Electroencephalogram (EEG)-driven innovations have gained prominence as pivotal research frontiers in various domains, including neurological disorder diagnostics, sensorimotor rehabilitation, and brain–computer interfaces (BCIs), and so on. Traditional EEG decoding methods encounter difficulties in effectively extracting global features from EEG signals while demonstrating constrained adaptability to high-dimensional EEG patterns. Furthermore, the scarcity of labeled EEG significantly restricts the applicability of supervised learning paradigms. To address these challenges, we propose IGEEGc , a novel unsupervised decoding method specifically designed for unlabeled EEG signal analysis. First, we extend the trend-based information granule (TIG) model by incorporating frequency-domain features, thereby developing a frequency-trend-based information granule (FTIG) model that simultaneously captures time-frequency features of EEG signals. Subsequently, an adaptive granule feature weighting mechanism is developed to dynamically optimize the contributions of heterogeneous granule features toward enhancing clustering accuracy. Finally, constraints are integrated into the unified one-step spectral clustering framework to optimize the objective function and enhance clustering performance. Comparative experiments across 30 real-world datasets in multiple scenarios demonstrate IGEEGc ’s consistent superiority over state-of-the-art methods, with its robustness and efficacy being validated through comprehensive sensitivity analyses and ablation studies. The proposed method not only addresses the inherent high-dimensional complexity of EEG signals but also establishes an effective paradigm for processing unlabeled EEG data. The source code can be found at https://github.com/Ljyyds/IGEEGc .

More and more recent studies highlight the crucial role of the human microbiome in maintaining health, while modern advancements in metagenomic sequencing technologies have been accumulating data that are associated with human diseases. Although metagenomic data offer rich, multifaceted information, including taxonomic and functional abundance profiles, their full potential remains underutilized, as most approaches rely only on one type of information to discover and understand their related correlations with respect to disease occurrences. To address this limitation, we propose a multistage fusion tabular transformer architecture (MSFT-Transformer), aiming to effectively integrate various types of high-dimensional tabular information extracted from metagenomic data. Its multistage fusion strategy consists of three modules: a fusion-aware feature extraction module in the early stage to improve the extracted information from inputs, an alignment-enhanced fusion module in the mid stage to enforce the retainment of desired information in cross-modal learning, and an integrated feature decision layer in the late stage to incorporate desired cross-modal information. We conduct extensive experiments to evaluate the performance of MSFT-Transformer over state-of-the-art models on five standard datasets. Our results indicate that MSFT-Transformer provides stable performance gains with reduced computational costs. An ablation study illustrates the contributions of all three models compared with a reference multistage fusion transformer without these novel strategies. The result analysis implies the significant potential of the proposed model in future disease prediction with metagenomic data.

Nowadays, various graph convolutional networks (GCNs) to process graph-structured data have been proposed for hyperspectral image (HSI) classification. Nevertheless, most GCN-based HSI classification methods emphasize graph node feature aggregation instead of graph pooling, resulting in them being shallow networks and unable to extract deep discriminative features. Besides, to obtain the new graph after the pooling layer, current graph pooling methods used for HSI classification just consider node feature information to select important nodes and directly discard unselected nodes, which could be a subjective process and may cause information loss. To solve this issue, we propose a novel graph U-Net with topology-feature awareness pooling (the so-called TFAP graph U-Net) for HSI classification considering a deep network to extract compelling features and automatically selecting nodes beneficial to classification. More specifically, to establish a more precise pooled graph, the graph’s topology structure and node feature information are taken into account, making the node selection process more convincing and objective. Furthermore, to allow that graph nodes preserve more useful graph information, our method aggregates node features from neighboring nodes that may not be selected, which can alleviate the loss of information during the pooling process. Moreover, a cross-attention module (CAM) is used to filter out irrelevant or noisy features. Finally, we evaluate the proposed method on three public HSI datasets, i.e., Indian Pines, University of Pavia (PaviaU), and University of Houston. The experimental results demonstrate the superiority of the proposed approach compared with other state-of-the-art methods.

