Search

Few-shot classification addresses the challenge of swiftly enabling a deep learning model to comprehend new classes based on minimal supporting image samples. Despite recent research predominantly focusing on devising increasingly intricate classifiers for gauging similarities between query and support images, there is room for improvement in the critical role of feature embeddings and relational measurements. In this paper, a novel technique called Progressive Multi-Scale Relation Network (PMRNet), is designed for few-shot classification tasks. Our work introduces a feature extraction module that adeptly extracts and interactively fuses multi-scale features to address the problem of insufficient feature extraction. Furthermore, an enhanced attention mechanism is integrated, which amplifies critical local and global features for increased discriminative power. A novel bilinear relation module is also designed specifically to accurately quantify the similarities between the extracted features. The PMRNet has been rigorously evaluated on three benchmark datasets. PMRNet’s empirical performance in few-shot image classification tasks exhibits commendable accuracy, substantiating its efficacy as a robust architectural framework for significantly boosting the precision of such tasks.

Line commutated converter based high-voltage direct-current (LCC-HVDC) transmissions are prone to harmonic oscillation under weak grids. Impedance modeling is an effective method for assessing interaction stability. Firstly, this paper proposes an improved calculation method for the DC voltage and AC currents of commutation stations to address the complex linearization of the commutation process and constructs an overall harmonic state-space (HSS) model of an LCC-HVDC. Based on the HSS model, the closed-loop AC impedances on the LCC-HVDC sending and receiving ends are then derived and verified. The impedance characteristics of the LCC-HVDC are then analyzed to provide a physical explanation for the harmonic oscillation of the system. The effects of the grid strength and control parameters on system stability are also analyzed. To improve the impedance characteristics and operating stability of the LCC-HVDC system, a virtual impedance based stability enhancement control is proposed, and a parameter design method is considered to ensure satisfactory phase margins at both the sending and receiving ends. Finally, simulation results are presented to verify the validity of the impedance model and virtual impedance based stability enhancement control.

Earlier studies have reported some calculation methods for commutation failure fault level (CFFL) in line-commutated-converter based high-voltage direct current (LCC-HVDC) system under single-line-to-ground (SLG) faults. The accuracy of earlier methods is limited because they only consider the commutating voltage drop and phase shift, while neglecting the DC current variation. Hence, this paper proposes a CFFL calculation method under SLG faults considering DC current variation, for better planning and designing of LCC-HVDC systems. First, the fault commutating voltage magnitude and phase shift are calculated. Then, the fault DC voltage during different commutation processes is deduced. Based on the commutating voltage magnitude and phase shift, and DC voltage during different commutation processes under SLG faults, the characteristics of CFFL with different fault time are demonstrated and analyzed. Next, the transient time-domain response of the DC current after the fault is obtained based on the DC transmission line model. Discrete commutation processes are constructed based on the commutation voltage-time area rule to solve the extinction angle under different fault levels and fault time. Finally, the CFFL is calculated considering the fault time, commutating voltage drop, phase shift, and DC current variation. The accuracy of the proposed method compared with the traditional method is validated based on the CIGRE benchmark model in PSCAD/EMTDC.

For the safe and fast recovery of line commutated converter based high-voltage direct current (LCC-HVDC) transmission systems after faults, a DC current order optimization based strategy is proposed. Considering the constraint of electric and control quantities, the DC current order with the maximum active power transfer is calculated by Thevenin equivalent parameters (TEPs) and quasi-state equations of LCC-HVDC transmission systems. Meanwhile, to mitigate the subsequent commutation failures (SCFs) that may come with the fault recovery process, the maximum DC current order that avoids SCFs is calculated through imaginary commutation process. Finally, the minimum value of the two DC current orders is sent to the control system. Simulation results based on PSCAD/EMT-DC show that the proposed strategy mitigates SCFs effectively and exhibits good performance in recovery.

