Sentiment analysis with echo state network and augmented water cycle algorithm.

Sentiment analysis using machine learning has become increasingly popular and has received considerable attention in recent years. The sentiment analysis is a critical and challenging task, which require networks with high accuracy. This study utilized the IMDb movie reviews dataset, which comprises 50,000 English reviews (25,000 designated for training and 25,000 for testing) with an equal distribution of positive and negative classes.

Joint Extraction of Cyber Threat Intelligence Entity Relationships Based on a Parallel Ensemble Prediction Model.

The construction of knowledge graphs in cyber threat intelligence (CTI) critically relies on automated entity-relation extraction. However, sequence tagging-based methods for joint entity-relation extraction are affected by the order-dependency problem. As a result, overlapping relations are handled ineffectively.

Dynamic-Attentive Pooling Networks: A Hybrid Lightweight Deep Model for Lung Cancer Classification.

Lung cancer is one of the leading causes of cancer-related mortality worldwide. The diagnosis of this disease remains a challenge due to the subtle and ambiguous nature of early-stage symptoms and imaging findings. Deep learning approaches, specifically Convolutional Neural Networks (CNNs), have significantly advanced medical image analysis.

A Vision Method for Detecting Citrus Separation Lines Using Line-Structured Light.

The detection of citrus separation lines is a crucial step in the citrus processing industry. Inspired by the achievements of line-structured light technology in surface defect detection, this paper proposes a method for detecting citrus separation lines based on line-structured light. Firstly, a gamma-corrected Otsu method is employed to extract the laser stripe region from the image.

Hybrid Algorithms Based on Two Evolutionary Computations for Image Classification.

Convolutional neural networks (CNNs) and their improved models (like DenseNet-121) have achieved significant results in image classification tasks. However, the performance of these models is still constrained by issues such as hyperparameter optimization and gradient vanishing and exploding. Owing to their unique exploration and exploitation capabilities, evolutionary algorithms offer new avenues for addressing these problems.

Design and Experimental Validation of a Multimodal Snake Robot with Elliptical Wheels.

Snake robots are characterized by their flexibility and environmental adaptability, achieved through various optimized gaits. However, their forward propulsion still requires improvement. This challenge can be addressed by integrating wheels or legs, but these mechanisms often limit the ability of snake robots to perform most optimized gaits.

A Hybrid Ensemble Equilibrium Optimizer Gene Selection Algorithm for Microarray Data.

As modern medical technology advances, the utilization of gene expression data has proliferated across diverse domains, particularly in cancer diagnosis and prognosis monitoring. However, gene expression data is often characterized by high dimensionality and a prevalence of redundant and noisy information, prompting the need for effective strategies to mitigate issues like the curse of dimensionality and overfitting. This study introduces a novel hybrid ensemble equilibrium optimizer gene selection algorithm in response.

A two stage multi object tracking algorithm with transformer and attention mechanism.

In the field of engineering safety, multi-object tracking encounters difficulties in effectively conducting object detection due to occlusion, as well as the issue of experiencing frequent switching of target identity ID switches (IDs). In response to the issues above, this paper proposes a multi-object tracking model that integrates improved You Only Look Once Version 8 (YOLOv8) and High-Performance Multi-Object Tracking by Tracking Bytes (ByteTrack). The model architecture is based on the paradigm of tracking-by-detection.

AI-Enabled Parallel Assembly of Thousands of Defect-Free Neutral Atom Arrays.

Assembling increasingly larger-scale defect-free optical-tweezer-trapped atom arrays is essential for quantum computation and quantum simulations based on atoms. Here, we propose an AI-enabled, rapid, constant-time-overhead rearrangement protocol, and we experimentally assemble defect-free 2D and 3D atom arrays with up to 2024 atoms with a constant-time cost of 60 ms. The AI model calculates the holograms for real-time atom rearrangement.

Breast Cancer Diagnosis Using a Dual-Modality Complementary Deep Learning Network With Integrated Attention Mechanism Fusion of B-Mode Ultrasound and Shear Wave Elastography.

Objective: To develop and evaluate a Dual-modality Complementary Feature Attention Network (DCFAN) that integrates spatial and stiffness information from B-mode ultrasound and shear wave elastography (SWE) for improved breast tumor classification and axillary lymph node (ALN) metastasis prediction.

Methods: A total of 387 paired B-mode and SWE images from 218 patients were retrospectively analyzed. The proposed DCFAN incorporates attention mechanisms to effectively fuse structural features from B-mode ultrasound with stiffness features from SWE.

Learning instrumental variable representation for debiasing in recommender systems.

Recommender systems are essential for filtering content to match user preferences. However, traditional recommender systems often suffer from biases inherent in the data, such as popularity bias. These biases, particularly those stemming from latent confounders, can result in inaccurate recommendations and reduce both the diversity and effectiveness of the system.

Survival prediction models for people living with HIV based on four machine learning models.

