Revista y Edición

Volumen 47 (2022): Edición 3 (September 2022)

Volumen 47 (2022): Edición 2 (June 2022)

Volumen 47 (2022): Edición 1 (February 2022)

Volumen 46 (2021): Edición 4 (December 2021)

Volumen 46 (2021): Edición 3 (September 2021)

Volumen 46 (2021): Edición 2 (June 2021)

Volumen 46 (2021): Edición 1 (March 2021)

Volumen 45 (2020): Edición 4 (December 2020)

Volumen 45 (2020): Edición 3 (September 2020)

Volumen 45 (2020): Edición 2 (June 2020)

Volumen 45 (2020): Edición 1 (March 2020)

Volumen 44 (2019): Edición 4 (December 2019)

Volumen 44 (2019): Edición 3 (September 2019)

Volumen 44 (2019): Edición 2 (June 2019)

Volumen 44 (2019): Edición 1 (March 2019)

Volumen 43 (2018): Edición 4 (December 2018)

Volumen 43 (2018): Edición 3 (September 2018)

Volumen 43 (2018): Edición 2 (June 2018)

Volumen 43 (2018): Edición 1 (March 2018)

Volumen 42 (2017): Edición 4 (December 2017)

Volumen 42 (2017): Edición 3 (September 2017)

Volumen 42 (2017): Edición 2 (June 2017)

Volumen 42 (2017): Edición 1 (February 2017)

Volumen 41 (2016): Edición 4 (November 2016)

Volumen 41 (2016): Edición 3 (September 2016)

Volumen 41 (2016): Edición 2 (June 2016)

Volumen 41 (2016): Edición 1 (March 2016)

Volumen 40 (2015): Edición 4 (December 2015)

Volumen 40 (2015): Edición 3 (September 2015)

Volumen 40 (2015): Edición 2 (June 2015)

Volumen 40 (2015): Edición 1 (March 2015)

Volumen 39 (2014): Edición 4 (December 2014)

Volumen 39 (2014): Edición 3 (September 2014)

Volumen 39 (2014): Edición 2 (June 2014)

Volumen 39 (2014): Edición 1 (February 2014)

Volumen 38 (2013): Edición 4 (December 2013)

Volumen 38 (2013): Edición 3 (September 2013)

Volumen 38 (2013): Edición 2 (June 2013)

Volumen 38 (2013): Edición 1 (March 2013)

Volumen 37 (2012): Edición 4 (December 2012)

Volumen 37 (2012): Edición 3 (September 2012)

Volumen 37 (2012): Edición 2 (June 2012)

Volumen 37 (2012): Edición 1 (March 2012)

Detalles de la revista
Formato
Revista
eISSN
2300-3405
Publicado por primera vez
24 Oct 2012
Periodo de publicación
4 veces al año
Idiomas
Inglés

Buscar

Volumen 45 (2020): Edición 3 (September 2020)

Detalles de la revista
Formato
Revista
eISSN
2300-3405
Publicado por primera vez
24 Oct 2012
Periodo de publicación
4 veces al año
Idiomas
Inglés

Buscar

5 Artículos
Acceso abierto

Artificial Intelligence Research Community and Associations in Poland

Publicado en línea: 18 Sep 2020
Páginas: 159 - 177

Resumen

Abstract

In last years Artificial Intelligence presented a tremendous progress by offering a variety of novel methods, tools and their spectacular applications. Besides showing scientific breakthroughs it attracted interest both of the general public and industry. It also opened heated debates on the impact of Artificial Intelligence on changing the economy and society. Having in mind this international landscape, in this short paper we discuss the Polish AI research community, some of its main achievements, opportunities and limitations. We put this discussion in the context of the current developments in the international AI community. Moreover, we refer to activities of Polish scientific associations and their initiative of founding Polish Alliance for the Development of Artificial Intelligence (PP-RAI). Finally two last editions of PP-RAI joint conferences are summarized.

Acceso abierto

Transfer Learning Methods as a New Approach in Computer Vision Tasks with Small Datasets

Publicado en línea: 18 Sep 2020
Páginas: 179 - 193

Resumen

Abstract

Deep learning methods, used in machine vision challenges, often face the problem of the amount and quality of data. To address this issue, we investigate the transfer learning method. In this study, we briefly describe the idea and introduce two main strategies of transfer learning. We also present the widely-used neural network models, that in recent years performed best in ImageNet classification challenges. Furthermore, we shortly describe three different experiments from computer vision field, that confirm the developed algorithms ability to classify images with overall accuracy 87.2-95%. Achieved numbers are state-of-the-art results in melanoma thickness prediction, anomaly detection and Clostridium di cile cytotoxicity classification problems.

