Search

The emergence of highly directional beamforming technology makes millimeter wave frequency band communication possible in future wireless communication networks. Based on the multipath characteristics of millimeter wave frequency communication, a high-precision multipath channel estimation algorithm based on signal subspace is proposed. In the mobile terminal, an iterative heuristic radio frequency combination algorithm based on spatial points is proposed. The analog precoding at the base station uses deep learning to accelerate the calculation, and then the multi-user communication is modeled to design the digital precoding. The simulation results show that the multi-channel estimation algorithm can estimate 4 paths with an error of no more than 0.3 rad. The proposed DL algorithm takes only 20% of the time when it is close to the 87% spectral efficiency of the traditional algorithm.

Because the ship wake spreads into an area much larger than that of the ship hull in the sea surface, it has been widely used in the ship detection. However, due to the complex sea wave motion and the high sea state, the ship wake detection is still a challenging task. In this paper, we propose a novel data-driven method based on dynamic mode decomposition (DMD) to detect, reconstruct, and locate the Kelvin wake on the two-dimensional dynamic sea surface. Through the proposed method, the sea's dynamic characteristics including the oscillation frequency and decay/growth rate of ship wakes and the time-varying sea surface can be obtained. Meanwhile, the spatial features of ship wakes can be derived by dynamic modes as well. The proposed method can distinguish the dynamic characteristics between the Kelvin wake and sea background. Then the corresponding modes of the Kelvin wake can be successfully identified. The proposed method is demonstrated by analyzing a 2D sea surface where the Kelvin ship wake is superposed. It is found that our new approach provides an effective and accurate ship detection, even in the case of high sea states. Meanwhile, the extracted mode of the wake shows the ship position clearly with very high resolution.

In this paper, a systematic and calculation-based parasitic decoupling technique (PDT) is proposed to mitigate the mutual coupling between two closely coupled antennas. The adopted parasitic decoupling structure consists of two transmission lines connected to the feed lines of antennas and a parasitic element connected with a transmission line and terminated by a reactive load. Rigorous decoupling theory and systematic design procedures are presented. The lengths of transmission lines and value of reactive load can be precisely calculated to increase antenna isolation. The superiority of the proposed PDT is verified by four decoupling examples. The simulated and measured results show that high isolations over 24 dB, efficiencies above 70%, and envelop correlation coefficients below 0.05 are achieved simultaneously. The results indicate the proposed PDT a promising decoupling method for MIMO systems.

High-power high-frequency transformer (HFT) is a key component in electrical energy routers. So far, the existing design of high-power HFT is mostly based on the single-phase double-winding transformer with the EE-type core or the C-type core. However, there is a lack of designs based on high-power HFT with other core types and multi-winding structures. An optimal design method for a 10kHz/250kVA dry-type natural-cooling HFT with six windings integrated based on the equilateral triangular closed nanocrystalline core is proposed. The core column specification is optimized based on the constraint between temperature rise and loss by traversing the width and thickness of the core column. In order to obtain the target inductance value, constraint between leakage inductance and the distance of main insulation is considered. The measured efficiency and the power density of the prototype are 99.76% and 4. 9kW/L, respectively. The maximum steady-state temperature rise of the prototype is 62. 65K, and the prototype has passed the insulation test. This work provides useful reference for the design and development of similar high-power HFT.

With the rapid development of e-commerce, the efficiency requirements for logistics distribution are getting higher and higher, so distribution routing optimisation has important theoretical and practical significance. In this paper, a new coding mechanism is designed to solve the distribution task in the multi-distribution centre scenario and vehicle scheduling problem with capacity constraints in the distribution scenario. Simulation results show that this algorithm has the advantages of high solution efficiency, variable input and avoidance of re-referencing compared with two heuristics of Google OR-Tools, ant colony algorithm and simulated annealing algorithm, thus this algorithm can effectively solve the logistics distribution routing optimisation problem and improve the efficiency of logistics distribution.

The generalization of face swapping detectors against unseen face manipulation methods is important to practical applications. Most existing methods based on convolutional neural networks (CNN) simply map the facial images to real/fake binary labels and achieve high performance on the known forgeries, but they almost fail to detect new manipulation methods. In order to improve the generalization of face swapping detection, this work concentrates on a practical scenario to protect specific persons by proposing a novel face swapping detector requiring a reference image. To this end, we design a new detection framework based on identity spatial constraints (DISC), which consists of a backbone network and an identity semantic encoder (ISE). When inspecting an image of a particular person, the ISE utilizes a real facial image of that person as the reference to constrain the backbone to focus on the identity-related facial areas, so as to exploit the intrinsic discriminative clues to the forgery in the query image. Cross-dataset evaluations on five large-scale face forgery datasets show that DISC significantly improves the performance against unseen manipulation methods and is robust against the distortions. Compared to the existing detection methods, the AUC scores achieve 10%~40% performance improvements.

