A "fractal" expander-compressor-supplier formative research method on array processing.

In the present research the typical triangle on formative research was extended to a double triangle for an overall career programme (here expander/ compressor) and funnel proposal was explored in a single course (as a "fractal" method). Array processing and ElectroEncephaloGram (EEG) techniques have been incorporated into a Digital Signal Processing (DSP) course and research projects. The present research question was: is it possible to insert array sensing on formative research in an undergraduate course of DSP? From over eight years, two semesters with different homework loads (homogeneous triangle vs expander-compressor-supplier distributions) were analysed in detail within the DSP evaluations and students chose between experimental applied analysis and a formative research project. Results showed that cognitive load was influenced positively in the expander-compressor-supplier distribution, showing that an increase of the efficiency undertook more undergraduate research on array processing and the decrease of the number of formative applied projects. Over a longer term (48 months) students undertook more undergraduate research works on array processing and DSP techniques. Supplementary Information: The online version contains supplementary material available at 10.1007/s10639-023-11837-y.

Automatic Classification of Subjects of the PSEN1-E280A Family at Risk of Developing Alzheimer's Disease Using Machine Learning and Resting State Electroencephalography.

BACKGROUND: The study of genetic variant carriers provides an opportunity to identify neurophysiological changes in preclinical stages. Electroencephalography (EEG) is a low-cost and minimally invasive technique which, together with machine learning, provide the possibility to construct systems that classify subjects that might develop Alzheimer's disease (AD). OBJECTIVE: The aim of this paper is to evaluate the capacity of the machine learning techniques to classify healthy Non-Carriers (NonCr) from Asymptomatic Carriers (ACr) of PSEN1-E280A variant for autosomal dominant Alzheimer's disease (ADAD), using spectral features from EEG channels and brain-related independent components (ICs) obtained using independent component analysis (ICA). METHODS: EEG was recorded in 27 ACr and 33 NonCr. Statistical significance analysis was applied to spectral information from channels and group ICA (gICA), standardized low-resolution tomography (sLORETA) analysis was applied over the IC as well. Strategies for feature selection and classification like Chi-square, mutual informationm and support vector machines (SVM) were evaluated over the dataset. RESULTS: A test accuracy up to 83% was obtained by implementing a SVM with spectral features derived from gICA. The main findings are related to theta and beta rhythms, generated in the parietal and occipital regions, like the precuneus and superior parietal lobule. CONCLUSION: Promising models for classification of preclinical AD due to PSEN-1-E280A variant can be trained using spectral features, and the importance of the beta band and precuneus region is highlighted in asymptomatic stages, opening up the possibility of its use as a screening methodology.

Stationary EEG pattern relates to large-scale resting state networks - An EEG-fMRI study connecting brain networks across time-scales.

Relating brain dynamics acting on time scales that differ by at least an order of magnitude is a fundamental issue in brain research. The same is true for the observation of stable dynamical structures in otherwise highly non-stationary signals. The present study addresses both problems by the analysis of simultaneous resting state EEG-fMRI recordings of 53 patients with epilepsy. Confirming previous findings, we observe a generic and temporally stable average correlation pattern in EEG recordings. We design a predictor for the General Linear Model describing fluctuations around the stationary EEG correlation pattern and detect resting state networks in fMRI data. The acquired statistical maps are contrasted to several surrogate tests and compared with maps derived by spatial Independent Component Analysis of the fMRI data. By means of the proposed EEG-predictor we observe core nodes of known fMRI resting state networks with high specificity in the default mode, the executive control and the salience network. Our results suggest that both, the stationary EEG pattern as well as resting state fMRI networks are different expressions of the same brain activity. This activity is interpreted as the dynamics on (or close to) a stable attractor in phase space that is necessary to maintain the brain in an efficient operational mode. We discuss that this interpretation is congruent with the theoretical framework of complex systems as well as with the brain's energy balance.

Volume Reduction Techniques for the Classification of Independent Components of rs-fMRI Data: a Study with Convolutional Neural Networks.

