Search

This article addresses novel real-valued consensus problems in the presence of malicious adversaries that can move within the network and induce faulty behaviors in the attacked agents. By adopting several mobile adversary models from the computer science literature, we develop protocols which can mitigate the influence of such malicious agents. The algorithms follow the class of mean subsequence reduced (MSR) algorithms, under which agents ignore the suspicious values received from neighbors during their state updates. Different from the static adversary models, even after the adversaries move away, the infected agents may remain faulty in their values, whose effects must be taken into account. We develop conditions on the network structures for both the complete and non-complete directed graph cases, under which the proposed algorithms are guaranteed to attain resilient consensus. The tolerance bound for network conditions becomes more strict as the adversaries are allowed to have more power. Extensive simulations are carried out over random graphs to verify the effectiveness of our approach when the information of the adversarial agents in terms of their models and numbers is unknown to the agents.

Non-orthogonal multiple access (NOMA) enables massive connectivity and achieves high spectral efficiency. The vast majority of the NOMA literature has adopted the ideal information rate as performance metric assuming perfect successive interference cancellation (SIC) without any error propagation, which, however, may lead to NOMA designs adverse to SIC. In this paper, we take into account imperfect SIC and practical modulation schemes for power-domain NOMA design. To characterize the error propagation, we derive the bit error rates (BERs) of the users for arbitrary-order quadrature amplitude modulation (QAM) schemes. Then, we propose a minimum error probability NOMA (MEP-NOMA) design, minimizing the average BER of the users via power allocation. Considering the complicated error probability expressions of the MEP-NOMA design, we derive lower and upper bounds on the average BER, based on which a simple closed-form power allocation is obtained. We show that the proposed power allocation minimizes both the lower and upper bounds on the average BER for a sufficiently large power budget and provides near-optimal error performance. On this basis, we theoretically prove the superiority of MEP-NOMA over existing OMA and NOMA schemes in terms of error performance. Comprehensive numerical results are provided to verify the accuracy of the error probability analysis of the considered practical NOMA scheme with imperfect SIC and to demonstrate the efficacy of the proposed MEP-NOMA design.

Background: With the advent of IoT, the deployment of batteries with a limited lifetime in remote areas is a major concern. In certain conditions, the network lifetime gets restricted due to limited battery constraints. Subsequently, the collaborative approaches for key facilities to reduce the constraint demands of the current security protocols. Objective: This work covers and combines a wide range of concepts linked by IoT based on security and energy efficiency. Specifically, this study examines the WSN energy efficiency problem among IoT devices and security for the management of threats in IoT through collaborative approaches and finally outlines the future. The concept of energy-efficient key protocols which clearly cover heterogeneous IoT communications among peers with different resources has been developed. Because of the low capacity of sensor nodes, the energy efficiency in WSNs has been an important concern. Methods: In this paper, we present an algorithm for Artificial Bee Colony (ABC) which reviews security and energy consumption to discuss their constraints in the IoT scenarios. Results: The results of a detailed experimental assessment are analyzed in terms of communication cost, energy consumption and security, which prove the relevance of a proposed ABC approach and a key establishment. Conclusion: The validation of DTLS-ABC consists of designing an inter-node cooperation trust model for the creation of a trusted community of elements that are mutually supportive. Initial attempts to design the key methods for management are appropriate individual IoT devices. This gives the system designers, an option that considers the question of scalability.

The differential steering vehicle uses the in-wheel motors to drive the wheels directly and individually. However, in order to deliver the required structural robustness, the differential steering vehicle discarded the mechanical steering system and achieved vehicle steering by applying differential speed between the left and right wheels. This paper presents a novel speed-adaptive motion control algorithm based on the unique chassis configuration to enhance the performance in vehicle handling and lateral stability. The proposed control method first estimates the driver’s driving intention, from which reference wheel speeds are individually generated for each wheel based on their respective slipping and skidding status. Finally, the torque command is automatically adjusted by the speed-tracking controller by proactive adaptation of the wheel spinning resistance to effectively avoid excessive slip on low friction. This method exploits the fact that the torque at the steady state will always be equal to the available longitudinal force, thereby delivering the sophisticated tire force estimation without additional computational efforts, and ultimately helping conserve energy and promote lateral stability. The essential road information collected by this algorithm is also made available to drivers for improved vehicle controllability. The algorithm is subjected to three experimental case scenarios—pivot steering, low-friction driving, and curvilinear driving—through TruckSim–Simulink co-simulations and real vehicle tests, and the results have validated the algorithm in realizing the high-performance steering and maneuvering capabilities for six-wheeled differential steering vehicles.

