Civil Aviation University of China

How to effectively learn temporal variation of target appearance, to exclude the interference of cluttered background, while maintaining real-time response, is an essential problem of visual object tracking. Recently, Siamese networks have shown great potentials of matching based trackers in achieving balanced accuracy and beyond realtime speed. However, they still have a big gap to classification & updating based trackers in tolerating the temporal changes of objects and imaging conditions. In this paper, we propose dynamic Siamese network, via a fast transformation learning model that enables effective online learning of target appearance variation and background suppression from previous frames. We then present elementwise multi-layer fusion to adaptively integrate the network outputs using multi-level deep features. Unlike state-of-theart trackers, our approach allows the usage of any feasible generally- or particularly-trained features, such as SiamFC and VGG. More importantly, the proposed dynamic Siamese network can be jointly trained as a whole directly on the labeled video sequences, thus can take full advantage of the rich spatial temporal information of moving objects. As a result, our approach achieves state-of-the-art performance on OTB-2013 and VOT-2015 benchmarks, while exhibits superiorly balanced accuracy and real-time response over state-of-the-art competitors.

As the failure of power line insulators leads to the failure of power transmission systems, an insulator inspection system based on an aerial platform is widely used. Insulator defect detection is performed against complex backgrounds in aerial images, presenting an interesting but challenging problem. Traditional methods, based on handcrafted features or shallow learning techniques, can only localize insulators and detect faults under specific detection conditions, such as when sufficient prior knowledge is available, with low background interference, at certain object scales, or under specific illumination conditions. This paper discusses the automatic detection of insulator defects using aerial images, accurately localizing insulator defects appearing in input images captured from real inspection environments. We propose a novel deep convolutional neural network (CNN) cascading architecture for performing localization and detecting defects in insulators. The cascading network uses a CNN based on a region proposal network to transform defect inspection into a two-level object detection problem. To address the scarcity of defect images in a real inspection environment, a data augmentation method is also proposed that includes four operations: 1) affine transformation; 2) insulator segmentation and background fusion; 3) Gaussian blur; and 4) brightness transformation. Defect detection precision and recall of the proposed method are 0.91 and 0.96 using a standard insulator dataset, and insulator defects under various conditions can be successfully detected. Experimental results demonstrate that this method meets the robustness and accuracy requirements for insulator defect detection.

In this paper, an improved ant colony optimization (ICMPACO) algorithm based on the multi-population strategy, co-evolution mechanism, pheromone updating strategy, and pheromone diffusion mechanism is proposed to balance the convergence speed and solution diversity, and improve the optimization performance in solving the large-scale optimization problem. In the proposed ICMPACO algorithm, the optimization problem is divided into several sub-problems and the ants in the population are divided into elite ants and common ants in order to improve the convergence rate, and avoid to fall into the local optimum value. The pheromone updating strategy is used to improve optimization ability. The pheromone diffusion mechanism is used to make the pheromone released by ants at a certain point, which gradually affects a certain range of adjacent regions. The co-evolution mechanism is used to interchange information among different sub-populations in order to implement information sharing. In order to verify the optimization performance of the ICMPACO algorithm, the traveling salesmen problem (TSP) and the actual gate assignment problem are selected here. The experiment results show that the proposed ICMPACO algorithm can effectively obtain the best optimization value in solving TSP and effectively solve the gate assignment problem, obtain better assignment result, and it takes on better optimization ability and stability.

Recent progress on salient object detection is beneficial from Fully Convolutional Neural Network (FCN). The saliency cues contained in multi-level convolutional features are complementary for detecting salient objects. How to integrate multi-level features becomes an open problem in saliency detection. In this paper, we propose a novel bi-directional message passing model to integrate multi-level features for salient object detection. At first, we adopt a Multi-scale Context-aware Feature Extraction Module (MCFEM) for multi-level feature maps to capture rich context information. Then a bi-directional structure is designed to pass messages between multi-level features, and a gate function is exploited to control the message passing rate. We use the features after message passing, which simultaneously encode semantic information and spatial details, to predict saliency maps. Finally, the predicted results are efficiently combined to generate the final saliency map. Quantitative and qualitative experiments on five benchmark datasets demonstrate that our proposed model performs favorably against the state-of-the-art methods under different evaluation metrics.

