Independent Component Analysis Technique Research Articles

An efficient FMRI classification technique in cloud using multiple parallel feature selection algorithm

Extensive research is going on in the field of analyzing the applications involving functional magnetic resonance imaging (fMRI) data with the help of machine learning classifiers. Studies have proven that inspiring new information can be obtained through neuroimaging data using machine learning classifiers. Feature selection has been an active research area and its key idea is to select a subset of input variables by removing features with little or no predictive data. Feature selection enhanced the clarity of the resulting classifier models and often dimensions a model that generalizes better to unseen points. In this work, fMRI classification technique is proposed using Multiple Parallel Feature Selection Algorithm. In case of parallel feature selection, the proposed algorithm’s computation is fully improved and parallelized based on data partitioning. Inputs for classifiers are used extensively through voxel-based features. The fMRI images are classified as normal or abnormal. From healthy persons normal fMRI images were obtained and from subjects with schizophrenia abnormal fMRI were obtained and a total of 140 normal fMRI and 67 abnormal fMRI were used. Multiple particle swarm optimization was used after independent component analysis phase and techniques varying by c1 and c2 were used through cluster computing techniques. From the obtained cluster the feature subset was selected and support vector machine is made use in classifying.

RETRACTED ARTICLE: Improving Solar Power Generation and Defects Detection Using a Smart IoT System for Sophisticated Distribution Control (SDC) and Independent Component Analysis (ICA) Techniques

These days, peoples are more concerned respects petroleum product energy and conservational issues caused on the power generation networks and renewable power resources at any other time. Amongst the renewable power resources, solar and windmill power generations are essential competitors. Photovoltaic modules additionally have moderately least transformation effectiveness. General system price was decreased utilizing significant productivity control which are made to determine for most significant achievable energy from solar PV array module utilizing MPPT procedures. Existing solar power generation likewise have the burden of being for the day outputs is less immediate introduction from natural sun radiation. By utilizing the Internet of Things (IoT) strategies for monitoring and controlling the solar power generation was significantly enhance the performance, and maintenance of the solar power plant. In this work explicitly argue advances IoT technique to increase output result of solar power generation at the system level. Covering turning the photovoltaic system in the position of maximum sunlight, obtaining significant available power obtained from the solar PV array and significant battery health management by using sophisticated distribution control (SDC) and independent component analysis techniques (ICA).The simulation work done under with the MATLAB software using proposed SDC and ICA logics the simulation results demonstrate the efficiency of the proposed method and its ability to track the maximum power of the PV panel. Over 97% efficiency achieved by using SDC and ICA methods.

