To address the current issue that existing steganographic techniques are highly dependent on the quality of carrier images and have insufficient adaptability to damaged images, we propose an MAE-based inpainting-steganography framework, which realizes steganography and inpainting for 2D color damaged images through multi-module collaboration. The encoder divides the original 244 × 244 images into non-overlapping patches and performs random masking to generate their feature sequences. The steganographic point prediction module locates suitable steganographic points by analyzing feature fluctuations during the inpainting process. The steganography module embeds information by introducing feature offsets at specific positions in the feature sequences according to the suitable steganographic points. The decoder completes the inpainting of masked regions to obtain stego-inpainted images. And the extraction module recovers the secret information through feature alignment. Experimental results show that with a feature fluctuation amplitude threshold of 0

To address the accuracy issues in monocular depth estimation caused by insufficient feature extraction and inadequate context modeling, a multi-scale feature optimization model named EFDepth was proposed to improve prediction performance. This framework adopted an encoder–decoder structure: the encoder (EC-Net) was composed of MobileNetV3-E and ETFBlock, and its features were optimized through multi-scale dilated convolution; the decoder (LapFA-Net) combined the Laplacian pyramid and the FMA module to enhance cross-scale feature fusion and output accurate depth maps. Comparative experiments between EFDepth and algorithms including Lite-mono, Hr-depth, and Lapdepth were conducted on the KITTI datasets. The results show that, for the three error metrics—RMSE (Root Mean Square Error), AbsRel (Absolute Relative Error), and SqRel (Squared Relative Error)—EFDepth is 1.623, 0.030, and 0.445 lower than the average values of the comparison algorithms, respectively, and for the three accuracy metrics, it is 0.052, 0.023, and 0.011 higher than the average values of the comparison algorithms, respectively. Experimental results indicate that EFDepth outperforms the comparison methods in most metrics, providing an effective reference for monocular depth estimation and 3D reconstruction of complex scenes.

The Social Internet of Things (SIoT) combines social networks and the Internet of Things, enabling closer interaction between devices, users, and services. However, this interaction brings risks of trust attacks. These trust attacks not only affect the stability of SIoT systems but also threaten personal privacy and data security. This paper provides a decade-long review of SIoT trust attack research. First, it outlines the SIoT architecture, social relationship types, concept of trust, and trust management processes. It maps seven attacks—bad mouthing attack (BMA), ballot stuffing attack (BSA), self-promoting attack (SPA), discriminatory attack (DA), whitewashing attack (WWA), on-off attack (OOA), and opportunistic service attack (OSA)—clarifying their mechanisms and traits. Next, we synthesize the literature on SIoT trust models, enumerate which attack types they address, and classify defense strategies. It then conducts simulation-based comparative experiments on trust attacks to reveal their impact on node trust and transaction processing, compares attack capabilities along disruption speed, attack strength, and stealthiness, and summarizes attack surfaces with corresponding defense recommendations to better guide the design of SIoT trust management schemes. Finally, we identify open challenges and future research directions, to support the development of new trust management models better equipped to address evolving trust attacks.

There are many problems in Social Internet of Things(IoTs), such as complex topology information, different degree of association between nodes and overlapping communities. The idea of set pair information grain computing and clustering is introduced to solve the above problems so as to accurately describe the similarity between nodes and fully explore the multi-community structure. A Set Pair Three-Way Overlapping Community Discovery Algorithm for Weighted Social Internet of Things (WSIoT-SPTOCD) is proposed. In the local network structure, which fully considers the topological information between nodes, the set pair connection degree is used to analyze the identity, difference and reverse of neighbor nodes. The similarity degree of different neighbor nodes is defined from network edge weight and node degree, and the similarity measurement method of set pair between nodes based on the local information structure is proposed. According to the number of nodes' neighbors and the connection degree of adjacent edges, the clustering intensity of nodes is defined, and an improved algorithm for initial value selection of k-means is proposed. The nodes are allocated according to the set pair similarity between nodes and different communities. Three-way community structures composed of a positive domain, boundary domain and negative domain are generated iteratively. Next, the overlapping node set is generated according to the calculation results of community node membership. Finally, experiments are carried out on artificial networks and real networks. The results show that WSIoT-SPTOCD performs well in terms of standardized mutual information, overlapping community modularity and F1.

