. The policy modelling processes, as complex and knowledge intensive activities, combine collaborative creation and analysis of narrative scenarios with agent-based simulation. The proposed architecture will support collaborative approach to the policy modelling (i.e. enhance the modelling processes by collective intelligence). A scope of the proposed system will be specified and platform architecture components, including some practical details regarding their implementation, will be described. I.

Research paper thumbnail of Task-Based Execution Engine for JBOWL

on Intelligent and Knowledge Oriented Technologies

Abstract. This paper describes design aspects for extension of our original software system devel... more Abstract. This paper describes design aspects for extension of our original software system developed in Java for support of information retrieval and text mining with specialized execution engine for different type of tasks. Some of our experiences and specific requirements of the real applications lead us to idea give the system possibility to run the tasks in distributive/parallel way. The result of the idea is task-based execution engine, which represents middlewarelike transparent layer (mostly for programmers who want to ...

Research paper thumbnail of The OCOPOMO Project: A Toolkit Supporting the Open Collaboration for Policy Modelling

tuke.sk

Abstract. The paper describes the FP7 ICT OCOPOMO project aimed at development of a software plat... more Abstract. The paper describes the FP7 ICT OCOPOMO project aimed at development of a software platform supporting collaborative policy modelling. After a short introduction of basic facts on the project, principles and key concepts of collaborative policy modelling are outlined and the adopted approach together with the envisioned functionality is described. Finally, a design of high-level architecture of the OCOPOMO system modules and inner software components are presented. Keywords: Collaborative policy modelling, e- ...

Research paper thumbnail of Explainability of deep learning models in medical image classification

Research paper thumbnail of The production of nitric oxide by centimetre-sized meteoroids in the upper atmosphere

European Planetary Science Congress, Sep 1, 2018

Research paper thumbnail of Cueing of Parkinson's Disease Patients by Standard Smart Devices and Deep Learning Approach

Acta Polytechnica Hungarica, 2023

Parkinson's disease is one of the most common neurological diseases. The patients suffer from dif... more Parkinson's disease is one of the most common neurological diseases. The patients suffer from different symptoms, e.g., tremor, bradykinesia, or walk gait disorders. One of the gait disorders which affects Parkinson's disease patients is freezing of gait, which shows as a sudden gait interruption without the ability to take the next step. It is hard to manage this symptom by medication. However, there are ways to address this symptom by applying different visual or vibration aids. This work presents a system for automatic detection and cue of freezing of gait events provided by ordinary smart devices. We used a deep learning approach to detect such events automatically. The test results and the doctors' opinions on the practical experience with the patients suggest the benefits of the provided solution.

Research paper thumbnail of Retrieval of important concepts from generalized one-sided concept lattice

One of the approaches used in data analysis area is related to the theory of concept lattices. It... more One of the approaches used in data analysis area is related to the theory of concept lattices. It is known as formal concept analysis (FCA), which is used for analysis of object-attribute input data models. The output of FCA is represented by concept lattice, which is the hierarchically organized structure of groups of objects with shared attributes (concepts). One of the main issues of FCA is a large number of concepts in generated concept lattice. In this paper, we present a solution based on information retrieval methods, where on the input is user query of what he/she wants to find in concept lattice and on the output we get concepts which best fits input query. Also, some interactive methods for visualization of best concepts are presented. Our approach is applied on concept lattice generated by the model of Generalized One-Side Concept Lattices (GOSCL), which against classical FCA models is suitable to work with different types of attributes used in input data tables. In order to work with this model, the modified Hamming distance was introduced for comparison of values of complex types of attributes.

