Infomax Independent Component Analysis Research Articles

Classification of Autism Spectrum Disorder using Resting State-Functional Magnetic Resonance Imaging and Artificial Neural Network

Autism Spectrum Disorder (ASD) represents a growing challenge in public health, characterized by irreversible neurodevelopmental abnormalities. Despite a rising prevalence, the underlying aetiology and neural substrates of ASD remain incompletely understood. Resting state-functional Magnetic Resonance Imaging (rs-fMRI) has emerged as a valuable non-invasive tool for probing the organization and cognitive functions of the brain by capturing hemodynamic changes. This study explores the relationship between Functional Connectivity (FC) alterations, measured by rs-fMRI, and the manifestation of ASD-related brain disorders. In this paper, we propose a hybrid approach employing an InfoMax Independent Component Analysis (ICA) algorithm and Artificial Neural Network to distinguish between the ASD subjects and Healthy Controls (HCs). Initially, rs-fMRI datasets are preprocessed using Statistical Parametric Mapping (SPM). Further, these datasets are processed using InfoMax ICA to extract the distinct features such as fractional Amplitude of Low-Frequency Fluctuations (fALFF) and Dynamic Range and visualize the FC alterations by region mapping. In addition to this, the number of activated voxels for each brain regions are estimated to observe the neural abnormalities. Finally, the extracted features are fed as input to train, test and validate the ANN classifier. The efficacy of the proposed network is evaluated using the Autism Brain Imaging Data Exchange (ABIDE) dataset and an accuracy of 75.3 percentage is achieved.

Extraction of the GVS electrical artifact from EEG recordings of the motor related cortical potential

BackgroundGalvanic vestibular stimulation (GVS) involves the administration of low-amplitude trans-mastoidal current which induces a dense electrical field across the scalp that is difficult to remove from the EEG record. In two proof-of-concept experiments, we designed a paradigm to evaluate functional limb movement, and tested a method of blind source separation to remove the scalp artifact induced by low-amplitude, alternating current GVS to allow measurement of the motor-related cortical response (MRCP) during voluntary movement. New MethodOff-line Extended Infomax Independent Component Analysis (ICA) was applied to the concatenated dataset to identify and remove core characteristics of the artifact induced by a trans-mastoidal current (Experiment 1: 0.01 Hz, 0.2–3 mA; Experiment 2: 0.01 Hz, 0.3–0.4 mA) during finger (Experiments 1 and 2) and foot tapping (Experiment 2). ResultsIn Experiment 1, a GVS-related independent component was identified and successfully removed without compromising measurement of the MRCP. This success was replicated in Experiment 2 which included both finger and foot tapping, and a higher GVS amplitude, which resulted in the identification of additional GVS-related artifacts. Comparison with existing methodsExisting methods of artifact rejection typically use an offline bandpass filter that overlaps with the frequency range of the MRCP. Even when similar ICA-based approaches have been employed, they have been applied during rest rather than active movement, have not been described in sufficient detail to enable replication, and require significant expertise and bespoke software to implement. ConclusionThe ICA-based approach described here provides a relatively simple and accessible means by which MRCPs can be measured during alternating current GVS. This provides opportunity to identify new biomarkers associated with the therapeutic effects of GVS in people with Parkinson’s disease and other disorders of voluntary movement.

An Empirical Study of Several Information Theoretic Based Feature Extraction Methods for Classifying High Dimensional Low Sample Size Data

A high dimensional low sample size (HDLSS) dataset typically contains many features but a limited number of samples. It is commonly found in domains such as microarray data and medical imaging. When sample size is small, the population probability density function (PDF) of a HDLSS dataset may not be well represented, causing difficulties of applying feature selection or feature extraction methods for HDLSS data classification. In this paper, we explore the possibility of designing feature selection and feature extraction methods for HDLSS data classification by making loose assumption on the underlying PDF of a HDLSS dataset. Specifically, we propose to leverage on Correlation Explanation (CorEx), a recent unsupervised probabilistic graphical model that assumes (hierarchical) hidden structure for generating subsets of features that are conditionally independent. We benchmark the proposed method against frequently cited Information Theory based feature extraction and feature selection methods, including Conditional Infomax Feature Extraction (CIFE), Maximum Relevance Minimum Redundancy (MRMR), Maximization of Mutual Information (MMI), Infomax Independent Component Analysis (Infomax ICA),and Kernel Entropy Component Analysis (KECA). The HDLSS datasets used in this study are Breast Cancer Dataset by Gravier et. al and West et. al, Colon Cancer dataset by Alon et. al., Leukemia Dataset by Golub et.al and the Gisette Dataset used by Guyon et. al. Experimental results demonstrate that the proposed method shows some improvement in classification performance over MMI, and Infomax ICA and is competitive with MRMR and CIFE.