入侵检测是目前网络安全防护的一个重要环节,由于传统入侵检测模型时间长、学习能力弱,因此提出了一种基于增量主成分分析方法(Incremental Principal Component Analysis,IPCA)和卷积神经网络(Convolutional Neural Networks,CNN)结合的方法,融合增量的思想能够使模型不断更新并拥有持续的学习能力.首先用IPCA方法对数据集进行降维处理,该算法将样本分批传入模型进行训练以不断更新特征基以及均值;最后找出主成分特征子集,再用CNN对其进行分类训练.实验采用 KDD-CUP99 以及 UNSW-NB15 作为实验的数据集进行对比.研究结果表明,IPCA-CNN 模型的准确率、F1 值和误报率分别达到了99.7％、99.3％和 0.2％;同传统机器学习入侵检测算法相比有所提升,验证了IPCA-CNN模型的有效性.

A complex network in reality contains a large amount of information, but some information cannot be obtained accurately or is missing due to various reasons. An uncertain complex network is an effective mathematical model to deal with this problem, but its related research is still in its infancy. In order to facilitate the research into uncertainty theory in complex network modeling, this paper summarizes and analyzes the research hotspots of set pair analysis, rough set theory and fuzzy set theory in complex network modeling. This paper firstly introduces three kinds of uncertainty theories: the basic definition of set pair analysis, rough sets and fuzzy sets, as well as their basic theory of modeling in complex networks. Secondly, we aim at the three uncertainty theories and the establishment of specific models. The latest research progress in complex networks is reviewed, and the main application fields of the three uncertainty theories are discussed, respectively: community discovery, link prediction, influence maximization and decision-making problems. Finally, the prospect of the modeling and development of uncertain complex networks is put forward.

The issue of climate and environment has been paid more and more attention by countries all over the world, especially regarding carbon emissions. Many national policies and scholars’ research contents have focused on this issue, which has become a hot topic in today’s society. As the world’s largest carbon emitter, it is vital for China to achieve green development, upgrade its industrial structure and explore the relationship between industrial structure upgrading and carbon emissions. To explore the decoupling and interactive effects of industrial structure upgrading and carbon emissions, this paper divides industrial structure upgrading into two aspects: rationalization of industrial structure and upgrading of industrial structure. Indicators related to industrial structure upgrading and carbon emissions are selected and the decoupling model of carbon emissions and industrial structure upgrading is constructed using panel data from 30 regions from 1997 to 2019. The core density function is used to analyze the decoupling distribution characteristics, and then the Gini coefficient decomposition method is used to analyze the carbon emissions decoupling index, revealing the regional differences and sources of carbon emissions decoupling index. Finally, spatial factors are included in the regression model to verify the spatial synergy effect of industrial structure upgrading on carbon emissions. The overall and local Moran indexes are used to reveal the spatial internal structure and agglomeration characteristics of industrial structure upgrading and carbon emissions, and, based on the research results, policy recommendations are put forward to promote sustainable and stable development of industrial structure upgrading in China. This provides a new perspective for understanding the relationship between industrial structure upgrading and carbon emissions and also provides a decision-making reference for promoting decoupling of industrial structure upgrading and carbon emissions under high-quality economic development and forcing low-carbon transformation of the industrial structure.

Multitarget threat evaluation of warship air attacks is one of the most urgent problems in warship defense operations. To evaluate the target threat quickly and accurately, an air attack multitarget threat evaluation method based on improved TOPSIS gray relational analysis is proposed. This method establishes threat assessment system of five attributes of target type, anti-jamming ability, heading angle, altitude, and speed. The weight coefficient of each index of the warship is obtained by combining the entropy weight method with the analytic hierarchy process. Topsis can make full use of the information of the original data, and its results can accurately reflect the gap between various evaluation schemes. The weighted Mahalanobis distance and comprehensive gray correlation between the attribute to be evaluated and the positive and negative ideal states are calculated by the improved TOPSIS gray correlation method. The target threat degree to be evaluated is obtained by combining the two methods. Finally, an example is given to prove the effectiveness of the evaluation model.