Deep belief network (DBN) is one of the most representative deep learning models. However, it has a disadvantage that the network structure and parameters are basically determined by experiences. In this article, an improved quantum-inspired differential evolution (MSIQDE), namely MSIQDE algorithm based on making use of the merits of the Mexh wavelet function, standard normal distribution, adaptive quantum state update, and quantum nongate mutation, is proposed to avoid premature convergence and improve the global search ability. Then, the MSIQDE with global optimization ability is used to optimize the parameters of the DBN to construct an optimal DBN model, which is further applied to propose a new fault classification, namely MSIQDE-DBN method. Finally, the vibration data of rolling bearings from the Case Western Reserve University and a real-world engineering application are carried out to verify the performance of the MSIQDE-DBN method. The experimental results show that the MSIQDE takes on better optimization performance, and the MSIQDE-DBN can obtain higher classification accuracy than the other comparison methods.

The electro-mechanical actuators (EMAs) play an important role in the new-generation aircraft, which makes the fault diagnosis of EMA become a hot topic in the industry. However, the EMA signals usually have nonlinear characteristics and seasonal tendency, which bring great challenge to the fault diagnosis. Furthermore, detecting faults in the early stage helps reduce the risk of serious damage to EMA, but most studies are focusing on the situation that the EMA faults are well-developed. To tackle the challenge, we present an innovative algorithm which combines a hybrid-spatial and temporal attention-based gated recurrent unit (HSTA-GRU) with Seasonal-Trend decomposition procedures based on Loess (STL) to predict multiple time-series data for more failure information. The STL extracts the seasonal factor for mitigating the influence of seasonal fluctuation, and the HSTA-GRU captures the spatio-temporal relationships among multivariate EMA sensors for a long-term prediction of multiple time-series data. Then, for the predicted time series, a similarity measure (SM) function based on dynamic time warping (DTW) is used to classify the fault types without training, so as to reduce the accumulated error and enhance the efficiency of classification. Ultimately, the analysis result on an experimental EMA fault dataset demonstrates that the proposed arithmetic can provide a superior performance not only in the time series prediction, but also for EMA fault diagnosis.

Quantum-inspired differential evolution (QDE) is an evolutionary algorithm, which can effectively solve complex optimization problems. However, sometimes, it easily leads to premature convergence and low search ability and falls to local optima. To overcome these problems, based on the MSIQDE (improved QDE with multistrategies) algorithm, an enhanced MSIQDE algorithm based on mixing multiple strategies, namely, EMMSIQDE is proposed in this article. In the EMMSIQDE, a new differential mutation strategy of a difference vector is proposed to enhance the search ability and descent ability. Then, a new multipopulation mutation evolution mechanism is designed to ensure the relative independence of each subpopulation and the population diversity. The feasible solution space transformation strategy is used to achieve the optimal solution by mapping the quantum chromosome from a unit space to solution space. Finally, some multidimensional unimodal and multimodal functions are selected to demonstrate the optimization performance of EMMSIQDE. The results demonstrate that the EMMSIQDE is significantly better than the DE, QDE, QGA, and MSIQDE, and has better optimization ability, scalability, efficiency, and stability.