Creep control is a kind of start-up control for electric vehicle. In the paper, two closed-loop control is contained in the creep control strategy. Proportional control with torque limitation, which adjusts vehicle speed, is the outer-loop control; and anti-slip control is the inner-loop control. In this way, the vehicle speed indicates no overshoot and has uniform convergence with driving torque. Moreover, the vehicle can start up on low adhesion or split road, and the driver can control the creep speed by the brake pedal only, so that the driver’s operation is reduced. Subjective evaluation method is proposed to determine the control performance metrics, and then the mathematical relationship between the performance metrics and the control parameters is established. The tuning method of the control parameters is proposed according to those performance metrics, which mitigates the workloads of calibration and provides a better driving experience. Some simulations and real vehicle experiments are conducted to verify that the control strategy has an expected performance.

At present, loss rate and grain damage are the most complicated problems for combine harvester. Besides, existing controllers that control threshing quality do not take into account environmental noise, data fluctuations, and other detection factors. In this paper, considering the interference of uncertain factors, a control strategy with low crashed rate and reduced loss rate using type-2 Fuzzy Logic Controller (FLC) is proposed. This control strategy takes threshing separation component as a research object and adopts combination of theory with experimental analysis. Firstly, basic data acquisition experiment of threshing system is designed. Secondly, a control strategy is established by adequately previous filled test data. In the process of control strategy design, Fuzzy Logic Toolbox evaluates the performance of type-2 FLC. Integral of Square Error (ISE) and Integral of the Absolute value of the Error (IAE) show a better performance of type-2 FLC than of type-1 FLC. At last, field experiments are designed to verify the effectiveness of type-2 control strategy. The field test shows that the maximum reduction of grain damage rate and loss rate can reach to 44.08 % and 29.6 %. Experiment results show that the type-2 FLC can significantly reduce loss rate, crashed rate, and improve threshing quality.

In-wheel motor-driven vehicle improves the overall performance with its torque vectoring system, which distributes the torque command of each motor. This paper proposes a novel torque allocation algorithm to dynamically optimize energy consumption of the vehicle. It splits the optimization problem into two sub-problems and obtains the executive torque of each side. The method also simplifies the solution by modification and discretization of feasible torque space, thus ensuring that there must be solvable and reducing online computational load. Two representative simulation cases—New European Driving Cycle and Fault Tolerance—have been selected and conducted through Cruise–Simulink co-simulation platform. The simulation verifies that the method decreases three energy consumption indices by 18.5%, 13.9%, and 14.7%, respectively, than those of the average allocation and coordinates all motors effectively based on vehicle’s operating status, which proves its practicability and robustness.

This paper presents the development of a brain–machine interfacing teleoperation control framework of a mobile robot using quadrupole potential function (QPF). The online brain–computer interface is based on steady-state visually evoked potentials, which employs the multivariate synchronization index classification algorithm to decode the human electroencephalograph (EEG) signals. In this way, human intentions can be recognized and EEG control commands can be produced for the mobile robot. Besides, a novel artificial potential function named QPF is designed to produce the potential fields to parameterize the EEG control commands. The classification results of the EEG signal are related to the distribution of the potential fields, and the collision-free path to a target position is automatically planned by the potential field. Such semi-automatic design builds the direct mapping from human intentions to the mobile robot’s behavior and reduces mental effort or exhaustion on subject’s part. Besides, based on the QPF with the capability of handling nonholonomic constraints, the integrated system can not only achieve obstacle avoidance but is also able to automatically stabilize the robot to a target configuration. Extensive experiment studies were conducted on several subjects to demonstrate the effectiveness of the proposed approaches.

Human beings have a great generalization ability to recognize a novel category by only seeing a few number of samples. This is because humans possess the ability to learn from the concepts that already exist in our minds. However, many existing few-shot approaches fail in addressing such a fundamental problem, {\it i.e.,} how to utilize the knowledge learned in the past to improve the prediction for the new task. In this paper, we present a novel purified memory mechanism that simulates the recognition process of human beings. This new memory updating scheme enables the model to purify the information from semantic labels and progressively learn consistent, stable, and expressive concepts when episodes are trained one by one. On its basis, a Graph Augmentation Module (GAM) is introduced to aggregate these concepts and knowledge learned from new tasks via a graph neural network, making the prediction more accurate. Generally, our approach is model-agnostic and computing efficient with negligible memory cost. Extensive experiments performed on several benchmarks demonstrate the proposed method can consistently outperform a vast number of state-of-the-art few-shot learning methods.

Aiming at the traffic safety problem caused by sudden agglomerate fog on the highway, this paper designs an early warning system of the robot for monitoring agglomerate fog on the highway based on Beidou short message and MQTT protocol. This system monitored environmental parameters such as visibility, location information, temperature and humidity in real time by the robot for monitoring agglomerate fog on the highway, and adopts the Beidou short message and MQTT protocol dual-channel communication mode to achieve two-way data communication with the cloud platform and server. The problem of data transmission loss caused by no mobile communication network is solved. Use the Internet of Things cloud platform and WEB application development technology to realize a system with the functions of monitoring data visualization, data monitoring and remote control of robot movement. The experimental results show that the communication that data interaction and remote control between the cloud platform and the robot is stable in the system, and the early warning of the level of fog is timely and effective, which improve the accuracy of monitoring agglomerate fog with broadly application foreground.

