MAGdb: a comprehensive high quality MAGs repository for exploring microbial metagenome-assemble genomes.

Metagenomic analyses of microbial communities have unveiled a substantial level of interspecies and intraspecies genetic diversity by reconstructing metagenome-assembled genomes (MAGs). The MAG database (MAGdb) boasts an impressive collection of 74 representative research papers, spanning clinical, environmental, and animal categories and comprising 13,702 paired-end run accessions of metagenomic sequencing and 99,672 high quality MAGs with manually curated metadata. MAGdb provides a user-friendly interface that users can browse, search, and download MAGs and their corresponding metadata information.

Advanced multimodal for Segmentation and Classification of breast cancer with DenseNet and Optimal Attention approach.

Background And Objective: The early detection of breast cancer plays a critical role in improving survival rates and facilitating precise medical interventions. Therefore, the automated identification of breast abnormalities becomes paramount, significantly enhancing the prospects of successful treatment outcomes. To address this imperative, our research leverages multiple modalities such as MRI, CT, and mammography to detect and screen for breast cancer.

A Nasal Resistance Measurement System Based on Multi-Sensor Fusion of Pressure and Flow.

Nasal obstruction is a common symptom of nasal conditions, with nasal resistance being a crucial physiological indicator for assessing severity. However, traditional rhinomanometry faces challenges with interference, limited automation, and unstable measurement results. To address these issues, this research designed a nasal resistance measurement system based on multi-sensor fusion of pressure and flow.

YOLO-FFRD: Dynamic Small-Scale Pedestrian Detection Algorithm Based on Feature Fusion and Rediffusion Structure.

To address the challenges of detecting dynamic small targets such as pedestrians in complex dynamic environments for mobile robots, this paper proposes a dynamic small-target detection algorithm based on feature fusion and rediffusion structure, which is suitable for deployment on mobile robot platforms. Mobile robots can utilize depth camera information to identify and avoid small targets like pedestrians and vehicles in complex environments. Traditional deep learning-based object detection algorithms perform poorly when applied to the field of mobile robotics, especially in detecting dynamic small targets.

A Hyperbolic Graph Neural Network Model with Contrastive Learning for Rating-Review Recommendation.

In recommender systems research, the data sparsity problem has driven the development of hybrid recommendation algorithms integrating multimodal information and the application of graph neural networks (GNNs). However, conventional GNNs relying on homogeneous Euclidean embeddings fail to effectively model the non-Euclidean geometric manifold structures prevalent in real-world scenarios, consequently constraining the representation capacity for heterogeneous interaction patterns and compromising recommendation accuracy. As a consequence, the representation capability for heterogeneous interaction patterns is restricted, thereby affecting the overall representational power and recommendation accuracy of the models.

A Multi-Branch Network for Integrating Spatial, Spectral, and Temporal Features in Motor Imagery EEG Classification.

: Efficient decoding of motor imagery (MI) electroencephalogram (EEG) signals is essential for the precise control and practical deployment of brain-computer interface (BCI) systems. Owing to the complex nonlinear characteristics of EEG signals across spatial, spectral, and temporal dimensions, efficiently extracting multidimensional discriminative features remains a key challenge to improving MI-EEG decoding performance. : To address the challenge of capturing complex spatial, spectral, and temporal features in MI-EEG signals, this study proposes a multi-branch deep neural network, which jointly models these dimensions to enhance classification performance.

Neurodevelopmentally rooted epicenters in schizophrenia: sensorimotor-association spatial axis of cortical thickness alterations.

Pathological disturbances in schizophrenia have been suggested to propagate via the functional and structural connectome across the lifespan. However, how the connectome guides early cortical reorganization of developing schizophrenia remains unknown. Here, we used early-onset schizophrenia (EOS) as a neurodevelopmental disease model to investigate putative early pathologic origins propagating through the functional and structural connectome.

Multi-site brain disease identification based on tensor decomposition and personalized federated learning.

Brain diseases significantly impact physical and mental health, making the development of models to identify biomarkers for early diagnosis essential. However, building high-quality models typically relies on large-scale datasets, while the privacy-sensitive nature of medical data often restricts its sharing and utilization. Multi-site studies provide a potential solution by integrating data from various sources, yet existing methods frequently neglect site-specific private features, such as demographic information.