With the advent of the era of Internet of Everything, the amount of data generated by edge devices in the distribution network has increased rapidly, bringing higher data transmission bandwidth requirements. At the same time, new applications have placed higher demands on the real-time nature of data processing, and traditional computing models have been unable to cope effectively. This paper proposes distributed power distribution fault detection based on edge computing, which can realize timely sensing and real-time response to distribution network faults, speed up distribution fault processing speed, shorten power outage time, improve power supply reliability and user satisfaction. Secondly, the basic principle of wavelet transform application in signal singularity detection is introduced, and a power signal fault signal analysis method based on wavelet transform is proposed. It not only makes full use of the advantages of wavelet transform in fault signal analysis, but also overcomes the shortcomings of traditional Fourier transform method, and verifies it through examples. Finally, based on the critical requirements of edge computing, such as agile connection, business real-time, data optimization, application intelligence, security and privacy protection, an evaluation system based on edge computing CROSS index fault detection model is proposed.

With the extensive application of Internet of things technology and visual object tracking technology in various neighborhoods, the traditional visual object tracking algorithm can no longer meet the needs of Internet of things. The Internet of things with its powerful perception, multi-information transmission ability and super intelligent processing ability force the traditional visual object tracking algorithm to innovate and improve. In order to improve the tracking algorithm’s ability to cope with complex and drastic changes in the target’s appearance, in this paper, an accurate and robust visual object tracking algorithm (visual object tracking) based on K-means clustering algorithm on the integrated model ENS is studied. The tracking target is divided into several sample packets, and the size of the sample packet is compressed to match different weights of the filter in frequency domain. Finally, a more accurate and robust filter is built to realize the tracking of the target. Experimental simulation results show that the improved visual object tracking algorithm ENS-CSK approximately conforms to two-dimensional gaussian distribution in tracking effect, and the tracking success rate and accuracy are higher than the AdaBoost algorithm and KCF algorithm mentioned in the paper. Therefore, the improved visual object tracking algorithm ENS-CSK algorithm in this paper can better match the visual object tracking under the Internet of things technology. Therefore, it can be extended to the process of ore phase transformation of pellet under continuous calcination with varying temperature. Thus, the pressure resistance of pellets at different calcining temperatures can be predicted more accurately.

针对虚拟物流网络物流任务调控的动态性、迅速性和及时性特点,提出了基于三支决策的虚拟物流任务动态调控模型.首先,根据物流任务的描述模型,将虚拟物流任务划分为13个小属性,建立物流任务决策信息表;其次,在已建立的物流任务决策信息表基础上,基于三支决策构造理论,提出改进的三支决策动态调控模型,建立了虚拟物流任务动态调控模型,设计实现了相关算法,给出了一种新的代价矩阵确定方法;最后通过实例说明了模型与算法的有效性和合理性.

针对虚拟物流联盟的特点,根据指标选取原则,首先构建企业核心能力指标体系,并给出指标评测方法.考虑企业的动态发展特性,从企业内部核心能力、企业外部竞争因子两个层面出发,提出时间、成本、服务质量、设备资源、人力资源、信息系统、物流网络服务能力七个内部能力评价维度,引入企业管理、资源整合能力、市场发展、企业文化、服务创新五个外部竞争因子,融合层次分析法(AHP)和熵权法对企业内部核心能力和外部竞争因子进行综合测度评价;最后加入时间因子设计了虚拟物流企业能力的动态评价方法,实验表明该模型对企业核心能力识别与评价具有更高的精确度和效率.

Based on the real time and uncertainty of logistics demand ,the fusion time series autoregressive-moving average model ARMA and BP Neural network were proposed ,and the logistics demand forecasting ARMA-BP model was modelled , An ARMA-BP combined prediction algorithm for predicting freight transport was proposed .Based on the logistics transportation data of Tangshan in recent years ,using ARMA model ,BP model and ARMA-BP model ,the logistics data were predicted .The results show that the ARMA-BP model has higher precision and practical value than the traditional prediction model .