Few-shot learning (FSL), aiming to extract new knowledge from very small amount of labeled samples, has attracted noticeable attentions recently. However, most of existing methods often fail when facing huge domain shift between seen and unseen classes. We think this should be attributed to the episode strategy which ignore utilizing support samples to induct the test classes. So in this paper, for the first time, we propose a bilevel episode strategy (BL-ES) to train a inductive graph network (IGN) that learn to both comparison and induction. Specifically, first, outer episodes in BL-ES simulate the cross-domain few-shot tasks constantly, while inner episodes learn to drive IGN to induct the common features of test classes. Then, the propsoed IGN captures the correlation among all samples to update meta points of each category in induction module. Finally, we introduce a geometrical constraint term utilizing meta points into the training loss, to update the nodes and edges in feature space. This way improves the robustness of training process. Extensive experiments show that our framework outperforms the state-of-the-art FSL alternatives, and are more suitable for real-world applications.

Few-shot learning, which attempts to predict unlabeled samples with only a few labeled samples, has drawn more and more attention. Though recent works have achieved promising progress, none of them have noticed to establish consistency among episodes, leading to the ambiguity in latent embedding space. In this paper, we propose a novel Cross-Modality Graph Neural Network (CMGNN) to uncover the associations among episodes for consistent global embedding. Since the semantic information induced from NLP is relatively fixed compared to visual information space, we leverage it to construct meta nodes for each category to guide the corresponding visual feature learning through GNN. Moreover, to ensure global embedding, a distance loss function is designed to force the visual nodes closer to their associated meta nodes to a greater extent. Extensive experiments and ablation studies on four benchmark datasets show its superiority over many SOTA comparison methods.

In this paper, an optimal controller is designed and applied to the lower-limb exoskeleton robot, which could improve the robustness under nonlinear perturbations. In order to derive the optimal controller, we build the modeling of the exoskeleton robot to simplify the structure of the robot, and then we define a cost function, because the cost function is difficult to solve, so we adopt the function approximation method to approximate its optimal value, and the optimal control is obtained by solving the Hamiltonian equation. Finally, simulation studies are carried out. These simulation studies verify that the controller has a good performance even in the presence of disturbance.

In order to cater to the advanced user positioning function of the Beidou satellite navigation system, the simulated domestic positioning point data is used to realize the visualization of user distribution in the form of a heat map through the Webside 3D visualization technology. In the case of a large amount of rendering data, by optimizing the kernel density estimation algorithm and optimizing the calculation method of the data points in the raster, the effect of real-time rendering of the heat map in the optimal display form is realized with the change of the viewpoint position, and the rendering Performance has been significantly improved.

In order to meet the requirements of airborne ultraviolet communication, the ultraviolet clustering structure model and an Ultraviolet Link Performance Dynamic Source Routing (UV-PDSR) that established by the traditional Dynamic Source Routing (DSR) routing protocol is proposed. Considering the characteristics of the ultraviolet link status and aircraft nodes, an appropriate weighted according to the actual requirements is given in this routing protocol, and the optimal route is selected rely on the link weight. The simulation results show that the UV-PDSR protocol has the characteristics of low end to end delay and high packet delivery ratio compared with the DSR protocol. The network performance was greatly improved, and the new protocol is more suitable for high-speed mobile airborne ultraviolet communication.

This paper describes the brain-actuated control of a dual-arm robot performing bimanual relative motion manipulation tasks, through the adoption of relative Jacobian matrix, wherein the dual-arm robot can be considered as a single manipulator and the movements of the end effectors can be calculated by the relative motion. An online brain–machine interface (BMI) system based on multichannel steady-state visual evoked potentials was developed, and it was able to perform band-pass filtering and visual stimuli classification using support vector machines. Considering the relative motion in a constrained plane, the asymmetric bimanual manipulation can be transformed into 2-D control tasks through polar coordinate transformation such that the end effectors can achieve smooth direction-and-distance motion in the arbitrary position of the operational space. Moreover, the kinematics redundancy scheme, using online neuro-dynamics optimization, was developed for joint velocity optimization subject to physical constraints. Five individuals participated in the experiments and successfully fulfilled the given manipulation task.

Model predictive control (MPC) for spray cooling control system requires a repeated online solution of an optimization problem that includes partial differential equations (PDEs). To simulate the future temperature behavior of steel billets, 3D dynamic heat transfer model is used. The special solution domain of PDEs has led to large computation cost, which is the main challenge in the real-time practical application of spray cooling control system. Meanwhile, the heat transfer coefficients need to be identified using the measured surface temperature. This work presents a two-level parallel solution method implemented on a Graphics processing unit (GPU) for MPC of spray cooling control systems and a weighted least squares modified conjugate gradient method (WLS–MCG) for identification of heat transfer coefficients. Two-level parallel solution method consists of parallel-based heat transfer model and stream parallel particle swarm optimization (PSO). PSO is used to solve the optimization problem. WLS–MCG consists of the weighted least squares (WLS) and modified conjugate gradient method (MCG). The experimental results show that the two-level parallel solution method has good computational performance and achieves satisfactory control performance.