Multi-axis compression fusion network for vehicle re-identification.

Vehicle re-identification (Re-ID) has become a challenging retrieval task due to the high inter-class similarity and low intra-class similarity among vehicles. To address this challenge, the self-attention mechanism has been extensively studied and applied, demonstrating its effectiveness in capturing long-range dependencies in vehicle Re-ID. Traditional spatial self-attention and channel self-attention assign different weights to each node (position/channel) based on pairwise dependencies at a global scale to model long-term dependencies, but this approach is not only computationally complex but also unable to fully mine refined features.

Research on deep learning model for stock prediction by integrating frequency domain and time series features.

In the field of financial technology, stock prediction has become a popular research direction due to its high volatility and uncertainty. Most existing models can only process single temporal features, failing to capture multi-scale temporal patterns and latent cyclical components embedded in price fluctuations, while also neglecting the interactions between different stocks-resulting in predictions that lack accuracy and stability. The StockMixer with ATFNet model proposed in this paper integrates both time-domain and frequency-domain features.

Automated detection of diabetic retinopathy lesions in ultra-widefield fundus images using an attention-augmented YOLOv8 framework.

Objective: To enhance the automatic detection precision of diabetic retinopathy (DR) lesions, this study introduces an improved YOLOv8 model specifically designed for the precise identification of DR lesions.

Method: This study integrated two attention mechanisms, convolutional exponential moving average (convEMA) and convolutional simple attention module (convSimAM), into the backbone of the YOLOv8 model. A dataset consisting of 3,388 ultra-widefield (UWF) fundus images obtained from patients with DR, each with a resolution of 2,600 × 2048 pixels, was utilized for both training and testing purposes.

A special machine for solving NP-complete problems.

A specialized computer named as the Electronic Probe Computer (EPC) has been developed to address large-scale NP-complete problems. The EPC employs a hybrid serial/parallel computational model, structured around four main subsystems: a converting system, an input/output system, and an operating system. The converting system is a software component that transforms the target problem into the graph coloring problem, while the operating system is designed to solve these graph coloring challenges.

Distinct roles of claws and adhesive pads in honey bees determine their adhesive performance under varying surface roughness conditions through a dual-mode synergistic adhesion mechanism.

Surface roughness is a critical factor that affects surface adhesion in bees. Investigating the mechanisms underlying surface adhesion in bees on substrates with varying surface roughness levels provides a theoretical basis for designing bioinspired adhesives and micro-climbing robots. In this study, a specialized adhesion measurement device was developed to compare the adhesive forces applied on substrates with different roughness levels by intact bees and by those whose adhesive pads have been removed.

A Simple Method to Prepare a Bioinspired Fog Collection System Combined with Wettability Patterns and Slippery Liquid Infused Porous Surfaces.

Freshwater shortage is a growing problem, and inspired by the ultrafast directional water transport structure of the Sarracenia trichomes and the excellent lubrication effect of SLIPS, bionic hierarchical structured surfaces with wettability patterns were prepared based on laser processing combined with dip and oil-infused modification. The prepared surfaces were tested for sliding performance, water impact, corrosion resistance, and fog collection, and the relationships between the surface structure, wettability, sliding properties, and droplet directional condensation, coalescence, absorption, and directional water transport, as well as their influences on the fog collection performance, were investigated by analyzing the fog collection process. In addition, the optimization direction of surfaces with wettability patterns to alleviate water collection obstacles and improve fog collection efficiency is given.

Sign language recognition based on dual-channel star-attention convolutional neural network.

To enhance effective communication between individuals with hearing impairments and those without, numerous researchers have developed a variety of sign language recognition technologies. However, in practical applications, sign language recognition devices must balance portability, energy consumption, cost, and user comfort, while vision-based sign language recognition must confront the challenge of model stability. Addressing these challenges, this study proposes an economical and stable dual-channel star-attention convolutional neural network (SACNN) deep learning network model based on computer vision technology.

In Silico Discovery and Sensory Validation of Umami Peptides in Fermented Sausages: A Study Integrating Deep Learning and Molecular Modeling.