In order to solve the issue of three way decisions under set’s dynamic changing, we put forward a model of three way decisions model based on two-direction PS-probabilistic rough set by analyzing the theory and properties of two-direction PS-probabilistic rough set. Firstly, according to the upper and lower approximation of two-direction PS-probabilistic rough set, we deduce the boundary region, negative region and boundary region, explain the rules of three way decisions and analyze the properties of confidence coefficient and error rate. Then, we define decision metric function and decision loss function of three way decisions based on two-direction PS-probabilistic rough set, and infer the estimation method of the threshold value based on the minimum risk decision rules of Bayesian decision theory. Finally, the properties of this dynamic model are discussed; the example shows the correctness and feasibility of this model.

为准确地估计货叉扁钢的宽度尺寸,利用有限元软件DEFORM对扁钢精轧过程进行了数值模拟.根据模拟结果分析了不同温度和摩擦系数对宽展系数的影响,并通过曲线拟合的方式得到了货叉扁钢宽展系数的数学模型,为制定合理的工艺参数、提高产品的尺寸精度提供可靠的理论依据.

Fusing the structure feature of interval concept lattice and the actual needs of rough control rules, we have constructed the decision interval concept lattice, further more, we also have built a rules mining model of rough control based on decision interval concept lattice, in order to achieve the optimality between rough control mining cost and control efficiency. Firstly, we have preprocessed the collected original data, so that we can transform it into Boolean formal context form, and then we have constructed the decision interval concept lattice in rough control; secondly, we have established the control rules mining algorithm based on decision interval concept lattice. By analyzing and judging redundant rules, we have formed the rough control association rule base in end. Analysis shows that under the premise of improving the reliability of rules, we have achieved the rough control optimization goal between cost and efficiency. Finally, the model of reservoir scheduling has verified its feasibility and efficiency.

为掌握异步轧制板带变形规律,采用刚塑性有限元法建立了三维异步轧制有限元模型,应用DEFORM-3D有限元软件分析了热轧板带钢生产过程中的变形规律,研究了不同异径比和不同压下量时变形区内等效应变、轧制方向上的应变、剪切应变及位移的变化规律,并通过异步轧制试验验证,得到的结果与有限元模拟结果一致,为现实生产提供很好的理论依据.

After deeply analyzing the properties of hierarchical structure and interval concept which is constituted by upper and lower bound extensions and intension, in order to achieve the optimal decision solutions by reducing the decision and realizing the dynamic regulation, the interval three-way decisions space is put forward, combining with the three-way deci-sions based on decision-theoretic rough set. Firstly, the positive region, negative region and boundary region are divided by extension of interval concept, and the decision rules, decision metric function and decision loss function of three-way decision based on interval concept are given;secondly, interval three-way decisions concept and the decision which is formed by decision action and decision loss are proposed, and the three-way decision space is built using the construction method of interval concept lattice;thirdly, the dynamic strategy optimizing model based on interval three-way decisions space is established to realize the dynamic decision of practical issues and reduce the loss of incorrect decisions effectively;finally, the example of medical diagnosis shows the correctness and feasibility of this model.

为了得到满足用户需求的区间概念格结构,进一步挖掘高效的区间关联规则,文中提出基于参数变化的区间概念格结构更新算法.通过分析格结构更新度,进一步构建区间概念格的参数优化模型.运用参数逐渐逼近的方法得到一种参数获取策略,解决人为设定参数的主观性和无法预知性的问题.最后通过实例验证算法和模型的有效性.

为了更好地控制货叉扁钢的尺寸精度,省去后续加工,根据某钢厂生产货叉扁钢的轧制工艺,建立了货叉扁钢的热连轧模型,利用有限元软件DEFORM对扁钢精轧过程进行数值模拟.根据模拟结果分析了不同温度和摩擦系数对金属流动规律的影响,并通过曲线拟合的方式,得到了货叉扁钢宽展系数的数学模型,为制定合理的工艺参数,提高产品的尺寸精度提供可靠的理论依据.