Brain functional connectivity networks (FCNs) derived from resting-state functional magnetic resonance imaging (rs-fMRI) data have been widely used to identify altered brain network patterns in attention-deficit/hyperactivity disorder (ADHD). Current graph neural network (GNN) approaches using FCNs predominantly emphasize node features while underutilizing edge information. Moreover, these GNN-based methods also inadequately represent dynamic interdependencies among evolving node features across network layers, limiting their diagnostic performance. We present a graph convolutional network via joint feature learning between nodes and edges (JNEL-GCN) that integrates neuroimaging features for ADHD classification and biomarker discovery. Our framework constructs dual graph representations: 1) a node graph using amplitude of low-frequency fluctuations (ALFF) measures across multiple frequency bands as nodal features, along with functional connectivity (FC) and node feature relationship matrices as edge attributes; and 2) an edge graph derived through line graph theory, enabling the interchange of node and edge roles. By leveraging the dual-graph design, our model implements an alternating feature update mechanism with optimized graph convolution operations, facilitating feature hierarchical learning of node-edge relationships across network layers. Extensive experiments demonstrate remarkable performance, achieving 97.3% accuracy on ADHD200 and 97.1% on ABIDE-I datasets, significantly outperforming current benchmarks. Meanwhile, gradient-based biomarker analysis identifies significant regions in bilateral limbic and default mode networks associated with ADHD, aligning with the findings in existing literature. Therefore, this dual-graph approach advances neuroimaging-based diagnosis by comprehensively capturing dynamic network interactions, while providing interpretable biomarkers for clinical neuroscience applications.

Large language models (LLMs), representing a breakthrough advancement in artificial intelligence, have demonstrated substantial application value and development potential in bioinformatics research, particularly showing significant progress in the processing and analysis of complex biological data. This comprehensive review systematically examines the development and applications of LLMs in bioinformatics, with particular emphasis on their advancements in protein and nucleic acid structure prediction, omics analysis, drug design and screening, and biomedical literature mining. This work highlights the distinctive capabilities of LLMs in end-to-end learning and knowledge transfer paradigms. Additionally, this paper thoroughly discusses the major challenges confronting LLMs in current applications, including key issues such as model interpretability and data bias. Furthermore, this review comprehensively explores the potential of LLMs in cross-modal learning and interdisciplinary development. In conclusion, this paper aims to systematically summarize the current research status of LLMs in bioinformatics, objectively evaluate their advantages and limitations, and provide insights and recommendations for future research directions, thereby positioning LLMs as essential tools in bioinformatics research and fostering innovative developments in the biomedical field.

In motor imagery (MI) tasks for brain computer interfaces (BCIs), the spatial covariance matrix (SCM) of electroencephalogram (EEG) signals plays a critical role in accurate classification. Given that SCMs are symmetric positive definite (SPD), Riemannian geometry is widely utilized to extract classification features. However, calculating distances between SCMs is computationally intensive due to operations like eigenvalue decomposition, and classical optimization techniques, such as gradient descent, cannot be directly applied to Riemannian manifolds, making the computation of the Riemannian mean more complex and reliant on iterative methods or approximations. In this paper, we propose a novel multiclass classification framework that integrates Riemannian geometry and neural networks to mitigate these challenges. The framework comprises two modules: a Riemannian module with multiple branches and a classification module. During training, a fusion loss function is introduced to update the branch corresponding to the true label, while other branches are updated using different loss functions along with the classification module. Comprehensive experiments on four sets of MI EEG data demonstrate the efficiency and effectiveness of the proposed model.

