To prevent fake news images from misleading the public, it is desirable not only to verify the authenticity of news images but also to trace the source of fake news, so as to provide a complete forensic chain for reliable fake news detection. To simultaneously achieve the goals of authenticity verification and source tracing, we propose a traceable and authenticable image tagging approach that is based on a design of Decoupled Invertible Neural Network (DINN). The designed DINN can simultaneously embed the dual-tags, \textit{i.e.}, authenticable tag and traceable tag, into each news image before publishing, and then separately extract them for authenticity verification and source tracing. Moreover, to improve the accuracy of dual-tags extraction, we design a parallel Feature Aware Projection Model (FAPM) to help the DINN preserve essential tag information. In addition, we define a Distance Metric-Guided Module (DMGM) that learns asymmetric one-class representations to enable the dual-tags to achieve different robustness performances under malicious manipulations. Extensive experiments, on diverse datasets and unseen manipulations, demonstrate that the proposed tagging approach achieves excellent performance in the aspects of both authenticity verification and source tracing for reliable fake news detection and outperforms the prior works.

In this paper, in pursuit of enhancing the spectral efficiency and reliability of transmission in multiple-input multiple-output (MIMO) communication system, a new design method, named as the generalization of quadrature index modulation (GQIM), is proposed. In GQIM system, the key and vector indications are exploited by the design of the transmitted spatial vector (TSV). Also, the transmit diversity gain by transmitting two versions produced by a three dimension (3D) symbol is achieved. More specifically, in our proposed GQIM system, an extended dimension signal constellation, so called extended 3D constellation (E3DC), is designed for the employment in the GQIM framework. Then, for achieving the transmit diversity gain, combing with the antenna indexes, the $X$ -axis, $Y$ -axis, $Z$ -axis components of two versions of the E3D symbol are constructed into four spatial vectors that are considered as candidates of the real/imaginary part of a complex TSV. Furthermore, two possible TSVs are obtained by using two adders and two key controllers with two states of 1 and $j$ . With the aid of the vector indication, one out of two possible TSVs is selected for transmission. Finally, the spectral efficiency and squared MED, the spatial index bits and computational complexity, the upper bound on the average bit error probability are analyzed. The analytical and simulation results demonstrate the correctness of GQIM and show that GQIM achieves a higher data rate and the reliability of transmission in comparison to the existing classic systems.

Human action recognition (HAR) is one of most important tasks in video analysis. Since video clips distributed on networks are usually untrimmed, it is required to accurately segment a given untrimmed video into a set of action segments for HAR. As an unsupervised temporal segmentation technology, subspace clustering learns the codes from each video to construct an affinity graph, and then cuts the affinity graph to cluster the video into a set of action segments. However, most of the existing subspace clustering schemes not only ignore the sequential information of frames in code learning, but also the negative effects of noises when cutting the affinity graph, which lead to inferior performance. To address these issues, we propose a sequential order-aware coding-based robust subspace clustering (SOAC-RSC) scheme for HAR. By feeding the motion features of video frames into multi-layer neural networks, two expressive code matrices are learned in a sequential order-aware manner from unconstrained and constrained videos, respectively, to construct the corresponding affinity graphs. Then, with the consideration of the existence of noise effects, a simple yet robust cutting algorithm is proposed to cut the constructed affinity graphs to accurately obtain the action segments for HAR. The extensive experiments demonstrate the proposed SOAC-RSC scheme achieves the state-of-the-art performance on the datasets of Keck Gesture and Weizmann, and provides competitive performance on the other 6 public datasets such as UCF101 and URADL for HAR task, compared to the recent related approaches.

