Clients in federated learning (FL) may exhibit varying computing capabilities, leading to prolonged training latency when deploying complex deep neural networks. To address this challenge, split federated learning (SFL) presents an approach that offloads the main computational workload from resource-constrained devices to a server, while enabling parallel training. However, there are two significant limitations of existing SFL frameworks: The adoption of a uniform cut layer strategy fails to take into account the heterogeneous among clients; it fails to effectively utilize server-side resources to improve training efficiency. This article presents a framework, i.e., heterogeneous split federated learning, which considers personalized cut layer selection and server resource configuration to accelerate SFL in heterogeneous edge computing environments. By splitting the global model into two components for each client, our framework jointly optimizes both client-side workload, batch size control, and server resource configuration strategy, while considering device heterogeneity. Specifically, we develop an alternating iterative scheduling algorithm to obtain an approximate scheme for the cut layer, batch sizes, and server resource configuration to alleviate the impact of device heterogeneity. The experimental results illustrate that HSFL outperforms the compared methods, achieving performance improvements of up to 3.9%$\sim$32.2% across two datasets under various data distribution scenarios, which demonstrates the effectiveness of the proposed strategies.

Additive manufacturing (AM) is widely used in fields, such as aerospace and medical treatment. However, the massive heterogeneous data generated during its production process face challenges, such as high transmission latency and large energy consumption. This article proposes a sustainable intelligent optimization strategy based on edge–cloud collaboration to enhance the intelligence and sustainability of AM. First, a hybrid model that integrates the local feature extraction of convolutional neural network (CNN) and the global dependency modeling of transformer (CNN–transformer) is designed to accurately predict the key process parameters of AM. Second, a multiobjective optimization model for surface roughness, processing time, and energy consumption is constructed. Combined with the improved Pareto set learning (PSL) algorithm, the collaborative optimization of economic and environmental sustainability is achieved. Finally, verification is carried out on selective laser melting (SLM) technology. The experimental results show that the prediction error of the CNN–transformer is lower than that of traditional models. It can reduce energy consumption and processing time while ensuring surface quality, thus providing a systematic solution for green intelligent manufacturing from Industry 4.0 to Industry 5.0.

A tensor-based anomaly detection framework for high-dimensional time series in edge–cloud environments is presented. It is capable of dealing with both point anomaly and pattern anomaly. The transformation of data to tensor is carried out by sliding window with full consideration of the time dimension. The high dimensionality of data is tackled with tensor dimensionality reduction. An efficient iterative tensor decomposition method with low rank approximation is developed to rapidly obtain an optimal core tensor. It retains key information of the original tensor and achieves dimensionality reduction at the same time. A key matrix factorization technique is employed to circumvent large amount of iterative calculation for singular vectors of matrices. For anomaly detection, a tensor-based statistical prediction model is devised to generate a predicted tensor. For the purpose of comparison, a reverse technique is used to transform the predicted tensor to the form of original data. The final anomaly detection is performed with least significant difference and majority voting. Extensive experiments are conducted with two notable real-world datasets in a specific edge-cloud environment. Our proposal is compared with six other popular methods in terms of performance metrics precision, recall, F1-score, AUC and delay. Experimental results show that our method is superior to the six other methods in both edge-cloud and pure cloud settings.

The advancement of the Industry 5.0 in information technology has led to increased interest in integrating edge-cloud cooperation with Internet of Things (IoT) and cyber-physical system (CPS) designs. This integration effectively reduces service delays and provides real-time analysis feedback to physical spaces, attracting attention from both academia and industry. These advanced technologies enhance production system intelligence, their alignment with circular economy principles for promoting sustainability has been overlooked. To address this gap, this article proposes an intelligent sustainability evaluation strategy driven by edge-cloud cooperation, IoT, and CPS. The proposed approach aims to enhance production sustainability and intelligence through circular economy perspectives. It introduces improved gray relation analysis and deep clustering network techniques to extract meaningful insights from diverse indicators within the evaluation system. By analyzing relationships between different equipment and workshops, it provides an analytical method that enhances production efficiency while reducing energy consumption and resource waste. To further validate the proposed method, an illustrative example using a partner company’s production data demonstrates its accuracy.