In this study, we apply a graph convolutional network (GCN) in attention deficit hyperactivity disorder (ADHD) classification by using multimodal data. Here, multimodal data is integrated to construct a dual graph for leveraging the modality information. Then, a GCN learning model is performed within an existing binary hypothesis testing (BHT) framework to fulfill the classification task. To preserve specifical topological structure of dual graph, we propose a graph-based feature selection approach to choose typical data (nodes) on the graphs. With these typical data, we design our GCN model, effectively learning the high-level features for identifying ADHD subjects. The experiments show the average accuracy of our method reaches 95.2% on various ADHD-200 datasets. Importantly, this result is achieved only on the right limbic system rather than the whole brain. The limited brain regions used indicate their potential ability as biomarkers. Moreover, biomarkers are found with their special topological structures. On the Peking University dataset, the found biomarkers center around the hippocampus and parahippocampal gyri, which are highly correlated with ADHD disease. Differing from isolated biomarker findings in traditional methods, our method discloses the abnormal circuit for ADHD and is more meaningful for further learning ADHD mechanism.

This paper introduces a novel joint spatio-temporal filtering algorithm and investigate its impact on data alignment in transfer learning (TL) for motion imagery (MI) tasks to deal with the variability in subjects, trials, or tasks. While spatial filtering is an integral part of the common spatial pattern (CSP) algorithm, temporal filtering is introduced to deal with EEG signals of each channel. The proposed algorithm jointly optimizes the coefficients and the subsequent alignment of covariance matrices. Experimental results on various public datasets validate the effectiveness of our proposed algorithm.

Point cloud segmentation plays a crucial role in extracting unique attributes and separating various objects, thereby enabling semantic comprehension and analysis. In this paper, we introduce a novel point cloud segmentation approach based on Diffusion Probabilistic Network (DDPM). The proposed model treats points as particles undergoing diffusion towards a noise distribution, and a reverse diffusion process transforms this noise distribution into the desired shape. Leveraging a Markov diffusion model in the reverse process enables generating point clouds with more refined and specific topological structures. After the diffusion step, multi-scale sampled features are fused to enhance the discriminative representation of 3D shapes. Objective and subjective experimental results demonstrate that our segmentation method outperforms state-of-the-art techniques in terms of evaluation metrics.

We propose a subspace-enhanced hypergraph neural network (seHGNN) for classifying anxiety disorder (AD). By leveraging a learnable incidence matrix, seHGNN strengthens the influence of hyperedges in graphs and enhances feature extraction performance of HGNNs. Then, we conduct this model within an existing binary hypothesis testing framework, where multi-modal data on the limbic system is integrated into a hypergraph. Experiments show that the seHGNN achieves a high accuracy of 90.7% for AD classification, surpassing other deep-learning-based methods, especially GNN-based methods. Our seHGNN also successfully identifies discriminative AD biomarkers, consistent with existing reports. This provides strong evidence supporting the effectiveness and interpretability of our proposed method.

Deep learning methods have been widely applied in Attention Deficit Hyperactivity Disorder (ADHD) classification in the past decade due to their effective learned features. However, these features are lack of neurobiological meanings and hard to be biomarkers. Here, we proposed an attention auto-encoding network with triplet loss (Tri-Att-AENet) for both ADHD classification and biomarker identification. Taking brain functional connectivities (FCs) as material, we introduced an attention encoding subnetwork to obtain the weighted FCs with their weights as attention scores. A triplet loss function was further employed on these scores, providing sufficient evidence for biomarker selection. Meanwhile, the weighted FCs became discriminative to pursue a higher accuracy. Experiments show that our method achieves an average accuracy of 99.6% for classification. The selected FC biomarkers are in accord with reported neurobiological results and well fulfill the task of biomarker identification.

In the realm of 3D single object tracking (SOT), Siamese network-based algorithms have shown remarkable performance. However, they can lose track of targets in complex environments. To enhance tracking accuracy and continuity, in this paper we introduce a new re-detection mechanism with a dynamic anchor relocation strategy. This mechanism includes: (i) dynamic anchor generation: When tracking fails, dynamic anchors are generated and adjusted until the target is re-detected. The most confident anchor prediction becomes the tracking result; (ii) model aggregation: A re-detected module is integrated into the PTT-Net framework, significantly improving tracking accuracy compared to other algorithms; (iii) reliability assessment: An assessment criterion for tracking reliability in PTT-Net is established to balance accuracy and speed.

