Rivista e Edizione

Volume 32 (2022): Edizione 3 (September 2022)
Recent Advances in Modelling, Analysis and Implementation of Cyber-Physical Systems (Special section, pp. 345-413), Remigiusz Wiśniewski, Luis Gomes and Shaohua Wan (Eds.)

Volume 32 (2022): Edizione 2 (June 2022)
Towards Self-Healing Systems through Diagnostics, Fault-Tolerance and Design (Special section, pp. 171-269), Marcin Witczak and Ralf Stetter (Eds.)

Volume 32 (2022): Edizione 1 (March 2022)

Volume 31 (2021): Edizione 4 (December 2021)
Advanced Machine Learning Techniques in Data Analysis (special section, pp. 549-611), Maciej Kusy, Rafał Scherer, and Adam Krzyżak (Eds.)

Volume 31 (2021): Edizione 3 (September 2021)

Volume 31 (2021): Edizione 2 (June 2021)

Volume 31 (2021): Edizione 1 (March 2021)

Volume 30 (2020): Edizione 4 (December 2020)

Volume 30 (2020): Edizione 3 (September 2020)
Big Data and Signal Processing (Special section, pp. 399-473), Joanna Kołodziej, Sabri Pllana, Salvatore Vitabile (Eds.)

Volume 30 (2020): Edizione 2 (June 2020)

Volume 30 (2020): Edizione 1 (March 2020)

Volume 29 (2019): Edizione 4 (December 2019)
New Perspectives in Nonlinear and Intelligent Control (In Honor of Alexander P. Kurdyukov) (special section, pp. 629-712), Julio B. Clempner, Enso Ikonen, Alexander P. Kurdyukov (Eds.)

Volume 29 (2019): Edizione 3 (September 2019)
Information Technology for Systems Research (special section, pp. 427-515), Piotr Kulczycki, Janusz Kacprzyk, László T. Kóczy, Radko Mesiar (Eds.)

Volume 29 (2019): Edizione 2 (June 2019)
Advances in Complex Cloud and Service Oriented Computing (special section, pp. 213-274), Anna Kobusińska, Ching-Hsien Hsu, Kwei-Jay Lin (Eds.)

Volume 29 (2019): Edizione 1 (March 2019)
Exploring Complex and Big Data (special section, pp. 7-91), Johann Gamper, Robert Wrembel (Eds.)

Volume 28 (2018): Edizione 4 (December 2018)

Volume 28 (2018): Edizione 3 (September 2018)

Volume 28 (2018): Edizione 2 (June 2018)
Advanced Diagnosis and Fault-Tolerant Control Methods (special section, pp. 233-333), Vicenç Puig, Dominique Sauter, Christophe Aubrun, Horst Schulte (Eds.)

Volume 28 (2018): Edizione 1 (March 2018)
Ediziones in Parameter Identification and Control (special section, pp. 9-122), Abdel Aitouche (Ed.)

Volume 27 (2017): Edizione 4 (December 2017)

Volume 27 (2017): Edizione 3 (September 2017)
Systems Analysis: Modeling and Control (special section, pp. 457-499), Vyacheslav Maksimov and Boris Mordukhovich (Eds.)

Volume 27 (2017): Edizione 2 (June 2017)

Volume 27 (2017): Edizione 1 (March 2017)

Volume 26 (2016): Edizione 4 (December 2016)

Volume 26 (2016): Edizione 3 (September 2016)

Volume 26 (2016): Edizione 2 (June 2016)

Volume 26 (2016): Edizione 1 (March 2016)

Volume 25 (2015): Edizione 4 (December 2015)
Special issue: Complex Problems in High-Performance Computing Systems, Editors: Mauro Iacono, Joanna Kołodziej

Volume 25 (2015): Edizione 3 (September 2015)

Volume 25 (2015): Edizione 2 (June 2015)

Volume 25 (2015): Edizione 1 (March 2015)
Safety, Fault Diagnosis and Fault Tolerant Control in Aerospace Systems, Silvio Simani, Paolo Castaldi (Eds.)

Volume 24 (2014): Edizione 4 (December 2014)

Volume 24 (2014): Edizione 3 (September 2014)
Modelling and Simulation of High Performance Information Systems (special section, pp. 453-566), Pavel Abaev, Rostislav Razumchik, Joanna Kołodziej (Eds.)

Volume 24 (2014): Edizione 2 (June 2014)
Signals and Systems (special section, pp. 233-312), Ryszard Makowski and Jan Zarzycki (Eds.)

Volume 24 (2014): Edizione 1 (March 2014)
Selected Problems of Biomedical Engineering (special section, pp. 7 - 63), Marek Kowal and Józef Korbicz (Eds.)

Volume 23 (2013): Edizione 4 (December 2013)

Volume 23 (2013): Edizione 3 (September 2013)

Volume 23 (2013): Edizione 2 (June 2013)

Volume 23 (2013): Edizione 1 (March 2013)

Volume 22 (2012): Edizione 4 (December 2012)
Hybrid and Ensemble Methods in Machine Learning (special section, pp. 787 - 881), Oscar Cordón and Przemysław Kazienko (Eds.)

