Wyniki wyszukiwania - Biblioteka Nauki

1

Akustyczny interfejs systemów diagnostycznych

100%

Batko W. , Wierzbicki J.

|

tom R. 51, nr 9 bis

234--235

PL

Akustyczny Interfejs Systemów Diagnostycznych zamienia pochodzące z systemu diagnostycznego sygnały o stanie obiektu na sygnały akustyczne. Dźwięki te mają być jednoznacznie identyfikowane przez obsługę. Dodatkowym uzupełnieniem interfejsu jest analiza stanu obiektu z sygnałów akustycznych rejestrowanych w jego pobliżu. Wynika to z faktu, iż w wielu przypadkach trudno jest umieścić sondę pomiarową w wymaganym miejscu diagnozowanego systemu a sprawny diagnosta wielokrotnie tylko na podstawie słyszanego dźwięku jest w stanie ocenić stan obiektu.

EN

In monitoring systems the main problem is connected with fast recognition of the most important diagnostic signal. Mainly image is used in such systems as information for operators. Such form can tire them and there are many moments when they do not look at the screen. Authors try to build supplementary interface based on sounds. This interface uses sounds to inform user about diagnostic signals. Problems concerning choice of sounds are described. The limitations are connected with human sense of hearing. Investigations with persons with and without trained hearing were carried out. The second goal of investigations is connected with cases when it is very difficult to install in proper place suitable number of measurement sensors and only sound signal is diagnostic information. There are still situations where human sense is better diagnostic tool then measurement equipment. In order to separate information from sounds the newest decomposition methods (Independent Component Analysis - 1CA) are used. Such diagnostic system based on sound signals can be easy tested and can be easy modified for another signals e.g. vibration.

2

ICA-Based EEG denoising: a comparative analysis of fifteen methods

94%

Albera L. , Kachenoura A. , Comon P. , Karfoul A. , Wendling F. , Senhadji L. , Merlet I.

|

2012

|

tom Vol. 60, nr 3

407-418

EN

Independent Component Analysis (ICA) plays an important role in biomedical engineering. Indeed, the complexity of processes involved in biomedicine and the lack of reference signals make this blind approach a powerful tool to extract sources of interest. However, in practice, only few ICA algorithms such as SOBI, (extended) InfoMax and FastICA are used nowadays to process biomedical signals. In this paper we raise the question whether other ICA methods could be better suited in terms of performance and computational complexity. We focus on ElectroEncephaloGraphy (EEG) data denoising, and more particularly on removal of muscle artifacts from interictal epileptiform activity. Assumptions required by ICA are discussed in such a context. Then fifteen ICA algorithms, namely JADE, CoM2, SOBI, SOBIrob, (extended) InfoMax, PICA, two different implementations of FastICA, ERICA, SIMBEC, FOBIUMJAD, TFBSS, ICAR3, FOOBI1 and 4- CANDHAPc are briefly described. Next they are studied in terms of performance and numerical complexity. Quantitative results are obtained on simulated epileptic data generated with a physiologically-plausible model. These results are also illustrated on real epileptic recordings.

3

Estimating independent components by mapping onto an orthogonal manifold

94%

Fiori S.

TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk

|

2008

|

tom Vol. 12, No 1-2

105-120

EN

: Algorithms for independent component analysis (ICA) based on information-theoretic criteria optimization over differential manifolds have been devised over the last few years. The principles informing their design lead to various classes of learning rules, including the fixed-point and the geodesic-based ones. Such learning algorithms mainly differ by the way in which single learning steps are effected in the neural system's parameter space, i. e. by the action that a connection variable is moved by in the parameter space toward the optimal connection pattern. In the present paper, we introduce a new class of learning algorithms by recalling from the literature on differential geometry the concept of mapping onto manifolds, which provides a general way of acting upon a neural system's connection variable in order to optimize the learning criteria. The numerical behavior of the introduced learning algorithms is illustrated and compared with experiments carried out on mixtures of statistically-independent signals.