Deep learning has great potential in the field of functional peptide prediction. This study combines metagenomics and deep learning to efficiently discover potential umami peptides in fermented sausages. A candidate peptide library was generated using metagenomic data from fermented sausages, an integrated deep learning model was constructed for prediction, and SHAP (SHapley Additive exPlanations) interpretability analysis was performed to elucidate the key amino acid features and contributions of the model in predicting umami peptides, screening the top ten peptides with the highest predicted probability.

Accelerated computation for 2D isogeometric acoustic model with ground reflection by integrating Taylor expansion and deep neural network.

This article provides a method that combines Taylor expansion and neural network technology to accelerate the solution of an isogeometric acoustic model with ground reflection. The Helmholtz equation for the acoustic problem is solved by the boundary element method (BEM), and the model structure shape is optimized by combining the isogeometric method. In addition, to mitigate the high computational cost arising from repeated evaluations at each discrete frequency point, the Hankel function is approximated via a Taylor series expansion.

Frame topology fusion-based hierarchical graph convolution for automatic assessment of physical rehabilitation exercises.

Stroke rehabilitation movements are significantly influenced by patient subjectivity, leading to challenges in capturing subtle differences and temporal characteristics of patient motions. Existing methods typically focus on adjacent joint movements, overlooking the intricate interdependencies among body joints. Moreover, they lack the capacity to assess motion quality based on diverse temporal characteristics.

Multi-scale spatio-temporal graph neural network for urban traffic flow prediction.

The Urban traffic flow is affected by both internal supply and demand changes and external random disturbances, and during its continuous spatiotemporal propagation, these factors overlap with each other, presenting a highly non-linear and complex spatiotemporal pattern, which poses a huge challenge to traffic flow prediction. In response to the above challenges, this paper proposes a novel Spatio-Temporal Graph neural network with Multi-timeScale (abbreviated as STGMS). In STGMS, a multi-timescale feature decomposition strategy was designed to decompose the traffic flow into signals at multiple timescales and residuals.

A Fluorescent Covalent Organic Framework NH Sensor with Femtomolar Limit-of-Detection by Facilitated Cis-to-Trans Isomerization.

Fluorescence sensing materials, especially for simple and robust chemical sensors that do not require the use of fragile enzymes while preserving excellent sensitivity and selectivity parallel to bioprobes, have been the focus of research due to their extreme convenience. However, it still remains challenging to detect analytes at femtomolar concentration levels using nonenzymatic chemical fluorescence materials because, so far, they have been limited to stoichiometric ligand-to-analyte response mechanisms. Herein, we report a completely novel fluorescence enhancement sensing approach in which a very small number of targeted analytes can trigger a domino cis-to-trans isomerization of a partially emitting covalent organic framework (COF), leading to fluorescence expansion throughout the material.

A Multi-Scale attention network for building extraction from high-resolution remote sensing images.

The information in remote sensing images often leads to incomplete building contours and suboptimal adaptability to complex building scenes. To address these issues, we propose a novel multi-scale network with dual attention mechanisms to extract clear building boundaries. The Squeeze-and-Excitation (SE) module is employed to bolster feature extraction, and the Atrous Spatial Pyramid Pooling (ASPP) module is integrated to capture multi-scale feature information.

A food safety targeted sampling decision-making method based on association rule mining and GNNs.

To solve the problem of subjectivity and low targeting of task-assigned food safety sampling, in this study, a targeted sampling decision-making method for food safety was proposed. First, a food decision-making factor reasoning module based on association analysis was constructed. An improved frequent pattern growth algorithm with constraints was used to mine food factor association rules based on decision-making factors.

Automated underwater plectropomus leopardus phenotype measurement through cylinder.

Accurate and non-invasive measurement of fish phenotypic characteristics in underwater environments is crucial for advancing aquaculture. Traditional manual methods require significant labor to anesthetize and capture fish, which not only raises ethical concerns but also risks causing injury to the animals. Alternative hardware-based approaches, such as acoustic technology and active structured light techniques, are often costly and may suffer from limited measurement accuracy.

Lateral connection convolutional neural networks for obstructive sleep apnea hypopnea classification.

Despite the successful operation of convolutional neural networks (CNN) with obstructive sleep apnea hypopnea (OSAHS) classification, the interpretability of these models is poor. The limited capacity to understand models hinders the comprehension of end-users, including sleep specialists. At the same time, these models need labeled data; however, this is a time-consuming, labor-intensive, and costly process.