In the last decade, neurosciences have had an increasing interest in resting state functional magnetic resonance imaging (rs-fMRI) as a result of its advantages, such as high spatial resolution, compared to other brain exploration techniques. To improve the technique, the elimination of artifacts through Independent Components Analysis (ICA) has been proposed, as this can separate neural signal and noise, opening possibilities for automatic classification. The main classification techniques have focused on processes based on typical machine learning. However, there are currently more robust approaches such as convolutional neural networks, which can deal with complex problems directly from the data without feature selection and even with data that does not have a simple interpretation, being limited by the amount of data necessary for training and its high computational cost. This research focused on studying four methods of volume reduction mitigating the computational cost for the training of 3 models based on convolutional neural networks. One of the reduction techniques is a novel approach that we call Reduction by Consecutive Binary Patterns (RCBP), which was shown to preserve the spatial features of the independent components. In addition, the RCBP showed networks in components associated with neuronal activity more clearly. The networks achieved accuracy above 98 % in classification, and one network was even found to be over 99 % accurate, outperforming most machine learning-based classification algorithms.

Decision Tree Based Salp Swarm Optimization for Multi Medical Data Classification with Feature Reduction Technique

Abstract The ambitious task in the domain of medical informatics is medical data classification. From medical datasets, intention to ameliorate human burden with the medical data classification entails to taking in classification designs. The medical data classification is the major focus of this paper, where a Decision Tree based Salp Swarm Optimization (DT-SWO) algorithm is proposed. After pre-processingthe hybrid feature selection method selects the medical data features. The high dimensional features are reduced by Discriminant Independent Component Analysis (DICA) and DT-SWO is to classify the most relevant class of medical data. The details of four datasets namely Leukemia, Diffuse Larger B-cell Lymphomas (DLBCL), Lung cancer and Colon relating to four diseases for heart, liver, cancer and lungs are collected from the UCI machine learning repository. Ultimately, the experimental outcomes demonstrated that the proposed DT-SWO algorithm is suitable for medical data classification than other algorithms.

Reduced fronto-striatal volume in attention-deficit/hyperactivity disorder in two cohorts across the lifespan.

Attention-Deficit/Hyperactivity Disorder (ADHD) has been associated with altered brain anatomy in neuroimaging studies. However, small and heterogeneous study samples, and the use of region-of-interest and tissue-specific analyses have limited the consistency and replicability of these effects. We used a data-driven multivariate approach to investigate neuroanatomical features associated with ADHD in two independent cohorts: the Dutch NeuroIMAGE cohort (n = 890, 17.2 years) and the Brazilian IMpACT cohort (n = 180, 44.2 years). Using independent component analysis of whole-brain morphometry images, 375 neuroanatomical components were assessed for association with ADHD. In both discovery (corrected-p = 0.0085) and replication (p = 0.032) cohorts, ADHD was associated with reduced volume in frontal lobes, striatum, and their interconnecting white-matter. Current results provide further evidence for the role of the fronto-striatal circuit in ADHD in children, and for the first time show its relevance to ADHD in adults. The fact that the cohorts are from different continents and comprise different age ranges highlights the robustness of the findings.

METROID: an automated method for robust quantification of subcellular fluorescence events at low SNR.

BACKGROUND: In cell biology, increasing focus has been directed to fast events at subcellular space with the advent of fluorescent probes. As an example, voltage sensitive dyes (VSD) have been used to measure membrane potentials. Yet, even the most recently developed genetically encoded voltage sensors have demanded exhausting signal averaging through repeated experiments to quantify action potentials (AP). This analysis may be further hampered in subcellular signals defined by small regions of interest (ROI), where signal-to-noise ratio (SNR) may fall substantially. Signal processing techniques like blind source separation (BSS) are designed to separate a multichannel mixture of signals into uncorrelated or independent sources, whose potential to separate ROI signal from noise has been poorly explored. Our aims are to develop a method capable of retrieving subcellular events with minimal a priori information from noisy cell fluorescence images and to provide it as a computational tool to be readily employed by the scientific community. RESULTS: In this paper, we have developed METROID (Morphological Extraction of Transmembrane potential from Regions Of Interest Device), a new computational tool to filter fluorescence signals from multiple ROIs, whose code and graphical interface are freely available. In this tool, we developed a new ROI definition procedure to automatically generate similar-area ROIs that follow cell shape. In addition, simulations and real data analysis were performed to recover AP and electroporation signals contaminated by noise by means of four types of BSS: Principal Component Analysis (PCA), Independent Component Analysis (ICA), and two versions with discrete wavelet transform (DWT). All these strategies allowed for signal extraction at low SNR (- 10 dB) without apparent signal distortion. CONCLUSIONS: We demonstrate the great capability of our method to filter subcellular signals from noisy fluorescence images in a single trial, avoiding repeated experiments. We provide this novel biomedical application with a graphical user interface at https://doi.org/10.6084/m9.figshare.11344046.v1 , and its code and datasets are available in GitHub at https://github.com/zoccoler/metroid .