Since the existence of fuzziness in the real world, uncertainty could be always present in the reasoning results. Therefore, how to tackle with the hesitation existing in the process of reasoning is a meaningful issue for the construction of the inference system. In this paper, a novel interval type-2 intuitionistic fuzzy neural network based on long-short term mechanism is proposed (LSTM-IT2IFNN). By means of interval type-2 intuitionistic set, the hesitation of reasoning is described and involved to determine fuzzy rules in inference system, by which the chosen of fuzzy rules not only considers the membership value but also non-membership degree. In order to handle the regression problems with long-term time dependency, long-short term mechanism is introduced into fuzzy neural networks, which can effectively improve the memory ability of long-term knowledge. Furthermore, by means of intuitionistic sets, an extended metacognitive learning mechanism is proposed for the adaptively online learning of network structure, where it achieves when, what, and how to learn from the sequential data. The performance of the LSTM-IT2IFNN is evaluated on different regression problems, including synthetic and real-world data. By comparing to existing algorithms, the experimental results show the efficiency and accuracy of the proposed scheme.

According to the link characteristics of satellite communication, this paper clarifies the principles of selecting the evaluation index of the satellite communication complex electromagnetic environment adaptability before the adaptability evaluation, constructs the satellite communication electromagnetic environment evaluation index system, and proposes the evaluation method of the complex electromagnetic environment adaptability. With the development of communication satellite technology and the massive launch of communication satellites, Communication satellites are facing increasingly complex electromagnetic environments caused by intentional and unintentional interference, this complex spatial electromagnetic environment composed of a large number of electromagnetic signals with complex patterns, densely overlapping, and dynamic overlapping forms a severe test for the normal operation of communication satellites. Therefore, how to improve the adaptability of complex electromagnetic environment and the level of scientific evaluation, has become a key issue that needs to be solved urgently for communication satellites.

Power load forecasting is an important work of power sector, which is very important for making scientific and reasonable power grid planning scheme. The concept of grid planning of distribution network puts forward new requirements for power load forecasting. In this paper, under the background of grid planning of distribution network, according to the characteristics of power load in the existing power grid, the spatial load forecasting technology in the area with regulatory planning and without planning is studied respectively, and the load forecasting methods of three levels of equipment capable of providing electricity, power supply grid and area where the electricity is supplied are given from bottom to top. The results show that the error between users and residents is better than 5% in the experiment, and the error between users and residents is not more than 5%.

Under the requirement of “green energy consumption” integrated energy system (IES) appeared as one of the most significant and powerful solutions, dispatching various kinds of available distributed energy resources to meet the demand, thus promoting the renewable energy consumption, as well as reducing the green house gas emission and the generation cost. However, due to the complexity and high cost of IES construction, the selection of different kinds of equipment and the cooperation of different energy parts are still problems limiting its popularization. This paper introduces a practical approach on system configuration planning and dispatch optimization for IES, which consider multiple economic indexes simultaneously based on local demand and installation conditions. This approach optimizes the energy equipment selections from the perspective of types and installed capacities, thus offers different results of equipment combinations, operational and economic conclusions and suggestions based on the system running simulations under typical days in different seasons, including heating, cooling and regular seasons. Two case studies are shown with this proposed approach on an industrial IES project in China. The results provide the IES investors with primal configuration plan and system design for IES based on considered economic indexes, as well as detailed dispatch plans for future investment.

Advanced Driving Assistant Systems (ADAS) are mature in vehicles. At the same time, automatic driving technology is starting to be applied. But compared with those intelligent cars, old vehicles without any assistance are exposed to the dangers of accidents. And by the fact that, it is unsuitable to install ADAS on old motor vehicles, we are in dilemma to monitor their behaviours of while driving. This paper introduces an intelligent behaviour monitoring and safeguard system with high accuracy, robustness and convenience for drivers in their regular vehicles to guarantee both public’s and their own safety. It merges computer vision,and multiple biosensors to collect both drivers behavioural data and health data. Considering the influence of emotion of drivers while driving, their facial expression and driving aggressiveness will be detected as well. For data from biosensors, we use a Statistical-based Bayes data fusion Method to deal with data from multiple sensors and different kinds of data. Using the cloud and Internet of Things (IoT) technology to concentrate those data, the visualized data can be checked and managed on a smartphone. Drivers in unsafe driving states will be warned by a voice assistant. The system can be connected to smart city system in progress, and drivers behaviour and health data is valuable for future data mining as well.

The frequency reuse technology is the key technology for improving the system capacity and the edge user communication quality in the wireless network. But for cell edge users, the current method cannot adjust the frequency reuse (FR) strategy with the distribution of the neighboring cell, resulting in a decrease in the edge user signal-to-interference-plus-noise ratio (SINR). In this chapter, a dynamic multimode FR scheme based on reinforcement learning is proposed. Through the sensing of the wireless network working scene by the reinforcement learning, the network automatically chooses the best frequency reuse mode. Four FR modes are established according to the spectrum utilization ratio and the interference degree of edge users, so as to optimize the network capacity and spectrum utilization ratio. Real-time network requirements are used as input parameters for reinforcement learning. The simulation results show that this method can effectively improve the communication performance of edge users, thereby improving the SINR of the received signal and the throughput of cell networks.

