Second Order Blind Identification of Event Related Potentials Sources.

Event-related potentials (ERPs) recorded on the surface of the head are a mixture of signals from many sources in the brain due to volume conductions. As a result, the spatial resolution of the ERPs is quite low. Blind source separation can help to recover source signals from multichannel ERP records. In this study, we present a novel implementation of a method for decomposing multi-channel ERP into components, which is based on the modeling of second-order statistics of ERPs. We also report a new implementation of Bayesian Information Criteria (BIC), which is used to select the optimal number of hidden signals (components) in the original ERPs. We tested these methods using both synthetic datasets and real ERPs data arrays. Testing has shown that the ERP decomposition method can reconstruct the source signals from their mixture with acceptable accuracy even when these signals overlap significantly in time and the presence of noise. The use of BIC allows us to determine the correct number of source signals at the signal-to-noise ratio commonly observed in ERP studies. The proposed approach was compared with conventionally used methods for the analysis of ERPs. It turned out that the use of this new method makes it possible to observe such phenomena that are hidden by other signals in the original ERPs. The proposed method for decomposing a multichannel ERP into components can be useful for studying cognitive processes in laboratory settings, as well as in clinical studies.

Second-order asymmetric convolution network for breast cancer histopathology image classification.

Recently, convolutional neural networks (CNNs) have been widely utilized for breast cancer histopathology image classification. Besides, research works have also convinced that deep high-order statistic models obviously outperform corresponding first-order counterparts in vision tasks. Inspired by this, we attempt to explore global deep high-order statistics to distinguish breast cancer histopathology images. To further boost the classification performance, we also integrate asymmetric convolution into the second-order network and propose a novel second-order asymmetric convolution network (SoACNet). SoACNet adopts a series of asymmetric convolution blocks to replace each stand square-kernel convolutional layer of the backbone architecture, followed by a global covariance pooling to compute second-order statistics of deep features, leading to a more robust representation of histopathology images. Extensive experiments on the public BreakHis dataset demonstrate the effectiveness of SoACNet for breast cancer histopathology image classification, which achieves competitive performance with the state-of-the-arts.

Coordinated multivoxel coding beyond univariate effects is not likely to be observable in fMRI data.

Simultaneous recording of activity across brain regions can contain additional information compared to regional recordings done in isolation. In particular, multivariate pattern analysis (MVPA) across voxels has been interpreted as evidence for distributed coding of cognitive or sensorimotor processes beyond what can be gleaned from a collection of univariate effects (UVE) using functional magnetic resonance imaging (fMRI). Here, we argue that regardless of patterns revealed, conventional MVPA is merely a decoding tool with increased sensitivity arising from considering a large number of 'weak classifiers' (i.e., single voxels) in higher dimensions. We propose instead that 'real' multivoxel coding should result in changes in higher-order statistics across voxels between conditions such as second-order multivariate effects (sMVE). Surprisingly, analysis of conditions with robust multivariate effects (MVE) revealed by MVPA failed to show significant sMVE in two species (humans and macaques). Further analysis showed that while both MVE and sMVE can be readily observed in the spiking activity of neuronal populations, the slow and nonlinear hemodynamic coupling and low spatial resolution of fMRI activations make the observation of higher-order statistics between voxels highly unlikely. These results reveal inherent limitations of fMRI signals for studying coordinated coding across voxels. Together, these findings suggest that care should be taken in interpreting significant MVPA results as representing anything beyond a collection of univariate effects.

Second-order ResU-Net for automatic MRI brain tumor segmentation.

Tumor segmentation using magnetic resonance imaging (MRI) plays a significant role in assisting brain tumor diagnosis and treatment. Recently, U-Net architecture with its variants have become prevalent in the field of brain tumor segmentation. However, the existing U-Net models mainly exploit coarse first-order features for tumor segmentation, and they seldom consider the more powerful second-order statistics of deep features. Therefore, in this work, we aim to explore the effectiveness of second-order statistical features for brain tumor segmentation application, and further propose a novel second-order residual brain tumor segmentation network, i.e., SoResU-Net. SoResU-Net utilizes a number of second-order modules to replace the original skip connection operations, thus augmenting the series of transformation operations and increasing the non-linearity of the segmentation network. Extensive experimental results on the BraTS 2018 and BraTS 2019 datasets demonstrate that SoResU-Net outperforms its baseline, especially on core tumor and enhancing tumor segmentation, illuminating the effectiveness of second-order statistical features for the brain tumor segmentation application.