Amygdala 5-HTT Gene Network Moderates the Effects of Postnatal Adversity on Attention Problems: Anatomo-Functional Correlation and Epigenetic Changes.

Variations in serotoninergic signaling have been related to behavioral outcomes. Alterations in the genome, such as DNA methylation and histone modifications, are affected by serotonin neurotransmission. The amygdala is an important brain region involved in emotional responses and impulsivity, which receives serotoninergic input. In addition, studies suggest that the serotonin transporter gene network may interact with the environment and influence the risk for psychiatric disorders. We propose to investigate whether/how interactions between the exposure to early life adversity and serotonin transporter gene network in the amygdala associate with behavioral disorders. We constructed a co-expression-based polygenic risk score (ePRS) reflecting variations in the function of the serotonin transporter gene network in the amygdala and investigated its interaction with postnatal adversity on attention problems in two independent cohorts from Canada and Singapore. We also described how interactions between ePRS-5-HTT and postnatal adversity exposure predict brain gray matter density and variation in DNA methylation across the genome. We observed that the expression-based polygenic risk score, reflecting the function of the amygdala 5-HTT gene network, interacts with postnatal adversity, to predict attention and hyperactivity problems across both cohorts. Also, both postnatal adversity score and amygdala ePRS-5-HTT score, as well as their interaction, were observed to be associated with variation in DNA methylation across the genome. Variations in gray matter density in brain regions linked to attentional processes were also correlated to our ePRS score. These results confirm that the amygdala 5-HTT gene network is strongly associated with ADHD-related behaviors, brain cortical density, and epigenetic changes in the context of adversity in young children.

A novel unsupervised change detection approach based on reconstruction independent component analysis and ABC-Kmeans clustering for environmental monitoring.

In this paper, I propose a new unsupervised change detection method for optical satellite imagery. The proposed technique consists of three phases. In the first stage, difference images are calculated using four different functions. Two of the functions were first used in this study. In the second stage, using Reconstruction Independent Component Analysis, this four-difference matrix is projected to one feature. In the last stage, clustering is performed. Kmeans tuned by Artificial Bee Colony (ABC-Kmeans) clustering technique has been developed and proposed by following a different strategy in the clustering phase. The effectiveness of the proposed approach was examined using two different datasets, Sardinia and Mexico. Quantitative evaluation was performed in two stages. In the first stage, proposed method was compared with different unsupervised change detection algorithms using False Alarm, Missed Alarm, Total Error, and Total Error Rate metrics which are calculated using ground truth image in dataset. In the second experimental study, the proposed approach is compared in detail with PCA-Kmeans approach, which is quite often preferred for similar studies, using the Mean Squared Error, Peak Signal to Noise Ratio, Structural Similarity Index, and Universal Image Quality Index metrics. According to quantitative and qualitative analysis, proposed approach can produce quite successful results using optical remote sensing data.

Prefrontal Cortex Dopamine Transporter Gene Network Moderates the Effect of Perinatal Hypoxic-Ischemic Conditions on Cognitive Flexibility and Brain Gray Matter Density in Children.

