ICA Filters Research Articles

CMONOC II Common Mode Error Analysis and Structural Region Division Research

The modern tectonic deformation of the Chinese mainland is dominated by landmass movements, and active tectonic block regions are geological units with a relatively uniform movement pattern. The removal of CMEs can provide more accurate GPS data for exploring the movement characteristics between active tectonic block regions. In order to improve the effect of CME extraction, we propose that the Crustal Movement Observation Network of China be divided into sub-regions based on the refined definition of active tectonic block regions of the Chinese mainland. In this paper, 247 stations in the CMONOC II network are used to form a large spatial scale GPS network and 6 sub-regions with small spatial scale GPS networks. For the large spatial scale GPS network, we compare and analyze the effects of PCA and ICA filtering, and the study shows that PCA is not suitable for CME extraction in this large spatial scale GPS network, while ICA filtering is better. Subsequently, the large spatial scale GPS network and six small spatial scale GPS networks were used to extract CME using ICA, with the results showing that the RMSE values of the residual time series of the large spatial scale GPS network were reduced by 9.60%, 17.08%, and 16.14% in the directions of E, N, and U, respectively, and that the subregions divided according to the refined and determined first-level active plots of the Chinese continent had their residual time series of the RMSE values were reduced by 26.19%, 26.95%, and 28.32% on average in the three respective directions of E, N, and U. The effect of extracting CMEs by dividing the subregions was 29.16%, 5.44%, and 39.84% higher than the effect of extracting them as a whole in the three directions of E, N, and U, respectively. The experimental results demonstrate that the CMONOC II observation network is an effective and feasible method to extract CMEs according to the finely defined active tectonic block region of the Chinese mainland at the first level.

Notice of Removal: Removal of ocular artifacts using ICA and adaptive filter for motor imagery-based BCI

Preprocessing is the first step of Brain Computer Interface U+0028 BCI U+0029 based on Electroencephalogram U+0028 EEG U+0029, the most important aspect in this step is to remove Ocular Artifacts U+0028 OAs U+0029 included in EEG signals. OAs are the main interference signals to the EEG signals. In this paper, a new method called ICA-AF is proposed. This method using Independent Component Analysis U+0028 ICA U+0029 and Adaptive Filter U+0028 AF U+0029 can remove OAs from the EEG signals without measuring Electrooculogram U+0028 EOG U+0029. The method firstly decomposes the multi-channel EEG signals into the statistically independent components by ICA, then extracts the exact OAs that do not include the brain activity information in the OA-related independent components, and converts the exact OAs to the OAs at each electrode using inverse ICA U+0028 iICA U+0029. An adaptive filter uses this OA and the EEG signal in each channel as reference and input signal, respectively. Compared to ICA and ICA-RLS U+0028 Independent Component Analysis-Robust Least Square U+0029 methods, the proposed method can remove most of exact OAs and preserve as much brain activity information as possible. In addition, the average classification accuracy of the new method is 19 U+0025 and 8 U+0025 higher than the previous two methods, in the ratio of the average classification accuracy of the raw EEG, respectively. Besides, the new method is 1.45 times faster than ICA-RLS method, with respect to the execution time of ICA method.

The Phase and Shift-Invariant Feature by Adaptive Independent Subspace Analysis for Cortical Complex Cells

It has previously been suggested that complex cells in primary visual cortex (V1) selectly respond to bars and edges at a particular location and orientation emerged from the natural image rather than random stimuli. In this paper, we proposed an adaptive independent subspace analysis (AISA) algorithm based on the maximum likelihood of super-gaussian distribution of the norm of the partially independent components involving difference to efficiently study the characteristics of complex cells. The multiple parameters are updated with different restrictions by contrast divergence (CD) method based on the super-Gaussian (sparse) distribution. In terms of the AISA results, the inside and outside subspace of energy correlation illustrate the properties of independence. Furthermore, AISA features, similar to the characteristics of complex cells in V1, have phase and shift-invariant, as well as frequency and orientation selectivity via the energy function of receptive fields (RFs) from tuning curve test with sinusoidal function. Compared with the principal component analysis (PCA) filters and other ICA filters, AISA filters are analogous to Gabor filters for edge detection and human visual system via varying the frequency and orientation representation.

Detecting masses in dense breast using independent component analysis.

Breast cancer is the second type of cancer that most affects women in the world, losing only for non-melanoma skin cancer. Breast density can hinder the location of masses, especially in early stages. In this work, the use of independent component analysis for detecting lesions in dense breasts is proposed. Several works suggest the use of computer aided diagnosis (CAD), increasing sensitivity to over 90% in detecting cancer in nondense breasts, however there are few published studies about detecting in dense breasts. To analyse its efficiency in relation to other segmentation techniques, we compare the performance with principal component analysis. To measure the quality of the segmentation obtained by the two methods, an area overlay measure will be used. To verify if there was any difference between the results of the proposed methods in the detection of lesions in nondense breasts and in dense breasts, a statistic test for two proportions was used. Experimental results on the Mini-MIAS and DDSM database showed an accuracy of 92.71% in detecting masses in nondense and 79.17% in dense breasts. All experiments showed that the ICA filters have a better performance for detect lesions in dense breast, compared with PCA. Contrary to previous works, our experiments showed that there is actually a significant difference between the detection of masses in dense and nondense breasts. This study can help specialist to detect lesions in dense breast.