The decode-and-forward (DF) based free-space optical-radio frequency (FSO-RF) hybrid system combines the advantages of both FSO links and RF links, which makes the system easy to be deployed and enables the extended transmission coverage. In the case of multiple users, the unreasonable dynamic antenna selection algorithm will lead to multi-user interference (MUI) and reduce the spectral efficiency of the system. Therefore, we propose hybrid precoding based on manifold learning with the antenna partitioning algorithm for dual-hop hybrid FSO-RF systems. In the hybrid precoding of dynamic subarray structure, the high-dimensional channels are embedded into the low-dimensional manifolds by the optimized multidimensional scaling (MDS). The potential spatial correlations of the high-dimensional channel are preserved by the scaling by majorizing a complicated function (SMACOF) algorithm. Through proper user clustering, the hybrid precoding is investigated for the sum-rate maximization problem by manifold quasi-conjugate gradient methods. Meanwhile, an antenna subarray partitioning algorithm is proposed, so that each antenna unit can be assigned to an RF chain based on the increment of the user’s maximum signal to interference noise ratio (SINR). By calculating the simulated equivalent channel SINR for the selected users, the antenna division can greatly reduce the computational complexity and the size of the search space, and ensure fairness among users. Simulation results show that this method can obtain almost the best summation rate and higher spectral efficiency compared with the conventional method.

The commutation failure (CF) mitigation effectiveness is normally restricted by the delay of extinction angle (EA) measurement or the errors of existing prediction methods for EA or firing angle (FA). For this purpose, this paper proposes a CF mitigation method based on the imaginary commutation process. For each sample point, an imaginary commutation process is constructed to simulate the actual commutation process. Then, the imaginary EA is calculated by comparing the imaginary supply voltage-time area and the imaginary demand voltage-time area, which can update the imaginary EA earlier than the measured EA. In addition, the proposed method considers the impacts of commutation voltage variation, DC current vari-ation, and phase angle shift of commutation voltage on the commutation process, which can ensure a more accurate EA calculation. Moreover, the DC current prediction is proposed to improve the CF mitigation performance under the single-phase AC faults. Finally, the simulation results based on CIGRE model prove that the proposed method has a good performance in CF mitigation.

Millimeter Wave (mmWave) massive multiple-input multiple-output (MIMO) systems with hybrid analog-digital architectures can greatly increase system capacity and communicate with multiple users at the same time. Accurate channel estimation is crucial for multi-user communications, but its accuracy is limited as the number of antennas and users increases. In the matrix high-dimensional operation for multi-user channel estimation, not only is it computationally intensive, but also the estimation accuracy is low. It makes our work turn to channel estimation of the user group within a certain region to improve the accuracy of estimation. In this paper, we propose a tensor dictionary manifold learning method for channel estimation and interference elimination of the multi-user mmWave massive MIMO system. A multi-user digital-analog mixed received signal model is presented. The tensor dictionary manifold learning scheme is proposed to model the received signal as a third-order low-rank tensor to handle the high-dimensional user, antenna, and channel. After segmentation, clustering and manifold learning, multiple tensor dictionary manifold models containing a group of user signals are fitted. Tensor dictionary manifold learning can take advantage of the inherent multi-domain properties of signals in the frequency, time, code and spatial domains to maintain inter-user correlation within a user group while reducing the high-dimensional channels of the user group. Using the convex relaxation property of the tensor alternating direction method, we propose a strategy to eliminate interference from other groups. And with the help of the multi-signal classification method, the channel parameters of user groups are obtained to improve the accuracy of multi-user channel estimation. This method can perform channel estimation for multiple users with only a few pilots, and improve the performance of the system. Numerical results confirm the good performance of this method.

The mitigation of commutation failure (CF) depends on the accuracy of CF prediction. In terms of the large error of the existing extinction angle (EA) calculation during the fault transient period, a method for CF prediction and mitigation is proposed. Variations in both DC current and overlap angle (OA) are considered in the proposed method to predict the EA rapidly. In addition, variations in critical EA and the effect of firing angle (FA) on both DC current and OA are considered in the proposed method to obtain the accurate FA order for the control system. The proposed method can achieve good performance in terms of CF mitigation and reduce reactive consumption at the inverter side when a fault occurs. Simulation results based on the PSCAD/EMTDC show that the proposed method predicts CF rapidly and exhibits good performance in terms of CF mitigation.