Research paper thumbnail of The effect of meteoroid impacts on the ozone and nitric oxide budget in the upper Earth's atmosphere

Research paper thumbnail of Interaktívna vizualizácia výsledkov vyhľadávania informácií pomocou konceptových zväzov

Klasický pohľad na výsledky vyhľadávania získaných z vyhľadávača je často vo forme usporiadaného ... more Klasický pohľad na výsledky vyhľadávania získaných z vyhľadávača je často vo forme usporiadaného zoznamu, poznáme však aj systémy poskytujúce štruktúrovanú formu výsledkov. Cieľom tohto príspevku je popísať implementovaný systém pre interaktívnu vizualizáciu výsledkov vyhľadávania vo forme konceptového zväzu. Tento poskytuje štruktúrovanú formu hierarchicky usporiadaných podmnožín vrátených dokumentov na základe metódy známej ako FCA (Formal Concept Analysis). Vytvorený nástroj umožňuje zvoliť dopyt a získať hierarchickú štruktúru zhlukov vrátených výsledkov na základe analýzy obsahu ich krátkych popisovtzv. snippet-ov. Takto vytvorený konceptový zväz sa zobrazuje ako interaktívny graf, na ktorý je následne možné aplikovať redukcie zvyšujúce prehľadnosť výstupnej vizualizácie. Okrem grafickej vizualizácie je možné prehliadať aj jednotlivé výsledky a odkazy na nich, analyzovať ich vzťahy a odlišnosti vzhľadom na ich pozíciu v hierarchickej štruktúre zhlukov, ako aj využiť interaktívne zobrazenie pre rozšírenú navigáciu v sub-doméne odpovedajúcej množine vrátených výsledkov. Kľúčové slová: formálna konceptová analýza, vyhľadávanie informácií, vizualizácia, konceptový zväz Poďakovanie: Tento príspevok vznikol s podporou VEGA projektu č.1/0493/16, KEGA projektu č.025TUKE-4/2015 a APVV projektu č.APVV-16-0213.

Research paper thumbnail of Meteor activities within the BigSkyEarth COST Action: enabling new approaches in modeling and observations

European Planetary Science Congress, Sep 1, 2018

Research paper thumbnail of Retrieval of important concepts from generalized one-sided concept lattice

2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES), 2017

One of the approaches used in data analysis area is related to the theory of concept lattices. It... more One of the approaches used in data analysis area is related to the theory of concept lattices. It is known as formal concept analysis (FCA), which is used for analysis of object-attribute input data models. The output of FCA is represented by concept lattice, which is the hierarchically organized structure of groups of objects with shared attributes (concepts). One of the main issues of FCA is a large number of concepts in generated concept lattice. In this paper, we present a solution based on information retrieval methods, where on the input is user query of what he/she wants to find in concept lattice and on the output we get concepts which best fits input query. Also, some interactive methods for visualization of best concepts are presented. Our approach is applied on concept lattice generated by the model of Generalized One-Side Concept Lattices (GOSCL), which against classical FCA models is suitable to work with different types of attributes used in input data tables. In order to work with this model, the modified Hamming distance was introduced for comparison of values of complex types of attributes.

Research paper thumbnail of Experimental study on reduction of one-sided concept lattice based on subsets quality measure

2015 IEEE 10th Jubilee International Symposium on Applied Computational Intelligence and Informatics, 2015

The methods from the area of Formal Concept Analysis (or FCA) are usually used for conceptual-bas... more The methods from the area of Formal Concept Analysis (or FCA) are usually used for conceptual-based exploratory data-mining tasks. One of the methods used in this area is based on one-sided fuzzification of standard approach, which provides the clusters of objects structured in concept hierarchy according to the specified set of fuzzy attributes. The limiting problem of FCA-based approaches is that they produce large set of concepts, which can be problematic for the interpretability of results and practical usage of the method. We have designed a method for evaluation of concepts from so-called generalized one-sided concept lattice, which is based on the quality measure of objects subsets. This method selects most relevant concepts and therefore leads to reduction of concept lattice. In this paper we will provide experimental study on the reduction, which can be achieved according to different settings of randomly generated data sets.

Research paper thumbnail of Reduction ratio for GOSCL constrained by Moore co-families on object set

2015 IEEE 13th International Symposium on Applied Machine Intelligence and Informatics (SAMI), 2015

Generalized one-sided concept lattices (GOSCL) represent an FCA-like method for analysis of objec... more Generalized one-sided concept lattices (GOSCL) represent an FCA-like method for analysis of object-attribute models with different types of attributes. Since the number of concepts can be exponential with respect to the number of objects in a model, study of various reduction methods represents one of the most recognized problems in FCA. One of such reduction is possible, provided that a Moore co-family on object set is considered as some kind of parameter. In order to investigate the efficiency of such reduction method, we experimentally study a reduction ratio for randomly generated contexts.