Volume 22 (2012): Edizione 3 (September 2012)

Volume 22 (2012): Edizione 2 (June 2012)
Analysis and Control of Spatiotemporal Dynamic Systems (special section, pp. 245 - 326), Dariusz Uciński and Józef Korbicz (Eds.)

Volume 22 (2012): Edizione 1 (March 2012)
Advances in Control and Fault-Tolerant Systems (special issue), Józef Korbicz, Didier Maquin and Didier Theilliol (Eds.)

Volume 21 (2011): Edizione 4 (December 2011)

Volume 21 (2011): Edizione 3 (September 2011)
Ediziones in Advanced Control and Diagnosis (special section, pp. 423 - 486), Vicenç Puig and Marcin Witczak (Eds.)

Volume 21 (2011): Edizione 2 (June 2011)
Efficient Resource Management for Grid-Enabled Applications (special section, pp. 219 - 306), Joanna Kołodziej and Fatos Xhafa (Eds.)

Volume 21 (2011): Edizione 1 (March 2011)
Semantic Knowledge Engineering (special section, pp. 9 - 95), Grzegorz J. Nalepa and Antoni Ligęza (Eds.)

Volume 20 (2010): Edizione 4 (December 2010)

Volume 20 (2010): Edizione 3 (September 2010)

Volume 20 (2010): Edizione 2 (June 2010)

Volume 20 (2010): Edizione 1 (March 2010)
Computational Intelligence in Modern Control Systems (special section, pp. 7 - 84), Józef Korbicz and Dariusz Uciński (Eds.)

Volume 19 (2009): Edizione 4 (December 2009)
Robot Control Theory (special section, pp. 519 - 588), Cezary Zieliński (Ed.)

Volume 19 (2009): Edizione 3 (September 2009)
Verified Methods: Applications in Medicine and Engineering (special issue), Andreas Rauh, Ekaterina Auer, Eberhard P. Hofer and Wolfram Luther (Eds.)

Volume 19 (2009): Edizione 2 (June 2009)

Volume 19 (2009): Edizione 1 (March 2009)

Volume 18 (2008): Edizione 4 (December 2008)
Ediziones in Fault Diagnosis and Fault Tolerant Control (special issue), Józef Korbicz and Dominique Sauter (Eds.)

Volume 18 (2008): Edizione 3 (September 2008)
Selected Problems of Computer Science and Control (special issue), Krzysztof Gałkowski, Eric Rogers and Jan Willems (Eds.)

Volume 18 (2008): Edizione 2 (June 2008)
Selected Topics in Biological Cybernetics (special section, pp. 117 - 170), Andrzej Kasiński and Filip Ponulak (Eds.)

Volume 18 (2008): Edizione 1 (March 2008)
Applied Image Processing (special issue), Anton Kummert and Ewaryst Rafajłowicz (Eds.)

Volume 17 (2007): Edizione 4 (December 2007)

Volume 17 (2007): Edizione 3 (September 2007)
Scientific Computation for Fluid Mechanics and Hyperbolic Systems (special issue), Jan Sokołowski and Eric Sonnendrücker (Eds.)

Volume 17 (2007): Edizione 2 (June 2007)

Volume 17 (2007): Edizione 1 (March 2007)

Dettagli della rivista
Formato
Rivista
eISSN
2083-8492
Pubblicato per la prima volta
05 Apr 2007
Periodo di pubblicazione
4 volte all'anno
Lingue
Inglese

Cerca

Volume 29 (2019): Edizione 3 (September 2019)
Information Technology for Systems Research (special section, pp. 427-515), Piotr Kulczycki, Janusz Kacprzyk, László T. Kóczy, Radko Mesiar (Eds.)

Dettagli della rivista
Formato
Rivista
eISSN
2083-8492
Pubblicato per la prima volta
05 Apr 2007
Periodo di pubblicazione
4 volte all'anno
Lingue
Inglese

Cerca

15 Articoli
Accesso libero

The Effect of Elastic and Inelastic Scattering on Electronic Transport in Open Systems

Pubblicato online: 28 Sep 2019
Pagine: 427 - 437

Astratto

Abstract

The purpose of this study is to apply the distribution function formalism to the problem of electronic transport in open systems, and to numerically solve the kinetic equation with a dissipation term. This term is modeled within the relaxation time approximation and contains two parts, corresponding to elastic or inelastic processes. The collision operator is approximated as a sum of the semi-classical energy dissipation term and the momentum relaxation term, which randomizes the momentum but does not change the energy. As a result, the distribution of charge carriers changes due to the dissipation processes, which has a profound impact on the electronic transport through the simulated region discussed in terms of the current–voltage characteristics and their modification caused by the scattering. Measurements of the current–voltage characteristics for titanium dioxide thin layers are also presented, and compared with the results of numerical calculations.

