Search

This letter proposes a new method for focusing ground maneuvering targets and estimating the motion parameters with a synthetic aperture radar (SAR) system. In this method, the Hough transform is applied to estimate the cross-track velocity from the slope of the range walk (RW) trajectory, and the RW and Doppler centroid shift are compensated. The second-order Keystone transform is performed to correct the additional range curve caused by the along-track velocity and cross-track acceleration. Then, we adopt the adaptive polynomial Fourier transform to estimate the second- and third-order Doppler parameters from a 1-D parameter interval, and the corresponding motion parameters are calculated. Finally, the moving target is well focused after the motion parameters compensation because the second- and third-order Doppler parameters are efficiently eliminated. Both the simulated and real data processing results are presented to demonstrate the validity of the proposed algorithm.

Downward-looking sparse linear array 3-D synthetic aperture radar (DLSLA 3-D SAR) cross-track dimensional imaging always suffers from incomplete observation which does not satisfy the Nyquist sampling theorem and leads to the failure of conventional 3-D frequency-domain methods. Although several sparse reconstruction-based methods have been presented to solve this problem, the basis mismatch issue in sparse reconstruction theory will degrade the image reconstruction performance. To address this issue, this article proposes a novel 3-D imaging method for DLSLA 3-D SAR, which provides another idea for 3-D imaging through sparse recovery. It utilizes recovered full-sampled data to achieve cross-track dimensional imaging instead of using the under-sampled data directly as before. The Along-track-Height plane imaging is first finished by the range-Doppler (RD) algorithm and motion error compensation. Then, an advanced nuclear norm and low-rank matrix factorization (NU-LRMF)-based matrix completion (MC) algorithm and a vector reconstruction framework are built to achieve accurate recovery of full-sampled data. Finally, the cross-track dimensional imaging is completed with recovered full-sampled data by geometric correction and beamforming. Moreover, a fast two-stage iteration strategy for NU-LRMF (TS-NU-LRMF) is also presented to accelerate convergence. The robustness and effectiveness of the proposed 3-D imaging method are verified by several numerical simulations and comparative studies based on both the complex 3-D ship model and the simulated 3-D distributed scenario.

This article presents a novel approach for the joint estimation of satellite attitude and size based on inverse synthetic aperture radar (ISAR) image interpretation and parametric optimization. The satellite's solar panel, which is segmented from the ISAR image by employing pix2pix generative adversarial network (Pix2pixGAN), is chosen for investigation in this article due to its unique rectangular structure. We innovatively use the principal component analysis (PCA) to explore the satellite solar panel's structural features in an ISAR imagery. The projection matrix is then established to link the extracted features and the satellite's absolute attitude and size. Parametric optimization is established based on the relationship between the extracted features and the satellite's absolute attitude and size. A Broyden-Fletcher-Goldfarb-Shanno (BFGS)-based fast iterative search algorithm is employed to search the satellite's absolute attitude and size simultaneously through an iterative approach. The simulation data are generated from actual satellite orbital parameters and computer-aided-design (CAD) models of the Aqua satellite in the experiments. Simulation experiments verify the effectiveness of the proposed method.

Deconvolution technique can be utilized in the forward-looking radar (FLR). However, the forward-looking imaging performance degenerates greatly due to the effect of high-speed movement of the platform. In this article, an efficient Bayesian forward-looking superresolution imaging algorithm based on Doppler deconvolution in expanded beam space is proposed. First, the Doppler phase information caused by the high-speed platform is fully exploited and the Doppler matrix is integrated with the antenna pattern. The Doppler convolution model of the echo signal for forward-looking is derived in this article. Then, the Doppler phase information is adopted to perform the Doppler deconvolution. Moreover, an expanded beam space is constructed to enhance the sparsity of the imaging scene. The complex Gaussian distribution and the Laplace distribution have been used to model the distribution characteristics of noise and targets in the imaging scene, respectively. Finally, based on the Bayesian framework, the forward-looking imaging problem is converted into the convex optimization problem. The performance assessment based on simulated and experimental data, also in comparison to the conventional real beam, truncated singular value decomposition (TSVD), iterative adaptive approach (IAA) methods, has demonstrated the effectiveness of our proposed algorithm under high-speed platform scenarios.