4

Dostrajanie regulatora z pominięciem eksperymentu identyfikacji obiektu przy użyciu Imperialist Competitive Algorithm

84%

Awtoniuk M.

Elektronika : konstrukcje, technologie, zastosowania

|

2012

|

tom Vol. 53, nr 12

46-49

PL

Celem pracy jest przybliżenie sposobu dostrajania nastaw regulatora PI, który pozwala na pominięcie eksperymentu identyfikacji. Wykorzystanie tej metody pozwala na znalezienie optymalnych nastaw wykorzystując tylko dane zebrane z pracy zamkniętej pętli regulacji. Początkowo praca regulatora odbywała się z parametrami otrzymanymi w wyniku działania funkcji autotuningu. Wykonano szereg eksperymentów symulujących różne aspekty pracy układu regulacji, a następnie wykorzystano zebrane dane do ponownego sparametryzowania układu. Za pomocą wskaźników całkowych oceniono jakość regulacji przed i po zastosowaniu opisanej metody. Do dostrojenia regulatora wykorzystano algorytm ewolucyjny.

EN

The paper presents a method of retuning PI regulator which allows to omit object identification experiment. This method allows to find optimum regulator settings by use only data collected from working closed loop. The goal of this paper is to compare the effectiveness of control quality given by automatic tuning procedure with effects of retuning by means of Imperialist Competitive Algorithm.

5

Rozpoznawanie twarzy: PCA czy ICA

84%

Miziołek W. , Sawicki D.

Przegląd Elektrotechniczny

|

2012

|

tom R. 88, nr 7a

286-288

PL

Praca jest opisem badań nad zastosowaniem metod ICA i PCA w rozpoznawaniu twarzy. Przeprowadzono szereg eksperymentów wykorzystując najczęściej stosowaną bazę obrazów twarzy FERET. Autorzy próbują analizować niezależnie wpływ różnych czynników na efektywność pracy metod ICA i PCA. Mimo że w obu metodach twarz jest analizowana holistycznie to jednak każdy z czynników inaczej wpływa na efektywność poszczególnych metod. Pokazuje to niezależną przydatność metod w różnych zadaniach testowych.

EN

The research on applying ICA and PCA methods in face recognition is described. Several experiments were conducted using FERET, the most often applied base of face images. Authors are trying to analyze the influence of different factors independently on the efficiency of the work of ICA and PCA. In both methods the face is being analyzed in holistic way; however each of factors influences differently the efficiency of individual methods. It shows the independent usefulness of methods to different recognition task.

6

Vibro-acoustic analysis of laminated double glazing using the force identification method

83%

Ben Jdidia M. , Akrout A. , Tounsi D. , Fakhfakh T. , Haddar M.

|

2014

|

tom Vol. 52 nr 4

895--904

EN

This paper presents a procedure for identifying wave forms and excitation frequencies of some forces applied on a given complex fluid-structure coupled system by using only its vibro-acoustic response. The considered concept is called the Independent Component Analysis (ICA) which is based on the Blind Source Separation (BSS). In this work, the ICA method is exploited in order to determine the excitation force applied to a thin-film laminated double glazing system enclosing a thin fluid cavity and limited by an elastic joint. The dynamic response of the studied fluid-structure coupled system is determined by finite element discretization and minimization of the homogenized energy functional of the coupled problem. This response will serve as the input for the ICA algorithm in order to extract the applied excitation.

7

Independent component analysis of EEG data for EGI system

83%

Gajos A. , Wójcik G. M.