Deep graph convolutional networks (GCNs) have shown promising performance in traffic prediction tasks, but their practical deployment on resource-constrained devices faces challenges. First, few models consider the potential influence of historical and future auxiliary information, such as weather and holidays, on complex traffic patterns. Second, the computational complexity of dynamic graph convolution operations grows quadratically with the number of traffic nodes, limiting model scalability. To address these challenges, this study proposes a deep encoder-decoder model named AIMSAN, which comprises an auxiliary information-aware module (AIM) and a sparse cross-attention-based graph convolutional network (SAN). From historical or future perspectives, AIM prunes multi-attribute auxiliary data into diverse time frames, and embeds them into one tensor. SAN employs a cross-attention mechanism to merge traffic data with historical embedded data in each encoder layer, forming dynamic adjacency matrices. Subsequently, it applies diffusion GCN to capture rich spatial-temporal dynamics from the traffic data. Additionally, AIMSAN utilizes the spatial sparsity of traffic nodes as a mask to mitigate the quadratic computational complexity of SAN, thereby improving overall computational efficiency. In the decoder layer, future embedded data are fused with feed-forward traffic data to generate prediction results. Experimental evaluations on three public traffic datasets demonstrate that AIMSAN achieves competitive performance compared to state-of-the-art algorithms, while reducing GPU memory consumption by 41.24%, training time by 62.09%, and validation time by 65.17% on average.

The rapid development of 5G and the widespread use of smart terminal devices bring explosive video traffic growth. Edge caching technology in mobile edge computing systems stores popular content of most interest to users in advance in edge servers closer to mobile users to alleviate the pressure of traffic congestion and excessive access latency caused by centralized storage. However, how to obtain popular videos while protect user data privacy with only implicit user feedback data, such as liking, viewing, favoriting, etc., is the key challenge. To tackle these challenges, we proposed a proactive video caching scheme based on federated learning and implicit feedback (FIPC). First, a mobile edge-cloud system model contained a three-tier network architecture is developed. Then, we introduced the federated process for training the denoised auto-encoder model and video caching in detail. Finally, experimental results in Movielens dataset show that, without user data leakage, the proposed FIPC scheme outperforms the baseline caching algorithm using user feedback data.

Graph convolutional network (GCN) has recently received increasing attention in hyperspectral image (HSI) classification, benefiting from its superiority in conducting shape adaptive convolutions on arbitrary non-Euclidean structure data. However, the performance of GCN heavily depends on the quality of the initial graph. Conventional GCN-based methods only adopt spectral-spatial similarity to build the initial graph without extracting other contextual information from neighboring nodes. In addition, most GCN-based methods use shallow layers, which cannot extract deep discriminative features from HSIs under the limited number of training samples. To solve these issues, we propose a superpixel feature learning via offset graph U-Net for HSI classification, which can learn deep discriminative features from HSIs. Multiple strategies of measuring similarity among superpixels are utilized to build the initial graph, including spectral information, spatial information and context-aware information among nodes, making the initial graph more accurate. Furthermore, the graph U-Net structure, containing the graph pooling layer and the graph unpooling layer, is helpful in constructing deep GCN layers and learning multi-scale features, which can alleviate the oversmoothing problem. Moreover, an offset module is introduced to emphasize the local spectral-spatial information. Finally, we comprehensively evaluate the proposed method on three public data sets. The experimental results demonstrate the superiority of the proposed approach compared with other state-of-the-art methods.

