Rivista e Edizione

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

Classification of High Resolution Satellite Images Using Improved U–Net

Pubblicato online: 29 Sep 2020
Pagine: 399 - 413

Astratto

Abstract

Satellite image classification is essential for many socio-economic and environmental applications of geographic information systems, including urban and regional planning, conservation and management of natural resources, etc. In this paper, we propose a deep learning architecture to perform the pixel-level understanding of high spatial resolution satellite images and apply it to image classification tasks. Specifically, we augment the spatial pyramid pooling module with image-level features encoding the global context, and integrate it into the U-Net structure. The proposed model solves the problem consisting in the fact that U-Net tends to lose object boundaries after multiple pooling operations. In our experiments, two public datasets are used to assess the performance of the proposed model. Comparison with the results from the published algorithms demonstrates the effectiveness of our approach.

Parole chiave

  • satellite image classification
  • deep learning
  • U-Net
  • spatial pyramid pooling
access type Accesso libero

Implementation and Evaluation of Medical Imaging Techniques Based on Conformal Geometric Algebra

Pubblicato online: 29 Sep 2020
Pagine: 415 - 433

Astratto

Abstract

Medical imaging tasks, such as segmentation, 3D modeling, and registration of medical images, involve complex geometric problems, usually solved by standard linear algebra and matrix calculations. In the last few decades, conformal geometric algebra (CGA) has emerged as a new approach to geometric computing that offers a simple and efficient representation of geometric objects and transformations. However, the practical use of CGA-based methods for big data image processing in medical imaging requires fast and efficient implementations of CGA operations to meet both real-time processing constraints and accuracy requirements. The purpose of this study is to present a novel implementation of CGA-based medical imaging techniques that makes them effective and practically usable. The paper exploits a new simplified formulation of CGA operators that allows significantly reduced execution times while maintaining the needed result precision. We have exploited this novel CGA formulation to re-design a suite of medical imaging automatic methods, including image segmentation, 3D reconstruction and registration. Experimental tests show that the re-formulated CGA-based methods lead to both higher precision results and reduced computation times, which makes them suitable for big data image processing applications. The segmentation algorithm provides the Dice index, sensitivity and specificity values of 98.14%, 98.05% and 97.73%, respectively, while the order of magnitude of the errors measured for the registration methods is 10−5.

Parole chiave

  • medical image segmentation
  • medical image registration
  • computational geometry
  • Clifford algebra
  • conformal geometric algebra
access type Accesso libero

An Intelligent Multimodal Framework for Identifying Children with Autism Spectrum Disorder

Pubblicato online: 29 Sep 2020
Pagine: 435 - 448

Astratto

Abstract

Early identification can significantly improve the prognosis of children with autism spectrum disorder (ASD). Yet existing identification methods are costly, time consuming, and dependent on the manual judgment of specialists. In this study, we present a multimodal framework that fuses data on a child’s eye fixation, facial expression, and cognitive level to automatically identify children with ASD, to improve the identification efficiency and reduce costs. The proposed methodology uses an optimized random forest (RF) algorithm to improve classification accuracy and then applies a hybrid fusion method based on the data source and time synchronization to ensure the reliability of the classification results. The classification accuracy of the framework was 91%, which is higher than that of the RF, support vector machine, and discriminant analysis methods. The results suggest that data on a child’s eye fixation, facial expression, and cognitive level are useful for identifying children with ASD. Because the proposed framework can separate ASD children from typically developing (TD) children, it can facilitate the early identification of ASD and may improve intervention programs for children with ASD.