A tractor is a type of agricultural machinery with complex structure and harsh operating conditions. It is evolving toward a large-scale, multifunctional, and intelligent system. Digital prototype technology is an effective approach for experts in multidisciplinary fields to collaborate in the development of new tractor products. Tractor performance prototype design is an important part of realizing digital tractor design. In the modeling process, the performance prototype models designed by experts have a problem with inconsistent expressions, making tractor digital design difficult to implement. This study aims to investigate the unified modeling of a tractor performance prototype. The design process of the tractor performance prototype was analyzed according to the characteristics of new tractor product development. Combined with the ontology modeling method, the construction process of the tractor performance prototype ontology was designed. Based on ontology metamodel theory, a multidisciplinary unified modeling method for a tractor performance prototype is proposed, and an ontology metamodel architecture was constructed. Using a wheeled tractor as an example, a performance prototype ontology was designed. Subsequently, an ontology model was created and verified in Protégé. The results indicate that the model can be used for the digital design of new tractor product development. An ontology model database was established, which realized the sharing and management of ontology model data, and the effectiveness of the method was verified.

This paper proposes a commonality learning strategy for face video forgery detection to improve the generalization. Considering various face forgery methods could leave certain similar forgery traces in videos, we attempt to learn the common forgery features from different forgery databases, so as to achieve better generalization in the detection of unknown forgery methods. Firstly, the Specific Forgery Feature Extractors (SFFExtractors) are trained separately for each of given forgery methods. We utilize the U-net structure and consider the triplet loss, location loss, classification loss, and automatic weighted loss to ensure the detection ability of SFFExtractors on the corresponding forgery methods. Next, the Common Forgery Feature Extractor (CFFExtractor) is trained under the supervision of SFFExtractors to explore the commonality of the forgery traces caused by different forgery methods. The extracted common forgery feature is expected to have a good generalization. The experimental results on FaceForensic++ show that the SFFExtractors outperform many state-of-the-arts in face forgery detection. The generalization performance of the CFFExtractor is verified on FaceForensic++, DFDC, and CelebDF. It is proved that commonality learning can be an effective strategy to improve generalization.

为使车辆在底盘测功机试验中具有实车道路试验的效果,需要为其室内试验系统创建更为接近实车道路试验的环境,利用虚拟现实技术创建虚拟环境为有效方法之一.本文根据车辆底盘测功机试验的功能,通过分析虚拟环境下试验系统的技术需求,构建了虚拟环境交流底盘测功机试验系统,分别设计了其虚拟环境子系统、测功机和电气子系统,以及测控子系统.通过对虚拟现实、动态加载控制和试验系统平台技术等关键技术的分析和应用,开发了Prescan软件的虚拟环境、Links-RT支撑的动态加载控制和DDS平台上计算机网络实时通信的底盘测功机试验系统.对比试验结果表明:室内底盘测功机试验与室外道路试验的受控速度误差在1 km/h的试验精度要求范围内,试验结果变化趋势一致,数据吻合.

实现无人测试车间及底盘测功机自动化是拖拉机新产品开发的必然趋势,试验拖拉机车速控制的精确度直接影响着试验加载力的精度.该研究以满足底盘测功机被试拖拉机车速精确控制为目的,根据辅助驾驶工作原理,制定了一种模糊PID控制策略,即在传统PID控制基础上,增加模糊推理模块参数进行实时调节,以实现更加快速的车速变化响应及对拖拉机车速更加精确的控制.建立了Matlab-Cruise联合仿真平台,采用NEDC工况及犁耕工况进行模拟仿真,并通过拖拉机底盘测功机进行试验验证,结果表明PID控制及模糊PID控制都能够实现车速跟随精度±0.5 km/h,模糊PID控制车速跟随精度更高,且速度变化时响应更快,车速波动更小,整体控制效果优于PID控制.该研究成果为拖拉机底盘测功试验时实现精确车速控制提供了技术基础,同时为实现底盘测功机无人测试车间提供了参考.

Generally, current image manipulation detection models are simply built on manipulation traces. However, we argue that those models achieve sub-optimal detection performance as it tends to: 1) distinguish the manipulation traces from a lot of noisy information within the entire image, and 2) ignore the trace relations among the pixels of each manipulated region and its surroundings. To overcome these limitations, we propose an Auto-Focus Contrastive Learning (AF-CL) network for image manipulation detection. It contains two main ideas, i.e., multi-scale view generation (MSVG) and trace relation modeling (TRM). Specifically, MSVG aims to generate a pair of views, each of which contains the manipulated region and its surroundings at a different scale, while TRM plays a role in modeling the trace relations among the pixels of each manipulated region and its surroundings for learning the discriminative representation. After learning the AF-CL network by minimizing the distance between the representations of corresponding views, the learned network is able to automatically focus on the manipulated region and its surroundings and sufficiently explore their trace relations for accurate manipulation detection. Extensive experiments demonstrate that, compared to the state-of-the-arts, AF-CL provides significant performance improvements, i.e., up to 2.5%, 7.5%, and 0.8% F1 score, on CAISA, NIST, and Coverage datasets, respectively.