In order to solve the problem of optimal scheduling and reasonable allocation of limited materials in a short time after a natural disaster, a clustering supply chain emergency material distribution priority decision algorithm based on density clustering algorithm is proposed. Perform clustering as a factor indicator to determine the priority level of emergency material distribution in each supply chain in the clustered supply chain. Based on the material importance, timeliness, and gap index factors, a fuzzy C-means clustering algorithm for supply chain emergency material demand importance decision algorithm is proposed to classify a variety of emergency materials required in disaster areas when an emergency occurs. , And decide the importance of each type of emergency supplies. The results of simulation experiments verify the feasibility of the emergency supply materials scheduling and importance decision-making method for the clustered supply chain. The decision results guarantee the optimal scheduling and allocation of limited supplies in the shortest possible time. And transportation programs provide theoretical support.

Based on the analysis of cluster supply chain risk characteristics, starting from the analysis of technical risk dimensions, information risk dimensions, human risk dimensions, and capital risk dimensions, a cluster supply chain risk severity assessment index system is designed. The fuzzy C-means clustering algorithm based on data flow is used to cluster each supply chain, analyze the risk severity of the supply chain, and evaluate the decision of the supply chain risk severity level based on the cluster weights and cluster center range. Based on the analytic hierarchy process, the risk severity of the entire clustered supply chain is made an early warning decision, and the clustered supply chain risk severity early warning level is obtained. The results of simulation experiments verify the feasibility of the decision method for cluster supply chain risk severity, and improve the theoretical support for cluster supply chain risk severity prediction.

The innovation of art teaching mode is to develop art teaching resources and organize professional teaching with the help of network teaching platform. According to the actual needs of users in the process of art teaching and the problems in the learning resource management system, this paper designs and implements a learning resource management system based on mobile cloud computing combining mobile cloud computing technology, framework, ontology technology and data mining technology, and provides the system architecture and functional modules. The system platform takes learners as the service center, and the sharing and retrieval efficiency of learning resources and enriching the classification of learning resources are taken as the design goal. Through the test of the function and performance of the system platform, it is verified that all the functional modules in the platform can operate normally, which achieves the initial design goal, and proves the feasibility of our scheme.

Single-image super-resolution plays an important role in computer vision area. However, previous works using convolutional neural networks perform badly when reconstructing high frequency details, result in over-smooth and lacking of textural information in the output. At the same time, super-resolution computation always relays on convolutional neural networks with huge depth, which is super tricky to train and use. In this paper, we propose a novel network with better textural details in wavelet domain, which is composed of a feature extract layer, residual channel attention groups (RCAG) and a residual up-sampling layer based on inverse discrete wavelet transform. Channel attention and spatial attention layers are inserted into residual channel and spatial attention blocks (RCSAB), enhancing the learning of high frequency information with attention maps. Composed of a chain of RCSAB and a channel attention layer with short skip connection, RCAG is good at catching long-term high frequency information. Then the feature mapping component is composed of a chain of RCAG. Experiment shows that our method performs better than state-of-the-art methods on benchmark datasets in different scales.

Based on the needs of power processing unit (PPU) in space propulsion system, this paper analyzes the application of four-switch Buck-Boost converter (FSBB) in this field. In terms of FSBB’s control strategies, the traditional single-mode strategy is low efficiency. While the two-mode strategy’s control loop is relatively complicated. What’s more, near the two modes’ switching point, the converter will continuously switch between the Buck and Boost modes, which is not conducive to the stable operation of the system. So this paper proposes an improved single-mode control strategy. By fixing the switches’ duty cycle of the Buck unit and controlling the duty cycle of the Boost unit, FSBB is enabled the function of buck-boost only in Boost mode. Also, an 80-160V input and 125-250V output prototype was built in the laboratory to verify the proposed strategy.

Nowadays, GF-1 (GF is the acronym for GaoFen which means high-resolution in Chinese) remote sensing images are widely utilized in agriculture because of their high spatio-temporal resolution and free availability. However, due to the transferrable rationale of optical satellites, the GF-1 remote sensing images are inevitably impacted by clouds, which leads to a lack of ground object’s information of crop areas and adds noises to research datasets. Therefore, it is crucial to efficiently detect the cloud pixel of GF-1 imagery of crop areas with powerful performance both in time consumption and accuracy when it comes to large-scale agricultural processing and application. To solve the above problems, this paper proposed a cloud detection approach based on hybrid multispectral features (HMF) with dynamic thresholds. This approach combined three spectral features, namely the Normalized Difference Vegetation Index (NDVI), WHITENESS and the Haze-Optimized Transformation (HOT), to detect the cloud pixels, which can take advantage of the hybrid Multispectral Features. Meanwhile, in order to meet the variety of the threshold values in different seasons, a dynamic threshold adjustment method was adopted, which builds a relationship between the features and a solar altitude angle to acquire a group of specific thresholds for an image. With the test of GF-1 remote sensing datasets and comparative trials with Random Forest (RF), the results show that the method proposed in this paper not only has high accuracy, but also has advantages in terms of time consumption. The average accuracy of cloud detection can reach 90.8% and time consumption for each GF-1 imagery can reach to 5 min, which has been reduced by 83.27% compared with RF method. Therefore, the approach presented in this work could serve as a reference for those who are interested in the cloud detection of remote sensing images.