Parole chiave

  • autism spectrum disorder
  • eye fixation
  • facial expression
  • cognitive level
  • improved random forest
access type Accesso libero

Mathematical Methods of Signal Analysis Applied in Medical Diagnostic

Pubblicato online: 29 Sep 2020
Pagine: 449 - 462

Astratto

Abstract

Digital signal processing, such as filtering, information extraction, and fusion of various results, is currently an integral part of advanced medical therapies. It is especially important in neurosurgery during deep-brain stimulation procedures. In such procedures, the surgical target is accessed using special electrodes while not being directly visible. This requires very precise identification of brain structures in 3D space throughout the surgery. In the case of deep-brain stimulation surgery for Parkinson’s disease (PD), the target area—the subthalamic nucleus (STN)—is located deep within the brain. It is also very small (just a few millimetres across), which makes this procedure even more difficult. For this reason, various signals are acquired, filtered, and finally fused, to provide the neurosurgeon with the exact location of the target. These signals come from preoperative medical imaging (such as MRI and CT), and from recordings of brain activity carried out during surgery using special brain-implanted electrodes. Using the method described in this paper, it is possible to construct a decision-support system that, during surgery, analyses signals recorded within the patient’s brain and classifies them as recorded within the STN or not. The constructed classifier discriminates signals with a sensitivity of 0.97 and a specificity of 0.96. The described algorithm is currently used for deep-brain stimulation surgeries among PD patients.

Parole chiave

  • classification
  • decision support system
  • signal filtering
  • data fusion
  • temporal analysis
access type Accesso libero

Recognition of Species and Genera of Bacteria By Means of the Product of Weights of the Classifiers

Pubblicato online: 29 Sep 2020
Pagine: 463 - 473

Astratto

Abstract

In microbiology, computer methods are applied in the analysis and recognition of laboratory-acquired microscopic images concerning, for example, bacterial cells or other microorganisms. Proper recognition of the species and genera of bacteria is a key stage in the microbiological diagnostics process, because it allows a quick start of the appropriate therapy. The original method proposed in the paper concerns the automatic recognition of selected species and genera of bacteria presented in digital images. The classification was made on the basis of the analysis of the physical characteristics of bacterial cells using the product of classifier confidence weights. The end result of the classification process is the classification list, sorted in descending order according to the weights of the classifiers. In addition to the correct classification, a list of other possible results of the analysis is obtained. The method thus allows not only the classification, but also an analysis of the confidence level of the selection made. The proposed method can be used to recognize not only bacterial cells, but also other microorganisms, for example, fungi that exhibit similar morphological characteristics. In addition, the use of the method does not require the application of specialized computer equipment, which widens the scope of applications regardless of the laboratory IT infrastructure, not only in microbiological diagnostics, but also in other diagnostic laboratories.

Parole chiave

  • pattern recognition
  • recognition of bacterial cells
  • classifiers
  • product of weights of the classifiers
access type Accesso libero

Approximate State–Space and Transfer Function Models for 2×2 Linear Hyperbolic Systems with Collocated Boundary Inputs

Pubblicato online: 29 Sep 2020
Pagine: 475 - 491

Astratto

Abstract

Two approximate representations are proposed for distributed parameter systems described by two linear hyperbolic PDEs with two time- and space-dependent state variables and two collocated boundary inputs. Using the method of lines with the backward difference scheme, the original PDEs are transformed into a set of ODEs and expressed in the form of a finite number of dynamical subsystems (sections). Each section of the approximation model is described by state-space equations with matrix-valued state, input and output operators, or, equivalently, by a rational transfer function matrix. The cascade interconnection of a number of sections results in the overall approximation model expressed in finite-dimensional state-space or rational transfer function domains, respectively. The discussion is illustrated with a practical example of a parallel-flow double-pipe heat exchanger. Its steady-state, frequency and impulse responses obtained from the original infinite-dimensional representation are compared with those resulting from its approximate models of different orders. The results show better approximation quality for the “crossover” input–output channels where the in-domain effects prevail as compared with the “straightforward” channels, where the time-delay phenomena are dominating.

Parole chiave

  • distributed parameter system
  • hyperbolic equations
  • approximation model
  • state space
  • transfer function
access type Accesso libero

Global Stability of Nonlinear Feedback Systems with Fractional Positive Linear Parts

Pubblicato online: 29 Sep 2020
Pagine: 493 - 499

Astratto

Abstract

The global (absolute) stability of nonlinear systems with fractional positive and not necessarily asymptotically stable linear parts and feedbacks is addressed. The characteristics u = f(e) of the nonlinear parts satisfy the condition k1ef(e) ≤ k2e for some positive k1 and k2. It is shown that the fractional nonlinear systems are globally asymptotically stable if the Nyquist plots of the fractional positive linear parts are located on the right-hand side of the circles (−1/k1, −1/k2).