Low-Cost Implementation of Independent Component Analysis for Biomedical Signal Separation Using Very-Large-Scale Integration

This brief proposes a low-cost implementation of the extended InfoMax independent component analysis (ICA) algorithm for biomedical signal separation by using very-large-scale integration (VLSI). On the basis of this algorithm, the implemented VLSI ICA core can be used to separate a mixed signal from a super-Gaussian signal source. By using mathematical operations of merging and simplification, the ICA core uses the systolic array and lookup table to implement the extended InfoMax ICA algorithm, thus achieving low cost and high speed. The measured results indicated that the ICA core consumed 9.5 mW when operated at 100 MHz using TSMC 90-nm complementary metal–oxide–semiconductor technology, with a gate count of only 36.8K. This represents a 59% reduction in area and a 35% saving in power compared with the previous design. Furthermore, the proposed ICA core was applied to mixed electrocardiogram signals, and the separated signals exhibited excellent quality.

A VLSI Implementation of Independent Component Analysis for Biomedical Signal Separation Using CORDIC Engine.

This study aims to design and implement a very large scale integration (VLSI) chip of the extend InfoMax independent component analysis (ICA) algorithm which can separate the super-Gaussian source signals. In order to substantially reduce the circuit area, the proposed circuit utilizes the time sharing matrix multiplication array (MMA) to realize a series of matrix multiplication operations and employs the coordinate rotation digital computer (CORDIC) algorithm to calculate the hyperbolic functions sinh(θ) and cosh(θ) with the rotation of the hyperbolic coordinate system. Also, the rotation of the linear coordinate system of the CORDIC is adopted for the design of a divider used for obtaining the required function value of tanh(θ) simply by evaluating sinh(θ)/cosh(θ). Implemented in a TSMC 90-nm CMOS technology, the proposed ICA has an operation frequency of 100MHz with 90.8K gate counts. Furthermore, the measurement results show the ICA core can be successfully applied to separating mixed medical signals into independent sources.

Optimizing the ICA-based removal of ocular EEG artifacts from free viewing experiments

Combining EEG with eye-tracking is a promising approach to study neural correlates of natural vision, but the resulting recordings are also heavily contaminated by activity of the eye balls, eye lids, and extraocular muscles. While Independent Component Analysis (ICA) is commonly used to suppress these ocular artifacts, its performance under free viewing conditions has not been systematically evaluated and many published reports contain residual artifacts. Here I evaluated and optimized ICA-based correction for two tasks with unconstrained eye movements: visual search in images and sentence reading. In a first step, four parameters of the ICA pipeline were varied orthogonally: the (1) high-pass and (2) low-pass filter applied to the training data, (3) the proportion of training data containing myogenic saccadic spike potentials (SP), and (4) the threshold for eye tracker-based component rejection. In a second step, the eye-tracker was used to objectively quantify the correction quality of each ICA solution, both in terms of undercorrection (residual artifacts) and overcorrection (removal of neurogenic activity). As a benchmark, results were compared to those obtained with an alternative spatial filter, Multiple Source Eye Correction (MSEC). With commonly used settings, Infomax ICA not only left artifacts in the data, but also distorted neurogenic activity during eye movement-free intervals. However, correction results could be strongly improved by training the ICA on optimally filtered data in which SPs were massively overweighted. With optimized procedures, ICA removed virtually all artifacts, including the SP and its associated spectral broadband artifact from both viewing paradigms, with little distortion of neural activity. It also outperformed MSEC in terms of SP correction. Matlab code is provided.

A SOC Design of ORICA-based Highly Effective Real-time Multi-channel EEG System.

Independent component analysis (ICA) has been wildly used to improve EEG based application such as brain computer interface (BCI). However, some well know ICA algorithm, such as Infomax ICA, suffering from the problem of convergence latency and make it hard to be apply on real-time application. This paper proposes a highly efficient chip implementation of multi-channel EEG real-time system based on online recursive independent component analysis algorithm (ORICA). The core size of the chip is 1.5525-mm2 using 28nm CMOS technology. The EEG demonstration board will be implemented with the ORICA chip. The operation frequency and power consumption of the chip are 100 MHz and 17.9 mW respectively. The proposed chip was validated with a real-time circuit integrated system and the average correlation coefficient between simulations results and chip processing results is 0.958.