Parole chiave

  • kinetic equation
  • relaxation time approximation
  • scattering processes
Accesso libero

The Phase–Space Approach to time Evolution of Quantum States in Confined Systems: the Spectral Split–Operator Method

Pubblicato online: 28 Sep 2019
Pagine: 439 - 451

Astratto

Abstract

Using the phase space approach, we consider the quantum dynamics of a wave packet in an isolated confined system with three different potential energy profiles. We solve the Moyal equation of motion for the Wigner function with the highly efficient spectral split-operator method. The main aim of this study is to compare the accuracy of the employed algorithm through analysis of the total energy expectation value, in terms of deviation from its exact value. This comparison is performed for the second and fourth order factorizations of the time evolution operator.

Parole chiave

  • Wigner distribution function
  • Moyal dynamics
  • spectral split-operator method
Accesso libero

On the Convergence of Sigmoidal Fuzzy Grey Cognitive Maps

Pubblicato online: 28 Sep 2019
Pagine: 453 - 466

Astratto

Abstract

Fuzzy cognitive maps (FCMs) are recurrent neural networks applied for modelling complex systems using weighted causal relations. In FCM-based decision-making, the inference about the modelled system is provided by the behaviour of an iteration. Fuzzy grey cognitive maps (FGCMs) are extensions of fuzzy cognitive maps, applying uncertain weights between the concepts. This uncertainty is expressed by the so-called grey numbers. Similarly as in FCMs, the inference is determined by an iteration process which may converge to an equilibrium point, but limit cycles or chaotic behaviour may also turn up. In this paper, based on the grey connections between the concepts and the parameters of the sigmoid threshold function, we give sufficient conditions for the existence and uniqueness of fixed points of sigmoid FGCMs.

Parole chiave

  • fuzzy cognitive map
  • grey system theory
  • fuzzy grey cognitive map
  • fixed point
Accesso libero

Efficient Astronomical Data Condensation Using Approximate Nearest Neighbors

Pubblicato online: 28 Sep 2019
Pagine: 467 - 476

Astratto

Abstract

Extracting useful information from astronomical observations represents one of the most challenging tasks of data exploration. This is largely due to the volume of the data acquired using advanced observational tools. While other challenges typical for the class of big data problems (like data variety) are also present, the size of datasets represents the most significant obstacle in visualization and subsequent analysis. This paper studies an efficient data condensation algorithm aimed at providing its compact representation. It is based on fast nearest neighbor calculation using tree structures and parallel processing. In addition to that, the possibility of using approximate identification of neighbors, to even further improve the algorithm time performance, is also evaluated. The properties of the proposed approach, both in terms of performance and condensation quality, are experimentally assessed on astronomical datasets related to the GAIA mission. It is concluded that the introduced technique might serve as a scalable method of alleviating the problem of the dataset size.

Parole chiave

  • big data
  • astronomy
  • data reduction
  • nearest neighbor search
  • kd-trees
Accesso libero

A Hybrid Cascade Neuro–Fuzzy Network with Pools of Extended Neo–Fuzzy Neurons and its Deep Learning

Pubblicato online: 28 Sep 2019
Pagine: 477 - 488

Astratto

Abstract

This research contribution instantiates a framework of a hybrid cascade neural network based on the application of a specific sort of neo-fuzzy elements and a new peculiar adaptive training rule. The main trait of the offered system is its competence to continue intensifying its cascades until the required accuracy is gained. A distinctive rapid training procedure is also covered for this case that offers the possibility to operate with non-stationary data streams in an attempt to provide online training of multiple parametric variables. A new training criterion is examined for handling non-stationary objects. Additionally, there is always an occasion to set up (increase) the inference order and the number of membership relations inside the extended neo-fuzzy neuron.

Parole chiave

  • data stream
  • membership function
  • training procedure
  • adaptive neuro-fuzzy system
  • extended neo-fuzzy neuron
Accesso libero

A Three–Level Aggregation Model for Evaluating Software Usability by Fuzzy Logic

Pubblicato online: 28 Sep 2019
Pagine: 489 - 501

Astratto

Abstract

Rapid deployment of IT brings about new issues with software usability measurement. Usability is based on users’ experience and is strongly subjective, having a qualitative character. The users’ comfort is usually collected by surveys in their daily work. The present article stems from an experimental study related to the evaluation of the usability of tools by a rule-based system. The work suggests a robust computational model that will be able to avoid the main problems arising from the experimental study (a large and less-legible rule base) and to deal with the vagueness of IT user experience, different levels of skills and various numbers of filled questionnaires in different departments. The computational model is based on three hierarchical levels of aggregation supported by fuzzy logic. Choices for the most suitable aggregation functions in each level are advocated and illustrated with examples. The number of questions and granularity of answers in this approach can be adjusted to each user group, which could reduce the response burden and errors. Finally, the paper briefly describes further possibilities of the suggested approach.