Parole chiave

  • global
  • stability
  • fractional
  • nonlinear
  • feedback
  • positive
  • system
access type Accesso libero

Fractional Order Tube Model Reference Adaptive Control for a Class of Fractional Order Linear Systems

Pubblicato online: 29 Sep 2020
Pagine: 501 - 515

Astratto

Abstract

We introduce a novel fractional order adaptive control design based on the tube model reference adaptive control (TMRAC) scheme for a class of fractional order linear systems. By considering an adaptive state feedback control configuration, the main idea is to replace the classical reference model with a single predetermined trajectory by a fractional order performance tube guidance model allowing a set of admissible trajectories. Besides, an optimization problem is formulated to compute an on-line correction control signal within specified bounds in order to update the system performance while minimizing a control cost criterion. The asymptotic stability of the closed loop fractional order control system is demonstrated using an extension of the Lyapunov direct method. The dynamical performance of the fractional order tube model reference adaptive control (FOTMRAC) is compared with the standard fractional order model reference adaptive control (FOMRAC) strategy, and the simulation results show the effectiveness of the proposed control method.

Parole chiave

  • fractional order linear system
  • model reference adaptive control
  • fractional adaptive control
  • optimization
  • performance tube
  • fractional order TMRAC
access type Accesso libero

Discrete–Time Sliding Mode Control of Linear Systems with Input Saturation

Pubblicato online: 29 Sep 2020
Pagine: 517 - 528

Astratto

Abstract

The paper proposes a discrete-time sliding mode controller for single input linear dynamical systems, under requirements of the fast response without overshoot and strong robustness to matched disturbances. The system input saturation is imposed during the design due to inevitable limitations of most actuators. The system disturbances are compensated by employing nonlinear estimation by integrating the signum of the sliding variable. Hence, the proposed control structure may be regarded as a super-twisting-like algorithm. The designed system stability is analyzed as well as the sliding manifold convergence conditions are derived using a discrete-time model of the system in the δ-domain. The results obtained theoretically have been verified by computer simulations.

Parole chiave

  • discrete-time sliding mode control
  • super-twisting controller
  • input saturation
  • disturbance compensation
access type Accesso libero

T–S Fuzzy Bibo Stabilisation of Non–Linear Systems Under Persistent Perturbations Using Fuzzy Lyapunov Functions and Non–PDC Control Laws

Pubblicato online: 29 Sep 2020
Pagine: 529 - 550

Astratto

Abstract

This paper develops an innovative approach for designing non-parallel distributed fuzzy controllers for continuous-time non-linear systems under persistent perturbations. Non-linear systems are represented using Takagi–Sugeno fuzzy models. These non-PDC controllers guarantee bounded input bounded output stabilisation in closed-loop throughout the computation of generalised inescapable ellipsoids. These controllers are computed with linear matrix inequalities using fuzzy Lyapunov functions and integral delayed Lyapunov functions. LMI conditions developed in this paper provide non-PDC controllers with a minimum *-norm (upper bound of the 1-norm) for the T–S fuzzy system under persistent perturbations. The results presented in this paper can be classified into two categories: local methods based on fuzzy Lyapunov functions with guaranteed bounds on the first derivatives of membership functions and global methods based on integral-delayed Lyapunov functions which are independent of the first derivatives of membership functions. The benefits of the proposed results are shown through some illustrative examples.