In this paper, we propose TSFE-Net, two stream feature extraction networks for active stereo matching. First, we perform extra local contrast normalization (LCN) for dataset due to dependency between speckle intensity and distance. Second, we construct two stream feature extraction layers which consist of convolutional layers and deconvolutional layers in different scales to simultaneously learn the features of the original images and LCN images and aggregate context information to form the left and right features. Third, we convert the obtained depth map into disparity map in virtue of camera parameters to construct a supervised learning model. The TSFE-Net not only solves illumination effects between speckle intensity and distance but also reserves details of the original image. Our dataset are captured by RealSense D435 camera. We research extensive quantitative and qualitative evaluations based on a series of scenes, and achieve the end point error (EPE) accuracy of 0.335 on the TITAN XP platform only for valid pixel. The assessment results show that our network has the ability of real-time deep reconstruction for active pattern.

Massive high-resolution spaceborne synthetic aperture radar (SAR) data are available nowadays, effecting rapid development in the urban remote sensing technology. In this study, we use a set of 27 scenes from TerraSAR-X to reconstruct the three-dimensional (3D) point clouds of a skyscraper-North Star Times Tower in Beijing, China. We study in detail the derivation process of a 3D model of tomographic SAR (TomoSAR) from the two-dimensional (2D) imaging mathematical model of SAR. We observe the presence of a spatial shift in the elevation direction of TomoSAR, which yields poor and even incorrect results when greedy algorithms such as orthogonal matching pursuit (OMP) or regularized orthogonal matching pursuit (ROMP) algorithms are applied. Then, we propose a phase compensation method to eliminate the spatial shift. Both OMP and ROMP algorithms are used for TomoSAR imaging on high-resolution TerraSAR-X data. The experimental results with North Star Times Tower demonstrate the accuracy of the theoretical analysis and the effectiveness of the algorithms. Finally, we compare the ROMP and OMP algorithms and conclude that both algorithms can yield similar reconstruction results in TomoSAR imaging. The ROMP algorithm does not depend on sparsity and can suppress noise through regularization selection at the cost of time. The OMP algorithm introduces noise when the sparsity is inaccurate.

Feld's friendship paradox is a widely accepted observation that states that the friends of any particular individual tend to have more friends on average than the individual has. Due to its implications for information transmission, the friendship paradox has become a generalized paradigm in many disciplines. However, how many of an individual's friends have more friends than the individual does is still unknown, yet interesting. In this paper, we revisited the Feld's friendship paradox and we found that only a limited number of a person's friends have more friends than the person herself has. This conclusion was reached from empirical studies using real-world networks and is true regardless of the number of one's neighbours, which contradicts the intuitive deduction from the friendship paradox. For one thing, if a person is unpopular, the number of her friends that have more friends than she does grows with the number of friends that she makes. This observation crystallizes the tenable margin of the friendship paradox. In another case, if a person is popular, as she acquires more friends, fewer of her friends have more friends than she does. This finding suggests an observation bias in the friendship paradox, which makes individuals feel less popular than their friends. Besides enriching our knowledge of the friendship paradox in psychological science, the findings reported here are also beneficial for technical areas such as large-scale triangle discovery. Although the friendship paradox was proposed from the perspective of the number of neighbours, the findings reported here can shed light on theories and applications from different disciplines like information, happiness, obesity, and extroversion, to name a few.

Two-tier massive multiple-input multiple-output (MIMO) systems achieve high sum spectral efficiency by simultaneously serving large numbers of users. However, as the number of service antennas and users tend to infinity, the performance is limited by directed inter-cell and intra-cell interferences. Handling these interferences are challenging due to the large channel dimensionality and the high complexity associated with implementing large precoding/combining matrices. Moreover, two-tier massive MIMO is computationally demanding, as the high antenna count results in high-dimensional matrix operations when conventional MIMO hybrid precoding is applied. In this paper, a manifold learning two-tier beamforming (MLTB) scheme is proposed to enable efficient and low-complexity operation in large scale dimensional MIMO systems. Users of multi-cell are clustered into several regions of user groups by manifold learning. Most of the high-dimensional channels are embedded in the low-dimensional subspace by manifold learning, while retaining the potential spatial correlation of the high-dimensional channels. The nonlinearity of high-dimensional channel is transformed into local linearity to achieve dimensionality reduction. Through proper user clustering, the beamformers are split into outer beamformers and inner beamformers. The outer beamformers can minimize inter-cell interference and the inner beamformers can minimize multi-user interference of intra-groups. The high signal to interference plus noise ratio (SINR) is achieved and the computational complexity is reduced by avoiding the conventional schemes to deal with high-dimensional channel parameters. Performance evaluations show that the proposed MLTB scheme can obtain near-optimal sum-rate and considerably higher energy efficiency than the conventional schemes.