A SOC Design of ORICA-based Highly Effective Real-time Multi-channel EEG System.

Independent component analysis (ICA) has been wildly used to improve EEG based application such as brain computer interface (BCI). However, some well know ICA algorithm, such as Infomax ICA, suffering from the problem of convergence latency and make it hard to be apply on real-time application. This paper proposes a highly efficient chip implementation of multi-channel EEG real-time system based on online recursive independent component analysis algorithm (ORICA). The core size of the chip is 1.5525-mm2 using 28nm CMOS technology. The EEG demonstration board will be implemented with the ORICA chip. The operation frequency and power consumption of the chip are 100 MHz and 17.9 mW respectively. The proposed chip was validated with a real-time circuit integrated system and the average correlation coefficient between simulations results and chip processing results is 0.958.

Utilization of independent component analysis for accurate pathological ripple detection in intracranial EEG recordings recorded extra- and intra-operatively

ObjectiveTo develop and validate a detector that identifies ripple (80–200 Hz) events in intracranial EEG (iEEG) recordings in a referential montage and utilizes independent component analysis (ICA) to eliminate or reduce high-frequency artifact contamination. Also, investigate the correspondence of detected ripples and the seizure onset zone (SOZ). MethodsiEEG recordings from 16 patients were first band-pass filtered (80–600 Hz) and Infomax ICA was next applied to derive the first independent component (IC1). IC1 was subsequently pruned, and an artifact index was derived to reduce the identification of high-frequency events introduced by the reference electrode signal. A Hilbert detector identified ripple events in the processed iEEG recordings using amplitude and duration criteria. The identified ripple events were further classified and characterized as true or false ripple on spikes, or ripples on oscillations by utilizing a topographical analysis to their time-frequency plot, and confirmed by visual inspection. ResultsThe signal to noise ratio was improved by pruning IC1. The precision of the detector for ripple events was 91.27 ± 4.3%, and the sensitivity of the detector was 79.4 ± 3.0% (N = 16 patients, 5842 ripple events). The sensitivity and precision of the detector was equivalent in iEEG recordings obtained during sleep or intra-operatively. Across all the patients, true ripple on spike rates and also the rates of false ripple on spikes, that were generated due to filter ringing, classified the seizure onset zone (SOZ) with an area under the receiver operating curve (AUROC) of >76%. The magnitude and spectral content of true ripple on spikes generated in the SOZ was distinct as compared with the ripples generated in the NSOZ (p < .001). ConclusionsUtilizing ICA to analyze iEEG recordings in referential montage provides many benefits to the study of high-frequency oscillations. The ripple rates and properties defined using this approach may accurately delineate the seizure onset zone. SignificanceStrategies to improve the spatial resolution of intracranial EEG and reduce artifact can help improve the clinical utility of HFO biomarkers.

Topographic Independent Component Analysis reveals random scrambling of orientation in visual space.

Neurons at primary visual cortex (V1) in humans and other species are edge filters organized in orientation maps. In these maps, neurons with similar orientation preference are clustered together in iso-orientation domains. These maps have two fundamental properties: (1) retinotopy, i.e. correspondence between displacements at the image space and displacements at the cortical surface, and (2) a trade-off between good coverage of the visual field with all orientations and continuity of iso-orientation domains in the cortical space. There is an active debate on the origin of these locally continuous maps. While most of the existing descriptions take purely geometric/mechanistic approaches which disregard the network function, a clear exception to this trend in the literature is the original approach of Hyvärinen and Hoyer based on infomax and Topographic Independent Component Analysis (TICA). Although TICA successfully addresses a number of other properties of V1 simple and complex cells, in this work we question the validity of the orientation maps obtained from TICA. We argue that the maps predicted by TICA can be analyzed in the retinal space, and when doing so, it is apparent that they lack the required continuity and retinotopy. Here we show that in the orientation maps reported in the TICA literature it is easy to find examples of violation of the continuity between similarly tuned mechanisms in the retinal space, which suggest a random scrambling incompatible with the maps in primates. The new experiments in the retinal space presented here confirm this guess: TICA basis vectors actually follow a random salt-and-pepper organization back in the image space. Therefore, the interesting clusters found in the TICA topology cannot be interpreted as the actual cortical orientation maps found in cats, primates or humans. In conclusion, Topographic ICA does not reproduce cortical orientation maps.