Parole chiave

  • linear matrix inequalities
  • Takagi–Suegno fuzzy systems
  • fuzzy Lyapunov functions
  • integral delayed Lyapunov functions (IDLFs)
  • non-parallel distributed fuzzy controllers (non-PDC)
  • generalised inescapable ellipsoids
access type Accesso libero

Distributed Fault Estimation of Multi–Agent Systems Using a Proportional–Integral Observer: A Leader–Following Application

Pubblicato online: 29 Sep 2020
Pagine: 551 - 560

Astratto

Abstract

This paper proposes a methodology for observer-based fault estimation of leader-following linear multi-agent systems subject to actuator faults. First, a proportional-integral distributed fault estimation observer is developed to estimate both actuator faults and states of each follower agent by considering directed and undirected graph topologies. Second, based on the proposed quadratic Lyapunov equation, sufficient conditions for the asymptotic convergence of the observer are obtained as a set of linear matrix inequalities. Finally, a numerical example is provided to illustrate the proposed approach.

Parole chiave

  • multiagent systems
  • fault estimation
  • state and fault observers
  • linear matrix inequalities
access type Accesso libero

Ant–Based Clustering for Flow Graph Mining

Pubblicato online: 29 Sep 2020
Pagine: 561 - 572

Astratto

Abstract

The paper is devoted to the problem of mining graph data. The goal of this process is to discover possibly certain sequences appearing in data. Both rough set flow graphs and fuzzy flow graphs are used to represent sequences of items originally arranged in tables representing information systems. Information systems are considered in the Pawlak sense, as knowledge representation systems. In the paper, an approach involving ant based clustering is proposed. We show that ant based clustering can be used not only for building possible large groups of similar objects, but also to build larger structures (in our case, sequences) of objects to obtain or preserve the desired properties.

Parole chiave

  • possibly certain sequences
  • flow graphs
  • rough sets
  • fuzzy sets
  • ant-based clustering
access type Accesso libero

Two Meta–Heuristic Algorithms for Scheduling on Unrelated Machines with the Late Work Criterion

Pubblicato online: 29 Sep 2020
Pagine: 573 - 584

Astratto

Abstract

A scheduling problem in considered on unrelated machines with the goal of total late work minimization, in which the late work of a job means the late units executed after its due date. Due to the NP-hardness of the problem, we propose two meta-heuristic algorithms to solve it, namely, a tabu search (TS) and a genetic algorithm (GA), both of which are equipped with the techniques of initialization, iteration, as well as termination. The performances of the designed algorithms are verified through computational experiments, where we show that the GA can produce better solutions but with a higher time consumption. Moreover, we also analyze the influence of problem parameters on the performances of these meta-heuristics.

Parole chiave

  • late work minimization
  • unrelated machines
  • tabu search
  • genetic algorithm
access type Accesso libero

Line Segmentation of Handwritten Text Using Histograms and Tensor Voting

Pubblicato online: 29 Sep 2020
Pagine: 585 - 596

Astratto

Abstract

There are a large number of historical documents in libraries and other archives throughout the world. Most of them are written by hand. In many cases they exist in only one specimen and are hard to reach. Digitization of such artifacts can make them available to the community. But even digitized, they remain unsearchable, and an important task is to draw the contents in the computer readable form. One of the first steps in this direction is to recognize where the lines of the text are. Computational intelligence algorithms can be used to solve this problem. In the present paper, two groups of algorithms, namely, projection-based and tensor voting-based, are compared. The performance is evaluated on a data set and with the procedure proposed by the organizers of the ICDAR 2009 competition.

Parole chiave

  • document image processing
  • handwritten text line segmentation
  • projection profile
  • text string
  • off-line cursive script recognition
  • competition
access type Accesso libero

Real–Time Hierarchical Predictive Risk Assessment at the National Level: Mutually Agreed Predicted Service Disruption Profiles

Pubblicato online: 29 Sep 2020
Pagine: 597 - 609

Astratto

Abstract

We present a real-time hierarchical approach to an on-line risk assessment at the national level taking into account both local risk analyses performed by key service operators and relevant interdependencies between those services. For this purpose we define mutually agreed predicted service disruption profiles and then propose a coordination mechanism to align those profiles. A simple, four-entity example is provided to illustrate the coordination.