With the continuous and rapid growth of air traffic demand, gate resource becomes a major bottleneck restricting airport development. Rational gate allocation is regarded as one of the most important means to solve this bottleneck. In this paper, in order to comprehensively considere different stakeholders, a three-objective gate allocation model is to consider a wider scope, in which the minimizing passenger walking distances, the most balanced idle time of each gate and the best full use of large gate are optimized simultaneously to improve the practical efficiency. To efficiently solve this model, an improved quantum evolutionary algorithm (QEA) based on the niche co-evolution strategy and enhanced particle swarm optimization (PSO), namely IPOQEA is designed. An IPOQEA-based gate allocation method is proposed to allocate the flights to suitable gates within different periods. Finally, the actual operation data of Baiyun Airport is used to validate the effectiveness of the proposed method. Comparison results show that the constructed model can address the passenger walking distances, robustness and costs in airport management. Moreover, the IPOQEA has better optimization ability in solving gate allocation problem. Therefore, the proposed gate allocation method has great potential for practical engineering since it can easily make decisions for airport managers.

BACKGROUND: MiR-221 and miR-222 (miR-221/222) are frequently up-regulated in various types of human malignancy including glioblastoma. Recent studies have reported that miR-221/222 regulate cell growth and cell cycle progression by targeting p27 and p57. However the underlying mechanism involved in cell survival modulation of miR-221/222 remains elusive. RESULTS: Here we showed that miR-221/222 inhibited cell apoptosis by targeting pro-apoptotic gene PUMA in human glioma cells. Enforced expression of miR-22/222 induced cell survival whereas knockdown of miR-221/222 rendered cells to apoptosis. Further, miR-221/222 reduced PUMA protein levels by targeting PUMA-3'UTR. Introducing PUMA cDNA without 3'UTR abrogated miR-221/222-induced cell survival. Notably, knockdown of miR-221/222 induces PUMA expression and cell apoptosis and considerably decreases tumor growth in xenograft model. Finally, there was an inverse relationship between PUMA and miR-221/222 expression in glioma tissues. CONCLUSION: To our knowledge, these data indicate for the first time that miR-221/222 directly regulate apoptosis by targeting PUMA in glioblastoma and that miR-221/222 could be potential therapeutic targets for glioblastoma intervention.

In this brief, we investigate the control problem of tracking a desired trajectory for a fully actuated marine surface vessel considering multiple outputs constraints. To prevent multiple output constraints violation, a symmetric barrier Lyapunov function (SBLF) is employed. Backstepping, in combination with adaptive feedback approximation techniques, is introduced to design an adaptive neural network control. Experimental simulations are provided to evaluate the feasibility and effectiveness of the proposed controller. Compared to the adaptive neural network control without multiple output constraints, the proposed adaptive neural network using the SBLF can guarantee that all the outputs remain bounded.

Abstract Electrochemical carbon monoxide reduction is a promising strategy for the production of value-added multicarbon compounds, albeit yielding diverse products with low selectivities and Faradaic efficiencies. Here, copper single atoms anchored to Ti 3 C 2 T x MXene nanosheets are firstly demonstrated as effective and robust catalysts for electrochemical carbon monoxide reduction, achieving an ultrahigh selectivity of 98% for the formation of multicarbon products. Particularly, it exhibits a high Faradaic efficiency of 71% towards ethylene at −0.7 V versus the reversible hydrogen electrode, superior to the previously reported copper-based catalysts. Besides, it shows a stable activity during the 68-h electrolysis. Theoretical simulations reveal that atomically dispersed Cu–O 3 sites favor the C–C coupling of carbon monoxide molecules to generate the key *CO-CHO species, and then induce the decreased free energy barrier of the potential-determining step, thus accounting for the high activity and selectivity of copper single atoms for carbon monoxide reduction.

Bearing fault diagnosis is of significance to ensure the safe and reliable operation of a motor. Deep learning provides a powerful ability to extract the features of raw data automatically. A convolutional deep belief network (CDBN) is an effective deep learning method. In this article, a novel vibration amplitude spectrum imaging feature extraction method using continuous wavelet transform and image conversion is proposed, which can extract the image features with two-dimensional and eliminate the effect of handcrafted features under low signal-to-noise ratio conditions, different operating conditions, and data segmentation. Then, a novel CDBN with Gaussian distribution is constructed to learn the representative features for bearing fault classification. The proposed method is tested on motor bearing dataset with four and ten classifications. The results have been compared with other methods. The experiment results show that the proposed method has achieved significant improvements and is more effective than the traditional methods.

Unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) is very important for battlefield awareness. For SAR systems mounted on a UAV, the motion errors can be considerably high due to atmospheric turbulence and aircraft properties, such as its small size, which makes motion compensation (MOCO) in UAV SAR more urgent than other SAR systems. In this paper, based on 3-D motion error analysis, a novel 3-D MOCO method is proposed. The main idea is to extract necessary motion parameters, i.e., forward velocity and displacement in line-of-sight direction, from radar raw data, based on an instantaneous Doppler rate estimate. Experimental results show that the proposed method is suitable for low- or medium-altitude UAV SAR systems equipped with a low-accuracy inertial navigation system.

Electronic band structure and optical properties of Cr-doped ZnO were studied using the density functional method within the generalized-gradient approximation. Three configurations with the substitution of Zn by one and two Cr atoms in different positions were considered. For the pure ZnO, the Fermi level locates at the valence band maximum, while it shifts to the conduction band and exhibits metal-like characteristic after Cr atoms are introduced into the ZnO supercell. The calculated optical properties indicate that the optical energy gap is increased after Cr doping. More importantly, strong absorption in the visible-light region is found, which originates from the intraband transition of the Cr 3d bands and the conduction bands. Our calculations provide electronic structure evidence that, in addition to usage as short-wavelength optoelectronic devices, the Cr-doped ZnO system could be a potential candidate for photoelectrochemical application due to the increase in its photocatalytic activity.

Lead halide perovskite (LHP) semiconductors show exceptional optoelectronic properties. Barriers for their applications, however, lie in their polymorphism, instability to polar solvents, phase segregation, and susceptibility to the leaching of lead ions. We report a family of scalable composites fabricated through liquid-phase sintering of LHPs and metal-organic framework glasses. The glass acts as a matrix for LHPs, effectively stabilizing nonequilibrium perovskite phases through interfacial interactions. These interactions also passivate LHP surface defects and impart bright, narrow-band photoluminescence with a wide gamut for creating white light-emitting diodes (LEDs). The processable composites show high stability against immersion in water and organic solvents as well as exposure to heat, light, air, and ambient humidity. These properties, together with their lead self-sequestration capability, can enable breakthrough applications for LHPs.

Abstract The purpose of this paper is mainly to investigate the existence of entire solutions of the stationary Kirchhoff type equations driven by the fractional p -Laplacian operator in ℝ N . By using variational methods and topological degree theory, we prove multiplicity results depending on a real parameter λ and under suitable general integrability properties of the ratio between some powers of the weights. Finally, existence of infinitely many pair of entire solutions is obtained by genus theory. Last but not least, the paper covers a main feature of Kirchhoff problems which is the fact that the Kirchhoff function M can be zero at zero. The results of this paper are new even for the standard stationary Kirchhoff equation involving the Laplace operator.

Broad Learning System (BLS) are widely used in many fields because of its strong feature extraction ability and high computational efficiency. However, the BLS is mainly used in supervised learning, which greatly limits the applicability of the BLS. And the obtained data is less labeled data, but is a large number of unlabeled data. Therefore, the BLS is extended based on the semi-supervised learning of manifold regularization framework to propose a semi-supervised broad learning system (SS-BLS). Firstly, the features are extracted from labeled and unlabeled data by building feature nodes and enhancement nodes. Then the manifold regularization framework is used to construct Laplacian matrix. Next, the feature nodes, enhancement nodes and Laplacian matrix are combined to construct the objective function, which is effectively solved by ridge regression in order to obtain the output coefficients. Finally, the validity of the SS-BLS is verified by three different complex data of G50C, MNIST, and NORB, respectively. The experiment result show that the SS-BLS can achieve higher classification accuracy for different complex data, takes on fast operation speed and strong generalization ability.