TMS-induced EEG Artifacts Removal Methods based on Cross-Correlation Coefficients of ICA Components

In this study a noble TMS-induced artifact removal method is developed and discussed by estimating its parameters for various aspects of data, such as sampling rate, filtering order and ICA decomposition method, in both the EEG time series and in the independent components of the EEG by using the EEG data obtained from four healthy subjects who were receiving single pulse TMS-EEG and sham-EEG stimulus on the left Broca’s area. A total of four healthy male subjects without any neurological disorder were selected in this study. ICA filters trained on the reduced version of 60 channel EEG data collected during single pulse TMS-EEG and sham-EEG recordings and identified the reduced number of statistically independent source channels. The decomposition algorithm of ICA considered in this study includes Jader , FastICA and cICA. The ICA components originating from the TMS-induced artifact are classified by comparing the cross-correlation coefficients between single pulse TMS-EEG and sham-EEG stimulus after ICA decomposition. Then, the estimation of parameters in the TMS-induced artifact removal for sampling rate 1.45kHz, filtering order 100 and ICA decomposition method FastICA was evaluated by the change of the ratio of the cross-correlation coefficients between single pulse TMS-EEG and sham-EEG stimulus before and after the ICA decomposition. The results showed the consistency in the assessment of the availability of the TMS-induced artifact removal suggesting the efficiency and the reliability of the method developed in this study.

Segmentation of Depth-of-Field Images Based on the Response of ICA Filters

Segmentation of Depth-of-Field Images Based on the Response of ICA Filters

Manifestation of ocular-muscle EMG contamination in human intracranial recordings

It is widely assumed that intracranial recordings from the brain are only minimally affected by contamination due to ocular-muscle electromyogram (oEMG). Here we show that this is not always the case. In intracranial recordings from five surgical epilepsy patients we observed that eye movements caused a transient biphasic potential at the onset of a saccade, resembling the saccadic spike potential commonly seen in scalp EEG, accompanied by an increase in broadband power between 20 and 200Hz. Using concurrently recorded eye movements and high-density intracranial EEG (iEEG) we developed a detailed overview of the spatial distribution and temporal characteristics of the saccade-related oculomotor signal within recordings from ventral, medial and lateral temporal cortex. The occurrence of the saccadic spike was not explained solely by reference contact location, and was observed near the temporal pole for small (<2deg) amplitude saccades and over a broad area for larger saccades. We further examined the influence of saccade-related oEMG contamination on measurements of spectral power and interchannel coherence. Contamination manifested in both spectral power and coherence measurements, in particular, over the anterior half of the ventral and medial temporal lobe. Next, we compared methods for removing the contaminating signal and found that nearest-neighbor bipolar re-referencing and ICA filtering were effective for suppressing oEMG at locations far from the orbits, but tended to leave some residual contamination at the temporal pole. Finally, we show that genuine cortical broadband gamma responses observed in averaged data from ventral temporal cortex can bear a striking similarity in time course and band-width to oEMG contamination recorded at more anterior locations. We conclude that eye movement-related contamination should be ruled out when reporting high gamma responses in human intracranial recordings, especially those obtained near anterior and medial temporal lobe.

Filtering by optimal projection and application to automatic artifact removal from EEG

A new approach to filter multi-channel signals is presented, called filtering by optimal projection (FOP) in this paper. This approach is based on common spatial subspace decomposition (CSSD) theory. Moreover, an evolution of this method for non-stationary signals is also introduced which is called adaptative FOP (AFOP). As ICA, a filtering matrix is set up in the best way to remove artifacts with linear combination of channels. This filtering matrix is characterized by two subspaces. The first one is determined during a learning phase, by finding components maximizing the ratio signal over noise. The second one will be determined during a filtering phase, by reconstructing signals of a sliding window, by a least square method. These methods are completely automated and enable to filter independently numerous artifact types. Moreover, this filtering can be improved by applying this process on frequency band decomposed signals. Various tests have been made on electroencephalogram (EEG) signals in order to remove ocular and muscular activity while conserving pathological activity (slow waves, paroxysms). The results are compared with ICA filtering and medical inspection has been carried out to prove that this approach yields very good performance.

Investigation of gastrointestinal transport by magnetic marker localization.

The method of magnetic marker monitoring MMM with a biomagnetic measurement system allows the tracking of the transport of solid drug forms with high spatiotemporal resolution. This technique enables to display the path and the disintegration of the magnetic marked pharmaceutical dosage form via the decrease of its magnetic moment. The method was used to assess exogenous factor on the esophageal transport of orally administered solid drug forms in five healthy volunteers. In a drug delivery study we have applied the MMM to monitor the path of a tablet during the gastrointestinal passage and to visualize the disintegration in the small intestine by the magnetic moment of the tablet. The signal to noise ratio of the measurement data was improved by ICA filtering.

The "independent components" of natural scenes are edge filters.

It has previously been suggested that neurons with line and edge selectivities found in primary visual cortex of cats and monkeys form a sparse, distributed representation of natural scenes, and it has been reasoned that such responses should emerge from an unsupervised learning algorithm that attempts to find a factorial code of independent visual features. We show here that a new unsupervised learning algorithm based on information maximization, a nonlinear "infomax" network, when applied to an ensemble of natural scenes produces sets of visual filters that are localized and oriented. Some of these filters are Gabor-like and resemble those produced by the sparseness-maximization network. In addition, the outputs of these filters are as independent as possible, since this infomax network performs Independent Components Analysis or ICA, for sparse (super-gaussian) component distributions. We compare the resulting ICA filters and their associated basis functions, with other decorrelating filters produced by Principal Components Analysis (PCA) and zero-phase whitening filters (ZCA). The ICA filters have more sparsely distributed (kurtotic) outputs on natural scenes. They also resemble the receptive fields of simple cells in visual cortex, which suggests that these neurons form a natural, information-theoretic coordinate system for natural images.