Many of the phenomena around us are a combination of directed and undirected relationships between different subjects, which will be more complex despite the existence of multiple relationships between objects. For example, in business relations between countries and social networks, communication is sometimes one-way or two-way. Checking and processing such information is managed in mixed graphs.

There is a phenomenon that better teachers cannot teach out better students in knowledge distillation due to the capacity mismatch. Especially in pixel-level object segmentation, there are some challenging pixels that are difficult for the student model to learn. Even if the student model learns from the teacher model for each pixel, the student’s performance still struggles to show significant improvement

With the rapid development of urbanization and global climate warming, complex environments and adverse weather conditions pose significant challenges to the accuracy of object detection and driving safety in autonomous driving systems. Addressing the challenges of severe occlusion and noise interference in target detection within complex foggy scenes and considering the YOLOv5 model’s small size and

The advent of ChatGPT and GPT-4 has generated substantial interest in large language model (LLM) research, showcasing remarkable performance in various applications such as conversation systems, machine translation, and research paper summarization. However, their efficacy diminishes when applied to low-resource languages, particularly in academic research contexts like Tibetan. In this study, we trained

Vehicle detection and tracking from a UAV perspective often encounters omission and misdetection due to the small targets, complex scenes and target occlusion, which finally influences hugely on detection accuracy and target tracking stability. Additionally, the number of parameters of current model is large that makes it is hard to be deployed on mobile devices. Therefore, this paper proposes a YOLO-LMP

Abstract Given the remarkable text generation capabilities of pre-trained language models, impressive results have been realized in graph-to-text generation. However, while learning from knowledge graphs, these language models are unable to fully grasp the structural information of the graph, leading to logical errors and missing key information. Therefore, an important research direction is to minimize

The UNet architecture, based on convolutional neural networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive fields and inherent bias of convolutional operations. Recently, numerous transformer-based techniques have been incorporated into the UNet architecture to overcome this

Legal question answering (Legal QA) aims to provide accurate and timely answers to legal questions, significantly reducing the workload of legal professionals. This approach improves the efficiency of the judiciary and ensures prompt, professional legal assistance to the public. Currently, a major challenge is the absence of a large-scale dataset tailored for Chinese generative legal question answering

We present a novel learning model with attention and prior guidance for view synthesis. In contrast to previous works that focus on optimizing for specific scenes with densely captured views, our model explores a generic deep neural framework to reconstruct radiance fields from a limited number of input views. To address challenges arising from under-constrained conditions, our approach employs cost

The daily occurrence of traffic accidents has led to the development of 3D reconstruction as a key tool for reconstruction, investigation, and insurance claims. This study proposes a novel virtual-real-fusion simulation framework that integrates traffic accident generation, unmanned aerial vehicle (UAV)-based image collection, and a 3D traffic accident reconstruction pipeline with advanced computer

The most common method for visual object tracking involves feeding an image pair comprising a template image and search region into a tracker. The tracker uses a backbone to process the information in the image pair. In pure Transformer-based frameworks, redundant information in image pairs exists throughout the tracking process and the corresponding negative tokens consume the same computational resources

With the advent of 3D Gaussian Splatting (3DGS), new and effective solutions have emerged for 3D reconstruction pipelines and scene representation. However, achieving high-fidelity reconstruction of complex scenes and capturing low-frequency features remain long-standing challenges in the field of visual 3D reconstruction. Relying solely on sparse point inputs and simple optimization criteria often

Dynamic multi-objective optimization problems (DMOPs) are challenging as they require capturing the Pareto optimal front (POF) and Pareto optimal set (POS) during the optimization process. In recent years, transfer learning (TL) has emerged the empirical knowledge and is an effective approach to solve DMOPs. However, negative transfer can occur when the transfer method is not suitable for the transfer

Low-light object detection involves identifying and locating objects in images captured under poor lighting conditions. It plays a significant role in surveillance and security, night pedestrian recognition, and autonomous driving, showcasing broad application prospects. Most existing object detection algorithms and datasets are designed for normal lighting conditions, leading to a significant drop

The COVID-19 pandemic has dramatically highlighted the importance of developing simulation systems for quickly characterizing and providing spatio-temporal forecasts of infection spread dynamics that take specific accounts of the population and spatial heterogeneities that govern pathogen transmission in real-world communities. Developing such computational systems must also overcome the cold-start

Heterogeneous attribute data (also called mixed data), characterized by attributes with numerical and categorical values, occur frequently across various scenarios. Since the annotation cost is high, clustering has emerged as a favorable technique for analyzing unlabeled mixed data. To address the complex real-world clustering task, this paper proposes a new clustering method called Adaptive Micro

Nowadays many algorithms have appeared to solve many-objective optimization problems (MaOPs), yet the balance between convergence and diversity is still an open issue. In this paper, we propose a dynamic decomposition and hyper-distance based many-objective evolutionary algorithm named DHEA. On one hand, to maximize the diversity of the population, we use dynamic decomposition to decompose the whole