The acquisition of stereoscopic video source will be an attractive subject when the way of stereoscopic display sees dramatic breakthroughs. A stereo image synthesis based on the oblique photography of unmanned aerial vehicle (UAV) is proposed to solve the problems of high data acquisition, high cost, and low modeling efficiency existing in the traditional three-dimensional video synthesis method. First, orthoimage and oblique image are captured by UAV lens following a planned path. Next, three-dimensional model is constructed by using the three-dimensional point cloud generated by aerial triangulation, and the wall texture extracted from multi-view image is mapped to the corresponding model. Then, taking Yangzhou building of Nanjing University as an example, the 3D model of the building was constructed and the 3D image pairs were synthesized. Experimental results show that this method not only meets the precision requirements of the model, but also greatly improves the efficiency of aerial image stereo synthesis and reduces the production cost.

Towards providing efficient human-robot interaction, surface electromyogram (EMG) signals have been widely adopted for the identification of different limb movement intentions. Since the available EMG signal sensors are highly susceptible to external interferences such as electromagnetic artifacts and muscle fatigues, the quality of EMG recordings would be mostly corrupted, which may decay the performance of EMG-based control systems. Given the fact that the muscle shape changes (MSC) would be different when doing various limb movements, the MSC signal would be nonsensitive to electromagnetic artifacts and muscle fatigues and maybe promising for movement intention recognition. In this study, a novel nanogold flexible and stretchable sensor was developed for the acquisition of MSC signals utilized for decoding multiple classes of limb movement intents. More precisely, four sensors were used to measure the MSC signals from the right forearm of each subject when they performed seven classes of movements. Also, six different features were extracted from the measured MSC signals, and a linear discriminant analysis- (LDA-) based classifier was built for movement classification tasks. The experimental results showed that using MSC signals could achieve an average recognition rate of about 96.06 ± 1.84% by properly placing the four flexible and stretchable sensors on the forearm. Additionally, when the MSC sampling rate was greater than 100 Hz and the analysis window length was greater than 20 ms, the movement recognition accuracy would be only slightly increased. These pilot results suggest that the MSC-based method should be feasible in movement identifications for human-robot interaction, and at the same time, they provide a systematic reference for the use of the flexible and stretchable sensors in human-robot interaction systems.

In this paper, a multiple camera eye localization for stereoscopic display is proposed. The multi-camera system contains an infrared camera and a binocular camera. Candidate face area for low-resolution infrared image is obtained by using YOLO-V3 network. Then face distance is calculated by an embedded ARM platform Raspberry Pi-3B+, which provides a priori knowledge for the face detection of the high-resolution visible light camera. AdaBoost and LBF algorithm are used for complete face detection and alignment, and finally they achieve the goal of eye location. Sliding window stereo matching method can improve the efficiency of stereo matching. The experiment results verify the feasibility of the proposed scheme. The speed, accuracy, and robustness of eye tracking are excellent.

The grounded electrical source airborne transient electromagnetic (GREATEM) system, which uses a grounded electrical transmitter and an aircraft for the receiver, offers deep exploration capability and detection efficiency. However, GREATEM field data usually includes mixed varied noises (white noise, sferics noise and human noise), which make identifying the exponential decaying signal too difficult. Traditional filtering methods mainly focus on suppressing specific noise types, which may cause the distortion of GREATEM signal, especially when the signal is affected by high residual sferics noise. This paper presents an exponential fitting-adaptive Kalman filter (EF-AKF) to remove mixed electromagnetic noises, while preserving the signal characteristics. The EF-AKF consists of an exponential fitting procedure and an adaptive scalar Kalman filter (SKF). The adaptive SKF uses the exponential fitting results in the weighting coefficients calculation. The EF-AKF is verified on an analytical three-layer model. It is compared with the SKF and wavelet threshold-exponential adaptive window width-fitting denoising algorithm (WEF) in synthetic data. The results showed that the EF-AKF outperformed the other methods in the noise reduction of GREATEM data. The EF-AKF is also tested on a synthetic quasi-2D earth model and applied to GREATEM field data in Huaide, Jilin province, China. Application of the EF-AKF allowed considerable improvement of the quality of the GREATEM field data.