Parole chiave

  • risk assessment
  • cyber security
  • hierarchical approach
  • service disruption profiles
  • coordination
15 Articoli
access type Accesso libero

Classification of High Resolution Satellite Images Using Improved U–Net

Pubblicato online: 29 Sep 2020
Pagine: 399 - 413

Astratto

Abstract

Satellite image classification is essential for many socio-economic and environmental applications of geographic information systems, including urban and regional planning, conservation and management of natural resources, etc. In this paper, we propose a deep learning architecture to perform the pixel-level understanding of high spatial resolution satellite images and apply it to image classification tasks. Specifically, we augment the spatial pyramid pooling module with image-level features encoding the global context, and integrate it into the U-Net structure. The proposed model solves the problem consisting in the fact that U-Net tends to lose object boundaries after multiple pooling operations. In our experiments, two public datasets are used to assess the performance of the proposed model. Comparison with the results from the published algorithms demonstrates the effectiveness of our approach.

Parole chiave

  • satellite image classification
  • deep learning
  • U-Net
  • spatial pyramid pooling
access type Accesso libero

Implementation and Evaluation of Medical Imaging Techniques Based on Conformal Geometric Algebra

Pubblicato online: 29 Sep 2020
Pagine: 415 - 433

Astratto

Abstract

Medical imaging tasks, such as segmentation, 3D modeling, and registration of medical images, involve complex geometric problems, usually solved by standard linear algebra and matrix calculations. In the last few decades, conformal geometric algebra (CGA) has emerged as a new approach to geometric computing that offers a simple and efficient representation of geometric objects and transformations. However, the practical use of CGA-based methods for big data image processing in medical imaging requires fast and efficient implementations of CGA operations to meet both real-time processing constraints and accuracy requirements. The purpose of this study is to present a novel implementation of CGA-based medical imaging techniques that makes them effective and practically usable. The paper exploits a new simplified formulation of CGA operators that allows significantly reduced execution times while maintaining the needed result precision. We have exploited this novel CGA formulation to re-design a suite of medical imaging automatic methods, including image segmentation, 3D reconstruction and registration. Experimental tests show that the re-formulated CGA-based methods lead to both higher precision results and reduced computation times, which makes them suitable for big data image processing applications. The segmentation algorithm provides the Dice index, sensitivity and specificity values of 98.14%, 98.05% and 97.73%, respectively, while the order of magnitude of the errors measured for the registration methods is 10−5.

Parole chiave

  • medical image segmentation
  • medical image registration
  • computational geometry
  • Clifford algebra
  • conformal geometric algebra
access type Accesso libero

An Intelligent Multimodal Framework for Identifying Children with Autism Spectrum Disorder

Pubblicato online: 29 Sep 2020
Pagine: 435 - 448

Astratto

Abstract

Early identification can significantly improve the prognosis of children with autism spectrum disorder (ASD). Yet existing identification methods are costly, time consuming, and dependent on the manual judgment of specialists. In this study, we present a multimodal framework that fuses data on a child’s eye fixation, facial expression, and cognitive level to automatically identify children with ASD, to improve the identification efficiency and reduce costs. The proposed methodology uses an optimized random forest (RF) algorithm to improve classification accuracy and then applies a hybrid fusion method based on the data source and time synchronization to ensure the reliability of the classification results. The classification accuracy of the framework was 91%, which is higher than that of the RF, support vector machine, and discriminant analysis methods. The results suggest that data on a child’s eye fixation, facial expression, and cognitive level are useful for identifying children with ASD. Because the proposed framework can separate ASD children from typically developing (TD) children, it can facilitate the early identification of ASD and may improve intervention programs for children with ASD.