Although antiretroviral therapy has prolonged the lifespan of people living with HIV, significant variations still exist in survival rates and risk factors among these people. This study compares the performance of the Cox proportional hazard models with four machine learning models in predicting the survival of people living with HIV, analyzing the survival factors among them, thereby assisting medical decision-making. We collected data on 676 people living with HIV from the Chinese Center for Disease Control and Prevention.

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.

Research progress in deep learning-based fundus image analysis for the diagnosis and prediction of hypertension-related diseases.

Hypertension-related diseases have widespread effects on the systemic microvasculature, with particularly significant impacts on the retinal vascular system. As a non-invasive window to observe vascular abnormalities, fundus imaging plays an important role in the diagnosis and prediction of hypertension-related conditions. In recent years, deep learning (DL) has rapidly advanced in the field of color fundus photography (CFP) analysis, demonstrating strong potential in vessel segmentation, artery/vein classification, lesion detection, and systemic disease prediction.

MetaMBP: Few-Shot Multilabel Prediction of Bioactive Peptides Based on Deep Metric Meta-Learning.

Bioactive peptides are highly specific and have low toxicity, making them a promising treatment option. There are many different types of bioactive peptides, while some types have limited samples (under 500). Methods that can handle limited types of bioactive peptides are needed to enhance the predictive ability of multilabel tasks with few sample categories.

Advancing electrocardiogram synthesis: Analyzing key metrics for enhanced evaluation.

The development of large, high-quality ECG datasets is essential for advancing automated cardiac disease diagnosis. However, challenges such as limited access to data, small dataset sizes, and class imbalances persist. Deep generative models offer an effective solution by generating synthetic ECG data, which not only addresses data scarcity but also enhances data privacy.

Prediction of Human Pathogenic Start Loss Variants Based on Multi-channel Features.

Start loss variants occur at the start codon that can disrupt the normal translation initiation process, potentially resulting in the production of abnormal protein isoforms. Although numerous computational methods have been developed to aid in the large-scale interpretation of genetic variants, they often show limited predictive accuracy for start-loss variants. A significant limitation of the majority of these methods is their dependence on manually curated features, which restricts their ability to predict variants that have not been studied and characterized.

BiSeNeXt: a yam leaf and disease segmentation method based on an improved BiSeNetV2 in complex scenes.

Introduction: Yam is an important medicinal and edible crop, but its quality and yield are greatly affected by leaf diseases. Currently, research on yam leaf disease segmentation remains unexplored. Challenges like leaf overlapping, uneven lighting and irregular disease spots in complex environments limit segmentation accuracy.

MANet: multi-attention network for polyp segmentation.

Currently, colonoscopy stands as the most efficient approach for detecting colorectal polyps. In clinical diagnosis, colorectal cancer is closely related to colorectal polyps. Therefore, precise segmentation of polyps holds paramount importance for the early detection and clinical diagnosis of colorectal cancer.

Graph neural network-based drug-drug interaction prediction.

With the growing variety of pharmacological compounds and the increasing need for polypharmacy, accurately predicting drug-drug interactions (DDIs) is essential to ensure both treatment efficacy and patient safety. Beneficial DDIs can enhance therapeutic outcomes. In contrast, adverse interactions may result in toxicity, reduced efficacy, or even fatality.

LABind: identifying protein binding ligand-aware sites via learning interactions between ligand and protein.

Protein-ligand interactions are crucial for understanding various biological processes and drug discovery and design. However, experimental methods are costly; single-ligand-oriented methods are tailored to specific ligands; multi-ligand-oriented methods are constrained by the lack of ligand encoding. In this study, we propose a structure-based method called LABind, designed to predict binding sites for small molecules and ions in a ligand-aware manner.

A network recovery strategy based on boundary nodes and tetrahedral approximation fermat points in three-dimensional wireless sensor networks.

Wireless Sensor Networks (WSNs) have emerged as a critical research frontier in the Internet of Things (IoT) domain, with widespread applications in three-dimensional environments. However, due to harsh environments (such as high temperature, high pressure, etc.), natural disasters (such as earthquakes, etc.

Temporal evolution of intralayer synchronizability in multiplex hypergraphs.

In practical applications, complex networks often model scenarios involving higher-order relationships, for which hypergraphs offer a suitable representation. This paper introduces synchronizability metrics to study the synchronization of a temporal two-layer multiplex hypergraph, where temporal characteristics are captured by time-evolving incidence matrix. By transforming hyperedges into maximal cliques, we construct a temporally evolving weighted network that reproduces the dynamics on the hypergraph under simple structure and symmetric coupling.

Reg2ST: recognizing potential patterns from gene expression for spatial transcriptomics prediction.

Spatial transcriptomics is able to acquire cellular gene expression while retaining spatial location. It is often accompanied by matched hematoxylin and eosin-stained histology whole-slide images. This retention of spatial information is critical for studying key issues in cell biology, developmental biology, neurobiology, and tumor biology.