Federated learning is a distributed machine learning approach that enables multiple devices or data sources to train models without sharing their raw data. However, heterogeneity within federated learning, including varying feature distributions, data ...

By employing vehicle-to-vehicle (V2V) charging, the electric logistics vehicles that are in transit can act as mobile power sources to provide electricity to small electric vehicles with urgent charging needs, this approach not only addresses the issue ...

In the field of warehousing and logistics, the path planning of Automated Guided Vehicle (AGV) is a key issue in industrial production. Aiming at the problem that the traditional A* algorithm has a large number of traversal nodes in AGV path planning, ...

Joint entity and relation extraction has achieved great improvements in Natural Language Processing (NLP) and has been widely applied, such as constructing knowledge graph, query understanding and question answering. Existing methods usually spend long ...

Vehicle-edge computing has emerged as a new paradigm based on vehicular networking to provide computing resources for mobile vehicles. However, traditional binary offloading methods result in wastage of vehicle and server resources, as well as the ...

Unmanned Aerial Vehicles (UAVs) equipped with Multi-Access Edge Computing (MEC) servers can assist Terminal Devices (TDs) in offloading data tasks. In this paper, we investigate a resource allocation and trajectory optimization problem of multiple UAVs ...

Aiming to address the challenges presented by limited samples of bearing faults and complex working conditions, this study attempts to overcome the problem of shallow deep learning models ignoring the temporal characteristics of bearing vibration signals ...

Primary Synchronization Signal detection is the first step for UE to access the 5/6G NR system, which can achieve downlink time-frequency synchronization. Considering the shortcomings of existing Primary Synchronization Signal detection algorithms in ...

In response to the shortcomings of manually adjusting parameters in the variable step size LMS algorithm and the contradiction between convergence speed and steady-state error performance, a variable step size LMS algorithm based on improved Particle ...

In recent years, with the continuous expansion of the scale of cloud data centers, resource allocation requirements have gradually increased to better meet the requirements of low latency and high revenue. However, due to the dynamic state of the system ...

Neural networks have been widely applied in various fields, including drones and autonomous vehicles. The performance of neural networks determines their effectiveness, but reliability is equally important. Building on previous research on factors ...

Sequential recommendation is essential in modern online service platforms. By modeling the evolving preferences of a user from the historical behavior sequence, sequential recommendation aims to predict the next interaction of the user in the near ...

Due to the limitation of network ossification, network virtualization is a promising architecture to solve the issue. Virtual network embedding is one of the challenges of network virtualization. However, existing algorithms cannot solve the online ...

The encryption domain Reversible data hiding algorithm differs from the plaintext domain in that after encrypting the image information, the redundant space decreases, leading to difficulties in embedding and low embedding capacity in the encryption ...

The Math Word Problem (MWP) refers to mathematical problems described in natural language. Recent research has mostly employed sequence-to-sequence (Seq2Seq) or sequence-to-tree (Seq2Tree) approaches to generate computational trees or expressions that ...

Mirrors often appear in various places, and personal privacy information will be reflected and leaked out without the user's awareness, affecting the security of personal information. Mirror detection is a very challenging task due to the non-uniform ...

Proposed is an improved production personnel wearing target detection algorithm based on YOLOv7, aiming to address the issues of false positives and false negatives caused by occlusion and detection of small to medium-sized objects in complex ...

In this paper, we propose an Edge-Cloud based and Artificial Intelligence (AI) supported Scheme (ECAIS) in Digital Twin-enabled 6G network. Specifically, we first analyze the traffic consumption of the backbone network based on the construction workflow ...

In the era of big data, electric power sensitive data recognition and network intrusion detection are concerned. Accurate pattern matching based sensitive data recognition software has low matching efficiency, poor flexibility and high resource ...

When measuring big data leakage risk tolerance, the lack of comprehensive analysis of big data leakage risk factors leads to large measurement error. Therefore, a measurement model of big data leakage risk tolerance based on extended Bayesian ...