Bio-Algorithms and Med-Systems

|

2016

|

tom Vol. 12, no. 2

67--72

EN

Component analysis is one of the most important methods used for electroencephalographic (EEG) signal decomposition, and the so-called independent component analysis (ICA) is commonly used. The main function of the ICA algorithm is to find a linear representation of non-Gaussian data whose elements are statistically independent or at least as independent as possible. There are many commercial solutions for EEG signal acquisition. Usually, together with the EEG, one gets a dedicated software to handle the signal. However, quite often, the software does not provide researchers with all necessary functions. A high-performance, dense-array EGI-EEG system is distributed with the NetStation software. Although NetStation is a powerful tool, it does not have any implementation of the ICA algorithm. This causes many problems for researchers who want to export raw data from the amplifier and then work on it using some other tools such as EEGLAB for MATLAB, as these data are not fully compatible with the EGI format. We will present the C++ implementation of ICA that can handle filtered data from the EGI with better affordability. Our tool offers visualization of raw signal and ICA algorithm results and will be distributed under Freeware license.

8

ICA based on Split Generalized Gaussian

83%

Spurek P. , Rola P. , Tabor J. , Czechowski A. , Bedychaj A.

Schedae Informaticae

|

2019

|

tom Vol. 28

25--47

EN

Independent Component Analysis (ICA) is a method for searching the linear transformation that minimizes the statistical dependence between its components. Most popular ICA methods use kurtosis as a metric of independence (non-Gaussianity) to maximize, such as FastICA and JADE. However, their assumption of fourth-order moment (kurtosis) may not always be satisfied in practice. One of the possible solution is to use third-order moment (skewness) instead of kurtosis, which was applied in ICASG and EcoICA. In this paper we present a competitive approach to ICA based on the Split Generalized Gaussian distribution (SGGD), which is well adapted to heavy-tailed as well as asymmetric data. Consequently, we obtain a method which works better than the classical approaches, in both cases: heavy tails and non-symmetric data.

9

Road profile identification using estimation techniques: comparison between independent component analysis and Kalman filter

83%

Chaabane M. M. , Ben Hassen D. , Abbes M. S. , Baslamisli S. C. , Chaari F. , Haddar M.

Journal of Theoretical and Applied Mechanics

|

2019

|

tom Vol. 57 nr 2

397--409

EN

This paper focuses on the identification of a road profile disturbance acting on vehicles. Vehicles are subjected to many kinds of excitation sources such as road profile irregularities, which constitute a major area of interest when designing suspension systems. Indeed, determining the road profile is important for passive suspension design on the one hand and for determining an appropriate control law for active suspensions on the other. Direct measurement techniques of the road profile are expensive, so solutions based on estimation theory are needed. The aim of this paper is to characterize the road excitation using the Independent Component Analysis (ICA). This proposed method can reconstruct original excitation sources by using physically measurable signals of the system under study. Here, the estimation of road disturbances is considered as output sources and identified from dynamic responses of the vehicle. These responses can be measured via sensors or can be numerically computed. In our case, they are numerically simulated using the Newmark method and consider different types of road profiles. The obtained results are validated after using a comparison with the Kalman filtering. The robustness of the ICA is confirmed via parametric study.

10

Inverse method for a one-stage spur gear diagnosis

83%

Akrout A. , Tounsi D. , Taktak M. , Abbes M. S. , Haddar M.

Journal of Theoretical and Applied Mechanics

|

2015

|

tom Vol. 53 nr 3

617--628

EN

In this paper, a source separation approach based on the Blind Source Separation (BSS) is presented. In fact, the Independent Component Analysis (ICA), which is the main technique of BSS, consists in extracting different source signals from several observed mixtures. This inverse method is very useful in many fields such as telecommunication, signal processing and biomedicine. It is also very attractive for diagnosis of mechanical systems such as rotating machines. Generally, dynamic responses of a given mechanical system (displacements, accelerations and speeds) measured through sensors are used as inputs for the identification of internal defaults. In this study, the ICA concept is applied to the diagnosis of a one-stage gear mechanism in which two types of defects (the eccentricity error and the localized tooth defect)are introduced. The finite element method allows determination of the signals corresponding to the acceleration in some locations of the system, and those signals may be used also in the ICA algorithm. Hence, the vibratory signatures of each defect can be identified by the ICA concept. Thus, a good agreement is obtained by comparing the expected default signatures to those achieved by the developed inverse method.