This article investigates the covert communication in a D2D underlaying cellular network consisting of a cellular transmitter, a base station, a cellular receiver, multiple colluding wardens, and an underlaid D2D pair with a transmitter and a receiver. For multiple colluding wardens, they fuse their observations to a fusion center (FC) with the maximum ratio combining (MRC) scheme and the equal gain combining (EGC) scheme. To protect the covert communication between the cellular transmitter and the base station from being detected by multiple colluding wardens, the underlaid D2D transmitter reuses the spectrum of the cellular user to transmit its signal to the D2D receiver with a random power to deliberately confuse multiple colluding wardens. We first provide the basic theoretical results for the detection performance of FC under MRC and EGC, respectively, i.e., the optimal detection threshold, the minimum detection error probability and its average value. We then explore the modeling of the average covert rate as well as the optimal power control for average covert rate maximization to enhance the covert performance under MRC and EGC. Finally, extensive numerical and simulation results are presented to validate theoretical analysis and also to illustrate the effects of some important system parameters on the average minimum detection error probability, the average covert rate, and the maximum average covert rate under MRC and EGC, respectively. We can find that the detection performance of multiple colluding wardens under the MRC scheme is better than that under the EGC scheme.

Visual foundation models (VFMs) have been widely applied in the field of remote sensing (RS). However, they still face two main challenges when applied to precise remote sensing change detection (RSCD) tasks in complex scenes. Firstly, the nonnegligible domain shift between natural scene and RS scene limits the direct application of VFMs to the RSCD task. Second, most of existing RSCD methods may suffer from the boundary displacement problem due to the inadequate exploration of temporal differences for bi-temporal features. To address the above issues, this study proposes a SAM2-based domain adaptive and spatial difference aggregation network (DA2-Net) for RSCD. The proposed DA2-Net has two main advantages. First, a hierarchical low-rank adaptation (LoRA) strategy is presented by introducing low-rank matrices at key positions of SAM2, which can inject inductive biases from the RS domain into the network and alleviate the domain shift problem. Second, a difference adaptive enhancement module (DAEM) is designed to explore temporal differences for hierarchical bi-temporal features. The DAEM provides respective attention weights for different information through a dual branch of global difference awareness and local detail optimization. Experimental results on SYSU-CD, WHU-CD, and LEVIR-CD datasets demonstrate the superiority of DA2-Net. Code is available at https://github.com/xuptheqi-hash/ DA2Net.

Large deployment of wireless sensor networks in various fields bring great benefits. With the increasing volume of sensor data, traditional data collection and processing schemes gradually become unable to meet the requirements in actual scenarios. As data quality is vital to data mining and value extraction, this paper presents a distributed anomaly detection framework which combines cloud computing and edge computing. The framework consists of three major components: k-nearest neighbors, locality sensitive hashing, and cosine similarity. The traditional k-nearest neighbors algorithm is improved by locality sensitive hashing in terms of computation cost and processing time. An initial anomaly detection result is given by the combination of k-nearest neighbors and locality sensitive hashing. To further improve the accuracy of anomaly detection, a second test for anomaly is provided based on cosine similarity. Extensive experiments are conducted to evaluate the performance of our proposal. Six popular methods are used for comparison. Experimental results show that our model has advantages in the aspects of accuracy, delay, and energy consumption.

Smart contracts are programs that run on a blockchain, where Ethereum is one of the most popular ones supporting them.Due to the fact that they are immutable, it is essential to design smart contracts bug-free before they are deployed.However, various defects have been found in the deployed smart contracts, causing huge economic losses and lowing people's trust.Writing secure smart contracts is far from trivial, where developers tend to engage in reliable resources or social coding platforms to reuse code.This leads to a large number of similar contracts with potential security risks.Therefore, detecting similarity of smart contracts helps to avoid vulnerabilities, identify threats, and improve the security of Ethereum.In this paper, we design a learning-effective and costefficient model, called SmartSD, for Ethereum smart contract similarity detection.Different from the current research efforts, SmartSD is performed on a bytecode level and leverages deep neural networks to learn the latent representations from the opcode sequences for smart contract bytecodes, where the representation learning and similarity measurement are supervised via siamese neural networks.The experimental evaluations demonstrate that SmartSD outperforms EClone's 93.27% accuracy, achieving 98.37% high detection accuracy and 0.9850 F1-score, which is computationally tractable and effectively mitigates the interference caused by compilers.