A Comparison of ERP Data Cleaning Strategies for Neuroergonomic Error Detection

Event Abstract Back to Event A Comparison of ERP Data Cleaning Strategies for Neuroergonomic Error Detection Ben D. Sawyer1*, Waldemar Karwowski2, 3, Petros Xanthopoulos4 and P. A. Hancock3 1 Massachusetts Institute of Technology, United States 2 University of Central Florida, Department of Industrial Engineering, United States 3 University of Central Florida, Department of Psychology, United States 4 Stetson University, United States The decision to employ postprocessing on electroencephalographic (EEG) data, toward the removal of undesirable artifacts, is associated with concerns of inadvertently filtering brain process data of interest to the research question. The rich data provided by multichannel EEGs supports a variety of postprocessing approaches. Brain process characteristics are often already well-studied1,2, and so the approach often impractical terms involves applying a postprocessing technique, and determining if the aggregate signal representing the brain process of interest matches those previously reported in the literature. However, as increased interest in real-time approaches to characterizing brain processes dominates the applied neuroergonomic literature, it is worth considering the absolute merits of various postprocessing techniques. For example, in event related potential/evoked response potential (ERP) work analyzed after collection it is common to utilize independent component analysis (ICA), which relies upon this statistical independence of variance accounted for by artifacts and separates them from variance accounted for by brain activity. ICA techniques, in effect, “clean” the waveform for analysis, preserving epics of interest. This is, however, a relatively computationally “expensive” approach for real-time applications. A relatively simple technique, moving window peak-to-peak amplitude detection (P2PW), uses differences between the highest and lowest voltages within successive epics of time to flag artifacts for removal. P2PW, therefore, does not preserve epics of interest, instead removes them entirely. The present work compares the performance of these two approaches in data collected by Sawyer et al.2,3 during an experiment which, for the first time, demonstrated the detection of the error related negativity (ERN) ERP in visual search for complex stimuli. In this work, participants completed tasks during 8 channel EEG recording, which was then analysed using ICA post-processing3. Successfully elicitation and detection of this ERN in visual search of complex images opens the door to applied neuroergonomics ‘in the field’ (as in Fedota & Parasuraman, 2010) 1,3. The question of how best to process data “on-the-fly”, however, is relevant specifically because of the context: computation costs power, which is heavy and expensive to carry in the field. For example, in event related potential/evoked response potential (ERP) work analyzed after collection it is common to utilize independent component analysis (ICA), which relies upon this statistical independence of variance accounted for by artifacts and separates them from variance accounted for by brain activity. ICA techniques, in effect, “clean” the waveform for analysis, preserving epics of interest. This is, however, a relatively computationally “expensive” approach for real-time applications. A relatively simple technique, moving window peak-to-peak amplitude detection (P2PW), uses differences between the highest and lowest voltages within successive epics of time to flag artifacts for removal. P2PW, therefore, does not preserve epics of interest, instead removes them entirely. The present work compares the performance of these two approaches in data collected by Sawyer et al.2,3 during an experiment which, for the first time, demonstrated the detection of the error related negativity (ERN) ERP in visual search for complex stimuli. In this work, participants completed tasks during 8 channel EEG recording, which was then analysed using ICA post-processing3. Successfully elicitation and detection of this ERN in visual search of complex images opens the door to applied neuroergonomics ‘in the field’ (as in Fedota & Parasuraman, 2010) 1,3. The question of how best to process data “on-the-fly”, however, is relevant specifically because of the context: computation costs power, which is heavy and expensive to carry in the field. Figure 1: Waveform data for errors and non-errors are shown across a simple letter flanker task and a complex motorcycle conspicuity task, separated by three postprocessing strategies, A) ICA B) P2PW, and C) raw data. These average time-locked ERP waveforms for are represented with negitive plotted down, and relative to a 50ms baseline time-locked against participant response by keypress. A full 100ms of pre response activity is shown here for evaluative purposes. The waveforms for ICA (A) show the clearest ERN pattern, but the negative trend of erroneous results and separation between correct and error trials can be clearly seen in the P2PW (A) and raw data (C) waveforms. Table 1 Task data loss by post-processing type Figure 1 Image 1

Ten Key Observations on the Analysis of Resting-state Functional MR Imaging Data Using Independent Component Analysis.

For more than 20 years, the powerful, flexible family of independent component analysis (ICA) techniques has been used to examine spatial, temporal, and subject variation in functional magnetic resonance (fMR) imaging data. This article provides an overview of 10 key principles in the basic and advanced application of ICA to resting-state fMR imaging. ICA's core advantages include robustness to artifact; false-positives and autocorrelation; adaptability to variant study designs; agnosticism to the temporal evolution of fMR imaging signals; and ability to extract, identify, and analyze neural networks. ICA remains in the vanguard of fMRI methods development.

GRADIENT ASCENT INDEPENDENT COMPONENT ANALYSIS ALGORITHM FOR TELECOMMUNICATION SIGNALS

Independent Component Analysis (ICA) algorithm is normallused for un-mixing and feature extraction of the fixed input block lengths. In case of varying block lengths re-adjustment of the maximum number of iterations and the step size parameter is required. In this paper, we introduced an Adaptive Step size Gradient Ascent ICA (AS-GAICA) technique for varying block length that can also controls the maximum number of iterations adaptively. The performance of the proposed technique is compared with Fast-ICA and Optimum Block Adaptation ICA (OBAICA) for telecommunication signals. Simulation results show that the proposed scheme outperforms the Fast-ICA and OBAICA algorithms.