11

Analysis of complex-valued functional magnetic resonance imaging data: are we just going through a "phase"?

71%

Calhoun V. , Adali T.

|

2012

|

tom Vol. 60, nr 3

371-418

EN

Functional magnetic resonance imaging (fMRI) data are acquired as a natively complex data set, however for various reasons the phase data is typically discarded. Over the past few years, interest in incorporating the phase information into the analyses has been growing and new methods for modeling and processing the data have been developed. In this paper, we provide an overview of approaches to understand the complex nature of fMRI data and to work with the utilizing the full information, both the magnitude and the phase. We discuss the challenges inherent in trying to utilize the phase data, and provide a selective review with emphasis on work in our group for developing biophysical models, preprocessing methods, and statistical analysis of the fully-complex data. Of special emphasis are the use of data-driven approaches, which are particularly useful as they enable us to identify interesting patterns in the complex-valued data without making strong assumptions about how these changes evolve over time, something which is challenging for magnitude data and even more so for the complex data. Finally, we provide our view of the current state of the art in this area and make suggestions for what is needed to make efficient use of the fully-complex fMRI data.

12

Independent component analysis and adaptive filtering as successful tools for an improvement of normogastric rhythm extraction in electrogastrographic signals

71%

Tkacz E. , Mika B.

|

2010

|

tom Vol. 16

27--34

EN

The aim of this study was to investigate the possibility of combining two methods: Independent Component Analysis (ICA) and Adaptive Signal Enhancement for the improvement of normogastric rhythm extraction from multichannel recording of electrogastrographic signals (EGG). Unfortunately the electrogastrogram, is a transcutaneous measurement of gastric electrical activity, does not contain pure signal but usually is a sort of mixture from both electrical activity of stomach as well as other organs surrounding it and random noise. In order to benefit the diagnostic power of multichannel recording of EGG, which can provide deeper understanding of gastric disorders, it is necessity to extract gastric slow wave in each channel. One of the parameters, which are analyzed and require proper registration is so called normogastric rhythm. According to the literature, the normogastric rhythm should cover around 70% of rhythmic behavior of signal for a healthy man. Proper extraction of basic 3-cpm normogastric rhythm in each channel is a subject of this paper. Independent Component Analysis is applied for extracting the reference signal for adaptive filtering what next result in obtaining less contaminated signal in each channel. Analysis has been perform for two postprandial phases with five minutes break between them. In both mention cases proposed procedure gives a promising results.

13

Development of Visual Evoked Potentials Detection AIgorithm for objective perimetry

71%

Drozd M. , Nowakowski A.

|

tom Vol. 25, no. 3

47-55

EN

Objective perimetry, based on the EEG signal analysis, represents a new trend in evaluation of the human visual system. At the moment, the work is concentrated on the effective algorithms of the EEG analysis for the weak transient VEP signal detection. A new algorithm for a rapid detection of visual cortical signals - the VEPDA - was developed. For evaluation of the algorithm, two approaches are considered. The first one, based on synthetic cortical potentials and artificial, spontaneous EEG, with all data generated in the developed model, and the second one, using the real EEG data taken from measurements and mixed with the synthetic VEP signal. The approach presented in this paper concerns application of VEPDA to the modelled VEP embedded in the real, ongoing EEG signal. The final step of the work is practical implementation of the method. The research results prove the validity of the algorithm applied to the modelled data. Here, the value of VEPDA usefulness in the analysis of the real EEG recording has been verified.

14

Zaczęło się w Brnie

71%

Ciołkosz A. , Ostrowski J.

Geodeta : magazyn geoinformacyjny

|

2009

|

tom nr 5

55-58

15

Design of instrumented wheelset for measuring wheel-rail interaction forces

71%

Bižić M. , Petrović D.

