Adversarial learning for semi-supervised pediatric sleep staging with single-EEG channel.

Symmetric positive definite (SPD) matrices used as feature descriptors in image recognition are usually high dimensional. Traditional manifold learning is only applicable for reducing the dimension of high-dimensional vector-form data.For high-dimensional SPD matrices, directly using manifold learning algorithms to reduce the dimension of matrix-form data is impossible. The SPD matrix must first be transformed into a long vector, and then the dimension of this vector must be reduced. However, this approach breaks the spatial structure of the SPD matrix space. To overcome this limitation, we propose a new dimension reduction algorithm on SPD matrix space to transform high-dimensional SPD matrices into low-dimensional SPD matrices. Our work is based on the fact that the set of all SPD matrices with the same size has a Lie group structure, and we aim to transform the manifold learning to the SPD matrix Lie group. We use the basic idea of the manifold learning algorithm called locality preserving projection (LPP) to construct the corresponding Laplacian matrix on the SPD matrix Lie group. Thus, we call our approach Lie-LPP to emphasize its Lie group character. We present a detailed algorithm analysis and show through experiments that Lie-LPP achieves effective results on human action recognition and human face recognition.

<p><b>Metric Learning has proved valuable in information retrieval and classification problems, with many algorithms using statistical formulations to their advantage. Optimal Transport, a powerful framework for computing distances between probability distributions, has seen significant uptake in Machine Learning and some applications in Metric Learning. The Bures-Wasserstein distance, a particular formulation of Optimal Transport, has seen limited application in Metric Learning despite being well suited to the field. In this thesis Linear Metric Learning algorithms incorporating the Bures-Wasserstein distance are developed, utilising its novel properties. The first set of algorithms we contribute use the Bures-Wasserstein distance for learning linear metrics using Cyclic Projections, Riemannian barycenters and gradient-based algorithms. The convergence properties and classification performance of these algorithms are then compared to benchmark Linear Metric Learning algorithms. Our algorithms achieve competitive classification performance on feature and image datasets and converge reliability.</b></p> <p>The second set of contributions extend Linear Metric Learning with the Bures-Wasserstein distance to a low-rank context to address issues related to scalability. An extension of the previous Cyclic Projections algorithm and a Riemannian optimisation method are developed. Convergence and classification experiments analogous to the full-rank case are conducted to examine how the reduced rank affects both of these performance metrics. Both algorithms converge reliably under a variety of synthetic conditions. Reduction in rank generally decreased the training time for algorithms until effects caused by the size of the training data dominated. Reducing rank either left classification error unchanged or increased it. With respect to other low-rank Linear Metric Learning algorithms our algorithms again performed competitively with respect to classification error. </p> <p>The last set of contributions consider Linear Metric Learning on Symmetric Positive Definite (SPD) matrices. Some datasets are expressed as or are suited to a SPD representation. As such, Metric Learning algorithms that respect the structure of these matrices have found success when adapted to this kind of data. Another extension of the Cyclic Projections algorithm is developed to use the Generalised Bures-Wasserstein distance on SPD matrices. Two other methods based on a ground metric formulation of the Bures-Wasserstein distance for learning linear metrics on SPD data are also introduced. One ground metric formulation uses an approximation (inspired by the Sinkhorn distance) to increase its scalability. Convergence experiments on synthetic problems adapted to SPD matrices are conducted on the ground metric algorithms to establish their convergence properties. Classification experiments are also conducted with respect to several types of SPD data. While the Cyclic Projections method is competitive, the ground metric algorithms have poor performance. Despite their poor classification performance, the approximation method does evaluate faster than the Generalised Bures-Wasserstein distance, potentially offering some scalability improvements.</p>

Electroencephalogram (EEG) signals convey abundant physiological and psychological information. Decoding EEG is fundamental for brain-computer interaction and medical rehabilitation. Nevertheless, the nonstationarity and inter-individual variability of EEG signals impedes current models from achieving robust crosssubject generalization without expensive subject-specific recalibration, thereby restricting practical deployment. Unsupervised domain adaptation (UDA) aims to improve generalization by minimizing distribution discrepancies between source and target domains. Recent studies regard different subjects as distinct domains and leverage UDA to facilitate cross-subject EEG classification by learning domain-invariant features through discrepancy minimization or adversarial training. However, these conventional methods are all developed in Euclidean space, which are insufficient to capture the non-linear structures inherent in EEG data. To address this limitation, we propose a Deep Adversarial Neural Network on the Symmetric Positive Definite (SPD) matrix manifold, referred to as SPD-DANN, which facilitates the extraction of subject-invariant features through adversarial learning. Additionally, we design an SPD domain feature alignment loss and an SPD class prototype pair loss to simultaneously promote feature alignment across subjects and enhance feature space discriminability. Extensive experiments on four brain-computer interface (BCI) datasets demonstrate that our method surpasses several state-of-the-art UDA techniques. Furthermore, the proposed loss functions are readily adaptable to broader unsupervised or semi-supervised domain adaptation frameworks.