GPS deformation related to the Mw 7.3, 2014, Papanoa earthquake (Mexico) reveals the aseismic behavior of the Guerrero seismic gap

AbstractWe present the study of 21 continuous GPS (cGPS) stations in Mexico during the time interval that goes from 1 October 2013 to 31 December 2014. The area under investigation produced a slow slip event (SSE) that started in February 2014 and lasted at least until December 2014. Superimposed on this transient signal, the Mw7.3 Papanoa earthquake struck the region on 18 April 2014 and affected multiple stations. Thanks to an independent component analysis (ICA) technique we are able to separate the postseismic deformation associated with this earthquake from the deformation related to the ongoing SSE. We infer the slip distributions associated with the three tectonically related processes: the coseismic and postseismic slip and the SSE. The inferred postseismic slip distribution reduces the amount of slip related to the SSE in the updip portion of the slab. The moment released by the postseismic processes (afterslip and aftershocks) is estimated to be [8.06 ± 0.24] × 1019 Nm, equivalent to [71 ± 4]% of the moment associated with the main shock. More than 88% of the postseismic moment is released aseismically and the afterslip spatially correlates with the Guerrero seismic gap, suggesting that the region is controlled by stable sliding behavior and rate‐strengthening frictional properties.

Blind Equalization Based on JADE in PDM-CO-OFDM

Optical orthogonal frequency division multiplexing (OOFDM) significantly reduces frequency overhead in data transmission. Channel equalization (CE) is an approach used to estimate the channel state, and generally with inserting periodic training symbols (TS) to assist channel estimation. By study the technique of independent component analysis, a blind CE method based on joint approximate diagonalization of eigen-matrices with only one-tap in each subcarrier and without TS for polarization division multiplexing coherent optical orthogonal frequency division multiplexing (PDM-CO-OFDM) is proposed. This method has a faster convergence speed than the conventional CE technique in PDM-CO-OFDM. For the free of TS, it also enhances the spectral efficiency of the systems. The given approach may offer an efficient technique in the fields such as data transmission in high speed and burst communication, as well as OFDM system. Simulation results indicate that our method is effective for blind CE in OOFDM.

Electroconvulsive therapy-induced brain functional connectivity predicts therapeutic efficacy in patients with schizophrenia: a multivariate pattern recognition study

Previous studies suggested that electroconvulsive therapy can influence regional metabolism and dopamine signaling, thereby alleviating symptoms of schizophrenia. It remains unclear what patients may benefit more from the treatment. The present study sought to identify biomarkers that predict the electroconvulsive therapy response in individual patients. Thirty-four schizophrenia patients and 34 controls were included in this study. Patients were scanned prior to treatment and after 6 weeks of treatment with antipsychotics only (n = 16) or a combination of antipsychotics and electroconvulsive therapy (n = 13). Subject-specific intrinsic connectivity networks were computed for each subject using a group information-guided independent component analysis technique. Classifiers were built to distinguish patients from controls and quantify brain states based on intrinsic connectivity networks. A general linear model was built on the classification scores of first scan (referred to as baseline classification scores) to predict treatment response. Classifiers built on the default mode network, the temporal lobe network, the language network, the corticostriatal network, the frontal-parietal network, and the cerebellum achieved a cross-validated classification accuracy of 83.82%, with specificity of 91.18% and sensitivity of 76.47%. After the electroconvulsive therapy, psychosis symptoms of the patients were relieved and classification scores of the patients were decreased. Moreover, the baseline classification scores were predictive for the treatment outcome. Schizophrenia patients exhibited functional deviations in multiple intrinsic connectivity networks which were able to distinguish patients from healthy controls at an individual level. Patients with lower classification scores prior to treatment had better treatment outcome, indicating that the baseline classification scores before treatment is a good predictor for treatment outcome.

Network modeling of resting state connectivity points towards the bottom up theories of schizophrenia