Metrology and Measurement Systems

|

2023

|

tom Vol. 30, nr 3

563--579

EN

The paper presents the design of a specific type of instrumented wheelset intended for continuous measuring of lateral and vertical wheel-rail interaction forces 𝑌 and 𝑄, in accordance with regulations EN 14363 and UIC 518. The platform is a standard heavy wheelset BA314 with an axle-load of 25 tons. The key problems of smart instrumentalization are solved by the use of the wheel’s numerical FEM model, which provides a significant cost reduction in the initial stage of development of the instrumented wheelset. The main goal is to ensure high measuring accuracy. The results of the FEM calculations in ANSYS are basis for identification of the distribution of strains on the internal and external side of the wheel disc. Consequently, the most convenient radial distances for installation of strain gauges of Wheatstone measuring bridges are determined. In the next stage, the disposition, number and ways of interconnection of strain gauges in the measuring bridges are defined. Ultimately, an algorithm for inverse determination of parameters 𝑌 and 𝑄 based on mixed signals from the measuring bridges is developed. The developed solution is validated through tests on specific examples, using a created numerical FEM model. A high accuracy of estimation of unknown parameters 𝑌 and 𝑄 is obtained with an error of less than 4.5%, while the error of estimation of their ratio 𝑌 𝑄 is less than 2%. Therefore, the proposed solution can be efficiently used in the instrumentalization of the considered wheelset, while the problems of its practical implementation will be the subject of further research.

16

Application of standard algorithms of automatic signal separation in medicine

71%

Nowak A.

|

2011

|

tom Vol. 7, no. 4

29--40

EN

In the present article various methods of automatic separation of acoustic signals have been described. The biggest focus was placed on two methods, Blind signal Separation (BSS) and Independent Component Analysis (ICA). In order to verify the efficacy of these methods, selected separation algorithms have been used for deconvolution of a specially prepared sinusoidal and saw-tooth sound signals as well as natural signals such as recordings of human voice. The obtained results have been compared and presented. More accurate results have been acquired from the analysis of artificially prepared signals that is the sinusoidal and saw-tooth signals which were mixed together using numerical transformations. Due to the potential practical usage of speech signal separation in medicine, more stress has been put on the analysis of life taken signals, which were created by mixing voices of few persons speaking simultaneously. The assessment of the usability of different algorithms, which effected from the research, may have practical application due to the fact that in the available literature the authors usually limit themselves only to presenting (and praising) algorithms created on their own, scarcely mentioning algorithms of different authors predominantly without doing necessary comparative researches. These missing researches constitute the essential part of the work presented in this article.

17

Impulse Noise Suppression Based on Power Iterative ICA in Power Line Communication

71%

Zhang W. , Luo Z. , Xiong X.

International Journal of Electronics and Telecommunications

|

2019

|

tom Vol. 65, No. 4

651--656

EN

To overcome the detrimental influence of impulse noise in power line communication and the trap of scarce prior information in traditional noise suppression schemes , a power iteration based fast independent component analysis (PowerICA) based noise suppression scheme is designed in this paper. Firstly, the pseudo-observation signal is constructed by weighted processing so that single-channel blind separation model is transformed into the multi-channel observed model. Then the proposed blind separation algorithm is used to separate noise and source signals. Finally, the effectiveness of the proposed algorithm is verified by experiment simulation. Experiment results show that the proposed algorithm has better separation effect, more stable separation and less implementation time than that of FastICA algorithm, which also improves the real-time performance of communication signal processing.

18

Definition of Mass Spring Parameters for Knitted Fabric Simulation Using the Imperialist Competitive Algorithm

67%

Mozafary V. , Payvandy P.