Traffic networks exhibit complex spatial-temporal dependencies, and accurately capturing such dependencies is critical to improving prediction accuracy. Recently, many deep learning models have been proposed for spatial-temporal dependency modeling. While numerous deep learning models have been developed for spatial-temporal dependency modeling, most rely on different types of convolutions to extract spatial and temporal correlations separately. To address this limitation, we propose a novel deep learning framework for traffic prediction called GraphSAGE-based Dynamic Spatial-Temporal Graph Convolutional Network (DST-GraphSAGE), which can capture dynamic spatial and temporal dependencies simultaneously. Our model utilizes a spatial-temporal GraphSAGE module to extract localized spatial-temporal correlations from past observations of a node’s spatial neighbors. Meanwhile, the attention mechanism is incorporated to dynamically learn weights between traffic nodes based on graph features. Additionally, to capture long-term trends in traffic data, we employ dilated causal convolution as the temporal convolution layer. A series of numerical experiments are conducted on five real-world datasets, which demonstrates the effectiveness of our model for spatial-temporal dependency modeling.

Common spatial pattern (CSP) is widely used in motor imagery classification tasks. Classical CSP depends only on spatial filters. To improve its performance, a novel and efficient spatio-temporal filtering strategy is proposed in this paper to extract discriminative features. Common temporal filters are shared among all the spatial channels, so as to reduce the overfitting risk in the case of a small sample size. An efficient alternating optimization algorithm is also developed to optimize coefficients of spatial and temporal filters. To alleviate adverse effects of noise and artifacts and improve implementation efficiency, an ℓ1-norm-based sparsity regularization term is further introduced. The resulting problem is tackled by the reweighting technique. The effectiveness of the proposed algorithm is validated by the experiments using open datasets of BCI Competition.

Attention Deficit Hyperactivity Disorder (ADHD) is a high incidence of neurobehavioral disease in school-age children. Its neurobiological classification is meaningful for clinicians. The existing ADHD classification methods suffer from two problems, i.e., insufficient data and noise disturbance. Here, a high-accuracy classification method is proposed, which uses brain Functional Connectivity (FC) as material for ADHD feature analysis. In detail, we introduce a binary hypothesis testing framework as the classification outline to cope with insufficient data of ADHD database. Under binary hypotheses, the FCs of test data are allowed to use for training and thus affect the subspace learning of training data. To overcome noise disturbance, an l2,1-norm LDA model is adopted to robustly learn ADHD features in subspaces. The subspace energies of training data under binary hypotheses are then calculated, and an energy-based comparison is finally performed to identify ADHD individuals. On the platform of ADHD-200 database, the experiments show our method outperforms other state-of-the-art methods with the significant average accuracy of 97.6%.

In this paper, we develop a novel deep-network architecture for semantic segmentation. In contrast to previous work that widely uses dilated convolutions, we employ the original ResNet as the backbone, and a multi-scale feature fusion module (MFFM) is introduced to extract long-range contextual information and upsample feature maps. Then, a graph reasoning module (GRM) based on graph-convolutional network (GCN) is developed to aggregate semantic information. Our graph reasoning network (GRNet) extracts global contexts of input features by modeling graph reasoning in a single framework. Experimental results demonstrate that our approach provides substantial benefits over a strong baseline and achieves superior segmentation performance on two benchmark datasets.

Because the spectrum folding phenomenon affects the down-sampling of graph signals, both critically sampled and oversampled graph filter banks with down-sampling operations can only be applied to bipartite graphs. However, general graph signals may not reside on bipartite graph structures. In this paper, we present a novel bipartite graph approximation algorithm, which aims to find a bipartite graph sufficiently close to the original graph. To tackle this problem, we first show that, if the non-negativity constraint of adjacency matrices is removed, closed-form solutions can be readily obtained by the eigenvalue decomposition. Based on this fact, an alternating direction method of multipliers (ADMM) is further developed to achieve a real adjacency matrix. Experimental results show that the proposed algorithm outperforms the other proposals in terms of approximation accuracy.