为解决虚拟环境底盘测功机试验系统数据量大且传递频繁,在实时性、数据吞吐量等方面存在局限性问题,将数据分发服务(data distribution service,DDS)技术应用于虚拟环境底盘测功机试验系统.在分析虚拟环境底盘测功机试验原理及数据传输需求的基础上,通过对DDS的技术及应用研究,构建了基于DDS技术的虚拟环境底盘测功机试验系统,建立了各域成员发布订阅模型,注册了数据类型,定义了主题,设计了DDS接口类,实现对DDS接口的封装,解决了试验系统中DDS数据传输关键技术问题.对试验系统的数据传输时延和吞吐量进行了测试分析,结果表明:当数据量达到4000 kB时,时延为9.4 ms,数据传输吞吐量接近20 Mbit/s,满足车辆底盘测功机虚拟试验系统指标要求.

针对拖拉机动力换挡变速器(Power Shifting Transmission,PST)虚拟试验系统以单机集中式为主,在系统扩展、模型重用及虚实融合验证等方面存在局限性的问题,建立基于高层体系结构(High Level Architecture,HLA)和数据分发服务(Data Distribution Service,DDS)复合体系的拖拉机PST分布式虚拟试验系统.分析PST虚拟试验系统逻辑结构和硬件结构,在对比HLA与DDS三种集成方案的基础上,确定基于桥接组件的HLA与DDS互连结构.应用元模型理论,建立桥接组件元模型、桥接组件UML模型及HLA与DDS映射规则,开发桥接组件插件,解决虚拟试验系统中HLA与DDS之间的数据交互关键问题.对该系统的数据传输时延和吞吐量进行测试分析,结果表明:当数据量达到4000 KB时,时延为9.1 ms,数据传输吞吐量接近20 Mbit/s,满足拖拉机PST分布式虚拟试验系统时延不超过10 ms、吞吐量不低于15 Mbit/s的指标要求.

Realizing automation of the chassis dynamometer and the unmanned test workshop is an inevitable trend in the development of new tractor products. The accuracy of the speed control of the test tractor directly affects the accuracy of the test loading force. In order to meet the purpose of precise control of the test tractor speed on the chassis dynamometer, a fuzzy PID control strategy was developed according to the working principle of assisted driving. On the basis of traditional PID control, the parameters of fuzzy inference module were added for real-time adjustment to achieve faster response to tractor speed changes and more precise control of tractor speed. The Matlab-Cruise co-simulation platform was established for simulation, and the experiment was verified by the tractor chassis dynamometer using the NEDC working condition and tractor ploughing working condition. The results show that both PID control and fuzzy PID control can achieve tractor speed following accuracy of ±0.5 km/h. Fuzzy PID control has higher tractor speed following accuracy, faster response when speed changes, less tractor speed fluctuation, and overall control effect is better than PID control. The research results can provide a reference for the realization of the chassis dynamometer unmanned test workshop.

Architecture modeling, simulation, and test verification are performed to meet the requirements of multi-domain modeling and simulation of tractor power shift transmission (PST). The principles of architecture modeling and high level architecture (HLA) are analyzed, and the PST architecture modeling connotation and simulation system structure are studied. Then the dynamic principles of PST mechanical, hydraulic and control subsystems are analyzed in the preparation phase, sliding friction phase and holding phase of clutch engagement. To build the PST system simulation model, the simulation models and components of the three subsystems are established, and the object and interaction classes of the simulation object model (SOM) for each component are defined. After that, the parameter mapping relationship between the components is analyzed, the interfaces between the simulation components and HLA are encapsulated, and the simulation component running sequence is analyzed. Finally, the PST clutch engagement law under tractor shift conditions is simulated and tested. The relative error and correlation coefficient between the simulated and test data of shift solenoid valve drive current are used as indexes to evaluate the PST system simulation model. The results show that the simulated drive current curves are consistent with the test ones. The maximum error between the simulated and test shift time appears at the third gear downshift point, with a value of 7.89%, and the minimum correlation coefficient value between the simulated and the test drive current at all shift points is 0.92, which indicate that the PST system simulation model is effective and accurate.