The autonomous driving industry has mushroomed over the past decade. Although autonomous driving has undoubtedly become one of the most promising technologies of this century, its development faces multiple challenges, of which security is the major concern. In this article, we present a thorough analysis of autonomous driving security. First, the attack surface of autonomous driving is presented. After an analysis of the operation of autonomous driving in terms of key components and technologies, the security of autonomous driving is elaborated in four dimensions: 1) sensors; 2) operating system; 3) control system; and 4) vehicle-to-everything (V2X) communication. Sensor security is examined from five components, which are mainly responsible for self-positioning and environmental perception. The analysis of operating system security, the second dimension, is concentrated on the robot operating system. Concerning the control system security, the controller area network is approached mainly from vulnerabilities and protection measures. The fourth dimension, V2X communication security, is probed from four categories of attacks: 1) authenticity/identification; 2) availability; 3) data integrity; and 4) confidentiality with corresponding solutions. Moreover, the drawbacks of existing methods adopted in the four dimensions are also provided. Finally, a conceptual multilayer defense framework is proposed to secure the information flow from external communication to the physical autonomous vehicle.

Communication performance relies largely on the availability of channel state information (CSI). This paper investigates the impact of outdated CSI on the achievable covert communication performance in a two-hop wireless relay system under two typical covert transmission schemes of rate-control transmission (RCT) and power-control transmission (PCT). We first apply the typical channel feedback delay model to determine the statistical distribution of outdated CSI, based on which we then develop theoretical models to depict the inherent relationship between outdated CSI and the fundamental covert performance metrics in terms of detection error probability (DEP) and covert rate (CR). With the help of these models, we further explore the optimization of DEP subject to the CR constraint as well as the optimization of CR subject to the DEP constraint to reveal the max-min DEP performance and the maximal CR performance with the outdated CSI. Finally, extensive numerical results are provided to illustrate the impact of outdated CSI on the covert communication performance.

With the large-scale application of lithium-ion batteries (LIB), using deep neural networks to predict the remaining useful life (RUL) of LIB has gradually become a hotshot in recent years. RUL prediction method based on deep neural network can avoid studying electrochemical phenomena and manual extracting the features in battery. But single neural network has the different prediction accuracy and features extraction on different dataset. In this study, an ensemble method for the heterogeneous neural network is proposed, which integrates the prediction results of multiple heterogeneous neural networks with the adaptive weight. The weight of the neural network is higher with the closer correlation to the majority prediction results, vice versa. Furthermore, the weight of the neural network is adjusted via the predicting results for neural network on the different dataset, so that the computed weight of the neural network is adapted to the various dataset, and the effects of poor predictions of certain neural networks can be reduced sufficiently. The effectiveness of the ensemble method is verified on MIT-Stanford LIB degradation dataset, and the results show that the proposed method has higher accuracy than the existing ensemble methods for neural network.

Abstract Wireless sensor networks (WSNs) are extensively deployed to collect various data. Due to harsh environments and limitation of computing and communication capabilities of sensor nodes, the quality and reliability of sensor data are compromised by outliers. With the advent of 5G, sensors tend to generate increasingly more complex data. When faced with big data, traditional outlier detection methods relied on sensor nodes and remote cloud are unable to accord satisfactory performance in terms of delay and energy consumption. To address this problem, we propose a mobile edge–cloud collaboration outlier detection framework. Outlier detection is performed by edge nodes between the remote cloud and the underlying WSNs, while the training and updating of detection model are conducted on the cloud. A fast angle‐based outlier detection method is developed to obtain training data. The detection model is constructed based on support vector data description. An on‐line learning‐based iterative optimization scheme is devised to update the detection model. Besides, a fuzzy concept is incorporated into the detection model to alleviate the problem of loose decision boundary. Extensive experiments are conducted on real‐world data set. Simulation results show that our model is superior to three popular methods in terms of delay and energy consumption. In addition, when the percentage of operational nodes is 60%, our proposal prolongs the network lifetime by 14.2% to 69.8% compared to the three methods.