Accurate 2-D frequency spectrum (2-D FS) with acceleration, two-way range coupling terms, and spatial-variant Doppler parameters are the main problems to be solved in translational-variant bistatic forward-looking synthetic aperture radar (SAR) (TV BFSAR) with curved trajectory. For these issues, a modified omega-K imaging algorithm is derived in this article. The maximum usage of 2-D FS based on the method of series reversion (MSR) is achieved by linear range cell migration correction, and 2-D FS is linearized in bistatic range by using high-order polynomial fitting. Then, a method of azimuth resampling is introduced to implement compensation of spatial-variant Doppler parameters. Different from other bistatic omega-K methods, our newly proposed method focuses on the small-aperture data in the azimuth frequency domain to avoid azimuth aliasing without padding zeros and uses the frequency focusing position to study the model of spatial-variant phase. Simulation results and real data verify the effectiveness of the proposed method.

Airborne downward-looking sparse linear array 3-D synthetic aperture radar (DLSLA 3-D SAR) usually uses a sparse and nonuniform linear array that often does not satisfy the Nyquist sampling theorem. Therefore, the cross-track dimensional imaging will fail with the traditional 3-D frequency-domain imaging algorithms. Several grid-based sparse reconstruction (GB-SR) algorithms have been presented to solve this issue. However, they assume that the scatterers are located on the discretized grids; otherwise, the off-grid effect or basis mismatch problem will occur. To address this issue, we propose a novel hyperparameter-free gridless-based sparse reconstruction (GL-SR) algorithm (i.e., 2-D adaptive iterative reweighted atomic norm minimization algorithm called 2-D IRAN) by a combination of the optimal covariance fitting criterion and atomic norm. It is a generalized model, while the other GL-SR algorithms (e.g., GLS, RGLS, and RAM) can be interpreted as the variants of 2-D IRAN. Moreover, since the interior-point method employed in toolboxes has high computational efficiency only for the small-scale matrix optimization problem, a fast implementation of 2-D IRAN via alternating direction method of multipliers (ADMM) is presented for the large-scale matrix optimization problem. Finally, we carry out extensive numerical simulations to demonstrate the advantages and effectiveness of 2-D IRAN for DLSLA 3-D SAR imaging based on the complex 3-D ship model and 3-D distributed scenario.

To improve the life-detection radar resolution under certain hardware conditions, in this letter, a deep mutual learning generative adversarial network model (Deep Mutual GAN) is proposed. In the proposed model, the generator can improve the angular resolution of the input low-resolution radar image by five times, which is enough to meet our requirements for the resolution of life detection. We innovatively use two generators in GAN with the same network structure and make the two generators learn from each other. In this way, the learning process of a generator is not only achieved by its confrontation with the discriminator but also guided by another generator. As a result, the knowledge of the generator is no longer only obtained through its own learning; each generator learns knowledge from another generator while learning knowledge by itself. The proposed model can effectively make the convergence of GAN more stable and improves the super resolution effect. We also introduce the details of the network structure of generator and discriminator, in which residual learning and a symmetrical network structure are applied. The experimental results show that the proposed method can achieve state-of-the-art imaging effect, which is meaningful for subsequent target detection and recognition.

Most state-of-the-art neural machine translation (NMT) models progressively encode feature representation in a bottom-up feed-forward fashion. This traditional encoding mechanism has no guidance from external signals. In computer vision tasks, the feedback connection plays a crucial role, particularly for understanding tasks. In this paper, we propose a simple but effective approach to learn latent feature representations explicitly from input sentences via a latent feature encoder (LFE), which are fed back to an NMT encoder via a top-down feedback mechanism. Through the feedback mechanism, the representations in one layer are influenced by representations of both lower and higher layers, resulting in a more effective encoding mechanism. Besides, to enhance the capability of the LFE in better capturing latent features from the source sentences, we pre-train the LFE via a Denoising Auto-Encoder (DAE) strategy. Experimentation on the large-scale WMT 2014 English-to-German and WMT 2017 Chinese-to-English translation tasks demonstrates that our proposed LFE, either pre-trained with the DAE or not, significantly outperforms the strong baseline.