Electroencephalogram (EEG)-based applications in Brain-Computer Interfaces (BCIs, or Human-Machine Interfaces, HMIs), diagnosis of neurological disease, rehabilitation,etc, rely on supervised techniques such as EEG classification that requires given class labels or markers. Incomplete or incorrectly labeled or unlabeled EEG data are increasing with the ever-expanding amount of EEG data generated by such applications and the ambiguities these generate degrade the performance of supervised techniques. To address the challenging task of clustering EEG data with limitedprioriknowledge, we introduce a semi-supervised graph embedding EEG clustering approach termedConsEEGcwith multiple constraints,i.e., label-transformed connectivity constraints that constrains the connection or disconnection among EEG data, compactness-and-scatter constraint that constrains the intra-cluster compactness and inter-cluster scatter of EEG clusters, and fairness constraint that constrains the fair ratio of elements between EEG clusters, to make best use of limitedprioriknowledge of EEG data and to achieve better EEG clustering results.ConsEEGcis conducted with an optimization objective function that integrates pseudo label learning, least-square error minimization and multiple constraints, and it can quickly converge to local optima. The experiments demonstrate thatConsEEGccan efficiently yield good clustering results on various types of real-world EEG datasets, compared to state-of-the-art standard unsupervised and semi-supervised EEG/time series clustering algorithms.

Recently, graph convolutional network (GCN) has drawn increasing attention in hyperspectral image (HSI) classification, as it can process arbitrary non-Euclidean data. However, dynamic GCN that refines the graph heavily relies on the graph embedding in the previous layer, which will result in performance degradation when the embedding contains noise. In this letter, we propose a novel dual residual graph convolutional network (DRGCN) for HSI classification that integrates two adjacency matrices of dual GCN. In detail, one GCN applies a soft adjacency matrix to extract spatial features, whereas the other utilizes the dynamic adjacency matrix to extract global context-aware features. Subsequently, the features extracted by dual GCN are fused to make full use of the complementary and correlated information among two graph representations. Moreover, we introduce residual learning to optimize graph convolutional layers during the training process, to alleviate the over-smoothing problem. The advantage of dual GCN is that it can extract robust and discriminative features from HSIs. Extensive experiments on four HSI datasets, including Indian Pines, Pavia University, Salinas, and Houston University, demonstrate the effectiveness and superiority of our proposed DRGCN, even with small-sized training data.

Recently, graph convolutional network (GCN) has been applied for hyperspectral image (HSI) classification and obtained better performance. The main issue in HSI classification is that the high-resolution HSI contains more complex spectral-spatial structure information. However, the previous GCN-based methods applied in HSI classification only adopted a shallow GCN layer and they can not extract the deeper discriminative features. In addition, these methods ignored the complementary and correlated information among multi-order neighboring information extracted by multiple GCN layers. In this letter, a novel feature fusion via deep residual graph convolutional network is proposed to explore the internal relationship among HSI data. On the one hand, benefiting from residual learning to alleviate the over-smoothing problem, we can construct deep GCN layers to excavate deeper abstract features of HSI. On the other hand, we fuse the outputs of different GCN layers, and thus, the local structural information within multi-order neighborhood nodes can be fully utilized. Extensive experiments on four real HSI data sets, including Indian Pines, Pavia University, Salinas, and Houston University, demonstrate the superiority of the proposed method compared with other state-of-the-art methods in various evaluation criteria.

Brain electroencephalography (EEG), the complex, weak, multivariate, nonlinear, and nonstationary time series, has been recently widely applied in neurocognitive disorder diagnoses and brain-machine interface developments. With its specific features, unlabeled EEG is not well addressed by conventional unsupervised time-series learning methods. In this article, we handle the problem of unlabeled EEG time-series clustering and propose a novel EEG clustering algorithm, that we call mwcEEGc. The idea is to map the EEG clustering to the maximum-weight clique (MWC) searching in an improved Fréchet similarity-weighted EEG graph. The mwcEEGc considers the weights of both vertices and edges in the constructed EEG graph and clusters EEG based on their similarity weights instead of calculating the cluster centroids. To the best of our knowledge, it is the first attempt to cluster unlabeled EEG trials using MWC searching. The mwcEEGc achieves high-quality clusters with respect to intracluster compactness as well as intercluster scatter. We demonstrate the superiority of mwcEEGc over ten state-of-the-art unsupervised learning/clustering approaches by conducting detailed experimentations with the standard clustering validity criteria on 14 real-world brain EEG datasets. We also present that mwcEEGc satisfies the theoretical properties of clustering, such as richness, consistency, and order independence.