BACKGROUND: Genetic polymorphisms of the dopamine transporter gene (DAT1) and perinatal complications associated with poor oxygenation are risk factors for attentional problems in childhood and may show interactive effects. METHODS: We created a novel expression-based polygenic risk score (ePRS) reflecting variations in the function of the DAT1 gene network (ePRS-DAT1) in the prefrontal cortex and explored the effects of its interaction with perinatal hypoxic-ischemic-associated conditions on cognitive flexibility and brain gray matter density in healthy children from two birth cohorts-MAVAN from Canada (n = 139 boys and girls) and GUSTO from Singapore (n = 312 boys and girls). RESULTS: A history of exposure to several perinatal hypoxic-ischemic-associated conditions was associated with impaired cognitive flexibility only in the high-ePRS group, suggesting that variation in the prefrontal cortex expression of genes involved in dopamine reuptake is associated with differences in this behavior. Interestingly, this result was observed in both ethnically distinct birth cohorts. Additionally, parallel independent component analysis (MAVAN cohort, n = 40 children) demonstrated relationships between single nucleotide polymorphism-based ePRS and gray matter density in areas involved in executive (cortical regions) and integrative (bilateral thalamus and putamen) functions, and these relationships differ in children from high and low exposure to hypoxic-ischemic-associated conditions. CONCLUSIONS: These findings reveal that the impact of conditions associated with hypoxia-ischemia on brain development and executive functions is moderated by genotypes associated with dopamine signaling in the prefrontal cortex. We discuss the potential impact of innovative genomic and environmental measures for the identification of children at high risk for impaired executive functions.

A Method for Simultaneous Evaluation of Muscular and Neural Prepulse Inhibition.

Prepulse inhibition (PPI) test has been widely used to evaluate sensorimotor gating. In humans, deficits in this mechanism are measured through the orbicularis muscle response using electromyography (EMG). Although this mechanism can be modulated by several brain structures and is impaired in some pathologies as schizophrenia and bipolar disorder, neural PPI evaluation is rarely performed in humans. Since eye blinks are a consequence of PPI stimulation, they strongly contaminate the electroencephalogram (EEG) signal. This paper describes a method to reduce muscular artifacts and enable neural PPI assessment through EEG in parallel to muscular PPI evaluation using EMG. Both types of signal were simultaneously recorded in 22 healthy subjects. PPI was evaluated by the acoustical startle response with EMG and by the P2-N1 event-related potential (ERP) using EEG in Fz, Cz, and Pz electrodes. In order to remove EEG artifacts, Independent Component Analysis (ICA) was performed using two methods. Firstly, visual inspection discarded components containing artifact characteristics as ocular and tonic muscle artifacts. The second method used visual inspection as gold standard to validate parameters in an automated component selection using the SASICA algorithm. As an outcome, EEG artifacts were effectively removed and equivalent neural PPI evaluation performance was obtained using both methods, with subjects exhibiting consistent neural as well as muscular PPI. This novel method improves PPI test, enabling neural gating mechanisms assessment within the latency of 100-200 ms, which is not evaluated by other sensory gating tests as P50 and mismatch negativity.

Raman hyperspectral imaging in conjunction with independent component analysis as a forensic tool for explosive analysis: The case of an ATM explosion.

In this work, Raman hyperspectral imaging, in conjunction with independent component analysis, was employed as an analytical methodology to detect an ammonium nitrate fuel oil (ANFO) explosive in banknotes after an ATM explosion experiment. The proposed methodology allows for the identification of the ANFO explosive without sample preparation or destroying the sample, at quantities as small as 70µgcm-2. The explosive was identified following ICA data decomposition by the characteristic nitrate band at 1044cm-1. The use of Raman hyperspectral imaging and independent component analysis shows great potential for identifying forensic samples by providing chemical and spatial information.

Precuneus Failures in Subjects of the PSEN1 E280A Family at Risk of Developing Alzheimer's Disease Detected Using Quantitative Electroencephalography.