With the development of rail transit, driver vigilance is increasingly important in railway safety. A vigilance detection method based on high-speed rail (HSR) is presented in this study. The proposed method includes three main parts: (i) a wireless wearable electroencephalography (EEG) collection module; (ii) HSR driver's vigilance detection module; and (iii) an early warning module. Drivers’ vigilance is monitored using eight EEG channels. A low-rank matrix decomposition (also called robust principal component analysis) algorithm is used to classify EEG signals which are collected through wireless wearable EEG collection technology. The warning module will sound an alarm and the early warning begins to message the train control centre if the driver is judged as fatigue. The method was tested on driving EEG data from ten different drivers and reached 99.4% correct classification in a 9 s time window. The feasibility of the proposed vigilance-detecting method for HSR safety is demonstrated through simulation and test results.

In the light field imaging, the geometrical parameters’ calibration of the light field camera is the foundation of computational imaging techniques, such as the calibration of the light field data, digital refocusing, depth reconstruction, all-in-focus imaging, and so on. In this paper, we propose a virtual image points based geometrical parameters’ calibration for focused light field camera. In the forward model, the mapping from the object points to the virtual image points with respect to the main lens as well as the mapping from the virtual image points to the image points on the detector with respect to the microlens array are established. While calibrating geometrical parameters, the inverse problem of calculating the virtual image points from the corner on the detector is established and the model of calculating the geometrical parameters of the focused light field camera is established. Levenberg–Marquardt algorithm is used to solve the geometrical parameters iteratively. We use the checkerboard for the calibration experiment and validate the calculation via the reprojection of the checkerboard corners.

In order to discover in time the potential interference coupling relationship caused by the installation of multiple types of frequency-using equipment and antennas on an aircraft or spacecraft platform, and to improve the rationality and compatibility of the antenna layout. The antenna isolation must be simulated at the beginning of the aircraft or spacecraft platform design, and the antenna isolation must be tested before the antenna is installed. In this article, the simulation and test results of the real case show that the model construction error during simulation, the actual spatial attenuation, the actual diffraction attenuation, the actual occlusion factor and the test error during the test process have formed the preliminary error relationship between simulation results and test results.

This paper proposes three spatial electromagnetic signal environment concepts from three levels: general electromagnetic signal environment, relative electromagnetic signal environment and electronic warfare signal environment. It can solve the difficult problem of comprehensive, accurate and targeted description of the electromagnetic environment in the space electromagnetic environment simulation of the spacecraft. This paper studies the synthesis method of various types of signals contained in the three electromagnetic signal environments in a certain area, and provides a reference for the accurate simulation of the dynamic and intuitive, hierarchical electromagnetic environment situation in a certain area of space.

During the observations made by imaging satellites, meteorological factors are likely to change frequently. The vagaries of weather conditions and significant effects on the actual observation results mean that there is an urgent need to apply more intelligence to satellite mission planning. Thus, this paper describes an autonomous replanning method for imaging satellites that considers the real-time weather conditions. Considering the characteristics of different input data, this method replans the low-yield task set and fine-tunes others to improve profitability. Moreover, the proposed method can heuristically select the appropriate adjustment rule to achieve autonomous satellite mission planning. A series of simulations with various task quantities and in different environments shows that the proposed method can respond effectively to real-time weather changes, and can steadily improve the total profits in a variety of weather conditions during Earth observation activities.

Satellite hardware has reached a level of development that enables imaging satellites to realize applications in the area of meteorology and environmental monitoring. As the requirements in terms of feasibility and the actual profit achieved by satellite applications increase, we need to comprehensively consider the actual status, constraints, unpredictable information, and complicated requirements. The management of this complex information and the allocation of satellite resources to realize image acquisition have become essential for enhancing the efficiency of satellite instrumentation. In view of this, we designed a satellite auto mission planning system, which includes two sub-systems: the imaging satellite itself and the ground base, and these systems would then collaborate to process complicated missions: the satellite mainly focuses on mission planning and functions according to actual parameters, whereas the ground base provides auxiliary information, management, and control. Based on the requirements analysis, we have devised the application scenarios, main module, and key techniques. Comparison of the simulation results of the system, confirmed the feasibility and optimization efficiency of the system framework, which also stimulates new thinking for the method of monitoring environment and design of mission planning systems.

Depth image based rendering (DIBR) is the most widely used technology among synthesis algorithms. Hole filling is a challenge in producing desirable synthesized images. In this paper, we propose an enhanced non local mean based hole filling method. Color, gradient and depth information is combined to select the optimal candidate patches. The missing information from holes is then formed by aggregating multiple candidate patches. Furthermore, an efficient invalid pixel classification method based on their chararcteristics is proposed to divide invalid pixels into three types, and use different methods to fill them, and reduce the computational load of the hole filling unit. The results show that the proposed method has a better robustness and performance for hole filling in DIBR systems than other hole filling based on algorithms.