Graph filters are a fundamental tool in the field of graph signal processing. This paper focuses on the design of autoregressive moving average (ARMA) graph filters. In the proposed algorithm, the denominator part of an ARMA graph filter is decomposed as a cascade of a few second-order factors (SOFs) and a higher order factor (HOF), whose coefficients are updated sequentially in each iteration. In the proposed design algorithm, stability constraints are only imposed on the roots of SOFs and coefficients of the HOF are left unconstrained to enhance the design accuracy. Moreover, the number of SOFs can be automatically determined, which is convenient in practical applications. Simulation results demonstrate that the proposed algorithm can achieve higher computational efficiency and also approximation accuracy, compared to the state-of-the-arts of graph filters.

In this paper, we propose a novel sparse common spatial pattern (CSP) algorithm to optimally select channels of EEG signals. Compared to the traditional CSP, which maximizes the variance of signals in one class and minimizes the variance of signals in the other class, the classification accuracy is guaranteed by a constraint that the ratio of variances of signals in two different classes is lower bounded. Then, a sparse spatial filter is achieved by minimizing the l1-norm of filter coefficients and channels of EEG signals can be further optimized. The original nonconvex optimization problem is relaxed to a semidefinite program (SDP), which can be efficiently solved by well-developed numerical solvers. Experimental results demonstrate that the proposed algorithm can identify and discard about 50% channels with only 1% decrease of classification accuracy.

In this paper, a new algorithm is proposed for the design of sparse FIR filters. Traditional l1-optimization-based methods take all the coefficients into l1-norm minimization. However, it is unnecessary since some of them can only take nonzero values to satisfy design specifications. Furthermore, minimizing l1norm of all the coefficients could drive the design results to deviate from the optimal ones. The proposed algorithm aims to identify nonzero coefficients at some crucial positions in each iteration to minimize the number of nonzero coefficients. Simulation results demonstrate that the proposed algorithm can achieve better design results than traditional l1-optimization methods.

This paper presents an interactive training platform of motor learning using movement imitation and synchronous speech instruction. This platform enables a child with autism spectrum disorder (ASD) and a robot to imitate each other. A robot can ask a child to copy its action and instruct human how to adjust his/her action to match its action. A robot can also ask a child to coach it, which is able to elicit children's response to increase their communication. The platform is built up by a NAO humanoid robot that demonstrates actions, and a depth camera that captures child's actions. We scaled the skeleton tracking data in order to evaluate the consistence of actions between human and robot. The pilot tests on both children with and without ASD have shown that our framework is flexible and convenient for assisting intervention, and that the synchronous speech instructions to some extend facilitate children with ASD to perform their actions for motor learning.

In this paper, a novel algorithm is developed for the minimax design of IIR digital filters. Using a partial second-order factorization (PSOF), the denominator polynomial of an IIR digital filter is decomposed as a cascade of second-order factors (SOFs) and a single higher-order factor (HOF). This is inspired by the fact that, when some poles are closer to the boundary of the stability domain, the other poles tend to stay inside the stability domain such that the specified frequency response can be best approximated. By means of the PSOF, stability constraints are only imposed on a limited number of SOFs and, thus, a better design could be attained. The proposed algorithm successively updates SOFs and HOF. To further reduce its computational complexity, the iterative weighted least-squares approach is applied to optimize each SOF or HOF. Simulation results demonstrate that the proposed algorithm can attain the balance between computational efficiency and design accuracy.