The dysconnectivity theory of schizophrenia proposes that schizophrenia symptoms arise from abnormalities in neuronal synchrony. Resting-state Functional Connectivity (FC) techniques allow us to highlight synchronization of large-scale networks, the Resting-state Networks (RNs). A large body of work suggests that disruption of RN synchronization could give rise to specific schizophrenia symptoms. The present study aimed to explore within- and between-network FC strength of 34 RNs in 29 patients suffering from schizophrenia, and their relationships with schizophrenia symptoms. Resting-state data were analyzed using independent component analysis and dual-regression techniques. Our results showed that both within-RN and between-RN FC were disrupted in patients with schizophrenia, with a global trend toward weaker FC. This decrease affected more particularly visual, auditory and crossmodal binding networks. These alterations were correlated with negative symptoms, positive symptoms and hallucinations, indicating abnormalities in visual processing and crossmodal binding in schizophrenia. Moreover, we stressed an anomalous synchronization between a visual network and a network thought to be engaged in mental imaging processes, correlated with delusions and hallucinations. Altogether, our results supported the assumption that some schizophrenia symptoms may be related to low-order sensory alterations impacting higher-order cognitive processes, i.e. the “bottom-up” hypothesis of schizophrenia symptoms.

Using Dual Regression to Investigate Network Shape and Amplitude in Functional Connectivity Analyses.

Independent Component Analysis (ICA) is one of the most popular techniques for the analysis of resting state FMRI data because it has several advantageous properties when compared with other techniques. Most notably, in contrast to a conventional seed-based correlation analysis, it is model-free and multivariate, thus switching the focus from evaluating the functional connectivity of single brain regions identified a priori to evaluating brain connectivity in terms of all brain resting state networks (RSNs) that simultaneously engage in oscillatory activity. Furthermore, typical seed-based analysis characterizes RSNs in terms of spatially distributed patterns of correlation (typically by means of simple Pearson's coefficients) and thereby confounds together amplitude information of oscillatory activity and noise. ICA and other regression techniques, on the other hand, retain magnitude information and therefore can be sensitive to both changes in the spatially distributed nature of correlations (differences in the spatial pattern or “shape”) as well as the amplitude of the network activity. Furthermore, motion can mimic amplitude effects so it is crucial to use a technique that retains such information to ensure that connectivity differences are accurately localized. In this work, we investigate the dual regression approach that is frequently applied with group ICA to assess group differences in resting state functional connectivity of brain networks. We show how ignoring amplitude effects and how excessive motion corrupts connectivity maps and results in spurious connectivity differences. We also show how to implement the dual regression to retain amplitude information and how to use dual regression outputs to identify potential motion effects. Two key findings are that using a technique that retains magnitude information, e.g., dual regression, and using strict motion criteria are crucial for controlling both network amplitude and motion-related amplitude effects, respectively, in resting state connectivity analyses. We illustrate these concepts using realistic simulated resting state FMRI data and in vivo data acquired in healthy subjects and patients with bipolar disorder and schizophrenia.

Compound fault prediction of rolling bearing using multimedia data

Catastrophic failure of mechanical systems due to faults occurring on rolling bearing is still a great challenge. These faults, which are of multiple type, are compounded in nature. Vibration analysis of multimedia signals is one of the most effective techniques for the health monitoring of these bearings. A compound fault signal usually consists of multiple characteristic signals and strong confusion noise, which makes it a tough task to separate weak fault signals from them. To resolve the compound fault diagnosis problem of rolling bearings byseparation of multimedia signals’ (obtained from acoustic or acceleration sensors), ensemble empirical mode decomposition (EEMD) method along with some classifier (like independent component analysis (ICA) technique) has been used to some degree of success. But, they are not found capable of detecting difficult faults existing on small balls of the bearing. In order to solve this problem, we are going to propose a new method based on use of Combined Mode Functions (CMF) for selecting the intrinsic mode functions(IMFs) instead of the maximum cross correlation coefficient based EEMD technique, sandwiched with, Convolution Neural Networks (CNN), which are deep neural nets, used as fault classifiers. This composite CNN-CMF-EEMD methodovercomes the deficiencies of other approaches, such as the inability to learn the complex non-linear relationships in fault diagnosis issues and fine compound faults like those occurring on small balls of the bearing. The difficult compound faults can be separated effectively by executing CNN-CMF-EEMD method, which makes the fault features more easily extracted and more clearly identified. Experimental results reinforce the effectiveness of using CNN-CMF--EEMD technique for fine compound faults. A comparison of CNN-CMF-EEMD with Artificial Neural Networks (ANN) based ANN-CMF-EEMD shows the capability of CNN as a powerful classifier in the domain of compound fault features of rolling bearing.

Multidimensional prediction of treatment response to antidepressants with cognitive control and functional MRI.