Improved FastICA algorithm in fMRI data analysis using the sparsity property of the sources

BackgroundAs a blind source separation technique, independent component analysis (ICA) has many applications in functional magnetic resonance imaging (fMRI). Although either temporal or spatial prior information has been introduced into the constrained ICA and semi-blind ICA methods to improve the performance of ICA in fMRI data analysis, certain types of additional prior information, such as the sparsity, has seldom been added to the ICA algorithms as constraints. New methodIn this study, we proposed a SparseFastICA method by adding the source sparsity as a constraint to the FastICA algorithm to improve the performance of the widely used FastICA. The source sparsity is estimated through a smoothed ℓ0 norm method. We performed experimental tests on both simulated data and real fMRI data to investigate the feasibility and robustness of SparseFastICA and made a performance comparison between SparseFastICA, FastICA and Infomax ICA. ResultsResults of the simulated and real fMRI data demonstrated the feasibility and robustness of SparseFastICA for the source separation in fMRI data. Comparison with existing methodsBoth the simulated and real fMRI experimental results showed that SparseFastICA has better robustness to noise and better spatial detection power than FastICA. Although the spatial detection power of SparseFastICA and Infomax did not show significant difference, SparseFastICA had faster computation speed than Infomax. ConclusionsSparseFastICA was comparable to the Infomax algorithm with a faster computation speed. More importantly, SparseFastICA outperformed FastICA in robustness and spatial detection power and can be used to identify more accurate brain networks than FastICA algorithm.

Task-evoked brain functional magnetic susceptibility mapping by independent component analysis (ϿICA)

BackgroundConventionally, independent component analysis (ICA) is performed on an fMRI magnitude dataset to analyze brain functional mapping (AICA). By solving the inverse problem of fMRI, we can reconstruct the brain magnetic susceptibility (Ͽ) functional states. Upon the reconstructed Ͽ dataspace, we propose an ICA-based brain functional Ͽ mapping method (ϿICA) to extract task-evoked brain functional map. New methodsA complex division algorithm is applied to a timeseries of fMRI phase images to extract temporal phase changes (relative to an OFF-state snapshot). A computed inverse MRI (CIMRI) model is used to reconstruct a 4D brain Ͽ response dataset. ϿICA is implemented by applying a spatial InfoMax ICA algorithm to the reconstructed 4D Ͽ dataspace. ResultsWith finger-tapping experiments on a 7T system, the ϿICA-extracted Ͽ-depicted functional map is similar to the SPM-inferred functional Ͽ map by a spatial correlation of 0.67±0.05. In comparison, the AICA-extracted magnitude-depicted map is correlated with the SPM magnitude map by 0.81±0.05. The understanding of the inferiority of ϿICA to AICA for task-evoked functional map is an ongoing research topic. Comparison with existing methodsFor task-evoked brain functional mapping, we compare the data-driven ICA method with the task-correlated SPM method. In particular, we compare ϿICA with AICA for extracting task-correlated timecourses and functional maps. ConclusionϿICA can extract a Ͽ-depicted task-evoked brain functional map from a reconstructed Ͽ dataspace without the knowledge about brain hemodynamic responses. The ϿICA-extracted brain functional Ͽ map reveals a bidirectional BOLD response pattern that is unavailable (or different) from AICA.

Automatically detecting auditory P300 in several trials

A method was demonstrated based on Infomax independent component analysis (Infomax ICA) for automatically extracting auditory P300 signals within several trials. A signaling equilibrium algorithm was proposed to enhance the effectiveness of the Infomax ICA decomposition. After the mixed signal was decomposed by Infomax ICA, the independent component (IC) used in auditory P300 reconstruction was automatically chosen by using the standard deviation of the fixed temporal pattern. And the result of auditory P300 was reconstructed using the selected ICs. The experimental results show that the auditory P300 can be detected automatically within five trials. The Pearson correlation coefficient between the standard signal and the signal detected using the proposed method is significantly greater than that between the standard signal and the signal detected using the average method within five trials. The wave pattern result obtained using the proposed algorithm is better and more similar to the standard signal than that obtained by the average method for the same number of trials. Therefore, the proposed method can automatically detect the effective auditory P300 within several trials.