Hydraulic separation of plastic wastes: Analysis of liquid-solid interaction.

The separation of plastic wastes in mechanical recycling plants is the process that ensures high-quality secondary raw materials. An innovative device employing a wet technology for particle separation is presented in this work. Due to the combination of the characteristic flow pattern developing within the apparatus and density, shape and size differences among two or more polymers, it allows their separation into two products, one collected within the instrument and the other one expelled through its outlet ducts. The kinematic investigation of the fluid flowing within the apparatus seeded with a passive tracer was conducted via image analysis for different hydraulic configurations. The two-dimensional turbulent kinetic energy results strictly connected to the apparatus separation efficacy. Image analysis was also employed to study the behaviour of mixtures of passive tracer and plastic particles with different physical characteristics in order to understand the coupling regime between fluid and solid phases. The two-dimensional turbulent kinetic energy analysis turned out to be fundamental to this aim. For the tested operating conditions, two-way coupling takes place, i.e., the fluid exerts an influence on the plastic particle and the opposite occurs too. Image analysis confirms the outcomes from the investigation of the two-phase flow via non-dimensional numbers (particle Reynolds number, Stokes number and solid phase volume fraction).

Subspace-based self-interference cancellation for full-duplex MIMO transceivers.

This paper addresses the self-interference (SI) cancellation at baseband for full-duplex MIMO communication systems in consideration of practical transmitter imperfections. In particular, we develop a subspace-based algorithm to jointly estimate the SI and intended channels and the nonlinear distortions. By exploiting the covariance and pseudo-covariance of the received signal, we can increase the dimension of the received signal subspace while keeping the dimension of the signal subspace constant, and hence, the proposed algorithm can be applied to most of full-duplex MIMO configurations with arbitrary numbers of transmit and receive antennas. The channel coefficients are estimated, up to an ambiguity term, without any knowledge of the intended signal. A joint detection and ambiguity identification scheme is proposed. Simulation results show that the proposed algorithm can properly estimate the channel with only one pilot symbol and offers superior SI cancellation performance.

Perception and coding of envelopes in weakly electric fishes.

Natural sensory stimuli have a rich spatiotemporal structure and can often be characterized as a high frequency signal that is independently modulated at lower frequencies. This lower frequency modulation is known as the envelope. Envelopes are commonly found in a variety of sensory signals, such as contrast modulations of visual stimuli and amplitude modulations of auditory stimuli. While psychophysical studies have shown that envelopes can carry information that is essential for perception, how envelope information is processed in the brain is poorly understood. Here we review the behavioral salience and neural mechanisms for the processing of envelopes in the electrosensory system of wave-type gymnotiform weakly electric fishes. These fish can generate envelope signals through movement, interactions of their electric fields in social groups or communication signals. The envelopes that result from the first two behavioral contexts differ in their frequency content, with movement envelopes typically being of lower frequency. Recent behavioral evidence has shown that weakly electric fish respond in robust and stereotypical ways to social envelopes to increase the envelope frequency. Finally, neurophysiological results show how envelopes are processed by peripheral and central electrosensory neurons. Peripheral electrosensory neurons respond to both stimulus and envelope signals. Neurons in the primary hindbrain recipient of these afferents, the electrosensory lateral line lobe (ELL), exhibit heterogeneities in their responses to stimulus and envelope signals. Complete segregation of stimulus and envelope information is achieved in neurons in the target of ELL efferents, the midbrain torus semicircularis (Ts).

Independent component analysis algorithm and its application in biomedical engineering / 国际生物医学工程杂志

Independent component algorithm (ICA) is a method of higher-order statistics(HOS) with the study objects of multivariate random signals that are mutual independent. It aim is to transform multivariate random signal into the signal having components that are mutually independent in complete statistical sense. This article briefly introduce series of the ICA algorisms including second order blind identification, multiple unknown source extraction algorithm based on second-order statistics, as well as Informax, modified Informax, fast fixedpoint ICA and joint approximative diagonalization of eigenmatrix (JADE) algorithm that are based on HOS. At the end of the article, the performance of each algorithm is compared and its application prospect is forecasted.