Image based fog density estimation.

Although the application of image-based fog density estimation brings excellent convenience and low-cost methods, the accuracy of such methods still needs to be improved, and further research is encouraged on accuracy evaluation methods. To improve the accuracy and computational efficiency of fog density estimation in images, we first construct three image features based on the image dark channel information, the image saturation information, and the proportion of gray noise points, respectively. Then, we use a feature fusion method to estimate fog density in the images.

A Hybrid Security Framework for Train-to-Ground (T2G) Communication Using DOA-Optimized BPNN Detection, Bayesian Risk Scoring, and RL-Based Response.

With the widespread adoption of wireless communication technologies in modern high-speed rail systems, the Train-to-Ground (T2G) communication system for Electric/Diesel Multiple Units (EMU/DMU) has become essential for train operation monitoring and fault diagnosis. However, this system is increasingly vulnerable to various cyber-physical threats, necessitating more intelligent and adaptive security protection mechanisms. This paper presents an intelligent security defense framework that integrates intrusion detection, risk scoring, and response mechanisms to enhance the security and responsiveness of the T2G communication system.

A hybrid security protocol based on honey encryption and hyperchaotic systems for improving security in internet of things.

Communication security in the internet of things (IoT) is essential to prevent devices and data from being vulnerable to cyber-attacks and possible abuses. In IoT systems, some sensors transmit critical data, so maintaining the security of these data and preventing their unauthorized interpretation is of great importance. For this reason, it is necessary to use advanced and complex encryption methods.

Fair ultrasound diagnosis via adversarial protected attribute aware perturbations on latent embeddings.

Deep learning techniques have significantly enhanced the convenience and precision of ultrasound image diagnosis, particularly in the crucial step of lesion segmentation. However, recent studies reveal that both train-from-scratch models and pre-trained models often exhibit performance disparities across sex and age attributes, leading to biased diagnoses for different subgroups. In this paper, we propose APPLE, a novel approach designed to mitigate unfairness without altering the parameters of the base model.

Robust projection parameter calibration in cryo-ET with L-norm optimization.

Fiducial marker-based alignment in cryo-electron tomography (cryo-ET) has been extensively studied over a long period. The calibration of projection parameters using nonlinear least squares technique methodologies stands as the ultimate and pivotal stage in the alignment procedure. The efficacy of calibration is substantially impacted by noise and outliers in the marker data obtained from previous steps.

scCompass: An Integrated Multi-Species scRNA-seq Database for AI-Ready.

Emerging single-cell sequencing technology has generated large amounts of data, allowing analysis of cellular dynamics and gene regulation at the single-cell resolution. Advances in artificial intelligence enhance life sciences research by delivering critical insights and optimizing data analysis processes. However, inconsistent data processing quality and standards remain to be a major challenge.

DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials.

In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks, such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of the DeePMD-kit exemplified these limitations.

3DGR-CT: Sparse-view CT reconstruction with a 3D Gaussian representation.

Sparse-view computed tomography (CT) reduces radiation exposure by acquiring fewer projections, making it a valuable tool in clinical scenarios where low-dose radiation is essential. However, this often results in increased noise and artifacts due to limited data. In this paper we propose a novel 3D Gaussian representation (3DGR) based method for sparse-view CT reconstruction.

Leveraging TME features and multi-omics data with an advanced deep learning framework for improved Cancer survival prediction.

Glioma, a malignant intracranial tumor with high invasiveness and heterogeneity, significantly impacts patient survival. This study integrates multi-omics data to improve prognostic prediction and identify therapeutic targets. Using single-cell data from glioblastoma (GBM) and low-grade glioma (LGG) samples, we identified 55 distinct cell states via the EcoTyper framework, validated for stability and prognostic impact in an independent cohort.

The reconstruction method for static exterior model of digital twin railway station based on mobile vehicle.

Constructing a static exterior model of railway passenger station is a preliminary and crucial step in achieving a digital twin station. Station modeling often relies on manual techniques, requiring significant labor for stations spanning tens of thousands of square meters. While the interior decoration is symmetrical, the asymmetrical placement of equipment often leads to confusion in manual modeling.

Relative importance sampling for off-policy actor-critic in deep reinforcement learning.

Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy (π) and the behavior policy (b) is a major cause of instability. High variance also originates from distributional mismatch.

Stereopy: modeling comparative and spatiotemporal cellular heterogeneity via multi-sample spatial transcriptomics.