With the rapid development of E-commerce, more and more people are used to shopping online, in which the reputation scores of sellers play an important role in helping consumers purchase satisfactory products. However, in the existing E-commerce environments, the reputation scores of users (including sellers and buyers) are centrally computed and stored on a centralized cloud server, which might make errors or even engage in fraud and forgery. To address this issue, we propose a blockchain-based decentralized reputation system (BC-DRS) in the E-commerce environment, i.e., online shopping. In this system, the product information including product descriptions and comments is stored in the interplanetary file system (IPFS) and the corresponding address is returned, and the returned address and the reputation scores of users are stored on the blockchain. The reputation evaluation is implemented by designing and deploying a smart contract on the blockchain. Different from the traditional centralized reputation systems (CRSs), the proposed BC-DRS can protect the product information and users reputation scores from intentional and unintentional modifications, since it is very hard to change any data stored in the blockchain and IPFS. Also, as the reputation scores of users are computed and updated by all the ratings of their transactions weighted by the practical transaction factors, it is effective to resist the common attacks, i.e., unfair rating and collusion. In addition, this system also contains a monetary incentive mechanism for the evaluation, which is helpful to form a virtuous circle in online shopping. The proposed BC-DRS is simulated on the popular blockchain platform, i.e., Ethereum with Solidity language. The experimental results and analysis demonstrate that the proposed BC-DRS has desirable usability and reliability.

Abstract The tractor performance prototype characterizes the multidisciplinary performance properties of tractor and plays an important role in the iterative upgrade process of new product performance. In order to meet the needs of collaborative development for tractor new products, the functions of distributed design and remote interconnection, and the performance verification of product system-level design, this paper analyzes the tractor collaborative development organizations and functions from the tractor performance prototype collaborative design theory. The performance prototype collaborative design process model is established with UML, and the design supporting environment characteristics are extracted. On this basis, a collaborative design architecture is constructed, and the key technologies which include the collaborative modeling and simulation, tool integration, data management and resource platform construction are proposed and analyzed. Through the preliminary study on the collaborative design architecture of tractor performance prototype, this paper aims to provide the theory and technical mode for developing the tractor digital, networked and intelligent design system.

As a necessary link for product development and evaluation, tractor testing covers new technologies in multidisciplinary fields and plays an important role in the research and development of product life cycle. This study discusses the research status of tractor test and evaluation technology and analyzes the new technology associated with the test and evaluation technology. Aiming at the problem of poor reusability, poor interoperability and weak expansion of the current tractor virtual test model, a virtual tractor-based test technology based on the architecture was proposed. The middleware technology, test data management technology, modeling technology and test environment construction technology in the tractor virtual test system were analyzed. Taking the tractor power shift transmission as an example, the application of the architecture-based virtual test system was verified, which pointed out the direction for the design verification of tractor innovative products.

Vehicle chassis dynamometer, as an important part of vehicle test equipment, plays an important role in the research and development of the vehicle's entire life cycle. The development history of vehicle chassis dynamometer from hydraulic dynamometer to AC dynamometer was reviewed, and it was proposed that AC chassis dynamometer has become the mainstream trend. The vehicle chassis dynamometer was further discussed from the aspects of measurement and control system and road simulation system. On the basis of the current research status of dynamometers, based on the virtual test technology, network, intelligence and function expansion, the development direction and research focus of vehicle chassis dynamometers are given to provide reference for the further development of vehicle chassis dynamometers.