Parole chiave

  • measuring software usability
  • rule-based system
  • fuzzy quantifiers
  • aggregation functions
  • questionnaire
Accesso libero

Using Neural Networks with data Quantization for time Series Analysis in LHC Superconducting Magnets

Pubblicato online: 28 Sep 2019
Pagine: 503 - 515

Astratto

Abstract

The aim of this paper is to present a model based on the recurrent neural network (RNN) architecture, the long short-term memory (LSTM) in particular, for modeling the work parameters of Large Hadron Collider (LHC) super-conducting magnets. High-resolution data available in the post mortem database were used to train a set of models and compare their performance for various hyper-parameters such as input data quantization and the number of cells. A novel approach to signal level quantization allowed reducing the size of the model, simplifying the tuning of the magnet monitoring system and making the process scalable. The paper shows that an RNN such as the LSTM or a gated recurrent unit (GRU) can be used for modeling high-resolution signals with the accuracy of over 0.95 and a small number of parameters, ranging from 800 to 1200. This makes the solution suitable for hardware implementation, which is essential in the case of monitoring the performance critical and high-speed signal of LHC superconducting magnets.

Parole chiave

  • Large Hadron Collider
  • LSTM architecture
  • signal modelling
Accesso libero

A Reference Trajectory Based Discrete Time Sliding Mode Control Strategy

Pubblicato online: 28 Sep 2019
Pagine: 517 - 525

Astratto

Abstract

This study presents a new, reference trajectory based sliding mode control strategy for disturbed discrete time dynamical systems. The desired trajectory, which is generated externally according to an existing switching type reaching law, determines the properties of the emerging sliding motion of the system. It is proved that an appropriate choice of the trajectory generator parameters ensures the existence of the quasi-sliding motion of the system according to the definition by Gao et al. (1995) in spite of the influence of disturbances. Moreover, the paper shows that the application of the desired trajectory based reaching law results in a significant reduction in the quasi-sliding mode band width and errors of all state variables. Therefore, in comparison with Gao’s control method, the system’s robustness is increased. The paper also presents an additional modification of the reaching law, which guarantees a further reduction in the quasi-sliding mode band in the case of slowly varying disturbances. The results are confirmed with a simulation example.

Parole chiave

  • discrete time systems
  • sliding mode control
  • reaching law
  • reference trajectory
Accesso libero

Realization of 2D (2,2)–Periodic Encoders by Means of 2D Periodic Separable Roesser Models

Pubblicato online: 28 Sep 2019
Pagine: 527 - 539

Astratto

Abstract

It is well known that convolutional codes are linear systems when they are defined over a finite field. A fundamental issue in the implementation of convolutional codes is to obtain a minimal state representation of the code. Compared with the literature on one-dimensional (1D) time-invariant convolutional codes, there exist relatively few results on the realization problem for time-varying 1D convolutional codes and even fewer if the convolutional codes are two-dimensional (2D). In this paper we consider 2D periodic convolutional codes and address the minimal state space realization problem for this class of codes. This is, in general, a highly nontrivial problem. Here, we focus on separable Roesser models and show that in this case it is possible to derive, under weak conditions, concrete formulas for obtaining a 2D Roesser state space representation. Moreover, we study minimality and present necessary conditions for these representations to be minimal. Our results immediately lead to constructive algorithms to build these representations.

Parole chiave

  • periodic 2D systems
  • convolutional codes
  • realizations
Accesso libero

Event–Based Feedforward Control of Linear Systems with input Time–Delay

Pubblicato online: 28 Sep 2019
Pagine: 541 - 553

Astratto

Abstract

This paper proposes a new method for the analysis of continuous and periodic event-based state-feedback plus static feed-forward controllers that regulate linear time invariant systems with time delays. Measurable disturbances are used in both the control law and triggering condition to provide better disturbance attenuation. Asymptotic stability and L2-gain disturbance rejection problems are addressed by means of Lyapunov–Krasovskii functionals, leading to performance conditions that are expressed in terms of linear matrix inequalities. The proposed controller offers better disturbance rejection and a reduction in the number of transmissions with respect to other robust event-triggered controllers in the literature.

Parole chiave

  • time delay systems
  • linear systems
  • process control
  • control system design
Accesso libero

Synergetic Control for HVAC System Control and VAV Box Fault Compensation

Pubblicato online: 28 Sep 2019
Pagine: 555 - 570

Astratto

Abstract

Synergetic control is proposed for heating, ventilating and air-conditioning (HVAC) system control. The synergetic controller is developed using the nonlinear model of the HVAC system. Occupancy information in each zone is required in the design of the controller which offers inherent comfort according to the occupancy in the zone. The stability of the building system using the proposed control is verified through the Lyapunov approach. It is also proved that the synergetic controller is robust to external disturbances. Then, synergetic theories are used to design a reconfigurable control for damper stuck failures in variable air volume (VAV) to recover the nominal performance. Simulations are provided to validate the effectiveness of the proposed controller for a three-zone building.