BACKGROUND: Presenilin-1 (PSEN1) mutations are the most common cause of familial early onset Alzheimer's disease (AD). The PSEN1 E280A (E280A) mutation has an autosomal dominant inheritance and is involved in the production of amyloid-ß. The largest family group of carriers with E280A mutation is found in Antioquia, Colombia. The study of mutation carriers provides a unique opportunity to identify brain changes in stages previous to AD. Electroencephalography (EEG) is a low cost and minimally invasiveness technique that enables the following of brain changes in AD. OBJECTIVE: To examine how previous reported differences in EEG for Theta and Alpha-2 rhythms in E280A subjects are related to specific regions in cortex and could be tracked across different ages. METHODS: EEG signals were acquired during resting state from non-carriers and carriers, asymptomatic and symptomatic subjects from E280A kindred from Antioquia, Colombia. Independent component analysis (ICA) and inverse solution methods were used to locate brain regions related to differences in Theta and Alpha-2 bands. RESULTS: ICA identified two components, mainly related to the Precuneus, where the differences in Theta and Alpha-2 exist simultaneously at asymptomatic and symptomatic stages. When the ratio between Theta and Alpha-2 is used, significant correlations exist with age and a composite cognitive scale. CONCLUSION: Theta and Alpha-2 rhythms are altered in E280A subjects. The alterations are possible to track at Precuneus regions using EEG, ICA, and inverse solution methods.

Efecto del pre-procesamiento del EEG en el Análisis por Componentes Independientes: reducción del artefacto del implante coclear en los Potenciales Evocados Auditivos / Effect of EEG pre-processing on Independent Component Analysis: reduction of cochlear implant artifact in Auditory Evoked Potentials

Resumen: El Análisis por Componentes Independientes (ICA, Independent Component Analysis) es una herramienta muy utilizada para eliminar los artefactos comunes del EEG, sin embargo existe poca bibliografía sobre el impacto que tienen etapas de pre-procesamiento de esta señal sobre el desempeño del ICA. En este trabajo se comparó el efecto de aplicar dos filtros digitales diferentes, pasabajas y pasabanda, en una etapa de procesamiento previa a ICA, para remover específicamente el artefacto de un implante coclear en registros de Potenciales Evocados Auditivos. Se analizaron señales de 10 sujetos usuarios de implante coclear y en 5 de estos registros con el pre-filtrado pasabajas se obtuvieron los mayores valores del índice de la Relación Señal Interferencia, utilizado para evaluar la calidad de la separación. El mayor efecto al remover el artefacto del implante coclear se nota en los electrodos T4 y T6, que corresponde a la zona donde los sujetos tienen colocado su implante (área temporal derecha).

Abstract: Independent Component Analysis (ICA) is an algorithm used to remove artifacts from the EEG. However, there is little current literature about the impact of preprocessing stages of this signal on the performance of ICA. In this paper the effect of applying two different digital filters - lowpass and bandpass -, in a pre-processing step to ICA, was compared. This to remove the cochlear implant artifact from the Auditory Evoked Potentials. Recordings from 10 cochlear implant users were analyzed. In 5 of these records using the pre-lowpass filtering, the highest Signal Interference Ratio (SIR) was obtained; this index was used to assess the quality of ICA separation. The greatest effect of removing the cochlear implant artifact is noted in both T4 and T6 electrodes, which correspond to the area where the subjects have placed their implants (right temporal area).

Neuronal Assemblies Evidence Distributed Interactions within a Tactile Discrimination Task in Rats.

Accumulating evidence suggests that neural interactions are distributed and relate to animal behavior, but many open questions remain. The neural assembly hypothesis, formulated by Hebb, states that synchronously active single neurons may transiently organize into functional neural circuits-neuronal assemblies (NAs)-and that would constitute the fundamental unit of information processing in the brain. However, the formation, vanishing, and temporal evolution of NAs are not fully understood. In particular, characterizing NAs in multiple brain regions over the course of behavioral tasks is relevant to assess the highly distributed nature of brain processing. In the context of NA characterization, active tactile discrimination tasks with rats are elucidative because they engage several cortical areas in the processing of information that are otherwise masked in passive or anesthetized scenarios. In this work, we investigate the dynamic formation of NAs within and among four different cortical regions in long-range fronto-parieto-occipital networks (primary somatosensory, primary visual, prefrontal, and posterior parietal cortices), simultaneously recorded from seven rats engaged in an active tactile discrimination task. Our results first confirm that task-related neuronal firing rate dynamics in all four regions is significantly modulated. Notably, a support vector machine decoder reveals that neural populations contain more information about the tactile stimulus than the majority of single neurons alone. Then, over the course of the task, we identify the emergence and vanishing of NAs whose participating neurons are shown to contain more information about animal behavior than randomly chosen neurons. Taken together, our results further support the role of multiple and distributed neurons as the functional unit of information processing in the brain (NA hypothesis) and their link to active animal behavior.