Predicting treatment response for major depressive disorder can provide a tremendous benefit for our overstretched health care system by reducing number of treatments and time to remission, thereby decreasing morbidity. The present study used neural and performance predictors during a cognitive control task to predict treatment response (% change in Hamilton Depression Rating Scale pre- to post-treatment). Forty-nine individuals diagnosed with major depressive disorder were enrolled with intent to treat in the open-label study; 36 completed treatment, had useable data, and were included in most data analyses. Participants included in the data analysis sample received treatment with escitalopram (n = 22) or duloxetine (n = 14) for 10 weeks. Functional MRI and performance during a Parametric Go/No-go test were used to predict per cent reduction in Hamilton Depression Rating Scale scores after treatment. Haemodynamic response function-based contrasts and task-related independent components analysis (subset of sample: n = 29) were predictors. Independent components analysis component beta weights and haemodynamic response function modelling activation during Commission errors in the rostral and dorsal anterior cingulate, mid-cingulate, dorsomedial prefrontal cortex, and lateral orbital frontal cortex predicted treatment response. In addition, more commission errors on the task predicted better treatment response. Together in a regression model, independent component analysis, haemodynamic response function-modelled, and performance measures predicted treatment response with 90% accuracy (compared to 74% accuracy with clinical features alone), with 84% accuracy in 5-fold, leave-one-out cross-validation. Convergence between performance markers and functional magnetic resonance imaging, including novel independent component analysis techniques, achieved high accuracy in prediction of treatment response for major depressive disorder. The strong link to a task paradigm provided by use of independent component analysis is a potential breakthrough that can inform ways in which prediction models can be integrated for use in clinical and experimental medicine studies.

CONTROL PROPOSAL FOR A HIGH PURITY COLUMN BASED ON THE SEPARATION OF VARIABLES BY THE INDEPENDENT COMPONENT ANALYSIS METHOD

Abstract Many industries are complex when it comes to operation mode. In order to reduce the problems related to strong coupling in these processes, the search for the incorporation of artificial intelligence devices has shown an increasing trend in recent years. Due to this complexity and control in multivariable processes, diagnosis and fault monitoring in the processes have become increasingly difficult. Therefore, the application of these devices has achieved satisfactory results regarding the procedures performed with human operators. Independent Component Analysis (ICA) is a signal separation technique that is based on the use of higher order statistics to estimate each of the unknown sources, through observation of various mixtures generated from these sources. Although there are recent works on using the ICA in industrial processes, few studies have been made in cases involving distillation columns. This paper proposes a control strategy based on the ICA technique, which makes the control loops decoupled and hence the performance easier. Compared to the conventional method, the technique provided a great improvement in control performance. Control structures were implemented in Simulink/Matlab® in communication with a 1,2-dichloroethane (1,2-EDC) plant simulated in Aspen Plus DynamicsTM.

Dimensionality Reduction using Hybrid Support Vector Machine and Discriminant Independent Component Analysis for Hyperspectral Image

Hyperspectral image is an image obtain from a satellite sensor. This image has more than 100 bands with a wide spectral range and increased spatial image resolution, providing detailed information on objects or materials that exist on the ground in a specific way. The hyperspectral image is well suited for the classification of the earth’s surface covering due to it. Due to the features of the hyperspectral data, then lately research related to trend hyperspectral data tend to increase. The transformation of the reduction of the dimensions of the original data into a new dimension reduction chamber is often done to overcome the problem of ‘curse of dimensionality’ in which its dimensions tend to increase exponentially. Data is mapped from the original data to a lower dimensionless space through a dimensional reduction procedure which must display the observation input effectively. Therefore, in this research we proposed a hyperspectral dimension hybrid reduction method which adopted Support Vector Machine (SVM) and Discriminant Independent Component Analysis (DICA) techniques to reduce original data in order to obtain better accuracy. By using SVM+DICA is used to reduction dimension hyperspectral images. In this research, we use KNN as classifier. From the experiment obtained that value of average accuracy is 0.7527, overall accuracy is 0.7901, and Kappa is 0.7608 for AVIRIS dataset.