Parole chiave

  • HVAC system
  • synergetic control
  • reconfigurable control
  • robustness
Accesso libero

Two–Stage Instrumental Variables Identification of Polynomial Wiener Systems with Invertible Nonlinearities

Pubblicato online: 28 Sep 2019
Pagine: 571 - 580

Astratto

Abstract

A new two-stage approach to the identification of polynomial Wiener systems is proposed. It is assumed that the linear dynamic system is described by a transfer function model, the memoryless nonlinear element is invertible and the inverse nonlinear function is a polynomial. Based on these assumptions and by introducing a new extended parametrization, the Wiener model is transformed into a linear-in-parameters form. In Stage I, parameters of the transformed Wiener model are estimated using the least squares (LS) and instrumental variables (IV) methods. Although the obtained parameter estimates are consistent, the number of parameters of the transformed Wiener model is much greater than that of the original one. Moreover, there is no unique relationship between parameters of the inverse nonlinear function and those of the transformed Wiener model. In Stage II, based on the assumption that the linear dynamic model is already known, parameters of the inverse nonlinear function are estimated uniquely using the IV method. In this way, not only is the parameter redundancy removed but also the parameter estimation accuracy is increased. A numerical example is included to demonstrate the practical effectiveness of the proposed approach.

Parole chiave

  • nonlinear systems
  • parameter estimation
  • dynamic models
  • polynomial models
Accesso libero

A Fast Neural Network Learning Algorithm with Approximate Singular Value Decomposition

Pubblicato online: 28 Sep 2019
Pagine: 581 - 594

Astratto

Abstract

The learning of neural networks is becoming more and more important. Researchers have constructed dozens of learning algorithms, but it is still necessary to develop faster, more flexible, or more accurate learning algorithms. With fast learning we can examine more learning scenarios for a given problem, especially in the case of meta-learning. In this article we focus on the construction of a much faster learning algorithm and its modifications, especially for nonlinear versions of neural networks. The main idea of this algorithm lies in the usage of fast approximation of the Moore–Penrose pseudo-inverse matrix. The complexity of the original singular value decomposition algorithm is O(mn2). We consider algorithms with a complexity of O(mnl),where l<n and l is often significantly smaller than n. Such learning algorithms can be applied to the learning of radial basis function networks, extreme learning machines or deep ELMs, principal component analysis or even missing data imputation.

Parole chiave

  • Moore–Penrose pseudo-inverse learning
  • radial basis function network
  • extreme learning machines
  • kernel methods
  • machine learning
  • singular value decomposition
  • deep extreme learning
  • principal component analysis
Accesso libero

On Explainable Fuzzy Recommenders and their Performance Evaluation

Pubblicato online: 28 Sep 2019
Pagine: 595 - 610

Astratto

Abstract

This paper presents a novel approach to the design of explainable recommender systems. It is based on the Wang–Mendel algorithm of fuzzy rule generation. A method for the learning and reduction of the fuzzy recommender is proposed along with feature encoding. Three criteria, including the Akaike information criterion, are used for evaluating an optimal balance between recommender accuracy and interpretability. Simulation results verify the effectiveness of the presented recommender system and illustrate its performance on the MovieLens 10M dataset.

Parole chiave

  • recommender systems
  • explainable recommendations
  • fuzzy systems
  • Akaike information criterion
Accesso libero

Utilizing Relevant RGB–D Data to Help Recognize RGB Images in the Target Domain

Pubblicato online: 28 Sep 2019
Pagine: 611 - 621

Astratto

Abstract

With the advent of 3D cameras, getting depth information along with RGB images has been facilitated, which is helpful in various computer vision tasks. However, there are two challenges in using these RGB-D images to help recognize RGB images captured by conventional cameras: one is that the depth images are missing at the testing stage, the other is that the training and test data are drawn from different distributions as they are captured using different equipment. To jointly address the two challenges, we propose an asymmetrical transfer learning framework, wherein three classifiers are trained using the RGB and depth images in the source domain and RGB images in the target domain with a structural risk minimization criterion and regularization theory. A cross-modality co-regularizer is used to restrict the two-source classifier in a consistent manner to increase accuracy. Moreover, an L2,1 norm cross-domain co-regularizer is used to magnify significant visual features and inhibit insignificant ones in the weight vectors of the two RGB classifiers. Thus, using the cross-modality and cross-domain co-regularizer, the knowledge of RGB-D images in the source domain is transferred to the target domain to improve the target classifier. The results of the experiment show that the proposed method is one of the most effective ones.

Parole chiave

  • object recognition
  • RGB-D images
  • transfer learning
  • privileged information
15 Articoli
Accesso libero

The Effect of Elastic and Inelastic Scattering on Electronic Transport in Open Systems

Pubblicato online: 28 Sep 2019
Pagine: 427 - 437

Astratto

Abstract

The purpose of this study is to apply the distribution function formalism to the problem of electronic transport in open systems, and to numerically solve the kinetic equation with a dissipation term. This term is modeled within the relaxation time approximation and contains two parts, corresponding to elastic or inelastic processes. The collision operator is approximated as a sum of the semi-classical energy dissipation term and the momentum relaxation term, which randomizes the momentum but does not change the energy. As a result, the distribution of charge carriers changes due to the dissipation processes, which has a profound impact on the electronic transport through the simulated region discussed in terms of the current–voltage characteristics and their modification caused by the scattering. Measurements of the current–voltage characteristics for titanium dioxide thin layers are also presented, and compared with the results of numerical calculations.