Understanding complex biological systems requires tracing cellular dynamic changes across conditions, time, and space. However, integrating multi-sample data in a unified way to explore cellular heterogeneity remains challenging. Here, we present Stereopy, a flexible framework for modeling and dissecting comparative and spatiotemporal patterns in multi-sample spatial transcriptomics with interactive data visualization.

Global Analysis of Protein and Small-Molecule Substrates of Ubiquitin-Like Proteins.

Ubiquitin-like proteins (UBLs) constitute a family of evolutionarily conserved proteins that share similarities with ubiquitin in 3D structures and modification mechanisms. For most UBLs including small-ubiquitin-like modifiers (SUMO), their modification sites on substrate proteins cannot be identified using the mass spectrometry-based method that has been successful for identifying ubiquitination sites, unless a UBL protein is mutated accordingly. To identify UBL modification sites without having to mutate UBL, we have developed a dedicated search engine pLink-UBL on the basis of pLink, a software tool for the identification of cross-linked peptide pairs.

A deep learning model for structure-based bioactivity optimization and its application in the bioactivity optimization of a SARS-CoV-2 main protease inhibitor.

Bioactivity optimization is a crucial and technical task in the early stages of drug discovery, traditionally carried out through iterative substituent optimization, a process that is often both time-consuming and expensive. To address this challenge, we present Pocket-StrMod, a deep-learning model tailored for structure-based bioactivity optimization. Pocket-StrMod employs an autoregressive flow-based architecture, optimizing molecules within a specific protein binding pocket while explicitly incorporating chemical expertise.

Applications of Artificial Intelligence in Food Industry.

With breakthroughs in artificial intelligence (AI) brought by the fourth industrial revolution, intelligent applications are providing innovative solutions across food industry [...

Digital twin system for manufacturing processes based on a multi-layer knowledge graph model.

Digital twin technology in the manufacturing process faces challenges like integrating diverse data sources and managing real-time data flow. To address this, we propose a novel three-layer knowledge graph architecture to enhance digital twin modeling for manufacturing processes. This architecture consists of a concept layer that structures key information into a knowledge network, a model layer that aligns digital and physical parameters, and a decision layer that leverages model and real-time data for decision support.

Predictive model for initial response to first-line treatment in children with infantile epileptic spasms syndrome.

Background: Previous studies have suggested that factors such as the treatment interval and aetiology may influence the initial response rate to first-line treatment for infantile epileptic spasms syndrome (IESS). However, few children with IECSS have undergone clinically accessible tests to determine the aetiology.

Methods: Using a dataset from our previously published research, we constructed and tested a predictive model for the initial response to first-line treatment in children with IESS.

Bridging the Gap between Transformer-Based Neural Networks and Tensor Networks for Quantum Chemistry.

The neural network quantum state (NNQS) method has demonstrated promising results in quantum chemistry, achieving remarkable accuracy in molecular systems. However, efficient calculation of systems with large active spaces remains challenging. This study introduces a novel approach that bridges tensor network states with the transformer-based NNQS-Transformer (QiankunNet) to enhance accuracy and convergence for systems with relatively large active spaces.

Modeling and Implementation of Synchronization for Large-Aperture Electromagnetic MEMS Mirrors.

MEMS-based LiDAR has showcased extensive application potential in the autonomous driving sector, attributed to its cost-effectiveness, compactness, and seamless integration capabilities. However, MEMS LiDAR suffers from a short detection range, due to the small receiving aperture of the MEMS mirror. Our early study attempted to increase the detection range of MEMS LiDAR with a semi-coaxial design.

Wearable device-measured physical activity and incident cardiovascular disease in cancer survivors.

Objective: To explore the association of wearable device-measured moderate-to-vigorous intensity physical activity (MVPA) with cardiovascular disease (CVD) risk in long-term cancer survivors.

Methods: This retrospective analysis involved a prospective cohort of 6109 cancer survivors without CVD from the UK Biobank accelerometry subsample. The MVPA volume is categorised into four groups based on guideline recommendations (0-75 min/week, 75-150 min/week, 150-300 min/week, ≥300 min/week).

Spatially-dense three-dimensional analysis of the midfacial skeletal shape asymmetry in skeletal Class III patients.

Introduction: This study aimed to analyze midfacial skeletal shape asymmetry in skeletal Class III patients using a three-dimensional spatially-dense method.

Methods: Sixty skeletal Class III patients' cone-beam computed tomography images were retrospectively enrolled and divided into three groups according to occlusal plane inclination (OPI) and mandibular lateral deviation (MD). A spatially-dense template of the anterior outer surface of the midfacial skeleton was established and validated.