Parole chiave

  • autism spectrum disorder
  • eye fixation
  • facial expression
  • cognitive level
  • improved random forest
access type Accesso libero

Mathematical Methods of Signal Analysis Applied in Medical Diagnostic

Pubblicato online: 29 Sep 2020
Pagine: 449 - 462

Astratto

Abstract

Digital signal processing, such as filtering, information extraction, and fusion of various results, is currently an integral part of advanced medical therapies. It is especially important in neurosurgery during deep-brain stimulation procedures. In such procedures, the surgical target is accessed using special electrodes while not being directly visible. This requires very precise identification of brain structures in 3D space throughout the surgery. In the case of deep-brain stimulation surgery for Parkinson’s disease (PD), the target area—the subthalamic nucleus (STN)—is located deep within the brain. It is also very small (just a few millimetres across), which makes this procedure even more difficult. For this reason, various signals are acquired, filtered, and finally fused, to provide the neurosurgeon with the exact location of the target. These signals come from preoperative medical imaging (such as MRI and CT), and from recordings of brain activity carried out during surgery using special brain-implanted electrodes. Using the method described in this paper, it is possible to construct a decision-support system that, during surgery, analyses signals recorded within the patient’s brain and classifies them as recorded within the STN or not. The constructed classifier discriminates signals with a sensitivity of 0.97 and a specificity of 0.96. The described algorithm is currently used for deep-brain stimulation surgeries among PD patients.

Parole chiave

  • classification
  • decision support system
  • signal filtering
  • data fusion
  • temporal analysis
access type Accesso libero

Recognition of Species and Genera of Bacteria By Means of the Product of Weights of the Classifiers

Pubblicato online: 29 Sep 2020
Pagine: 463 - 473

Astratto

Abstract

In microbiology, computer methods are applied in the analysis and recognition of laboratory-acquired microscopic images concerning, for example, bacterial cells or other microorganisms. Proper recognition of the species and genera of bacteria is a key stage in the microbiological diagnostics process, because it allows a quick start of the appropriate therapy. The original method proposed in the paper concerns the automatic recognition of selected species and genera of bacteria presented in digital images. The classification was made on the basis of the analysis of the physical characteristics of bacterial cells using the product of classifier confidence weights. The end result of the classification process is the classification list, sorted in descending order according to the weights of the classifiers. In addition to the correct classification, a list of other possible results of the analysis is obtained. The method thus allows not only the classification, but also an analysis of the confidence level of the selection made. The proposed method can be used to recognize not only bacterial cells, but also other microorganisms, for example, fungi that exhibit similar morphological characteristics. In addition, the use of the method does not require the application of specialized computer equipment, which widens the scope of applications regardless of the laboratory IT infrastructure, not only in microbiological diagnostics, but also in other diagnostic laboratories.

Parole chiave

  • pattern recognition
  • recognition of bacterial cells
  • classifiers
  • product of weights of the classifiers
access type Accesso libero

Approximate State–Space and Transfer Function Models for 2×2 Linear Hyperbolic Systems with Collocated Boundary Inputs

Pubblicato online: 29 Sep 2020
Pagine: 475 - 491

Astratto

Abstract

Two approximate representations are proposed for distributed parameter systems described by two linear hyperbolic PDEs with two time- and space-dependent state variables and two collocated boundary inputs. Using the method of lines with the backward difference scheme, the original PDEs are transformed into a set of ODEs and expressed in the form of a finite number of dynamical subsystems (sections). Each section of the approximation model is described by state-space equations with matrix-valued state, input and output operators, or, equivalently, by a rational transfer function matrix. The cascade interconnection of a number of sections results in the overall approximation model expressed in finite-dimensional state-space or rational transfer function domains, respectively. The discussion is illustrated with a practical example of a parallel-flow double-pipe heat exchanger. Its steady-state, frequency and impulse responses obtained from the original infinite-dimensional representation are compared with those resulting from its approximate models of different orders. The results show better approximation quality for the “crossover” input–output channels where the in-domain effects prevail as compared with the “straightforward” channels, where the time-delay phenomena are dominating.

Parole chiave

  • distributed parameter system
  • hyperbolic equations
  • approximation model
  • state space
  • transfer function
access type Accesso libero

Global Stability of Nonlinear Feedback Systems with Fractional Positive Linear Parts

Pubblicato online: 29 Sep 2020
Pagine: 493 - 499

Astratto

Abstract

The global (absolute) stability of nonlinear systems with fractional positive and not necessarily asymptotically stable linear parts and feedbacks is addressed. The characteristics u = f(e) of the nonlinear parts satisfy the condition k1ef(e) ≤ k2e for some positive k1 and k2. It is shown that the fractional nonlinear systems are globally asymptotically stable if the Nyquist plots of the fractional positive linear parts are located on the right-hand side of the circles (−1/k1, −1/k2).