The non-orthogonal multiple access (NOMA) technology enables visible light communication (VLC) downlink system to serve the users with the enhanced spectrum and power efficiencies by utilizing the multiplexing in the power domain. In this paper, we investigate the resource allocation issue for multi-carriers (MC) NOMA VLC systems, and propose to minimize the energy consumption (EC) subject to constraints of minimum user date rate requirements. In our design, we decompose the energy consumption minimization (ECM) problem into a joint power allocation and sub carrier assignment problem. Then based on the VLC channel characteristics, we propose a low-complexity suboptimal subcarrier assignment strategy to minimize the EC. Simulation results demonstrate that using the proposed strategy, the EC is lower than that of the benchmark system while meeting the minimum data rate demands of each user ends (UEs).

Edge states in topological photonic systems have the robust unidirectional propagation feature which originates from the topological nature of the bulk band dispersion. In this work, we propose a topological photonic crystal (PC) waveguide that is formed by introducing an air gap in an all-dielectric PC with $C_{6v}$ symmetry. The dispersion of the line defect states is tunable by varying the width of the air gap. Based on their field distributions, the states can be classified into even- and odd-symmetric states. The even-symmetric states are found to be the nontrivial topological edge states and exhibit pseudospin-locking unidirectional propagation property. By introducing disorders to the waveguide, these states are proven to be robust with well suppressed backscattering.

Active microwave remote sensing is essential to monitor the conditions of the environment by analyzing the microwave returns from the earth terrain. Various Computational Electromagnetics (CEM) techniques are implemented to study the backscattering coefficient of numerous earth terrains such as vegetation and snow medium. In this paper, a theoretical model based on second order radiative transfer equation is investigated by incorporating two computational methods which are known as coupled Finite Element Method (FEM) and Method of Moment (MoM), and Relaxed Hierarchical Equivalent Source Algorithm (RHESA). These theoretical models consider three shapes of scatterers which can be used to represent the ice particles of snow medium. These mentioned shapes are sphere, droxtal and hexagonal column. These methods are used to investigate the effect of various incident angles and frequencies on the backscattering mechanism. These results are compared with analytical Mie solution and ground truth measurement to analyze and verify the model.

High resolution and large range force/torque (F/T) measurements are usually required in many engineering tasks. However, most existing F/T sensors only have a fixed resolution over their whole ranges. The key lies in that it is difficult to well balance high resolution and large range in the sensor design. Taking the torque sensor for example, this paper presents a better compromise for this problem i.e., a novel variable resolution torque sensor based on variable stiffness principle. From the structural points of view, the sensor is constructed with multiple radial flexures to achieve a pure rotational motion with negligible parasitic center motions. Two resistive strain gauges (RSGs) are selected as the measuring units of the sensor to detect the applied external torque and meanwhile provide variable resolutions in the two different measuring ranges (each RSG for one range). Static and dynamic models of the sensor are established in details and validated through finite element analysis (FEA) to evaluate its characteristics. A principle prototype is finally fabricated and tested to verify the effectiveness of the presented design. RSGs are calibrated through a commercial six-axis F/T sensor from ATI Industrial Automation, Inc. Experimental results show that the torque sensor can provide high and low resolutions in the small and large ranges respectively and possesses the first natural frequency of 67.3 Hz. In addition, the proposed variable resolution method can also be applied to the development of multi-axis F/T sensors.

With the rapid development of the Internet, the number of cyber threats increases exponentially. More and more cyber threats come from new and unexpected sources, leading organizations and individuals to facing more security risks and vulnerabilities. Automatically obtaining and structuring security information from cybersecurity news can help security analysts to identify useful information more quickly. Most existing studies on extracting security events merely focused on the event detection task, aiming to discover and categorize cybersecurity events from the plain text. However, such event detection methods cannot capture useful information such as who performed the cyberattack, when the data breach event happened, who was the victim, etc. These arguments of a cybersecurity event are needed for analysts to get cybersecurity event details directly. Several studies have tried to extract rich semantic information of cybersecurity events, but they merely focused on extracting event arguments within the sentence scope. These studies still have limitations when the event arguments needed to recognize spread across multiple sentences. In this paper, we proposed a framework that effectively extracts cybersecurity events at the document-level from cybersecurity news, blogs and announcements. We model the document-level event extraction task as a sequence tagging problem. The goal is to identify the related arguments of cybersecurity events from documents. Firstly, we get the characters embedding and incorporate the word information into the character representations. Then we design a sliding window mechanism to get the cross-sentence context information. Finally, we predict the label of each character. We build a Chinese cybersecurity dataset and use three methods to evaluate our method, and the experimental results demonstrate the effectiveness of the proposed model.

