Search

Smoothing filters are widely used in EEG signal processing for noise removal while preserving signals’ features. Inspired by our recent work on Upscale and Downscale Representation (UDR), this paper proposes a cascade arrangement of some effective image-processing techniques for signal filtering in the image domain. The UDR concept is to visualize EEG signals at an appropriate line width and convert it to a binary image. The smoothing process is then conducted by skeletonizing the signal object to a unit width and projecting it back to the time domain. Two successive UDRs could result in a better-smoothing performance, but their binary image conversion should be restricted. The process is computationally ineffective, especially at higher line width values. Cascaded Thinning UDR (CTUDR) is proposed, exploiting morphological operations to perform a two-stage upscale and downscale within one binary image representation. CTUDR is verified on a signal smoothing and classification task and compared with conventional techniques, such as the Moving Average, the Binomial, the Median, and the Savitzky Golay filters. Simulated EEG data with added white Gaussian noise is employed in the former, while cognitive conflict data obtained from a 3D object selection task is utilized in the latter. CTUDR outperforms its counterparts, scoring the best fitting error and correlation coefficient in signal smoothing while achieving the highest gain in Accuracy (0.7640%) and F-measure (0.7607%) when used as a smoothing filter for training data of EEGNet.

Summary: In this paper, we propose two new provable algorithms for tracking online low-rank approximations of high-order streaming tensors with missing data. The first algorithm, dubbed adaptive Tucker decomposition (ATD), minimizes a weighted recursive least-squares cost function to obtain the tensor factors and the core tensor in an efficient way, thanks to an alternating minimization framework and a randomized sketching technique. Under the canonical polyadic (CP) model, the second algorithm, called ACP, is developed as a variant of ATD when the core tensor is imposed to be identity. Both algorithms are low-complexity tensor trackers that have fast convergence and low memory storage requirements. A unified convergence analysis is presented for ATD and ACP to justify their performance. Experiments indicate that the two proposed algorithms are capable of streaming tensor decomposition with competitive performance with respect to estimation accuracy and runtime on both synthetic and real data. The bigger picture: Low-rank approximation methods are a class of mathematical techniques commonly used to help process large datasets, especially in signal processing and machine learning applications. These methods allow multidimensional data to be represented by a set of low-dimensional components and can be powerful tools for discovering valuable information or deriving new insights from complex data. Applying these methods to streaming data, which are being continuously generated and must be analyzed in real time, remains challenging due to the increasing size and complexity of these datasets over time. These challenges are particularly acute for datasets with missing values. This paper proposes a novel adaptive method for tracking online low-rank approximations of multidimensional streaming data, resulting in two efficient tensor trackers that accurately estimate the underlying components of noisy, incomplete, and high-dimensional observations. The effectiveness of the proposed approach is demonstrated in various experiments, including the analysis of EEG data and video sequences.

Correct detection of peaks in electroencephalogram (EEG) signals is of essence due to the significant correlation of those potentials with cognitive performance and disorders. This paper proposes a novel and non-parametric approach to detect prediction error negativity (PEN) in cognitive conflict processing. The PEN candidates are first located from the input signal via an adaptation of a recent effective method for local maxima extraction, processed in a multi-scale manner. The found candidates are then fused and ranked based on their shape and location-based features. False positives caused by candidates’ magnitude are eliminated by rotating the sorted candidate list where the one with the second-best ranking score will be identified as PEN. The EEG data collected from a 3D object selection task have been used to verify the efficacy of the proposed approach. Compared with the state-of-the-art peak detection techniques, the proposed method shows an improvement of at least 2.67% in accuracy and 6.27% in sensitivity while requires only about 4 ms to process an epoch. The accuracy and computational efficiency of the proposed technique in the detection of PEN in cognitive conflict processing would lead to promising applications in performance improvement of brain-computer interfaces (BCIs).

This paper presents a method of ranking the effectiveness of brain region of interest (ROI) in order to separate Normal Control (NC) from Alzheimer’s disease (AD) brains Positron Emission Tomography (PET) images based on AutoEncoder (AE) networks. Firstly, PET brains are mapped into ROIs using an anatomical atlas. Then, multiple AE models are trained and fine-tuned with softmax. After that, the connection weights learned from AEs are used to rank ROIs according to the total contribution of ROIs to the networks. We proposed a 2-phase feature ranking method which is able to significantly improve the ranking results. Lastly, the top-ranked ROIs are then input into a support vector machine (SVM) classifier. In experiments on ADNI dataset, the proposed method significantly improves the accuracy of the classifier when compared to other popular feature ranking methods such as: Fisher score, T-score, Conditional Mutual Information Maximization (CMIM), and Lasso. Our result shows that simple single-hidden-layer AE models can be used effectively to perform the feature ranking task. The proposed method could be easily applied to any image dataset where a feature selection is needed.