Palabras clave

  • Deep neural networks
  • Transfer learning
  • Signal processing
  • Image analysis
  • Anomaly detection
Acceso abierto

Mining Cardinality Restrictions in OWL

Publicado en línea: 18 Sep 2020
Páginas: 195 - 216

Resumen

Abstract

We present an approach to mine cardinality restriction axioms from an existing knowledge graph, in order to extend an ontology describing the graph. We compare frequency estimation with kernel density estimation as approaches to obtain the cardinalities in restrictions. We also propose numerous strategies for filtering obtained axioms in order to make them more available for the ontology engineer. We report the results of experimental evaluation on DBpedia 2016-10 and show that using kernel density estimation to compute the cardinalities in cardinality restrictions yields more robust results that using frequency estimation. We also show that while filtering is of limited usability for minimum cardinality restrictions, it is much more important for maximum cardinality restrictions. The presented findings can be used to extend existing ontology engineering tools in order to support ontology construction and enable more efficient creation of knowledge-intensive artificial intelligence systems.

Palabras clave

  • Semantic Web
  • ontology learning
  • frequency estimation
  • kernel density estimation
  • cardinality restrictions
Acceso abierto

Application of Machine Learning Algorithms for Traffic Forecasting in Dynamic Optical Networks with Service Function Chains

Publicado en línea: 18 Sep 2020
Páginas: 217 - 232

Resumen

Abstract

Knowledge about future optical network traffic can be beneficial for network operators in terms of decreasing an operational cost due to efficient resource management. Machine Learning (ML) algorithms can be employed for forecasting traffic with high accuracy. In this paper we describe a methodology for predicting traffic in a dynamic optical network with service function chains (SFC). We assume that SFC is based on the Network Function Virtualization (NFV) paradigm. Moreover, other type of traffic, i.e. regular traffic, can also occur in the network. As a proof of effectiveness of our methodology we present and discuss numerical results of experiments run on three benchmark networks. We examine six ML classifiers. Our research shows that it is possible to predict a future traffic in an optical network, where SFC can be distinguished. However, there is no one universal classifier that can be used for each network. Choice of an ML algorithm should be done based on a network traffic characteristics analysis.

Palabras clave

  • Dynamic Optical Networks
  • Traffic Prediction
  • Service Function Chaining
  • Machine Learning
Acceso abierto

Analysis of statistical model-based optimization enhancements in Generalized Self-Adapting Particle Swarm Optimization framework

Publicado en línea: 18 Sep 2020
Páginas: 233 - 254

Resumen

Abstract

This paper presents characteristics of model-based optimization methods utilized within the Generalized Self-Adapting Particle Swarm Optimization (GA– PSO) – a hybrid global optimization framework proposed by the authors. GAPSO has been designed as a generalization of a Particle Swarm Optimization (PSO) algorithm on the foundations of a large degree of independence of individual particles. GAPSO serves as a platform for studying optimization algorithms in the context of the following research hypothesis: (1) it is possible to improve the performance of an optimization algorithm through utilization of more function samples than standard PSO sample-based memory, (2) combining specialized sampling methods (i.e. PSO, Differential Evolution, model-based optimization) will result in a better algorithm performance than using each of them separately. The inclusion of model-based enhancements resulted in the necessity of extending the GAPSO framework by means of an external samples memory - this enhanced model is referred to as M-GAPSO in the paper.

We investigate the features of two model-based optimizers: one utilizing a quadratic function and the other one utilizing a polynomial function. We analyze the conditions under which those model-based approaches provide an effective sampling strategy. Proposed model-based optimizers are evaluated on the functions from the COCO BBOB benchmark set.

Palabras clave

  • Particle Swarm Optimization
  • global optimization
  • metaheuristic
5 Artículos
Acceso abierto

Artificial Intelligence Research Community and Associations in Poland

Publicado en línea: 18 Sep 2020
Páginas: 159 - 177

Resumen

Abstract

In last years Artificial Intelligence presented a tremendous progress by offering a variety of novel methods, tools and their spectacular applications. Besides showing scientific breakthroughs it attracted interest both of the general public and industry. It also opened heated debates on the impact of Artificial Intelligence on changing the economy and society. Having in mind this international landscape, in this short paper we discuss the Polish AI research community, some of its main achievements, opportunities and limitations. We put this discussion in the context of the current developments in the international AI community. Moreover, we refer to activities of Polish scientific associations and their initiative of founding Polish Alliance for the Development of Artificial Intelligence (PP-RAI). Finally two last editions of PP-RAI joint conferences are summarized.