The research and exploration of time series prediction (TSP) have attracted much attention recently. Researchers can achieve effective TSP based on the deep learning model and a large amount of data. However, when sufficient high-quality data are not available, the performance of prediction models based on deep learning techniques may degrade. Therefore, this paper focuses on few-shot time series prediction

In order to improve the topology optimization results for the requirements such as manufacturability and functionality, and to strengthen the link between structural topology optimization and computational topology, this paper measures the topology and thickness of the structure using topological invariants (i.e., Euler characteristic and Betti numbers) in the computational topology. Based on set theory

Displacement response spectra (DRS) are crucial for seismic design as earthquake damage correlates more with displacements than forces. Previous efforts to develop attenuation relations for DRS have been largely approximate. Permanent displacement or Fling poses significant design, repair and rehabilitation challenges. Consideration of DRS and Fling in seismic design and performance assessment necessitates

The role of dimensionless ratios in engineering and physics is ubiquitous; but their utility in the multiphysics community is sometimes overlooked. Notably, in the multiphysics modelling community, coupling methods are often discussed and developed without an explicit monitoring of the various dimensionless ratios of the various inter-physics coupling terms. However, it is evident that the varying

In this work, a topology optimization algorithm has been developed to design bi-material lattice structures showing a band gap around a target frequency, using just one unit cell through the application of Bloch-Floquet theorem. The Bidirectional Evolutionary Structural optimization (BESO) method has been employed, based on bi-material interpolation. A new objective function has been defined, which

This paper introduces a novel approach for analyzing the frictionless two-dimensional contact between dielectric solids in an electrostatic medium. This analysis is achieved by combining the finite element and boundary element methods. The finite elements model elastic dielectric solids undergoing geometrically nonlinear mechanical deformation and electric polarization. We present a finite element-based

In this study, two state-of-the-art implementations of the rate-dependent Crystal Plasticity Finite Element Method (CPFEM) as user material subroutines in the finite element solvers Abaqus/Explicit and Abaqus/Standard (Implicit) are presented. Adaptive substepping in the explicit solver and line-search stabilized implementation in the implicit solver enable fast and stable calculations also for small

The quadrilateral surface mesh modification method based on dual cycle operations shows promising advantages in hexahedral mesh generation. However, as only simple cycle eliminations are considered, the existing methods can not handle complex surface meshes. In this study, an improved method based on cycle elimination is proposed for high-quality hexahedral mesh generation from a given quadrilateral

This paper introduces a new quadrilateral plate element named DSPM4, which improves upon the previous Q4γs element. The DSPM4 element has twelve DOFs and four temporary DOFs at the mid-sides of the element. The rotation functions βs are modified by adding an incomplete quadratic function to improve the bending performance. An orthogonality condition between the lower and higher-order bending energy

To ensure secure and reliable communication in wireless systems, authenticating the identities of numerous nodes is imperative. Traditional cryptography-based authentication methods suffer from issues such as low compatibility, reliability, and high complexity. Physical-Layer Authentication (PLA) is emerging as a promising complement due to its exploitation of unique properties in wireless environments

This paper presents a machine learning-based finite element construction method (MLBFE) to predict a precise strain field with minimal nodes. The method first establishes a standardized MLBFE model via the substructure concept and the static condensation method. Then, a training data collection method involving nodal displacements and strain fields, and considering (1) boundary continuity, (2) strain

A space-time approach is proposed to simulate the propagation of brittle cracks in an isotropic and elastic solid in dynamics. We adopt the so called phase-field description of crack that is based on a variational representation of fracture mechanics. Due to this variational structure, the crack initiation and propagation can be then described thanks to a well chosen potential. In this approach, we

Recently, massive research has achieved significant development in improving the performance of rumor detection. However, identifying rumors in an invisible domain is still an elusive challenge. To address this issue, we propose an unsupervised cross-domain rumor detection model that enhances contrastive learning and cross-attention by label-aware learning to alleviate the domain shift. The model performs

The challenge of link overutilization in networking persists, prompting the development of load-balancing methods such as multi-path strategies and flow rerouting. However, traditional rule-based heuristics struggle to adapt dynamically to network changes. This leads to complex models and lengthy convergence times, unsuitable for diverse QoS demands, particularly in time-sensitive applications. Existing

The traditional architecture of networks in Software Defined Networking (SDN) is divided into three distinct planes to incorporate intelligence into networks. However, this structure has also introduced security threats and challenges across these planes, including the widely recognized Distributed Denial of Service (DDoS) attack. Therefore, it is essential to predict such attacks and their variants

High computing power and large storage capacity are necessary for running big data tasks, which leads to high infrastructure costs. Infrastructure-as-a-Service (IaaS) clouds can provide configuration environments and computing resources needed for running big data tasks, while saving users from expensive software and hardware infrastructure investments. Many studies show that the cost of computation