Direct estimation of dissolved organic carbon using synchronous fluorescence and independent component analysis (ICA): advantages of a multivariate calibration.

Dissolved organic carbon (DOC) is frequently used as a diagnostic parameter for the identification of environmental contamination in aqueous systems. Since this organic matter is evolving and decaying over time. If samples are collected under environmental conditions, some sample stabilization process is needed until the corresponding analysis can be made. This may affect the analysis results. This problem can be avoided using the direct determination of DOC. We report a study using in situ synchronous fluorescence spectra, with independent component analysis to retrieve relevant major spectral contributions and their respective component contributions, for the direct determination of DOC. Fluorescence spectroscopy is a very powerful and sensitive technique to evaluate vestigial organic matter dissolved in water and is thus suited for the analytical task of direct monitoring of dissolved organic matter in water, thus avoiding the need for the stabilization step. We also report the development of an accurate calibration model for dissolved organic carbon determinations using environmental samples of humic and fulvic acids. The method described opens the opportunity for a fast, in locus, DOC estimation in environmental or other field studies using a portable fluorescence spectrometer. This combines the benefits of the use of fresh samples, without the need of stabilizers, and also allows the interpretation of various additional spectral contributions based on their respective estimated properties. We show how independent component analysis may be used to describe tyrosine, tryptophan, humic acid and fulvic acid spectra and, thus, to retrieve the respective individual component contribution to the DOC.

Diabetes classification using a redundancy reduction preprocessor

Introduction Diabetes patients can benefit significantly from early diagnosis. Thus, accurate automated screening is becoming increasingly important due to the wide spread of that disease. Previous studies in automated screening have found a maximum accuracy of 92.6%. Methods This work proposes a classification methodology based on efficient coding of the input data, which is carried out by decreasing input data redundancy using well-known ICA algorithms, such as FastICA, JADE and INFOMAX. The classifier used in the task to discriminate diabetics from non-diaibetics is the one class support vector machine. Classification tests were performed using noninvasive and invasive indicators. Results The results suggest that redundancy reduction increases one-class support vector machine performance when discriminating between diabetics and nondiabetics up to an accuracy of 98.47% while using all indicators. By using only noninvasive indicators, an accuracy of 98.28% was obtained. Conclusion The ICA feature extraction improves the performance of the classifier in the data set because it reduces the statistical dependence of the collected data, which increases the ability of the classifier to find accurate class boundaries.

On the Identification of an ICA Algorithm for Auditory Evoked Potentials Extraction: A Study on Synthetic Data / Identificación de un algoritmo ICA para la extracción de potenciales evocados auditivos: un estudio en señales sintéticas

Extracting characteristics and information from Auditory Evoked Potentials recordings (AEPs) involves difficulties due to their very low amplitude, which makes the AEPs easily hidden by artifacts from physiological or external sources like the EEG/EMG, blinking, and line-noise. To tackle this problem, some authors have used Independent Component Analysis (ICA) to successfully de-noise brain signals. However, since interest has been mainly focused on removing artifacts like blinking, not much attention has been paid to the quality of the recovered evoked potential. This is the AEP case, where literature reports interesting results on the de-noising matter, but without an objective evaluation of the AEP finally extracted (and the influence of different implementations or configurations of ICA). Here, to study the performance of three popular ICA algorithms (FastICA, Ext-Infomax, and SOBI) at separating AEPs from a mixture, a synthetic dataset composed of one Long Latency Auditory Evoked Potential (LLAEP) signal and the most frequent artifacts was generated. Next, the quality of the independent components (ICs) estimated by such algorithms was measured by using the AMARI performance index (Am), the signal interference ratio index (SIR), and the time required to achieve separation. Results indicated that the FastICA implementation, with the symmetric approach and the power cubic contrast function, is more likely to provide the best and faster separation of the LLAEP, which makes it suitable for this purpose.