A novel stability condition is developed in this paper. It is both necessary and sufficient, which ensures that optimal design cannot be excluded from the admissible solutions. Compared to other necessary and sufficient stability conditions, the proposed one can be expressed as a quadratic constraint in terms of denominator coefficients, which facilitates its combination with other widely used IIR filter design strategies. In this paper, we adopt the Steiglitz-McBride scheme to design IIR filters. In each iteration, an approximation version of the proposed stability condition is further expressed as a set of linear inequality constraints, such that the resulting design problem becomes a quadratic program that can be efficiently and reliably solved. Simulations demonstrate the effectiveness of the proposed stability condition.

In this paper, a sparse approximation algorithm using eigenvectors of the graph Laplacian is proposed for image denoising, in which the eigenvectors of the graph Laplacian of images are incorporated in the sparse model as basis functions. Here, an eigenvector-based sparse approximation problem is presented under a set of residual error constraints. The corresponding relaxed iterative solution is also provided to efficiently solve such problem in the framework of the double sparsity model. Experiments show that the proposed algorithm can achieve a better performance than some state-of-art denoising methods, especially measured with the SSIM index.

A large number of experiments have demonstrated that for an FIR filter the sparsity of filter coefficients is highly related to its filter order. However, traditional sparse FIR filter design methods focus on how to increase the number of zero-valued coefficients, but overlook the impact of filter orders on design performance. As an attempt to jointly optimize filter length and sparsity of an FIR filter, a novel method is proposed in this paper to design sparse linear-phase FIR filters. With peak error constraints, the objective function of the design problem is formulated as a combination of the sparsity of filter coefficients and a measure of the effective filter order. Then, the design problem is then recast as a weighted l0-norm optimization problem, which is solved by an efficient numerical method based on the iterative-reweighted-least-squares (IRLS) algorithms. Experimental results illustrate that the proposed method can efficiently reduce the effective filter order while enhancing the sparsity of an FIR filter.

Sparse representation theory has been well developed in recent years. In this paper, we consider an image denoising problem which can be efficiently solved under the framework of the sparse representation theory. The traditional image denoising methods based on the sparse representation seldom take into account the special structure of the data. As an attempt to overcome such problem, the Graph regularized K-means singular value decomposition (Graph K-SVD) algorithm is proposed with the manifold learning. The local geometrical structure of the image is considered in the sparse optimization model with the graph Laplacian. This manifold-based optimization problem is well solved in the framework of the traditional K-SVD algorithm. Since the novel strategy adds a graph regularizer to the sparse representation model in order to emphasize the correlations among image blocks, the Graph K-SVD can achieve better denoising performance than the traditional K-SVD.

In this paper, we present a novel algorithm to design sparse FIR digital filters in the minimax sense. To tackle the nonconvexity of the design problem, an efficient iterative procedure is developed to find a potential sparsity pattern. In each iteration, a subproblem in a simpler form is constructed. Instead of directly resolving these nonconvex subproblems, we resort to their respective dual problems. It can be proved that under a weak condition, globally optimal solutions of these subproblems can be attained by solving their dual problems. In this case, the overall iterative procedure can converge to a locally optimal solution of the original design problem. The real minimax design can then be achieved by refining the FIR filter obtained by the iterative procedure. The design procedure described above can be repeated for several times to further improve the sparsity of design results. The output of the previous stage can be used as the initial point of the subsequent design. Simulation results demonstrate the effectiveness of our proposed algorithm.

A novel algorithm is presented in this paper to design sparse FIR filters in the weighted least-squares (WLS) sense. The original design problem is cast as a constrained l0-norm optimization problem. To tackle the nonconvexity, an efficient iterative procedure is developed. In each iterative step, a subproblem in a simpler form is constructed. It can be demonstrated that in each iteration an optimal solution to each subproblem can be efficiently and reliably attained by the successive activation algorithm proposed in this paper, such that the overall design algorithm can converge to a local solution of the original design problem. Since its major part only involves scalar operations, compared with other sparse filter design approaches, the proposed design algorithm is computationally efficient. The effectiveness of the proposed design algorithm is demonstrated by numerical examples.