Parole chiave

  • kinetic equation
  • relaxation time approximation
  • scattering processes
Accesso libero

The Phase–Space Approach to time Evolution of Quantum States in Confined Systems: the Spectral Split–Operator Method

Pubblicato online: 28 Sep 2019
Pagine: 439 - 451

Astratto

Abstract

Using the phase space approach, we consider the quantum dynamics of a wave packet in an isolated confined system with three different potential energy profiles. We solve the Moyal equation of motion for the Wigner function with the highly efficient spectral split-operator method. The main aim of this study is to compare the accuracy of the employed algorithm through analysis of the total energy expectation value, in terms of deviation from its exact value. This comparison is performed for the second and fourth order factorizations of the time evolution operator.

Parole chiave

  • Wigner distribution function
  • Moyal dynamics
  • spectral split-operator method
Accesso libero

On the Convergence of Sigmoidal Fuzzy Grey Cognitive Maps

Pubblicato online: 28 Sep 2019
Pagine: 453 - 466

Astratto

Abstract

Fuzzy cognitive maps (FCMs) are recurrent neural networks applied for modelling complex systems using weighted causal relations. In FCM-based decision-making, the inference about the modelled system is provided by the behaviour of an iteration. Fuzzy grey cognitive maps (FGCMs) are extensions of fuzzy cognitive maps, applying uncertain weights between the concepts. This uncertainty is expressed by the so-called grey numbers. Similarly as in FCMs, the inference is determined by an iteration process which may converge to an equilibrium point, but limit cycles or chaotic behaviour may also turn up. In this paper, based on the grey connections between the concepts and the parameters of the sigmoid threshold function, we give sufficient conditions for the existence and uniqueness of fixed points of sigmoid FGCMs.

Parole chiave

  • fuzzy cognitive map
  • grey system theory
  • fuzzy grey cognitive map
  • fixed point
Accesso libero

Efficient Astronomical Data Condensation Using Approximate Nearest Neighbors

Pubblicato online: 28 Sep 2019
Pagine: 467 - 476

Astratto

Abstract

Extracting useful information from astronomical observations represents one of the most challenging tasks of data exploration. This is largely due to the volume of the data acquired using advanced observational tools. While other challenges typical for the class of big data problems (like data variety) are also present, the size of datasets represents the most significant obstacle in visualization and subsequent analysis. This paper studies an efficient data condensation algorithm aimed at providing its compact representation. It is based on fast nearest neighbor calculation using tree structures and parallel processing. In addition to that, the possibility of using approximate identification of neighbors, to even further improve the algorithm time performance, is also evaluated. The properties of the proposed approach, both in terms of performance and condensation quality, are experimentally assessed on astronomical datasets related to the GAIA mission. It is concluded that the introduced technique might serve as a scalable method of alleviating the problem of the dataset size.

Parole chiave

  • big data
  • astronomy
  • data reduction
  • nearest neighbor search
  • kd-trees
Accesso libero

A Hybrid Cascade Neuro–Fuzzy Network with Pools of Extended Neo–Fuzzy Neurons and its Deep Learning

Pubblicato online: 28 Sep 2019
Pagine: 477 - 488

Astratto

Abstract

This research contribution instantiates a framework of a hybrid cascade neural network based on the application of a specific sort of neo-fuzzy elements and a new peculiar adaptive training rule. The main trait of the offered system is its competence to continue intensifying its cascades until the required accuracy is gained. A distinctive rapid training procedure is also covered for this case that offers the possibility to operate with non-stationary data streams in an attempt to provide online training of multiple parametric variables. A new training criterion is examined for handling non-stationary objects. Additionally, there is always an occasion to set up (increase) the inference order and the number of membership relations inside the extended neo-fuzzy neuron.

Parole chiave

  • data stream
  • membership function
  • training procedure
  • adaptive neuro-fuzzy system
  • extended neo-fuzzy neuron
Accesso libero

A Three–Level Aggregation Model for Evaluating Software Usability by Fuzzy Logic

Pubblicato online: 28 Sep 2019
Pagine: 489 - 501

Astratto

Abstract

Rapid deployment of IT brings about new issues with software usability measurement. Usability is based on users’ experience and is strongly subjective, having a qualitative character. The users’ comfort is usually collected by surveys in their daily work. The present article stems from an experimental study related to the evaluation of the usability of tools by a rule-based system. The work suggests a robust computational model that will be able to avoid the main problems arising from the experimental study (a large and less-legible rule base) and to deal with the vagueness of IT user experience, different levels of skills and various numbers of filled questionnaires in different departments. The computational model is based on three hierarchical levels of aggregation supported by fuzzy logic. Choices for the most suitable aggregation functions in each level are advocated and illustrated with examples. The number of questions and granularity of answers in this approach can be adjusted to each user group, which could reduce the response burden and errors. Finally, the paper briefly describes further possibilities of the suggested approach.