VGA is a video transmission standard, which is widely used in the field of display. In the development of embedded system, the traditional microprocessor can not realize the timing of VGA interface. In this paper, discussedthe VGA display timing , and designedthe hardware interface circuit of VGA display. The VGA display driver is realized by hardware description language, and the VGA display of static characters is realized by customized character ROM. The system is simulated and tested to verify the correctness of the design.

A novel parallel dual-frequency single-phase grid-connected inverter (PDF inverter) is proposed to improve the quality of the output current and reduce the loss of the grid-connected inverter. In the PDF inverter, there are two units which operate at different switching frequencies. The low-frequency unit has a low switching frequency (2kHz), which transfers electrical energy to the grid. The high-frequency unit operate at a high switching frequency (40 kHz), and its current is reversed to the harmonic current of the low-frequency power unit. The principle and control strategy of the novel grid-connected inverter is presented. And the comparison of power loss of two inverters shows that the novel grid-connected inverter has higher efficiency than the LCL-type grid-connected inverter. These capabilities have been demonstrated by mathematical derivation and experiment. For the experiments, a 1500-W prototype has been built in the laboratory. Results obtained confirm the practicality and performance of the proposed inverter.

When a DC line fault happens, the converter will be blocked instantly. This leads to an interruption of power transmission and influences the stability of DC and AC systems. To avoid the blocking of converters, this paper presents a novel protection scheme for VSC-HVDC system, which consists fault isolation and auto-reclosing of DC circuit breaker (DCCB). First, this paper coordinates the protective actions of converters and DCCB. The DC line fault is cut immediately by DCCB while the blocking signal of converter is isolated during the fault. Second, since the faults of long overhead transmission DC lines are mostly transient, an auto-reclosing strategy is developed. The emphasise of this part, which includes fault discrimination and time sequences, between DCCB and converter is elaborated, and the value of reclosing delay is derived by analysing the charging and discharging characteristics of capacitor paralleled with converter. Finally, the protection scheme is evaluated by overcurrent, overvoltage, and recovery time of DC system, and simulation results of a point-to-point VSC-HVDC transmission system proves its validity.

Most of the published research work mainly emphasizes one aspect of knowledge graph construction in isolation and neglects the big data processing flow in this process, which lacks of value in the practical construction of knowledge graph. Therefore, the paper proposes a construction method of domain knowledge graph based on big data-driven and build an artificial intelligence domain knowledge graph to prove the feasibility of this method, which covers artificial intelligence enterprises, patents, news, technology labels and other entities.

In the context of personalization e-commerce cyberspace based on massive data, the traditional single-domain recommendation algorithm is difficult to adapt to cross-domain information recommendation service. Collaborative filtering is a simple and common recommendation algorithm, but when the target domain is very sparse, the performance of collaborative filtering algorithm will seriously degrade. Cross domain recommendation is an effective way to solve this problem because it is made by means of the auxiliary data domain associated with the target data domain. Most of the existing cross-domain recommendation models are based on two-dimensional rating matrix, and much other dimension information is lost, which leads to a decrease in recommended accuracy. In this paper, we propose a cross-domain recommendation method based on tensor decomposition, which can reduce the sparseness of data and improve the diversity and accuracy. It extracts the scoring patterns in different fields to fill the vacancy value in the target domain by transfer learning method. Many experiments on three public real data sets show that the proposed model’s recommendation accuracy is superior to some of the most advanced recommendation models. It can be applied to large-scale cross-domain information recommendation service and cybersecurity data analytics.

Saliency detection plays an important role in computer vision area. However, most of the previous works focus on detecting the salient regions, rather than the objects, which is more reasonable in many practical applications. In this paper, a framework is proposed for detecting the salient objects in input images. This framework is composed of two main components: (1) progressively enhanced network (PEN) for amplifying the specified layers of the network and merging the global context simultaneously; (2) object-level boundary extraction module (OBEM) for extracting the complete boundary of the salient object. Experiments and comparisons show that the proposed framework achieves state-of-the-art results. Especially on many challenging datasets, our method performs much better than other methods.

This paper made a related survey on the current situation of the garbage in colleges in Dongguan and Jieyang, discussed the main types of garbage on campus, analyzed the attitude and behavior of college students towards garbage sorting and recycling, demonstrated the feasibility of campus garbage sorting and recycling, and put forward constructive suggestions accordingly. Relevant systems should be improved, the campers’ management of garbage classification should be strengthened, publicity should be strengthened, and students’ environmental awareness should be improved.

This paper studies the cross-dock truck scheduling problem, which considers the uncertainty of trucks’ arrival and operational times. We introduce a concept named conflict and present a two-stage optimization model, aiming at minimizing the total cost and number of conflicts. Furthermore, an extended model by introducing K-means clustering is presented, for which the performance guarantees are provided to validate its efficiency. A column and constraint generation algorithm, which is proved to converge in a finite number of iterations, is designed to solve the developed models. Extensive numerical experiments are conducted to validate the performance of the developed models and algorithm.

This paper proposes a method for increasing the efficiency of identifying key nodes in a road network, especially in large-scale complex ones. The method was established based on spatial we...