Application and Evaluation of Independent Component Analysis Methods to Generalized Seizure Disorder Activities Exhibited in the Brain

EEG records the spontaneous electrical activity of the brain using multiple electrodes placed on the scalp, and it provides a wealth of information related to the functions of brain. Nevertheless, the signals from the electrodes cannot be directly applied to a diagnostic tool like brain mapping as they undergo a "mixing" process because of the volume conduction effect in the scalp. A pervasive problem in neuroscience is determining which regions of the brain are active, given voltage measurements at the scalp. Because of which, there has been a surge of interest among the biosignal processing community to investigate the process of mixing and unmixing to identify the underlying active sources. According to the assumptions of independent component analysis (ICA) algorithms, the resultant mixture obtained from the scalp can be closely approximated by a linear combination of the "actual" EEG signals emanating from the underlying sources of electrical activity in the brain. As a consequence, using these well-known ICA techniques in preprocessing of the EEG signals prior to clinical applications could result in development of diagnostic tool like quantitative EEG which in turn can assist the neurologists to gain noninvasive access to patient-specific cortical activity, which helps in treating neuropathologies like seizure disorders. The popular and proven ICA schemes mentioned in various literature and applications were selected (which includes Infomax, JADE, and SOBI) and applied on generalized seizure disorder samples using EEGLAB toolbox in MATLAB environment to see their usefulness in source separations; and they were validated by the expert neurologist for clinical relevance in terms of pathologies on brain functionalities. The performance of Infomax method was found to be superior when compared with other ICA schemes applied on EEG and it has been established based on the validations carried by expert neurologist for generalized seizure and its clinical correlation. The results are encouraging for furthering the studies in the direction of developing useful brain mapping tools using ICA methods.

Erasing the Milky Way: new cleaning technique applied to GBT intensity mapping data

We present the first application of a new foreground removal pipeline to the current leading HI intensity mapping dataset, obtained by the Green Bank Telescope (GBT). We study the 15hr and 1hr field data of the GBT observations previously presented in Masui et al (2013) and Switzer et al (2013), covering about 41 square degrees at 0.6<z<1.0, for which cross-correlations may be measured with the galaxy distribution of the WiggleZ Dark Energy Survey. In the presented pipeline, we subtract the Galactic foreground continuum and the point source contamination using an independent component analysis technique (fastica), and develop a Fourier-based optimal estimator to compute the temperature power spectrum of the intensity maps and cross-correlation with the galaxy survey data. We show that fastica is a reliable tool to subtract diffuse and point-source emission through the non-Gaussian nature of their probability distributions. The temperature power spectra of the intensity maps is dominated by instrumental noise on small scales which fastica, as a conservative subtraction technique of non-Gaussian signals, can not mitigate. However, we determine similar GBT-WiggleZ cross-correlation measurements to those obtained by the Singular Value Decomposition (SVD) method, and confirm that foreground subtraction with fastica is robust against 21cm signal loss, as seen by the converged amplitude of these cross-correlation measurements. We conclude that SVD and fastica are complementary methods to investigate the foregrounds and noise systematics present in intensity mapping datasets.

Application of the Independent Components Analysis in the Reconstruction of Acoustic Sources in Duct Systems

The development of new reconstruction methods of acoustic sources presents a domain of great interest seen its applications in reducing the noise, realizing the acoustic comfort and diagnosing systems. The duct systems are used in several systems such as building, ventilation and aeronautic systems. In this work, a new reconstruction technique of the acoustic sources in duct systems is presented. This technique is based on the multimodal scattering matrix that provides an estimation of the acoustic power dissipation and attenuation in the case of a point acoustic source. These energetic parameters are then injected into an identification technique based on the independent component analysis technique allowing the reconstruction of original sources. The method was applied to a cylindrical rigid-lined-rigid duct element. A comparison between the estimated and imposed acoustic pressures emitted by point sources is presented. This comparison showed that the proposed method gives good results, and the original signals are well reconstructed.