Parole chiave

  • measuring software usability
  • rule-based system
  • fuzzy quantifiers
  • aggregation functions
  • questionnaire
Accesso libero

Using Neural Networks with data Quantization for time Series Analysis in LHC Superconducting Magnets

Pubblicato online: 28 Sep 2019
Pagine: 503 - 515

Astratto

Abstract

The aim of this paper is to present a model based on the recurrent neural network (RNN) architecture, the long short-term memory (LSTM) in particular, for modeling the work parameters of Large Hadron Collider (LHC) super-conducting magnets. High-resolution data available in the post mortem database were used to train a set of models and compare their performance for various hyper-parameters such as input data quantization and the number of cells. A novel approach to signal level quantization allowed reducing the size of the model, simplifying the tuning of the magnet monitoring system and making the process scalable. The paper shows that an RNN such as the LSTM or a gated recurrent unit (GRU) can be used for modeling high-resolution signals with the accuracy of over 0.95 and a small number of parameters, ranging from 800 to 1200. This makes the solution suitable for hardware implementation, which is essential in the case of monitoring the performance critical and high-speed signal of LHC superconducting magnets.

Parole chiave

  • Large Hadron Collider
  • LSTM architecture
  • signal modelling
Accesso libero

A Reference Trajectory Based Discrete Time Sliding Mode Control Strategy

Pubblicato online: 28 Sep 2019
Pagine: 517 - 525

Astratto

Abstract

This study presents a new, reference trajectory based sliding mode control strategy for disturbed discrete time dynamical systems. The desired trajectory, which is generated externally according to an existing switching type reaching law, determines the properties of the emerging sliding motion of the system. It is proved that an appropriate choice of the trajectory generator parameters ensures the existence of the quasi-sliding motion of the system according to the definition by Gao et al. (1995) in spite of the influence of disturbances. Moreover, the paper shows that the application of the desired trajectory based reaching law results in a significant reduction in the quasi-sliding mode band width and errors of all state variables. Therefore, in comparison with Gao’s control method, the system’s robustness is increased. The paper also presents an additional modification of the reaching law, which guarantees a further reduction in the quasi-sliding mode band in the case of slowly varying disturbances. The results are confirmed with a simulation example.

Parole chiave

  • discrete time systems
  • sliding mode control
  • reaching law
  • reference trajectory
Accesso libero

Realization of 2D (2,2)–Periodic Encoders by Means of 2D Periodic Separable Roesser Models

Pubblicato online: 28 Sep 2019
Pagine: 527 - 539

Astratto

Abstract

It is well known that convolutional codes are linear systems when they are defined over a finite field. A fundamental issue in the implementation of convolutional codes is to obtain a minimal state representation of the code. Compared with the literature on one-dimensional (1D) time-invariant convolutional codes, there exist relatively few results on the realization problem for time-varying 1D convolutional codes and even fewer if the convolutional codes are two-dimensional (2D). In this paper we consider 2D periodic convolutional codes and address the minimal state space realization problem for this class of codes. This is, in general, a highly nontrivial problem. Here, we focus on separable Roesser models and show that in this case it is possible to derive, under weak conditions, concrete formulas for obtaining a 2D Roesser state space representation. Moreover, we study minimality and present necessary conditions for these representations to be minimal. Our results immediately lead to constructive algorithms to build these representations.

Parole chiave

  • periodic 2D systems
  • convolutional codes
  • realizations
Accesso libero

Event–Based Feedforward Control of Linear Systems with input Time–Delay

Pubblicato online: 28 Sep 2019
Pagine: 541 - 553

Astratto

Abstract

This paper proposes a new method for the analysis of continuous and periodic event-based state-feedback plus static feed-forward controllers that regulate linear time invariant systems with time delays. Measurable disturbances are used in both the control law and triggering condition to provide better disturbance attenuation. Asymptotic stability and L2-gain disturbance rejection problems are addressed by means of Lyapunov–Krasovskii functionals, leading to performance conditions that are expressed in terms of linear matrix inequalities. The proposed controller offers better disturbance rejection and a reduction in the number of transmissions with respect to other robust event-triggered controllers in the literature.

Parole chiave

  • time delay systems
  • linear systems
  • process control
  • control system design
Accesso libero

Synergetic Control for HVAC System Control and VAV Box Fault Compensation

Pubblicato online: 28 Sep 2019
Pagine: 555 - 570

Astratto

Abstract

Synergetic control is proposed for heating, ventilating and air-conditioning (HVAC) system control. The synergetic controller is developed using the nonlinear model of the HVAC system. Occupancy information in each zone is required in the design of the controller which offers inherent comfort according to the occupancy in the zone. The stability of the building system using the proposed control is verified through the Lyapunov approach. It is also proved that the synergetic controller is robust to external disturbances. Then, synergetic theories are used to design a reconfigurable control for damper stuck failures in variable air volume (VAV) to recover the nominal performance. Simulations are provided to validate the effectiveness of the proposed controller for a three-zone building.