Independent Component Analysis Methods to Improve Electrocardiogram Patterns Recognition in the Presence of Non-Trivial Artifacts

 Abstract—Electrocardiogram (ECG) signals are affected by various kinds of noise and artifacts that may impede correct recognition by automated monitoring or diagnosis systems. Independent component analysis (ICA) is considered as a new technique suitable for the separation and removal of diverse noises independent of ECG signals. This paper first proposes the application of independent component analysis to ECG signal pre-processing and then compares the performances of two major types of ICAs namely Infomax and Fast ICAs in ECG signal de-noising. The annotated benchmark samples from MIT-BIH arrhythmia database are used for experiments. We compare the signal to noise ratio improvements in the real ECG data with different ICA algorithms and the recognition rates. It is found that both types of ICA can effectively improve the ECG recognition in the presence of non-trivial artifacts, but FastICA slightly outperforms. However, it is worth mentioning that the Infomax algorithm might be further optimized.

A Constrained ICA Approach for Real-Time Cardiac Artifact Rejection in Magnetoencephalography

Recently, magnetoencephalography (MEG)-based real-time brain computing interfaces (BCI) have been developed to enable novel and promising methods of neuroscience research and therapy. Artifact rejection prior to source localization largely enhances the localization accuracy. However, many BCI approaches neglect real-time artifact removal due to its time consuming processing. With cardiac artifact rejection for real-time analysis (CARTA), we introduce a novel algorithm capable of real-time cardiac artifact (CA) rejection. The method is based on constrained independent component analysis (ICA), where a priori information of the underlying source signal is used to optimize and accelerate signal decomposition. In CARTA, this is performed by estimating the subject's individual density distribution of the cardiac activity, which leads to a subject-specific signal decomposition algorithm. We show that the new method is capable of effectively reducing CAs within one iteration and a time delay of 1 ms. In contrast, Infomax and Extended Infomax ICA converged not until seven iterations, while FastICA needs at least ten iterations. CARTA was tested and applied to data from three different but most common MEG systems (4-D-Neuroimaging, VSM MedTech Inc., and Elekta Neuromag). Therefore, the new method contributes to reliable signal analysis utilizing BCI approaches.

Cortical surface alignment in multi-subject spatiotemporal independent EEG source imaging

Brain responses to stimulus presentations may vary widely across subjects in both time course and spatial origins. Multi-subject EEG source imaging studies that apply Independent Component Analysis (ICA) to data concatenated across subjects have overlooked the fact that projections to the scalp sensors from functionally equivalent cortical sources vary from subject to subject. This study demonstrates an approach to spatiotemporal independent component decomposition and alignment that spatially co-registers the MR-derived cortical topographies of individual subjects to a well-defined, shared spherical topology (Fischl et al., 1999). Its efficacy for identifying functionally equivalent EEG sources in multi-subject analysis is demonstrated by analyzing EEG and behavioral data from a stop-signal paradigm using two source-imaging approaches, both based on individual subject independent source decompositions. The first, two-stage approach uses temporal infomax ICA to separate each subject's data into temporally independent components (ICs), then estimates the source density distribution of each IC process from its scalp map and clusters similar sources across subjects (Makeig et al., 2002). The second approach, Electromagnetic Spatiotemporal Independent Component Analysis (EMSICA), combines ICA decomposition and source current density estimation of the artifact-rejected data into a single spatiotemporal ICA decomposition for each subject (Tsai et al., 2006), concurrently identifying both the spatial source distribution of each cortical source and its event-related dynamics. Applied to the stop-signal task data, both approaches gave IC clusters that separately accounted for EEG processes expected in stop-signal tasks, including pre/postcentral mu rhythms, anterior-cingulate theta rhythm, and right-inferior frontal responses, the EMSICA clusters exhibiting more tightly correlated source areas and time-frequency features.

Robot Assisted Walking Affects the Synchrony Between Premotor and Somatosensory Areas

We recorded the electroencephalogram (EEG) from 14 healthy volunteers during standing and active walking with a robotic gait orthosis. Infomax independent component analysis decomposed the EEG into independent components (ICs), representing brain, muscle and artifact sources. ICs were clustered across participants based on their anatomical position and spectral patterns. Coherence was computed between clusters. We show that walking compared to standing decreases α (8-12Hz) band coherence between sensorimotor areas. Additionally lower γ band (3036Hz) coherence between the premotor cortex and the sensory cortex is enhanced. Our results suggest different functionalities at α and γ synchrony on sensorimotor processing during locomotion.