Acceso abierto

Transfer Learning Methods as a New Approach in Computer Vision Tasks with Small Datasets

Publicado en línea: 18 Sep 2020
Páginas: 179 - 193

Resumen

Abstract

Deep learning methods, used in machine vision challenges, often face the problem of the amount and quality of data. To address this issue, we investigate the transfer learning method. In this study, we briefly describe the idea and introduce two main strategies of transfer learning. We also present the widely-used neural network models, that in recent years performed best in ImageNet classification challenges. Furthermore, we shortly describe three different experiments from computer vision field, that confirm the developed algorithms ability to classify images with overall accuracy 87.2-95%. Achieved numbers are state-of-the-art results in melanoma thickness prediction, anomaly detection and Clostridium di cile cytotoxicity classification problems.

Palabras clave

  • Deep neural networks
  • Transfer learning
  • Signal processing
  • Image analysis
  • Anomaly detection
Acceso abierto

Mining Cardinality Restrictions in OWL

Publicado en línea: 18 Sep 2020
Páginas: 195 - 216

Resumen

Abstract

We present an approach to mine cardinality restriction axioms from an existing knowledge graph, in order to extend an ontology describing the graph. We compare frequency estimation with kernel density estimation as approaches to obtain the cardinalities in restrictions. We also propose numerous strategies for filtering obtained axioms in order to make them more available for the ontology engineer. We report the results of experimental evaluation on DBpedia 2016-10 and show that using kernel density estimation to compute the cardinalities in cardinality restrictions yields more robust results that using frequency estimation. We also show that while filtering is of limited usability for minimum cardinality restrictions, it is much more important for maximum cardinality restrictions. The presented findings can be used to extend existing ontology engineering tools in order to support ontology construction and enable more efficient creation of knowledge-intensive artificial intelligence systems.

Palabras clave

  • Semantic Web
  • ontology learning
  • frequency estimation
  • kernel density estimation
  • cardinality restrictions
Acceso abierto

Application of Machine Learning Algorithms for Traffic Forecasting in Dynamic Optical Networks with Service Function Chains

Publicado en línea: 18 Sep 2020
Páginas: 217 - 232

Resumen

Abstract

Knowledge about future optical network traffic can be beneficial for network operators in terms of decreasing an operational cost due to efficient resource management. Machine Learning (ML) algorithms can be employed for forecasting traffic with high accuracy. In this paper we describe a methodology for predicting traffic in a dynamic optical network with service function chains (SFC). We assume that SFC is based on the Network Function Virtualization (NFV) paradigm. Moreover, other type of traffic, i.e. regular traffic, can also occur in the network. As a proof of effectiveness of our methodology we present and discuss numerical results of experiments run on three benchmark networks. We examine six ML classifiers. Our research shows that it is possible to predict a future traffic in an optical network, where SFC can be distinguished. However, there is no one universal classifier that can be used for each network. Choice of an ML algorithm should be done based on a network traffic characteristics analysis.

Palabras clave

  • Dynamic Optical Networks
  • Traffic Prediction
  • Service Function Chaining
  • Machine Learning
Acceso abierto

Analysis of statistical model-based optimization enhancements in Generalized Self-Adapting Particle Swarm Optimization framework

Publicado en línea: 18 Sep 2020
Páginas: 233 - 254

Resumen

Abstract

This paper presents characteristics of model-based optimization methods utilized within the Generalized Self-Adapting Particle Swarm Optimization (GA– PSO) – a hybrid global optimization framework proposed by the authors. GAPSO has been designed as a generalization of a Particle Swarm Optimization (PSO) algorithm on the foundations of a large degree of independence of individual particles. GAPSO serves as a platform for studying optimization algorithms in the context of the following research hypothesis: (1) it is possible to improve the performance of an optimization algorithm through utilization of more function samples than standard PSO sample-based memory, (2) combining specialized sampling methods (i.e. PSO, Differential Evolution, model-based optimization) will result in a better algorithm performance than using each of them separately. The inclusion of model-based enhancements resulted in the necessity of extending the GAPSO framework by means of an external samples memory - this enhanced model is referred to as M-GAPSO in the paper.

We investigate the features of two model-based optimizers: one utilizing a quadratic function and the other one utilizing a polynomial function. We analyze the conditions under which those model-based approaches provide an effective sampling strategy. Proposed model-based optimizers are evaluated on the functions from the COCO BBOB benchmark set.

Palabras clave

  • Particle Swarm Optimization
  • global optimization
  • metaheuristic

Planifique su conferencia remota con Sciendo