Automatic microstructural characterization and classification using probabilistic neural network on ultrasound signals

During the gas tungsten arc welding of nickel based superalloys, the secondary phases such as Laves and carbides are formed in final stage of solidification. But, other phases such as $$\gamma ^{{\prime \prime }}$$ and $$\delta $$ phases can precipitate in the microstructure, during aging at high temperatures. However, it is possible to minimize the formation of the Nb-rich Laves phases and therefore reduce the possibility of solidification cracking by adopting the appropriate welding conditions. This paper aims at the automatic microstructurally characterizing the kinetics of phase transformations on an Nb-base alloy, thermally aged at 650 and 950 $$^{\circ }$$ C for 10, 100 and 200 h, through backscattered ultrasound signals at frequency of 4 MHz. The ultrasound signals are inherently non-linear and thus the conventional linear time and frequency domain methods can not reveal the complexity of these signals clearly. Consequently, an automated processing system is designed using the higher-order statistics techniques, such as 3rd-order cumulant and bispectrum. These techniques are non-linear methods which are highly robust to noise. For this, the coefficients of 3rd-order cumulant and bispectrum of ultrasound signals are subjected to the independent component analysis (ICA) technique to reduce the statistical redundancy and reveal discriminating features. These dimensionality reduced features are fed to the probabilistic neural network (PNN) to automatic microstructural classification. The training process of PNN depends only on the selection of the smoothing parameters of pattern neurons. In this article, we propose the application of the bees algorithm to the automatic adaptation of smoothing parameters. The ICA components of cumulant coefficients coupled with the optimized PNN yielded the highest average accuracy of 97.0 and 83.5 %, respectively for thermal aging at 650 and 950 $$^{\circ }$$ C. Thus, the proposed processing system provides high reliability to be used for microstructure characterization through ultrasound signals.

Coprolalia as a manifestation of epileptic seizures.

The aim of this study was to investigate the lateralizing and localizing value of ictal coprolalia and brain areas involved in its production. A retrospective search for patients manifesting ictal coprolalia was conducted in our EMU database. Continuous video-EEG recordings were reviewed, and EEG activity before and during coprolalia was analyzed using independent component analysis (ICA) technique and was compared to the seizures without coprolalia among the same patients. Nine patients were evaluated (five women), eight with intracranial video-EEG recordings (icVEEG). Four had frontal or temporal lesions, and five had normal MRIs. Six patients showed impairment in the language functions and five in the frontal executive tasks. Two hundred six seizures were reviewed (60.7% from icVEEG). Ictal coprolalia occurred in 46.6% of them, always associated with limbic auras or automatisms. They arose from the nondominant hemisphere in five patients, dominant hemisphere in three, and independently from the right and left hippocampus-parahippocampus in one. Electroencephalographic activity always involved orbitofrontal and/or mesial temporal regions of the nondominant hemisphere when coprolalia occurred. Independent component analysis of 31 seizures in seven patients showed a higher number of independent components in the nondominant hippocampus-parahippocampus before and during coprolalia and in the dominant lateral temporal region in those seizures without coprolalia (p=0.009). Five patients underwent surgery, and all five had an ILAE class 1 outcome. Ictal coprolalia occurs in both males and females with temporal or orbitofrontal epilepsy and has a limited lateralizing value to the nondominant hemisphere but can be triggered by seizures from either hemisphere. It involves activation of the paralimbic temporal-orbitofrontal network.

Application of Independent Component Analysis techniques in speckle noise reduction of retinal OCT images

Optical Coherence Tomography (OCT) is an emerging technique in the field of biomedical imaging, with applications in ophthalmology, dermatology, coronary imaging, etc. OCT images usually suffer from a granular pattern, called speckle noise, which restricts the process of interpretation. Therefore the need for speckle noise reduction techniques is of high importance. To the best of our knowledge, use of Independent Component Analysis (ICA) techniques has never been explored for speckle reduction of OCT images. Here, a comparative study of several ICA techniques (InfoMax, JADE, FastICA and SOBI) is provided for noise reduction of retinal OCT images. Having multiple B-scans of the same location, the eye movements are compensated using a rigid registration technique. Then, different ICA techniques are applied to the aggregated set of B-scans for extracting the noise-free image. Signal-to-Noise-Ratio (SNR), Contrast-to-Noise-Ratio (CNR) and Equivalent-Number-of-Looks (ENL), as well as analysis on the computational complexity of the methods, are considered as metrics for comparison. The results show that use of ICA can be beneficial, especially in case of having fewer number of B-scans.