Level of participation in robotic-assisted treadmill walking modulates midline sensorimotor EEG rhythms in able-bodied subjects

In robot assisted gait training, a pattern of human locomotion is executed repetitively with the intention to restore the motor programs associated with walking. Several studies showed that active contribution to the movement is critical for the encoding of motor memory. We propose to use brain monitoring techniques during gait training to encourage active participation in the movement. We investigated the spectral patterns in the electroencephalogram (EEG) that are related to active and passive robot assisted gait. Fourteen healthy participants were considered. Infomax independent component analysis separated the EEG into independent components representing brain, muscle, and eye movement activity, as well as other artifacts. An equivalent current dipole was calculated for each independent component. Independent components were clustered across participants based on their anatomical position and frequency spectra. Four clusters were identified in the sensorimotor cortices that accounted for differences between active and passive walking or showed activity related to the gait cycle. We show that in central midline areas the mu (8-12 Hz) and beta (18-21 Hz) rhythms are suppressed during active compared to passive walking. These changes are statistically significant: mu (F(1, 13)=11.2 p ≤ 0.01) and beta (F(1, 13)=7.7, p ≤ 0.05). We also show that these differences depend on the gait cycle phases. We provide first evidence of modulations of the gamma rhythm in the band 25 to 40 Hz, localized in central midline areas related to the phases of the gait cycle. We observed a trend (F(1, 8)=11.03, p ≤ 0.06) for suppressed low gamma rhythm when comparing active and passive walking. Additionally we found significant suppressions of the mu (F(1, 11)=20.1 p ≤ 0.01), beta (F(1, 11)=11.3 p ≤ 0.05) and gamma (F(1, 11)=4.9 p ≤ 0.05) rhythms near C3 (in the right hand area of the primary motor cortex) during phases of active vs. passive robot assisted walking. To our knowledge this is the first study showing EEG analysis during robot assisted walking. We provide evidence for significant differences in cortical activation between active and passive robot assisted gait. Our findings may help to define appropriate features for single trial detection of active participation in gait training. This work is a further step toward the evaluation of brain monitoring techniques and brain-computer interface technologies for improving gait rehabilitation therapies in a top-down approach.

Stability of ICA decomposition across within-subject EEG datasets.

Independent Component Analysis (ICA) has been successfully used to identify brain related signals and artifacts from multi-channel electroencephalographic (EEG) data. However the stability of ICA decompositions across sessions from a single subject has not been investigated. The goal of this study was to isolate EEG independent components (ICs) across sessions for each subject so as to assess whether ICs are reproducible across sessions. We used 64-channel EEG data recorded from two subjects during a simple mind-wandering experiment. Each subject participated in 11 twenty-minute sessions over a period of five weeks. Extended Infomax ICA decomposition was performed on the continuous data of each session. We used a simple IC clustering technique based on correlation of scalp topographies. Several clusters of homogenous components were identified for each subject. Typical component clusters accounting for eye movement and eye blink artifacts were identified. Both clusters included one component from each recording session. In addition, several clusters corresponding to brain electrical sources, among them clusters exhibiting prominent alpha, beta and Mu band activities, included components from most sessions. These results present evidence that ICA can provide relatively stable solutions across sessions, with important implications for Brain Computer Interface research.

Increased Intra-Participant Variability in Children with Autistic Spectrum Disorders: Evidence from Single-Trial Analysis of Evoked EEG

Intra-participant variability in clinical conditions such as autistic spectrum disorder (ASD) is an important indicator of pathophysiological processing. The data reported here illustrate that trial-by-trial variability can be reliably measured from EEG, and that intra-participant EEG variability is significantly greater in those with ASD than in neuro-typical matched controls. EEG recorded at the scalp is a linear mixture of activity arising from muscle artifacts and numerous concurrent brain processes. To minimize these additional sources of variability, EEG data were subjected to two different methods of spatial filtering. (i) The data were decomposed using infomax independent component analysis, a method of blind source separation which un-mixes the EEG signal into components with maximally independent time-courses, and (ii) a surface Laplacian transform was performed (current source density interpolation) in order to reduce the effects of volume conduction. Data are presented from 13 high functioning adolescents with ASD without co-morbid ADHD, and 12 neuro-typical age-, IQ-, and gender-matched controls. Comparison of variability between the ASD and neuro-typical groups indicated that intra-participant variability of P1 latency and P1 amplitude was greater in the participants with ASD, and inter-trial α-band phase coherence was lower in the participants with ASD. These data support the suggestion that individuals with ASD are less able to synchronize the activity of stimulus-related cell assemblies than neuro-typical individuals, and provide empirical evidence in support of theories of increased neural noise in ASD.