Research paper thumbnail of Social-Media Data Analysis Using Tessera Framework in the Hadoop Cluster Environment

Advances in Intelligent Systems and Computing, 2016

The presented paper describes the design and implementation of R functions for twitter feeds anal... more The presented paper describes the design and implementation of R functions for twitter feeds analysis and visualization based on a combination of analytical technologies with big data processing tools. The main idea was to utilize the Hadoop processing framework and its storage and computational capabilities in analytical tasks designed and implemented in R language. For such purposes, we decided to use the Hadoop HDFS and MapReduce v2 for storage and handling of the processing logic connected via Tessera framework to analytical functions written in R. The results of the analysis were presented as the graph visualizations. Visualizations were implemented using the Trelliscope framework for flexible visualizations of large complex data in R environment in fast and effective fashion.

Research paper thumbnail of Interaktívna vizualizácia hierarchických štruktúr

V súčasnosti existuje množstvo dát v digitálnej podobe. Tieto dáta obsahujú informácie, ktoré môž... more V súčasnosti existuje množstvo dát v digitálnej podobe. Tieto dáta obsahujú informácie, ktoré môžu byť potencionálne užitočné napr. pre spoloč-nosti pri podpore rozhodovania. Na extrakciu informácií z dát je možné použiť širokú škálu metód analýzy dát. Problémom pri analýze dát je interpretácia jej výsledkov koncovým používateľom, tak aby získané informácie dokázali po-chopiť a následne vhodným spôsobom využiť. Jednou z možností ako čo naj-rýchlejšie porozumieť výsledkom je ich transformácia do grafickej podoby. Preto sa v tomto článku zameriame na prezentáciu rozličných vizualizačných techník určených na vizualizáciu výsledkov získaných z hierarchických metód analýzy dát akou je napr. formálna konceptová analýza

Research paper thumbnail of Automatic detection of atmospherics and tweek atmospherics in radio spectrograms based on a deep learning approach

Earth and Space Science, 2021

Lightning strikes can be routinely observed by the radio receivers that measure electromagnetic s... more Lightning strikes can be routinely observed by the radio receivers that measure electromagnetic signals in the very low frequency range. The acquired pulses called atmospherics provide valuable details about source lightning discharges and also about the Earth‐ionosphere waveguide where they can propagate thousands of kilometers. The automatic acquisition of the events requires also automatic methods for extraction of atmospherics' details to confirm the observed trends with statistical significance. For this purpose, we have developed a method based on a deep learning approach to automatically obtain the type of atmospherics, their exact time, and the frequency range from the frequency‐time spectrograms. The method that employs convolutional neural networks is designed to be adaptable to scientific needs and provide reliable results according to the requirements on the sensitivity to events, computation performance, and precision of extracted details. The efficiency and specific steps of our method are demonstrated for data recorded by the ELMAVAN‐G instrument. The comprehensive description of the method allows its usage for regular characterization of the ionospheric D‐layer or for other similar applications in the future.

Research paper thumbnail of Comparison of experimental identification methods using measured data from a turbojet engine

2016 IEEE 14th International Symposium on Applied Machine Intelligence and Informatics (SAMI), 2016

In this work, we compare nine methods of experimental identification (polynomial models, artifici... more In this work, we compare nine methods of experimental identification (polynomial models, artificial neural networks and deterministic methods). We use measured data from the small turbojet engine iSTC-21v to create experimental models through programming environment MATLAB/Simulink. Comparing the output of these calculated models with the real measured data, we get the amount of the mean absolute error (MAE) and mean absolute percentage error (MAPE) on the basis of which we determine the accuracy of each method.