Forward-looking correlated imaging plays an increasingly important role in modern radar imaging systems. It overcomes disadvantages of traditional side or squint synthetic aperture radar (SAR) which is dependent on specific relative motion between the radar and target scene. A new microwave forward-looking correlated 3-D imaging method based on random radiation field combined with sparse reconstruction is proposed in this article. Firstly, phased array radar (PAR) is adopted to form different and random antenna patterns. Then, combined with the compressed sensing (CS) theory, the target image can be recovered with very few samples which can break through Rayleigh resolution limitation. Furthermore, the proposed method can achieve resolution at least 5.5 times higher than real aperture imaging. To raise computation efficiency of sparse reconstruction, an improved quasi-Newton iteration method based on graphics processing unit (GPU) platform is developed. Meanwhile, a GPU-based (NVIDIA Tesla K40c) accelerated computing method can significantly reduce the processing time compared with the time given by a personal computer (PC). Both simulation and field experiment verify the validity of the proposed method.

Subword segmentation plays an important role in Tibetan neural machine translation (NMT). The structure of Tibetan words consists of two levels. First, words consist of a sequence of syllables, and then a syllable consists of a sequence of characters. According to this special word structure, we propose two methods for Tibetan subword segmentation, namely syllable-based and character-based methods. The former generates subwords based on the Tibetan syllables, and the latter is based on Tibetan characters. In addition, we carry out experiments with these two subword segmentation methods on low-resource Tibetan-to-Chinese NMT, respectively. The experimental results show that both of them can improve translation performance, in which the subword segmentation based on character sequences can achieve better results. Overall, our proposed character-based subword segmentation is more simple and effective. Moreover, it can achieve better experimental results without paying much attention to the linguistic features of Tibetan.

The rotation matching between synthetic aperture radar (SAR) and optical images is essential for their registration. In this article, we introduce a novel fast rotation matching method for SAR and optical images. In the method, the absolute directional derivative histograms (ADDHs) of SAR and optical images can be used to reflect the rotation difference between them, and then the rotation difference is removed by the cross correlation of the two images’ ADDHs. Subsequently, we generate the ADDHs by oriented Gaussian-Gamma-shaped operator. Then, the cross correlation based on fast Fourier transform is used to deal with the ADDHs of SAR and optical images in order to determine the rotation difference of the two images. The experiment results demonstrate that the proposed method can detect the rotation difference in various conditions and achieves rotation matching with high speed.

Memoryless nonlinear transform (MNLT) method was widely used in the statistical model for sea clutter simulations. When the radar scattering data sets were obtained, we can simulate large scene and long-time varying 3-D sea surface scattering using expended power spectral quickly and accurately. Compared with the personal computer platform, field-programmable gate array (FPGA) has the unique merit of energy efficiency, high performance and adaptability. In this article, we proposed a novel architecture for implementing the 3-D MNLT algorithm on FPGA using high-level synthesis. As the simulation size increases, the demand for storage resources will also increase rapidly, and the on-chip memory resource will be limited on FPGA. Aiming at these problems, we divided the 3-D space-time simulation into a 2-D spatial simulation and a 3-D temporal simulation, so that we can make full use of the off-chip memory. Our design employs multiple on-chip buffer structures to decrease the transfer time of internal and external data on the FPGA. We also design a dataflow inverse fast Fourier transform processing engine (PE). The dataflow implementation overlapped butterfly operation, increasing concurrency and the overall throughput of this PE. Experimental results show that we can obtain the same accuracy and higher efficiency on a Xilinx Zynq XC7Z100 SoC platform.

The rigid oscillation and flexible deformation baseline errors occur in dual-antenna unmanned aerial vehicle (UAV) SAR interferometry (InSAR). The errors caused by airflow disturbances and UAV platform mechanical oscillation will lead to interferometric phase undulation. Measuring the errors has high requirements for length and time accuracy for the equipment. In this paper, a time-varying baseline error (TBE) estimation and compensation method based on continuous time-domain subaperture data is proposed. Firstly, we model the TBE and derive its expression in each subaperture image focused by the chirp scaling dechirp (CS-dechirp) algorithm. Then it is possible to extract the estimated differential TBE (D-TBE) from the differential interferogram of overlapping scenes in subaperture images. Further, the full-aperture TBE can be obtained through an integration of the estimated D-TBE. Finally, the full-aperture compensation can be accomplished by a phase correction after the range variation estimation. Taking advantage of the time-domain subaperture, the D-TBE phases are sampled at each subaperture center time, and the proposed method can be well combined with a motion compensation algorithm in the processing flow for UAV InSAR. Furthermore, the case of low coherence is overcome. The results of simulation and real measured airborne single-pass dual-antenna data validate the proposed approach.