Representing images and videos with Symmetric Positive Definite (SPD) matrices, and considering the Riemannian geometry of the resulting space, has been shown to yield high discriminative power in many visual recognition tasks. Unfortunately, computation on the Riemannian manifold of SPD matrices -especially of high-dimensional ones- comes at a high cost that limits the applicability of existing techniques. In this paper, we introduce algorithms able to handle high-dimensional SPD matrices by constructing a lower-dimensional SPD manifold. To this end, we propose to model the mapping from the high-dimensional SPD manifold to the low-dimensional one with an orthonormal projection. This lets us formulate dimensionality reduction as the problem of finding a projection that yields a low-dimensional manifold either with maximum discriminative power in the supervised scenario, or with maximum variance of the data in the unsupervised one. We show that learning can be expressed as an optimization problem on a Grassmann manifold and discuss fast solutions for special cases. Our evaluation on several classification tasks evidences that our approach leads to a significant accuracy gain over state-of-the-art methods.

Sleep quality has gradually become an important issue concerned by people in today's society, and the judgment of sleep quality requires professional doctors to stage the subjects' sleep stage all night, and doctors need to spend a lot of time and energy to stage sleep. Lack of medical resources in China, the proportion of small problems, this paper proposes a new sleep staging algorithm based on hybrid neural network, this algorithm can be collected by the data of sleep, the hybrid neural network training. The proposed hybrid neural network model mainly includes two parts: the feature learning and extraction stage based on convolutional neural network, and the learning stage based on the sleep sequence rule of short and long time memory network. The trained hybrid neural network can perform automatic sleep staging based on single channel EEG and generate sleep phase diagrams. The proposed algorithm was tested in sleep-EDF database, and the accuracy of Sleep staging reached 92.21%. The results show that the proposed algorithm has higher accuracy and better robustness in the case of higher noise in the data.

We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based ASR system. We call the scheme speaker-invariant training (SIT). In SIT, a DNN acoustic model and a speaker classifier network are jointly optimized to minimize the senone (tied triphone state) classification loss, and simultaneously mini-maximize the speaker classification loss. A speaker-invariant and senone-discriminative deep feature is learned through this adversarial multi-task learning. With SIT, a canonical DNN acoustic model with significantly reduced variance in its output probabilities is learned with no explicit speaker-independent (SI) transformations or speaker-specific representations used in training or testing. Evaluated on the CHiME-3 dataset, the SIT achieves 4.99% relative word error rate (WER) improvement over the conventional SI acoustic model. With additional unsupervised speaker adaptation, the speaker-adapted (SA) SIT model achieves 4.86% relative WER gain over the SA SI acoustic model.

Symmetric Positive Definite (SPD) matrices have been used in many fields of medical data analysis. Many Riemannian metrics have been defined on this manifold but the choice of the Riemannian structure lacks a set of principles that could lead one to choose properly the metric. This drives us to introduce the principle of balanced metrics that relate the affine-invariant metric with the Euclidean and inverse-Euclidean metric, or the Bogoliubov-Kubo-Mori metric with the Euclidean and log-Euclidean metrics. We introduce two new families of balanced metrics, the mixed-power-Euclidean and the mixed-power-affine metrics and we discuss the relation between this new principle of balanced metrics and the concept of dual connections in information geometry.

The geometry of mixed-Euclidean metrics on symmetric positive definite matrices

We present a distributed memory algorithm for the approximate hierarchical of symmetric positive definite (SPD) matrices. Our method is based on the distributed memory GOFMM, an algorithm that appeared in SC18 (doi:10.1109/SC.2018.00018). GOFMM constructs a hierarchical matrix approximation of an arbitrary SPD matrix that compresses the matrix by creating low-rank approximations of the off-diagonal blocks. GOFMM method has no guarantees of success for arbitrary SPD matrices. (This is similar to the SVD; not every matrix admits a good low-rank approximation.) But for many SPD matrices, GOFMM does enable compression that results in fast matrix-vector multiplication that can reach N logN time—as opposed to N2 required for a dense matrix. GOFMM supports shared and distributed memory parallelism. In this paper, we build an approximate based on the Hierarchically Semi-Separable (HSS) compression of the GOFMM. This requires O(N) work (given the compressed matrix) and O(N=p) + O(log p) time on p MPI processes (assuming a hypercube topology). The previous state-of-the-art required O(N logN) work. We present the algorithm, discuss its complexity, and present weak and strong scaling results for the factorization and phases of our algorithm. We also discuss the performance of the inexact ULV as a preconditioner for a few exemplary large dense linear systems. In our largest run, we were able to factorize a 67M-by-67M matrix in less than one second; and solve a system with 64 right-hand sides in less than one-tenth of a second. This run was on 6,144 Intel Skylake cores on the SKX partition of the Stampede2 system at the Texas Advanced Computing Center.