Parole chiave

  • global
  • stability
  • fractional
  • nonlinear
  • feedback
  • positive
  • system
access type Accesso libero

Fractional Order Tube Model Reference Adaptive Control for a Class of Fractional Order Linear Systems

Pubblicato online: 29 Sep 2020
Pagine: 501 - 515

Astratto

Abstract

We introduce a novel fractional order adaptive control design based on the tube model reference adaptive control (TMRAC) scheme for a class of fractional order linear systems. By considering an adaptive state feedback control configuration, the main idea is to replace the classical reference model with a single predetermined trajectory by a fractional order performance tube guidance model allowing a set of admissible trajectories. Besides, an optimization problem is formulated to compute an on-line correction control signal within specified bounds in order to update the system performance while minimizing a control cost criterion. The asymptotic stability of the closed loop fractional order control system is demonstrated using an extension of the Lyapunov direct method. The dynamical performance of the fractional order tube model reference adaptive control (FOTMRAC) is compared with the standard fractional order model reference adaptive control (FOMRAC) strategy, and the simulation results show the effectiveness of the proposed control method.

Parole chiave

  • fractional order linear system
  • model reference adaptive control
  • fractional adaptive control
  • optimization
  • performance tube
  • fractional order TMRAC
access type Accesso libero

Discrete–Time Sliding Mode Control of Linear Systems with Input Saturation

Pubblicato online: 29 Sep 2020
Pagine: 517 - 528

Astratto

Abstract

The paper proposes a discrete-time sliding mode controller for single input linear dynamical systems, under requirements of the fast response without overshoot and strong robustness to matched disturbances. The system input saturation is imposed during the design due to inevitable limitations of most actuators. The system disturbances are compensated by employing nonlinear estimation by integrating the signum of the sliding variable. Hence, the proposed control structure may be regarded as a super-twisting-like algorithm. The designed system stability is analyzed as well as the sliding manifold convergence conditions are derived using a discrete-time model of the system in the δ-domain. The results obtained theoretically have been verified by computer simulations.

Parole chiave

  • discrete-time sliding mode control
  • super-twisting controller
  • input saturation
  • disturbance compensation
access type Accesso libero

T–S Fuzzy Bibo Stabilisation of Non–Linear Systems Under Persistent Perturbations Using Fuzzy Lyapunov Functions and Non–PDC Control Laws

Pubblicato online: 29 Sep 2020
Pagine: 529 - 550

Astratto

Abstract

This paper develops an innovative approach for designing non-parallel distributed fuzzy controllers for continuous-time non-linear systems under persistent perturbations. Non-linear systems are represented using Takagi–Sugeno fuzzy models. These non-PDC controllers guarantee bounded input bounded output stabilisation in closed-loop throughout the computation of generalised inescapable ellipsoids. These controllers are computed with linear matrix inequalities using fuzzy Lyapunov functions and integral delayed Lyapunov functions. LMI conditions developed in this paper provide non-PDC controllers with a minimum *-norm (upper bound of the 1-norm) for the T–S fuzzy system under persistent perturbations. The results presented in this paper can be classified into two categories: local methods based on fuzzy Lyapunov functions with guaranteed bounds on the first derivatives of membership functions and global methods based on integral-delayed Lyapunov functions which are independent of the first derivatives of membership functions. The benefits of the proposed results are shown through some illustrative examples.