Bistatic forward-looking synthetic aperture radar (BFSAR) breaks through the limitations of the conventional monostatic SAR on the forward-looking imaging. However, the problems of range cell migration (RCM) caused by the linear range walk and 2-D spatial variability of Doppler parameters become more serious and complicated in translational variant BFSAR. In this article, a keystone transform is introduced to correct the linear RCM. Based on the characteristics of a small aperture, the nonlinear chirp scaling (NCS) is discussed in the frequency domain to equalize the azimuth-range-dependent Doppler parameters. The improved NCS in our newly proposed BFSAR imaging algorithm, especially the re-definition of range direction and the model of spatial variant phase, differentiates this article from all the existing studies in the literature on BFSAR signal processing. Simulation results and real data processing further validate the effectiveness of the proposed algorithm.

In neural machine translation (NMT), the source and target words are at the two ends of a large deep neural network, normally mediated by a series of non-linear activations. The problem with such consequent non-linear activations is that they significantly decrease the magnitude of the gradient in a deep neural network, and thus gradually loosen the interaction between source words and their translations. As a result, a source word may be incorrectly translated into a target word out of its translational equivalents. In this article, we propose short-path units (SPUs) to strengthen the association of source and target words by allowing information flow over adjacent layers effectively via linear interpolation. In particular, we enrich three critical NMT components with SPUs: (1) an enriched encoding model with SPU, which interpolates source word embeddings linearly into source annotations; (2) an enriched decoding model with SPU, which enables the source context linearly flow to target-side hidden states; and (3) an enriched output model with SPU, which further allows linear interpolation of target-side hidden states into output states. Experimentation on Chinese-to-English, English-to-German, and low-resource Tibetan-to-Chinese translation tasks demonstrates that the linear interpolation of SPUs significantly improves the overall translation quality by 1.88, 1.43, and 3.75 BLEU, respectively. Moreover, detailed analysis shows that our approaches much strengthen the association of source and target words. From the preceding, we can see that our proposed model is effective both in rich- and low-resource scenarios.

In a short observation time, after the range alignment and phase adjustment, the motion of a target can be approximated as a uniform rotation. The radar observing process can be simply described as multiplying an observation matrix on the ISAR image, which can be thought of as a linear system. It is known that the longer observation time is, the higher cross-range resolution is. In order to deal with the conflict between short observation time and high cross-range resolution, we introduce Kalman filtering (KF) into the ISAR imaging and propose a novel method to reconstruct a high-resolution image with short time observed data. As KF has excellent reconstruction performance, it leads to a good application in ISAR image reconstruction. At each observation aperture, the reconstructed image denotes the state vector in KF at the aperture time. It is corrected by a two-step KF process: prediction and update. As iteration continues, the state vector is gradually corrected to a well-focused high-resolution image. Thus, the proposed method can obtain a high-resolution image in a short observation time. Both simulated and real data are applied to demonstrate the performance of the proposed method.

The target detection of the passive multiple-input multiple-output (MIMO) radar that is comprised of multiple illuminators of opportunity and multiple receivers is investigated in this paper. In the passive MIMO radar, the transmitted signals of illuminators of opportunity are totally unknown, and the received signals are contaminated by the colored Gaussian noise with an unknown covariance matrix. The generalized likelihood ratio test (GLRT) is explored for the passive MIMO radar when the channel coefficients are also unknown, and the closed-form GLRT is derived. Compared with the GLRT with unknown transmitted signals and channel coefficients but a known covariance matrix, the proposed method is applicable for a more practical case whenthe covariance matrix of colored noise is unknown, although it has higher computational complexity. Moreover, the proposed GLRT can achieve similar performance as the GLRT with the known covariance matrix when the number of training samples is large enough. Finally, the effectiveness of the proposed GLRT is verified by several numerical examples.