The region covariance descriptors have recently become a popular method for detection and tracking of objects in an image. However, these descriptors are not suitable for classification of images with heterogeneous contents. In this paper, we present an image-level descriptor obtained using an affine-invariant geodesic mean of region covariance descriptors on the Riemannian manifold of symmetric positive definite (SPD) matrices. The resulting image descriptors are also SPD matrices, lending themselves to tractable geodesic distance based k-nearest neighbour classification using efficient kernels. We show that the proposed descriptor yields high classification accuracy on a challenging problem of nuclear pleomorphism scoring in breast cancer histology images.

An explainable deep-learning model to stage sleep states in children and propose novel EEG-related patterns in sleep apnea

A novel semi-supervised meta learning method for subject-transfer brain–computer interface

The most important part of sleep quality assessment is the classification of sleep stages, which helps to diagnose sleep-related disease. In the traditional sleep staging method, subjects have to spend a night in the sleep clinic for recording polysomnogram. Sleep expert classifies the sleep stages by monitoring the signals, which is time consuming and frustrating task and can be affected by human error. New studies propose fully automated techniques for classifying sleep stages that makes sleep scoring possible at home. Despite comprehensive studies have been presented in this field the classification results have not yet reached the gold standard due to the concentration on the use of a limited source of information such as single channel EEG. Therefore, this article introduces a new method for fusing two sources of information, including electroencephalogram (EEG) and electrooculogram (EOG), to achieve promising results in the classification of sleep stages. In the proposed method, extracted features from the EEG and EOG signals, are divided into two feature sets consisting of the EEG features and fused features of EEG and EOG. Then, each feature set transformed into a horizontal visibility graph (HVG). The images of the HVG are produced in a novel framework and classified by proposed transfer learning convolutional neural network for data fusion (TLCNN-DF). Employing transfer learning at the training stage of the model has accelerated the training process of the CNN and improved the performance of the model. The proposed algorithm is used to classify the Sleep-EDF and Sleep-EDFx benchmark datasets. The algorithm can classify the Sleep-EDF dataset with an accuracy of 93.58% and Cohen’s kappa coefficient of 0.899. The results show proposed method can achieve superior performance compared to state-of-the-art studies on classification of sleep stages. Furthermore, it can attain reliable results as an alternative to conventional sleep staging.

Poor quality and poor duration of sleep have been associated with cognitive decline, diseases, and disorders. Therefore, sleep studies are imperative to recapitulate phenotypes associated with poor sleep quality and uncover mechanisms contributing to psychopathology. Classification of sleep stages, vigilance state bout durations, and number of transitions amongst vigilance states serves as a proxy for evaluating sleep quality in preclinical studies. Currently, the gold standard for sleep staging is expert human inspection of polysomnography (PSG) obtained from preclinical rodent models and this approach is immensely time consuming. To accelerate the analysis, we developed a deep-learning-based software tool for automated sleep stage classification in rats. This study aimed to develop an automated method for classifying three sleep stages in rats (REM/paradoxical sleep, NREM/slow-wave sleep, and wakefulness) using a deep learning approach based on single-channel EEG data. Single-channel EEG data were acquired from 16 rats, each undergoing two 24 h recording sessions. The data were labeled by human experts in 10 s epochs corresponding to three stages: REM/paradoxical sleep, NREM/slow-wave sleep, and wakefulness. A deep neural network (DNN) model was designed and trained to classify these stages using the raw temporal data from the EEG. The DNN achieved strong performance in predicting the three sleep stages, with an average F1 score of 87.6% over a cross-validated test set. The algorithm was able to predict key parameters of sleep architecture, including total bout duration, average bout duration, and number of bouts, with significant accuracy. Our deep learning model effectively automates the classification of sleep stages using single-channel EEG data in rats, reducing the need for labor-intensive manual annotation. This tool enables high-throughput sleep studies and may accelerate research into sleep-related pathologies. Furthermore, we provide over 700 h of expert-scored sleep data, available for public use in future research studies.

We developed a machine learning methodology for automatic sleep stage scoring. Our time-frequency analysis-based feature extraction is fine-tuned to capture sleep stage-specific signal features as described in the American Academy of Sleep Medicine manual that the human experts follow. We used ensemble learning with an ensemble of stacked sparse autoencoders for classifying the sleep stages. We used class-balanced random sampling across sleep stages for each model in the ensemble to avoid skewed performance in favor of the most represented sleep stages, and addressed the problem of misclassification errors due to class imbalance while significantly improving worst-stage classification. We used an openly available dataset from 20 healthy young adults for evaluation. We used a single channel of EEG from this dataset, which makes our method a suitable candidate for longitudinal monitoring using wearable EEG in real-world settings. Our method has both high overall accuracy (78%, range 75–80%), and high mean F_1-score (84%, range 82–86%) and mean accuracy across individual sleep stages (86%, range 84–88%) over all subjects. The performance of our method appears to be uncorrelated with the sleep efficiency and percentage of transitional epochs in each recording.