The increasing household loads make series arc faults more complex, which are difficult to be detected by traditional circuit breakers and lead to the frequent occurrence of residential fire accidents. In this paper, a comprehensive approach of complex load recognition and series arc detection is proposed on the basis of principal component analysis and support vector machine (PCA-SVM) combination model. Several typical loads were selected and analyzed, especially nonlinear and complex loads like power electronics load and multi-state load. Three time-domain parameters, maximum slip difference (MSD), zero current period (ZCP) and maximum Euclidean distance (MED), and nine frequency-domain harmonics information are collected to complex waveforms. To decrease the computation cost and further to enhance the response velocity, all the time-domain and frequency-domain information were blended and dimensionally reduced to three parameters by principal component analysis (PCA). Prior to the series arc detection, load recognition is trained and completed with the artificial intelligence (AI) algorithm. At last, the comprehensive model of load recognition and series arc detection is achieved based on a support vector machine (SVM). The accuracy of load recognition and series arc detection reaches 99.1% and 99.3%, respectively, demonstrating the excellent performances of the intelligent approach to diagnose the series arcing activities in modern household applications.

Object recognition in real-world environments is one of the fundamental and key tasks in computer vision and robotics communities. With the advanced sensing technologies and low-cost depth sensors, the high-quality RGB and depth images can be recorded synchronously, and the object recognition performance can be improved by jointly exploiting them. RGB-D-based object recognition has evolved from early methods that using hand-crafted representations to the current state-of-the-art deep learning-based methods. With the undeniable success of deep learning, especially convolutional neural networks (CNNs) in the visual domain, the natural progression of deep learning research points to problems involving larger and more complex multimodal data. In this paper, we provide a comprehensive survey of recent multimodal CNNs (MMCNNs)-based approaches that have demonstrated significant improvements over previous methods. We highlight two key issues, namely, training data deficiency and multimodal fusion. In addition, we summarize and discuss the publicly available RGB-D object recognition datasets and present a comparative performance evaluation of the proposed methods on these benchmark datasets. Finally, we identify promising avenues of research in this rapidly evolving field. This survey will not only enable researchers to get a good overview of the state-of-the-art methods for RGB-D-based object recognition but also provide a reference for other multimodal machine learning applications, e.g., multimodal medical image fusion, audio-visual speech recognition, and multimedia retrieval and generation.

In this paper, we utilize the deep learning approach for the subwavelength imaging in far-field, which is realized by the near-field resonant metalens at microwave frequencies. The resonating metalens consisting of split-ring resonators (SRRs) are equipped with the strong magnetic coupling ability and can convert evanescent waves into propagating waves using the localized resonant modes. The propagating waves in the far-field are utilized as the input of a trained deep convolutional neural network (CNN) to realize the imaging. The training data for establishing the deep CNN are obtained by the EM simulation tool. Besides, the white Gaussian noise is added into the training data to simulate the interference in the real application scenario. The proposed CNN composes of three pairs of convolutional and activation layers with one additional fully connected layer to realize the recognition, i.e., the imaging process. The feasibility of utilizing the trained deep CNN for imaging is validated by numerical benchmarks. Distinguished from the subwavelength imaging methods, the spatial response and Green's function need not be measured and evaluated in the proposed method.

Customer’s reviews play an important role in social e-commerce. It can help merchants establish word-of-mouth and adjust marketing strategies. Because of a large number of customer’s reviews, it is difficult to analyze the sentimental polarities of the reviews in time. Aspect level sentiment classification is designed to identify sentimental tendency of the aspect in the sentence. In the previous works, averaged vector was used to represent the original vector usually, but it may lose information when the aspect has multiple words. In order to solve the aforementioned issue, we propose the Complementary Attention Network(CAN), which incorporates the average pooling mechanism, circular convolution method and circular correlation method to complement the information in the averaged vector. We evaluate our model on three datasets: laptop reviews, restaurant reviews and twitter posts. Experiments show that our model is advanced and have achieved excellent performance on multiple datasets. In specifically, we compare different variants of CAN model. The CAN model we proposed achieved better performance on three datasets, especially outperforming A-CAN(attention mechanism) by 3% on laptop reviews.

This paper proposes a novel decoupling method for two antennas operating in adjacent/contiguous frequency bands using a cascaded power dividing decoupling network (C- PDDN). An n-order C-PDDN can be designed to increase antenna isolation at n desired frequency points. Each PDDN is composed of two power dividers, two transmission lines, and one reactive component. Explicit design formulas are founded for determining design parameters. For illustration, a two-order C- PDDN is applied to a testing array. Results show that it could increase isolation by over 20 dB, verifying the effectiveness.