Fibres & Textiles in Eastern Europe

|

2017

|

tom Vol. 25, no. 1 (121)

65--74

EN

The 3D simulation of fabrics is an interesting issue in many fields, such as computer engineering, textile engineering, cloth design and so on. Several methods have been presented for fabric simulation. The mass spring model, a typical physically-based method, is one of the methods for fabric simulation which is widely considered by researchers due to rapid simulation and being more consistent with reality. The aim of this paper is the optimization of mass spring parameters in the simulation of the drape behaviour of knitted fabric using the Imperialist Competitive Algorithm. First a mass spring model is proposed to simulate the drape behavior of knitted fabric. Then in order to reduce the error value between the simulated and actual result (reducing the simulation error value), parameters of the mass spring model such as the stiffness coefficient, damping coefficient, elongation rate, topology and natural length of the spring are optimized using the Imperialist Competitive Algorithm (ICA). The ICA parameters are specified using the Taguchi Design of Experiment. Finally fabrics drape shapes are simulated in other situations and compared with their actual results to validate the model parameters. Results show that the optimized model is able to predict the drape behavior of knitted fabric with an error value of 2.4 percent.

PL

Celem niniejszej pracy jest optymalizacja parametrów masowo-sprężystych w symulacji układalności struktur dzianych przy wykorzystaniu imperialistycznego algorytmu konkurencji. Zaproponowano model mas i sprężyn symulujących zachowanie dzianin. Następnie, dla polepszenia korelacji pomiędzy strukturami teoretycznymi a rzeczywistymi, określone parametry modelu, takie jak: współczynnik sztywności, współczynnik tłumienia, wydłużenie, topologia i naturalna długości sprężyny zoptymalizowano posługując się imperialistycznym algorytmem konkurencji (ICA). Parametry określono przy użyciu planowania eksperymentu metodą Taguchi. Przedstawiono i porównano symulacje układalności z rzeczywistą układalnością dzianin. Stwierdzono, że opracowany model pozwala na przewidywanie układalności dzianin z dokładnością do 2,4%.

19

Direct assessment of the fetal heart rate from abdominal composite recordings

67%

Moslem B. , Bazzi O. , Khalaf J. , Diab M. O.

Journal of Medical Informatics & Technologies

|

2013

|

tom Vol. 22

143--149

EN

In respect to the main goal of our ongoing work for analyzing fetal electrocardiogram (FECG) signals for monitoring the health of the fetus, we investigate in this paper the possibility of extracting the fetal heart rate (FHR) directly from the abdominal composite recordings. Our proposed approach is based on a combination of Independent Component Analysis (ICA) and least mean square (LMS) adaptive filter. The FHR of the estimated FECG signal is finally compared to a reference value extracted from a FECG signal recorded by using a spiral electrode attached directly to the fetal scalp. The experimental results show that FHR can be successfully evaluated directly from the abdominal composite recordings without the need of using any external reference signal.

20

Stochastic risk and reliability assessments of energy management system in grid of microgrids under uncertainty

67%

Nikmehr N. , Najafi-Ravadanegh S.

Journal of Power Technologies

|

2017

|

tom Vol. 97, nr 3

179--189

EN

As various renewable energy resources (RERs) are exploited within microgrids (MGs), some important challenges have arisen as regards coping with generation fluctuations. This paper proposes a probabilistic method aimed at achieving optimal coordinated operation in a grid of microgrids under uncertainties of RERs and variable load demand. In the supposed structure based on networked microgrids (NMGs), a two-level strategy is required for guaranteeing efficient coordination between the MGs and distribution network operator (DNO). Another contribution of the paper deals with the flexibility of NMGs in improving the reliability of the whole system. Additionally, the value at risk (VaR) calculations for output results are carried out for different confidence levels with two important methods. In sum, the aim of the paper is to minimize total energy costs considering the environmental effects. To achieve this purpose, the Imperialist Competitive Algorithm (ICA) as a heuristic algorithm is applied to solve the optimal power dispatch problem and the obtained results are compared using the Monte Carlo Simulation (MCS) method. As the input data are modeled under uncertainties, the output results are described with probability distribution function (PDF).