Chinese authors indirectly portray real social relationships in society by incorporating their own experiences and feelings about politics, economic life, and cultural habits. Social and natural knowledge are mixed and hidden in natural literary language. Therefore, by well defining the type of original text, the pipeline for processing the text and the rules to build the graph, we can extract enough valid and useful information. Based on higher-level information, we can build a literary character graph to promote computers' comprehension of literature. The identification of opposite characters is a challenging topic because the character relationships are intricate and complex. The cryptic expression in literary works can enhance the readability of the plot, but it is obvious that it increases the cost of understanding. Even for human readers different types of characters are difficult to classify and identify, and it usually needs careful reading for several times to get the subtle differences among the characters. Though extracting knowledge from Chinese literature is a complicated and difficult topic, this paper models the graph of polar literary characters and divides polar communities by extracting polar vertices and polar edges based on the concept of literary sentiment polarity. The results show that using a long-sentence window is a good trade-off. The experiments of modern Chinese polar literature show that the accuracy of the community division method for the integrated graph polarity is obviously better than the method based on the co-occurrence network, and it can automatically match the positive and negative communities as well as build the complete graph structure. It clearly reflects the meaning of literary works from the perspective of polarity. This systematic model describes general standard operation steps for the machine to understand complex Chinese literature. The experiments conducted on seven benchmark Chinese novel datasets demonstrate that the method based on emotional polarity shows a significant improvement compared to baseline performance. Though we use Chinese datasets in this paper, the model and methods are important references for literature analysis and graph extraction in other languages.

Accurately obtaining road vehicle information is important in intelligent traffic surveillance systems for smart cities. Especially smart vehicle detection is recognized as the critical research issue of intelligent traffic surveillance systems. In this paper, a robust real-time vehicle detection method for the system is proposed. The method combines background subtraction model MOG2(Mixture of Gaussians) with a modified SqueezeNet model (H-SqueezeNet). The MOG2 model is utilized to create scale-insensitive Region of Interest (RoIs) from video frames. H-SqueezeNet is then proposed to accurately identify vehicle category. The effectiveness of the method was verified in CDnet2014 dataset, UA-DETRAC dataset and video data from a traffic intersection in Suzhou, China. The experiment results show that the method can achieves excellent detection accuracy in traffic surveillance systems, and achieve an average detection speed of 39.1 FPS.

A successive interference cancellation (SIC)-based weighted least-squares (WLS) estimation for the carrier frequency offset (CFO) and the sampling frequency offset (SFO) is presented for wireless local area networks (WLANs) based on orthogonal frequency division multiplexing (OFDM). The proposed SIC-based WLS performs the estimation by exploiting the phase rotation in the frequency domain caused by the CFO and the SFO. SIC-based WLS estimates the CFO and the SFO successively instead of by traditional simultaneous estimation. The estimation of CFO based on the Taylor series is performed first, and then the WLS estimation of SFO based on successive cancellation of the CFO is carried out. The simulation results show that the SIC-based WLS can estimate the CFO and the SFO effectively. Compared to the WLS scheme, a performance improvement of more than 0.6 dB is achieved by SIC-based WLS, and nearly 10 percent of the complexity is reduced.

Building Information Modeling (BIM) is a promising technology for building informatics. Currently, an increasing number of applications adopt BIM to improve the building operations and facility management. In these applications, matching real-world facilities to the corresponding BIM items is a fundamental yet challenging task. This study addresses this issue using Natural Language Processing. Firstly, a novel BIM hierarchy tree (HiTree) is proposed to model the original spatial structure relationships of a BIM. Then, the locations of facilities are extracted from natural language through processes of word segmentation, keyword extraction, and semantic disambiguation. Thirdly, an algorithm that matches real-world facilities to the BIM data is developed using the HiTree and the extracted locations. Finally, a concrete case for a 35,000 m2 library is presented to verify the effectiveness of the proposed solution. BIM has become a common paradigm in the construction industry, and our scheme can facilitate more applications of BIM in building operations and facility management. One of the most representative applications is integrating the BIM data and information within IoT (Internet of Things) system intelligently by matching the BIM data to real-world facilities.