针对拖拉机旋耕作业动力输出轴(PTO)载荷降噪中载荷先验特性预判的问题,提出了PTO载荷经验模态分解(EMD)软阈值降噪方法,得到了PTO载荷相同时域内不同频率固有模态函数(IMF).利用边界局部特征尺度延拓算法对IMF出现的端点效应进行了抑制,与镜像对称延拓算法和多项式拟合延拓算法比较,在运行时间、正交指数及IMF数量3项评价指标中均占优势.利用IMF分量与载荷相关系数,辨识出前3阶IMF分量为噪声主导分量,对前3阶IMF分量分别进行了软阈值降噪,与剩余分量叠加重构了降噪后的PTO载荷.降噪后的PTO载荷主频为4.492Hz,与试验中旋耕机刀轴旋转频率相符.与EMD低通滤波降噪算法比较,EMD软阈值降噪算法属于自适应数据驱动,不需要设定截止频率.以含噪信号与噪声误差比(dnSNR)为降噪性能评价指标,EMD软阈值降噪算法的dnSNR为12.712 5,小于EMD低通滤波降噪算法的dnSNR值13.266 6,对比结果表明EMD软阈值降噪算法对实测拖拉机PTO载荷降噪效果明显.

Mobile edge computing provides low-latency service computing for the Internet of Things (IoT). Considering the computational cost of high-quality image steganography in practical mobile applications, we believe that mobile edge computing could provide real-time service computing for covert communications. As a mainstream approach to convert communication, image steganographic algorithms prefer to hide secret data in well-textured regions in order to reduce the possibility of being detected. Recently, the generative adversarial networks (GAN) has become one of the most popular architectures for image steganography. However, the GAN-based image steganographic algorithms directly conduct the secret data embedding on the entire cover images and do not sufficiently take the regional texture complexity into account, which will compromise the anti-detection ability. To address this issue, we propose a novel image steganographic algorithm on the generated foreground object region with rich textures. More specifically, the foreground object region is generated onto a given cover image by the GAN, and the secret data is embedded in the foreground object region simultaneously during the generation of the region. The experimental results show that the proposed method can resist steganalysis effectively without significant degradation of image quality and achieve real-time processing.

The tractor load is a continuous and dynamic random load with time-varying amplitude and frequency, the time domain characteristics of which are represented by steady-state value, instantaneous value and dynamic load variation coefficient. The time domain characteristics of the random load reflect tractor working state, which are important parameters of tractor control systems for ploughing depth, selection of operating gears and timing of shifting, and load distribution of hybrid power. This kind of dynamic load signal is a colored random signal mixed in other random noises, and its time domain characteristics are difficult to obtain online, which becomes the bottleneck influencing the random load characteristics applied to the field of tractor real-time control. In this paper, based on the study of time domain and frequency domain characteristics of tractor random load signal, the triggered quadratic frequency conversion adaptive Kalman filter algorithm is used to realize the real-time extraction of random load characteristics. Then white noise is eliminated by Kalman filter to extract colored random load signals, and the load steady-state value is obtained after the colored noise is whitened by reducing sampling frequency of secondary filtering. In view of the unknown statistical characteristics of secondary filtering noise, a triggered fading adaptive filter combined with vehicle bus network information sharing technology is adopted to ensure the ability of filter to quickly track the load change. The simulation results show that the random load signal obtained by the algorithm is close to the reference value, and the load variation coefficient can reflect the characteristic changes of the random load, which lays a foundation for the dynamic control of tractor operation process.

At present, the coverless information hiding has been developed. However, due to the limited mapping relationship between secret information and feature selection, it is challenging to further enhance the hiding capacity of coverless information hiding. At the same time, the steganography algorithm based on object detection only hides secret information in foreground objects, which contribute to the steganography capacity is reduced. Since object recognition contains multiple objects and location, secret information can be mapped to object categories, the relationship of location and so on. Therefore, this paper proposes a new steganography algorithm based on object detection and relationship mapping, which integrates coverless information hiding and steganography. In this method, the coverless information hiding is realized by mapping the object type, color and secret information in object detection method. At the same time, the object detection method is used to find the safe area to hide secret messages. The proposed algorithm can not only improve the steganographic capacity of the two information hiding methods but also make the coverless information hiding more secure and robust.