Parole chiave

  • linear matrix inequalities
  • Takagi–Suegno fuzzy systems
  • fuzzy Lyapunov functions
  • integral delayed Lyapunov functions (IDLFs)
  • non-parallel distributed fuzzy controllers (non-PDC)
  • generalised inescapable ellipsoids
access type Accesso libero

Distributed Fault Estimation of Multi–Agent Systems Using a Proportional–Integral Observer: A Leader–Following Application

Pubblicato online: 29 Sep 2020
Pagine: 551 - 560

Astratto

Abstract

This paper proposes a methodology for observer-based fault estimation of leader-following linear multi-agent systems subject to actuator faults. First, a proportional-integral distributed fault estimation observer is developed to estimate both actuator faults and states of each follower agent by considering directed and undirected graph topologies. Second, based on the proposed quadratic Lyapunov equation, sufficient conditions for the asymptotic convergence of the observer are obtained as a set of linear matrix inequalities. Finally, a numerical example is provided to illustrate the proposed approach.

Parole chiave

  • multiagent systems
  • fault estimation
  • state and fault observers
  • linear matrix inequalities
access type Accesso libero

Ant–Based Clustering for Flow Graph Mining

Pubblicato online: 29 Sep 2020
Pagine: 561 - 572

Astratto

Abstract

The paper is devoted to the problem of mining graph data. The goal of this process is to discover possibly certain sequences appearing in data. Both rough set flow graphs and fuzzy flow graphs are used to represent sequences of items originally arranged in tables representing information systems. Information systems are considered in the Pawlak sense, as knowledge representation systems. In the paper, an approach involving ant based clustering is proposed. We show that ant based clustering can be used not only for building possible large groups of similar objects, but also to build larger structures (in our case, sequences) of objects to obtain or preserve the desired properties.

Parole chiave

  • possibly certain sequences
  • flow graphs
  • rough sets
  • fuzzy sets
  • ant-based clustering
access type Accesso libero

Two Meta–Heuristic Algorithms for Scheduling on Unrelated Machines with the Late Work Criterion

Pubblicato online: 29 Sep 2020
Pagine: 573 - 584

Astratto

Abstract

A scheduling problem in considered on unrelated machines with the goal of total late work minimization, in which the late work of a job means the late units executed after its due date. Due to the NP-hardness of the problem, we propose two meta-heuristic algorithms to solve it, namely, a tabu search (TS) and a genetic algorithm (GA), both of which are equipped with the techniques of initialization, iteration, as well as termination. The performances of the designed algorithms are verified through computational experiments, where we show that the GA can produce better solutions but with a higher time consumption. Moreover, we also analyze the influence of problem parameters on the performances of these meta-heuristics.

Parole chiave

  • late work minimization
  • unrelated machines
  • tabu search
  • genetic algorithm
access type Accesso libero

Line Segmentation of Handwritten Text Using Histograms and Tensor Voting

Pubblicato online: 29 Sep 2020
Pagine: 585 - 596

Astratto

Abstract

There are a large number of historical documents in libraries and other archives throughout the world. Most of them are written by hand. In many cases they exist in only one specimen and are hard to reach. Digitization of such artifacts can make them available to the community. But even digitized, they remain unsearchable, and an important task is to draw the contents in the computer readable form. One of the first steps in this direction is to recognize where the lines of the text are. Computational intelligence algorithms can be used to solve this problem. In the present paper, two groups of algorithms, namely, projection-based and tensor voting-based, are compared. The performance is evaluated on a data set and with the procedure proposed by the organizers of the ICDAR 2009 competition.

Parole chiave

  • document image processing
  • handwritten text line segmentation
  • projection profile
  • text string
  • off-line cursive script recognition
  • competition
access type Accesso libero

Real–Time Hierarchical Predictive Risk Assessment at the National Level: Mutually Agreed Predicted Service Disruption Profiles

Pubblicato online: 29 Sep 2020
Pagine: 597 - 609

Astratto

Abstract

We present a real-time hierarchical approach to an on-line risk assessment at the national level taking into account both local risk analyses performed by key service operators and relevant interdependencies between those services. For this purpose we define mutually agreed predicted service disruption profiles and then propose a coordination mechanism to align those profiles. A simple, four-entity example is provided to illustrate the coordination.

Parole chiave

  • risk assessment
  • cyber security
  • hierarchical approach
  • service disruption profiles
  • coordination

Pianifica la tua conferenza remota con Sciendo