La extracción de características e información de los registros de Potenciales Evocados Auditivos (AEPs) es complicada debido a su baja energía, la que lo hace fácilmente enmascarable por artefactos de origen fisiológico o externo, como el EEG/EMG, el parpadeo y el ruido de línea. Este problema ha sido abordado por algunos autores mediante el uso del Análisis por Componentes Independientes (ICA, por sus siglas en inglés), que se ha utilizado principalmente para reducir artefactos. Estos trabajos han enfocado su interés en la tarea de remover artefactos como el parpadeo, por lo que han descuidado el estudio de la calidad del potencial evocado recuperado. Este es el caso del AEP, donde aun cuando la literatura reporta resultados interesantes en la reducción de artefactos, no existe una evaluación objetiva del AEP finalmente extraído (y el efecto de usar diferentes implementaciones/configuraciones de ICA). En este trabajo, con el objetivo de cuantificar el desempeño de tres algoritmos de ICA (FastICA, Ext-Infomax, y SOBI) en la calidad de la separación de los AEPs, se generó una mezcla sintética de señales compuesta por un Potencial Evocado Auditivos de Latencia Larga (LLAEP) y artefactos frecuentemente presentes en estos registros. Después, se cuantificó la calidad de los componentes independientes (ICs, por sus siglas en inglés) estimados por estos algoritmos utilizando el índice de desempeño (AMARI, por sus siglas en inglés) el índice de la relación de interferencia entre señales (SIR, por sus siglas en inglés) y el tiempo requerido para realizar la separación. Los resultados indican que FastICA, con el enfoque simétrico y la función de contraste potencia cúbica, proporciona la mejor y más rápida separación del LLAEP, lo que lo vuelve idóneo para esta tarea.

Detection of explosives on the surface of banknotes by Raman hyperspectral imaging and independent component analysis.

The aim of this study was to develop a methodology using Raman hyperspectral imaging and chemometric methods for identification of pre- and post-blast explosive residues on banknote surfaces. The explosives studied were of military, commercial and propellant uses. After the acquisition of the hyperspectral imaging, independent component analysis (ICA) was applied to extract the pure spectra and the distribution of the corresponding image constituents. The performance of the methodology was evaluated by the explained variance and the lack of fit of the models, by comparing the ICA recovered spectra with the reference spectra using correlation coefficients and by the presence of rotational ambiguity in the ICA solutions. The methodology was applied to forensic samples to solve an automated teller machine explosion case. Independent component analysis proved to be a suitable method of resolving curves, achieving equivalent performance with the multivariate curve resolution with alternating least squares (MCR-ALS) method. At low concentrations, MCR-ALS presents some limitations, as it did not provide the correct solution. The detection limit of the methodology presented in this study was 50 µg cm(-2).

A method for environmental acoustic analysis improvement based on individual evaluation of common sources in urban areas.

Noise levels of common sources such as vehicles, whistles, sirens, car horns and crowd sounds are mixed in urban soundscapes. Nowadays, environmental acoustic analysis is performed based on mixture signals recorded by monitoring systems. These mixed signals make it difficult for individual analysis which is useful in taking actions to reduce and control environmental noise. This paper aims at separating, individually, the noise source from recorded mixtures in order to evaluate the noise level of each estimated source. A method based on blind deconvolution and blind source separation in the wavelet domain is proposed. This approach provides a basis to improve results obtained in monitoring and analysis of common noise sources in urban areas. The method validation is through experiments based on knowledge of the predominant noise sources in urban soundscapes. Actual recordings of common noise sources are used to acquire mixture signals using a microphone array in semi-controlled environments. The developed method has demonstrated great performance improvements in identification, analysis and evaluation of common urban sources.