In this paper, a new iterative algorithm is proposed to design IIR digital filters in the minimax sense. Instead of directly minimizing the error limit of the approximation error, the proposed algorithm employs a bisection searching procedure to locate the minimum error limit. At each iteration, a feasibility problem with a given error limit is to be solved, which is constructed by applying the semidefinite programming (SDP) relaxation technique to transform the nonconvex approximation error into a convex form. In practice, however, the truly minimax solution cannot be always obtained by using this iterative procedure. Therefore, a regularization term needs to be incorporated in the objective of the feasibility problem at each iteration. Another bisection searching procedure is then deployed to find the minimum weight utilized in the regularized objective function of the feasibility problem. The stability of designed filters can be guaranteed by a monitoring strategy, which does not need to incorporate any other constraint to the formulation of the feasibility problem. The convergence of the proposed method can be guaranteed. The performances have been demonstrated by filter examples.

A two-stage design method of low-order fixed denominator IIR variable fractional delay (VFD) digital filters is presented in this paper. In the first stage, a set of FIR fractional delay (FD) filters are designed first. Each FIR FD filter design problem is formulated in the peak-constrained weighted least-squares (PCWLS) sense and solved by the projected least-squares (PLS) algorithm. Then, model reduction technique is applied on a time-domain average FIR filter to obtain the fixed denominator. The remaining numerators of the IIR FD filters can be obtained by solving linear equations derived from the orthogonality principle. In the second stage of the design, these FD filter coefficients are to be approximated by polynomial functions of FD. Three sets of filter-examples are given to illustrate the effectiveness of the proposed design method.

An iterative second-order cone programming (SOCP) approach is proposed in this paper. The original nonconvex design problem is first relaxed into an SOCP problem, which can provide a lower bound on the optimal value of the original problem. For reducing the gap between the original and the convex problem, an iterative procedure is developed. The initial point of the iterative procedure can be chosen as the solution obtained from the relaxed SOCP problem. Unlike other iterative approaches, the convergence of the proposed iterative procedure is definitely guaranteed. Design examples demonstrate the effectiveness of the proposed method.

A method for designing IIR digital filters with a novel stability criterion based on the argument principle is proposed in this paper. Unlike the stability criteria used in some design algorithms, this stability condition is both sufficient and necessary. In the paper, the weighted least-squares (WLS) design of IIR filters is first formulated as an iterative quadratic programming (QP) problem without any constraint. Then the stability criterion is incorporated in the quadratic form at each iteration. Two examples are presented to illustrate the effectiveness of the proposed approach.

In this paper, a peak-constrained weighted least-squares (PCWLS) method is presented for designing a general FIR digital filter with constant group delay passband, using the projected least-squares (PLS) algorithm. In the design of a general FIR filter, peak error constraints are nonlinear functions of filter coefficients and can not be accepted by the PLS algorithm. In the proposed method, peak error constraints are formulated, through some approximation, as a set of linear inequalities to be incorporated into the design problem. Design examples show the effectiveness of the peak error control of the proposed method.

In this paper, a novel method for designing IIR variable fractional delay (VFD) digital filters with variable and fixed denominator is presented. First of all, a peak-constrained weighted least-squares (PCWLS) method is employed to design a set of FIR fixed fractional delay (FD) filters according to given specifications. The PCWLS FIR filters are implemented by the projected least-squares (PLS) algorithm. An iterative WLS model reduction technique is utilized to design denominators, which can guarantee the stability of designed IIR VFD filter if the iteration converges. The numerator of IIR fixed FD filters can be designed by two approaches: The Approach 1 solves linear equations based on the orthogonality principle; and the Approach 2 formulates the numerator design problem as a standard quadratic programming (QP) problem. The coefficients of IIR fixed FD filters are finally approximated by polynomial functions of FD. Three sets of examples are given to demonstrate the effectiveness of the proposed method.