When a small portion of the decision makers hold the correct information and the majority hold the opposite, the correct ranking of the alternatives for the group decision-making cannot be obtained with the current methods. A novel method is thus developed to tackle this challenge in this article. The priori probabilities of each alternative can be calculated via the opinions of the group decision makers, which are presented as the pairwise comparisons of the alternatives in the form of the linguistic preference relation. Based on the aggregated probabilities of the alternatives in the group of the decision makers, the normalized-prediction selection rate (NPSR) is defined and calculated accordingly. The alternative with maximal NPSR is selected as the correct answer, whereas the accuracy of the correct alternative selection (CAS) is guaranteed by two propositions. The iterative algorithm is first devised to determine the ranking of the alternatives depending on the CAS. For the proposed method, the decision makers require no modification of the opinions as can avoid the consensus problem, and the CAS can be obtained under the circumstances that the correct information is held by the minority of the group. Finally, the experiment has been conducted to demonstrate the efficacy of the proposed method to obtain the CAS, and the main limitations of proposed method are carefully addressed as well.

Pythagorean Fuzzy Preference Relations (PFPRs) have been considered in recent literature more powerful and flexible than the popular intuitionistic fuzzy preference relation in dealing with the linguistic imprecision for decision makers in the large scale group decision making. Following on this promising trend, a novel approach based on the PFPRs is proposed for decision support. In particular, the proposed work starts with the acquisition of the optimal comparison matrices, which essentially record the pairwise comparison of the alternatives from the positive and negative opinions. The proposed consensus reaching process is then utilised to guide the decision makers to revise the provided information in order to reach the overall group consensus, before the derivation of rankings of the alternatives. Experimental studies are provided to demonstrate the workings and effectiveness of the proposed approach in comparison with two state-of-the-art methods.

As the volume of data grows exponentially, big data brings an unprecedented burden to the current computing infrastructure. How to deal with big data efficiently and concisely and reduce the burden of computing infrastructure has always been a big challenge. Therefore, this paper proposes a high-quality core data extraction method in edge computing nodes. Firstly, heterogeneous data are fused into a unified model, the data characteristics of the original data are retained. Then, a Lanzcos-based incremental tensor decomposition method is proposed to extracted the high quality core tensor dynamically. Finally, the model algorithm is verified using real data. The experimental results show that the approximate tensor reconstructed from the tensor containing 15% of the core data can guarantee 90% accuracy. At the same time, IncLHOSVD is significantly better than non-incremental HOSVD in execution time in guaranteeing the accuracy of approximate equal error.

The methods with consensus reaching process can obtain a collective solution which is supported by most of decision makers in larger-scale group decision making. However, in case decision makers who could give correct opinions are from the minority, the conventional methods with consensus reaching process can not obtain the correct answer. In this paper, a novel method is developed to tackle this challenge. The decision makers give the opinions utilizing pairwise comparisons of the alternatives from positive and negative views based on intuitionistic fuzzy preference relation. The obtained opinions are translated into intuitionistic fuzzy numbers, and are further grouped and aggregated according to the alternatives. Based on the aggregated intuitionistic fuzzy numbers, the prediction normalized rate is defined and calculated for each alternative, the alternative with the minimal prediction normalized rate is selected as correct one. The experimental results show that the proposed method can obtain the correct answer even when the actual correct opinions are reflected by a small number of decision makers.

Crowd intelligence opens up new ways for decision making in open environments, traditional decision making is unable to effectively make correct decisions in open environments. In this paper, positive and negative comparing method using linguistic scale is proposed to make decisions in the open environments with crowd intelligence. Firstly, the crowd participants compare the alternative with the corresponding positive and negative assessment points, and give their evaluations using linguistic scales form positive and negative views. The crowd participants' evaluations can be translated into Intuitionistic Fuzzy Numbers (IFNs). In the proposed methods, the evaluations given by the crowd participants do not depend on the pairwise comparisons of the alternatives, the consistent problem can be avoided. Secondly, the consensus measures between aggregating results and IFNs are proposed. Based on these concepts, the aggregating methods that without discarding any IFNs are proposed and studied. The studying results show that the proposed methods can improve the consensus measures between the aggregating result and evaluations given by crowd participants.

A novel multi-objective optimization based particle swarm optimization algorithm is presented to solve the global optimization problem for based services selecting in Web services composition technology. This algorithm takes Web services selection as a multi-objective constrained optimization problem with constraints. It introduces multi-objective PSO intelligent theory to optimize multi parameters simultaneously, and produces a set of constraints to meet the Pareto optimal solution. The experiments show that the algorithm is a feasible and efficient method for Web services selection.