Research paper thumbnail of Design and integration of ICT tools for OCOPOMO policy modelling approach

2012 7th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI), 2012

This paper describes design and integration of several tools for ICT-based support of knowledge i... more This paper describes design and integration of several tools for ICT-based support of knowledge intensive activities within the process of collaborative policy modelling proposed by the project OCOPOMO. This process combines collaborative creation and analysis of narrative scenarios with agent-based simulation models. The policy model for a given domain is created iteratively using cooperation of several stakeholder groups (decision makers, analysts, companies, civic societies, and the general public). Integration of scenario generation module, annotation module, model preparing phases and simulation tool (with the visualization tools) makes the whole OCOPOMO platform. The main focus of the paper is on the presentation of design and integration aspects of the architecture. Therefore, we describe software components, functionality, as well as some integration details. I.

Research paper thumbnail of Semantic Support for Educational IT Services

Acta Electrotechnica et Informatica, 2012

Technology enhanced learning is one of the intensively researched domains, because it promises in... more Technology enhanced learning is one of the intensively researched domains, because it promises interesting contribution to educational processes at various levels, in particular in higher education. This paper presents our approach to design and implementation of semantic-based electronic services, which will support selected educational processes, especially in mathematical and computer science disciplines. The resulting, semantically enhanced electronic services will provide powerful means to educators at the university, for preparation and running of their courses. Added semantics will make it possible to integrate various parts of the educational processes and help educators to minimize their efforts when preparing and running a new instance of a course, as well as effectively analyse the whole process and the students' performance.

Research paper thumbnail of Distributed task-based execution engine for support of text-mining processes

SAMI 2009 - 7th International Symposium on Applied Machine Intelligence and Informatics, Proceedings, 2009

This paper describes design and implementation aspects for extension of our original software sys... more This paper describes design and implementation aspects for extension of our original software system developed in Java for support of information retrieval and text mining with specialized execution engine for different type of tasks. Some of our experiences and specific requirements of the real applications lead us to idea give the system possibility to run the tasks in distributive way. The result of the idea is task-based execution engine, which represents middleware-like transparent layer (mostly for programmers who want to re-use functionality of our package) for running of different tasks in multi-thread environment. The original system is being developed as open source with the intention to provide an easy extensible, modular framework for pre-processing, indexing and further exploration of large text collections. This specialized execution engine has been implemented within APVV project called PoZnaŤ (Support for knowledge creation processes) in order to extend proposed text-mining platform for educational and experimental purposes. Conceptual architecture of the system is provided as well as details regarding our extension of library like usage of content repository paradigm, representation and encapsulation of tasks, implementation of the engine itself and its role within PoZnaŤ platform. I. II.

Research paper thumbnail of Design of a system architecture for support of collaborative policy modelling processes

2011 6th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI), 2011

The paper describes a design of system architecture for support of collaborative policy modelling... more The paper describes a design of system architecture for support of collaborative policy modelling processes in electronic governance. The policy modelling processes, as complex and knowledge intensive activities, combine collaborative creation and analysis of narrative scenarios with agent-based simulation. The proposed architecture will support collaborative approach to the policy modelling (i.e. enhance the modelling processes by collective intelligence). A scope of the proposed system will be specified and platform architecture components, including some practical details regarding their implementation, will be described. I.

Research paper thumbnail of Task-Based Execution Engine for JBOWL

on Intelligent and Knowledge Oriented Technologies

Abstract. This paper describes design aspects for extension of our original software system devel... more Abstract. This paper describes design aspects for extension of our original software system developed in Java for support of information retrieval and text mining with specialized execution engine for different type of tasks. Some of our experiences and specific requirements of the real applications lead us to idea give the system possibility to run the tasks in distributive/parallel way. The result of the idea is task-based execution engine, which represents middlewarelike transparent layer (mostly for programmers who want to ...

Research paper thumbnail of The OCOPOMO Project: A Toolkit Supporting the Open Collaboration for Policy Modelling

tuke.sk

Abstract. The paper describes the FP7 ICT OCOPOMO project aimed at development of a software plat... more Abstract. The paper describes the FP7 ICT OCOPOMO project aimed at development of a software platform supporting collaborative policy modelling. After a short introduction of basic facts on the project, principles and key concepts of collaborative policy modelling are outlined and the adopted approach together with the envisioned functionality is described. Finally, a design of high-level architecture of the OCOPOMO system modules and inner software components are presented. Keywords: Collaborative policy modelling, e- ...