The modern intelligent transportation system brings not only new opportunities for vehicular Internet of Things (IoT) services but also new challenges for vehicular ad-hoc networks (VANETs). Apart from enhanced network performance, a practical and reliable security scheme is needed to handle the trust management while preserving user privacy at the same time. The emerging 5G mobile communication system is viewed as a prominent technology for ultra-reliable, low-latency wireless communication services. Furthermore, incorporating software-defined network (SDN) architecture into the 5G-VANET enables global information gathering and network control. Hence, real-time IoT services on transportation monitoring and reporting can be well supported. Both pave the way for an innovative vehicular security scheme. This paper investigates the security and privacy issue in the transportation system and the vehicular IoT environment in SDN-enabled 5G-VANET. Due to the decentralized and immutable characteristics of blockchain, a blockchain-based security framework is designed to support the vehicular IoT services, i.e., real-time cloud-based video report and trust management on vehicular messages. This paper explicitly illustrates the SDN-enabled 5G-VANET model and the scheduling procedures of the blockchain-based framework. The numerical simulation results also show that malicious vehicular nodes or messages can be well detected while the overhead and impact on the network performance are acceptable for large-scale scenarios. Through case studies and theoretical analysis, we demonstrate our design substantially guarantees a secure and trustworthy vehicular IoT environment with user privacy preserved.

With the development of cities, urban congestion is nearly an unavoidable problem for almost every large-scale city. Road planning is an effective means to alleviate urban congestion, which is a classical non-deterministic polynomial time (NP) hard problem, and has become an important research hotspot in recent years. A K-means clustering algorithm is an iterative clustering analysis algorithm that has been regarded as an effective means to solve urban road planning problems by scholars for the past several decades; however, it is very difficult to determine the number of clusters and sensitively initialize the center cluster. In order to solve these problems, a novel K-means clustering algorithm based on a noise algorithm is developed to capture urban hotspots in this paper. The noise algorithm is employed to randomly enhance the attribution of data points and output results of clustering by adding noise judgment in order to automatically obtain the number of clusters for the given data and initialize the center cluster. Four unsupervised evaluation indexes, namely, DB, PBM, SC, and SSE, are directly used to evaluate and analyze the clustering results, and a nonparametric Wilcoxon statistical analysis method is employed to verify the distribution states and differences between clustering results. Finally, five taxi GPS datasets from Aracaju (Brazil), San Francisco (USA), Rome (Italy), Chongqing (China), and Beijing (China) are selected to test and verify the effectiveness of the proposed noise K-means clustering algorithm by comparing the algorithm with fuzzy C-means, K-means, and K-means plus approaches. The compared experiment results show that the noise algorithm can reasonably obtain the number of clusters and initialize the center cluster, and the proposed noise K-means clustering algorithm demonstrates better clustering performance and accurately obtains clustering results, as well as effectively capturing urban hotspots.

Traditional feature extraction methods are used to extract the features of signal to construct the fault feature matrix, which exists the complex structure, higher correlation, and redundancy. This will increase the complex fault classification and seriously affect the accuracy and efficiency of fault identification. In order to solve these problems, a new fault diagnosis (PABSFD) method based on the principal component analysis (PCA) and the broad learning system (BLS) is proposed for rotor system in this paper. In the proposed PABSFD method, the PCA with revealing the signal essence is used to reduce the dimension of the constructed feature matrix and decrease the linear feature correlation between data and eliminate the redundant attributes in order to obtain the low-dimensional feature matrix with retaining the essential features for the classification model. Then, the BLS with low time complexity and high classification accuracy is regarded as a classification model to realize the fault identification; it can efficiently accomplish the fault classification of rotor system. Finally, the actual vibration data of rotor system are selected to test and verify the effectiveness of the PABSFD method. The experimental results show that the PCA method can effectively eliminate the feature correlation and realize the dimension reduction of the feature matrix, the BLS can take on better adaptability, faster computation speed, and higher classification accuracy, and the PABSFD method can efficiently and accurately obtain the fault diagnosis results.