Parole chiave

  • HVAC system
  • synergetic control
  • reconfigurable control
  • robustness
Accesso libero

Two–Stage Instrumental Variables Identification of Polynomial Wiener Systems with Invertible Nonlinearities

Pubblicato online: 28 Sep 2019
Pagine: 571 - 580

Astratto

Abstract

A new two-stage approach to the identification of polynomial Wiener systems is proposed. It is assumed that the linear dynamic system is described by a transfer function model, the memoryless nonlinear element is invertible and the inverse nonlinear function is a polynomial. Based on these assumptions and by introducing a new extended parametrization, the Wiener model is transformed into a linear-in-parameters form. In Stage I, parameters of the transformed Wiener model are estimated using the least squares (LS) and instrumental variables (IV) methods. Although the obtained parameter estimates are consistent, the number of parameters of the transformed Wiener model is much greater than that of the original one. Moreover, there is no unique relationship between parameters of the inverse nonlinear function and those of the transformed Wiener model. In Stage II, based on the assumption that the linear dynamic model is already known, parameters of the inverse nonlinear function are estimated uniquely using the IV method. In this way, not only is the parameter redundancy removed but also the parameter estimation accuracy is increased. A numerical example is included to demonstrate the practical effectiveness of the proposed approach.

Parole chiave

  • nonlinear systems
  • parameter estimation
  • dynamic models
  • polynomial models
Accesso libero

A Fast Neural Network Learning Algorithm with Approximate Singular Value Decomposition

Pubblicato online: 28 Sep 2019
Pagine: 581 - 594

Astratto

Abstract

The learning of neural networks is becoming more and more important. Researchers have constructed dozens of learning algorithms, but it is still necessary to develop faster, more flexible, or more accurate learning algorithms. With fast learning we can examine more learning scenarios for a given problem, especially in the case of meta-learning. In this article we focus on the construction of a much faster learning algorithm and its modifications, especially for nonlinear versions of neural networks. The main idea of this algorithm lies in the usage of fast approximation of the Moore–Penrose pseudo-inverse matrix. The complexity of the original singular value decomposition algorithm is O(mn2). We consider algorithms with a complexity of O(mnl),where l<n and l is often significantly smaller than n. Such learning algorithms can be applied to the learning of radial basis function networks, extreme learning machines or deep ELMs, principal component analysis or even missing data imputation.

Parole chiave

  • Moore–Penrose pseudo-inverse learning
  • radial basis function network
  • extreme learning machines
  • kernel methods
  • machine learning
  • singular value decomposition
  • deep extreme learning
  • principal component analysis
Accesso libero

On Explainable Fuzzy Recommenders and their Performance Evaluation

Pubblicato online: 28 Sep 2019
Pagine: 595 - 610

Astratto

Abstract

This paper presents a novel approach to the design of explainable recommender systems. It is based on the Wang–Mendel algorithm of fuzzy rule generation. A method for the learning and reduction of the fuzzy recommender is proposed along with feature encoding. Three criteria, including the Akaike information criterion, are used for evaluating an optimal balance between recommender accuracy and interpretability. Simulation results verify the effectiveness of the presented recommender system and illustrate its performance on the MovieLens 10M dataset.

Parole chiave

  • recommender systems
  • explainable recommendations
  • fuzzy systems
  • Akaike information criterion
Accesso libero

Utilizing Relevant RGB–D Data to Help Recognize RGB Images in the Target Domain

Pubblicato online: 28 Sep 2019
Pagine: 611 - 621

Astratto

Abstract

With the advent of 3D cameras, getting depth information along with RGB images has been facilitated, which is helpful in various computer vision tasks. However, there are two challenges in using these RGB-D images to help recognize RGB images captured by conventional cameras: one is that the depth images are missing at the testing stage, the other is that the training and test data are drawn from different distributions as they are captured using different equipment. To jointly address the two challenges, we propose an asymmetrical transfer learning framework, wherein three classifiers are trained using the RGB and depth images in the source domain and RGB images in the target domain with a structural risk minimization criterion and regularization theory. A cross-modality co-regularizer is used to restrict the two-source classifier in a consistent manner to increase accuracy. Moreover, an L2,1 norm cross-domain co-regularizer is used to magnify significant visual features and inhibit insignificant ones in the weight vectors of the two RGB classifiers. Thus, using the cross-modality and cross-domain co-regularizer, the knowledge of RGB-D images in the source domain is transferred to the target domain to improve the target classifier. The results of the experiment show that the proposed method is one of the most effective ones.

Parole chiave

  • object recognition
  • RGB-D images
  • transfer learning
  • privileged information

Pianifica la tua conferenza remota con Sciendo