Currently, electroencephalogram (EEG) is mostly analyzed in a supervised way, which requires EEG labels (e.g., EEG classification). With the ever-increasing amount of unlabeled/mislabeled EEG in neuropsychiatric disorder diagnosis, BCI, and rehabilitation, manually labeling of EEG data is a labor intensive and time-consuming process, and few labs have developed algorithms to analyze EEG in an unsupervised manner (i.e., EEG clustering). In this paper, we propose a cooperative game inspired approach to cluster multi-trial EEG data. The idea is to map multi-trial EEG clustering to the coalition formation in a cooperative game, and then identify cluster center (the EEG trial with highest Shapley value) and assign EEG trials into proper clusters based on their cross correlation-transformed Shapley values. We demonstrate the mapped EEG cooperative game is convex, and it leads to an algorithm for multi-trial EEG clustering named CoGEEGc. The CoGEEGc yields high-quality multi-trial EEG clustering with respect to intra-cluster compactness and inter-cluster scatter. We show that CoGEEGc outperforms 15 state-of-the-art EEG or time series clustering approaches through detailed experimentation on real-world multi-trial EEG datasets. Comparison against 15 methods with four theoretical properties of clustering further illustrates the superiority of CoGEEGc, as it satisfies two properties while other approaches only satisfy one.

This article proposes an approach to select EEG channels based on EEG shapelet transformation, aiming to reduce the setup time and inconvenience for subjects and to improve the applicable performance of Brain-Computer Interfaces (BCIs). In detail, the method selects top- k EEG channels by solving a logistic loss-embedded minimization problem with respect to EEG shapelet learning, hyperplane learning, and EEG channel weight learning simultaneously. Especially, to learn distinguished EEG shapelets for weighting contributions of each EEG channel to the logistic loss, EEG shapelet similarity is also minimized during the procedure. Furthermore, the gradient descent strategy is adopted in the article to solve the non-convex optimization problem, which finally leads to the algorithm termed StEEGCS. In a result, classification accuracy, with those EEG channels selected by StEEGCS, is improved compared to that with all EEG channels, and classification time consumption is reduced as well. Additionally, the comparisons with several state-of-the-art EEG channel selection methods on several real-world EEG datasets also demonstrate the efficacy and superiority of StEEGCS.

This article explores valid brain electroencephalography (EEG) selection for EEG classification with different classifiers, which has been rarely addressed in previous studies and is mostly ignored by existing EEG processing methods and applications. Importantly, traditional selection methods are not able to select valid EEG signals for different classifiers. This article focuses on a source control-based valid EEG selection to reduce the impact of invalid EEG signals and aims to improve EEG-based classification performance for different classifiers. We propose a novel centroid-based EEG selection approach named CenEEGs, which uses a scale-and-shift-invariance similarity metric to measure similarities of EEG signals and then applies a globally optimal centroid strategy to select valid EEG signals with respect to a similarity threshold. A detailed comparison with several state-of-the-art time series selection methods by using standard criteria on 8 EEG datasets demonstrates the efficacy and superiority of CenEEGs for different classifiers.

Brain Electroencephalography (EEG) classification is widely applied to analyze cerebral diseases in recent years. Unfortunately, invalid/noisy EEGs degrade the diagnosis performance and most previously developed methods ignore the necessity of EEG selection for classification. To this end, this paper proposes a novel maximum weight clique-based EEG selection approach, named mwcEEGs, to map EEG selection to searching maximum similarity-weighted cliques from an improved Fréchet distance-weighted undirected EEG graph simultaneously considering edge weights and vertex weights. Our mwcEEGs improves the classification performance by selecting intra-clique pairwise similar and inter-clique discriminative EEGs with similarity threshold δ. Experimental results demonstrate the algorithm effectiveness compared with the state-of-the-art time series selection algorithms on real-world EEG datasets.