Federated Learning (FL) is an emerging training framework for machine learning to protect data privacy without accessing the original data from each client. However, the participating clients have different computing resources in FL. Clients with insufficient resources may not cooperate in the training due to hardware limitations. The restricted computing speeds may also slow down the overall computing

Federated Learning is a collaborative machine learning (ML) framework designed to train a globally shared model without accessing participants’ private data. However, due to the statistical heterogeneity in the participants’ data, federated learning faces significant challenges. This approach generates a similar output for all participants, without adapting the model to each individual. Consequently

The advent of quantum computers has justified the development of quantum machine learning algorithms, based on the adaptation of the principles of machine learning to the formalism of qubits. Among such quantum algorithms, anomaly detection represents an important problem crossing several disciplines from cybersecurity, to fraud detection to particle physics. We summarize the key concepts involved

In this work, a novel finite element approach for the computational aeroelastic analysis of flexible lifting structures in subsonic flow is presented. The numerical simulation of the fluid-structure interaction relies on the physical concept and mathematical formulation of an aeroelastic beam element, that is based on Euler-Bernoulli and De Saint-Venant theories for the structure dynamics and modified

Low Earth Orbit (LEO) satellites have been widely used to collect sensing data from ground-based IoT devices. Comprehensive and timely collection of sensor data is a prerequisite for conducting analysis, decision-making, and other tasks, ultimately enhancing services such as geological hazard monitoring and ecological environment monitoring. To improve the efficiency of data collection, many models

Decentralized Finance (DeFi) utilizes the key principles of blockchain to improve the traditional finance system with greater freedom in trade. However, due to the absence of access restrictions in the implementation of decentralized finance protocols, effective regulatory measures are crucial to ensuring the healthy development of DeFi ecosystems. As a prominent DeFi platform, Ethereum has witnessed

Owing to the widespread application of artificial intelligence, deep learning (DL) has attracted considerable attention from both academia and industry. The DL workload-training process is a key step in determining the quality of DL-based applications. However, owing to the limited computational power of conventionally centralized clusters, it is more beneficial to accelerate workload training while

This study presents a topology optimization method for thermal actuators that accounts for boundary conditions influenced by variables such as thermal convection and pressure load. Thermal actuators with gripper-like designs are essential for handling hot and brittle materials. The objective of this study is to design actuator shapes that achieve an optimal balance between flexibility and stiffness

Segmentation of brain tissue from MR images provides detailed quantitative brain analysis for accurate diagnosis, detection, and classification of brain diseases, and plays an important role in neuroimaging research and clinical environments. Recently, a plethora of deep learning-based approaches have been employed to achieve brain tissue segmentation in fetuses, infants, and adults with impressive

With the rapid development and deep application of artificial intelligence, modern air combat is incrementally evolving towards intelligent combat. Although deep reinforcement learning algorithms have contributed to dramatic advances in in air combat, they still face challenges such as poor interpretability and weak transferability of adversarial strategies. In this regard, this paper proposes a tactical

In recent years, deep learning has significantly advanced the development of image depth estimation algorithms. The depth estimation network with single-view input can only extract features from a single 2D image, often neglecting the information contained in neighboring views, resulting in learned features that lack real geometrical information in the 3D world and stricter constraints on the 3D structure

The concept of green scheduling, which deals with the environmental impact of the scheduling process, is becoming increasingly important due to growing environmental concerns. Most green scheduling problem variants focus on modelling the energy consumption during the execution of the schedule. However, the dynamic unrelated machines environment is rarely considered, mainly because it is difficult to

Drug repositioning, the discovery of new therapeutic uses for existing drugs, is increasingly gaining attention as a cost-effective and high-yield drug discovery strategy. Existing methods integrate diverse biological information into heterogeneous networks, providing a comprehensive framework for understanding complex drug–disease associations, which also will introduces noise into the data and affect

Traditional education systems obscure the diverse interconnections inherent within subject knowledge, thus failing to meet the current demand for personalized and adaptive learning experiences. Recent advances have explored various relation extraction techniques to construct educational knowledge graphs that integrate dispersed subject knowledge into a unified framework. However, educational conceptual

With the emergence of Internet of Things (IoT) devices collecting large amounts of data at the edges of the network, a new generation of hyper-distributed applications is emerging, spanning cloud, fog, and edge computing resources. The automated deployment and management of such applications requires orchestration tools that take a deployment descriptor (e.g. Kubernetes manifest, Helm chart or TOSCA)

Significance of structural components with local abnormality in buckling analysis has drawn considerable interest from researchers. A versatile and effective non-uniform spline finite strip method (N-u SFSM) is developed to allow for mesh refinement in local zones, enabling a comprehensive analysis of buckling characteristics of structures with local abnormality. The inclusion of non-uniform spline

Deep learning-based object detectors excel on mobile devices but often struggle with blurry images that are common in real-world scenarios, like unmanned aerial vehicle (UAV)-assisted images. Current models are designed for sharp images, leading to potential detection failures in blurry images. Using image deblurring before object detection is an option, but it demands significant computing power and