In this article, we show that word translations can be explicitly incorporated into NMT effectively to avoid wrong translations. Specifically, we propose three cross-lingual encoders to explicitly incorporate word translations into NMT: (1) Factored encoder, which encodes a word and its translation in a vertical way; (2) Gated encoder, which uses a gated mechanism to selectively control the amount of word translations moving forward; and (3) Mixed encoder, which stitchingly learns a word and its translation annotations over sequences where words and their translations are alternatively mixed. Besides, we first use a simple word dictionary approach and then a word sense disambiguation (WSD) approach to effectively model the word context for better word translation. Experimentation on Chinese-to-English translation demonstrates that all proposed encoders are able to improve the translation accuracy for both traditional RNN-based NMT and recent self-attention-based NMT (hereafter referred to as Transformer ). Specifically, Mixed encoder yields the most significant improvement of 2.0 in BLEU on the RNN-based NMT, while Gated encoder improves 1.2 in BLEU on Transformer . This indicates the usefulness of an WSD approach in modeling word context for better word translation. This also indicates the effectiveness of our proposed cross-lingual encoders in explicitly modeling word translations to avoid wrong translations in NMT. Finally, we discuss in depth how word translations benefit different NMT frameworks from several perspectives.

Target detection and recognition of bistatic SAR image has been widely studied in recently. However, how to accurately detect and recognize targets with low-resolution and small size in the image is still a problem. Image super-resolution reconstruction technology can increase image resolution and expand target size to improve detection and recognition performance. Thus, we in this paper bring deep learning onto the topic of bistatic SAR image super-resolution reconstruction and propose a novel super-resolution reconstruction model (named FSRCNN) for bistatic SAR images. The proposed model is characterized by a feature extractor with different structures, a feedback feature enhancement block, and a feature fusion module. During the experiments of bistatic SAR measured data, our method is proved to perform clearer visual effects than other image super-resolution reconstruction method. Moreover, our model achieves the best value on peak signal to noise ratio and structural similarity, which indicates that our model can effectively super-resolution reconstruct bistatic SAR images.

Hidden Markov Model (HMM) is a commonly used modeling approach for the radar target recognition based on high-resolution range profile (HRRP). The HMM describes HRRP with the assumption of Gaussian observation probability, which results in the inaccurate description due to the non-Gaussian property of HRRP. To this end, we propose a hybrid HMM framework, which uses an extra model to fit the observation probability rather than making distribution assumptions. The extra model estimates the posterior probability of the state, and then can calculate the pseudo observation probability, which in turn modulates the other model parameters in HMM. The interplay between HMM and the extra model ultimately leads to a better description for observed data. In this paper, we use the support vector machine (SVM) and deep neural network (DNN) separately as the extra model and validate the superiority of our hybrid HMM in HRRP-based target recognition.

Phase gradient autofocus (PGA) is widely used in estimating residue phase error due to its efficient and robust. However, its precision severely relies on sample quality. In this paper, an expediting phase gradient autofocus algorithm is proposed to solve the above problem. First, we extract valid echo data area from the received contaminated data. Second, the optimization of the azimuth window size is presented. It gets rid of the limitation that the traditional PGA depends on the experience value. Third, the phase error can be fast calculated without numerous IFFT and zero padding which decrease computational complexity. Furthermore, the computational cost is derived in detail. Finally, Numerical simulation and raw SAR data demonstrate that the new method can achieve better performance than conventional PGA.

As the demand for energy grows, a large number of distributed energy resources with small capacity, intermittent and random output are incorporated into the operation of large power grid, and many prosumers participate in the electricity market transactions, which brings great influence to the current electricity market transaction mode. In view of the decentralized, tamper-proof, smart contract and other features of blockchain technology, which is naturally suitable for the transaction demand of distributed energy resources, it is necessary to develop peer-to-peer energy trading based on blockchain technology which can improve the efficiency of market participants and promote the construction of distributed energy resources. In this context, we propose a peer-to-peer energy trading platform using consortium blockchain named Hyperledger Fabric. Then we design market mechanism through smart contract. We show that our proposed platform meets the needs of peer-to-peer energy trading.

The reconstruction of sea clutter plays an important role in target detection and recognition in a maritime environment. Reproducing the temporal and spatial correlations of real data simultaneously is always a problem in the reconstruction of sea clutter due to the complex coupling between them. In this paper, the spatial&ndash, temporal correlated proportional method (STCPM), based on a compound model, is proposed to reconstruct K-distributed sea clutter with correlation characteristics obtained from the real data. The texture component with spatial&ndash, temporal correlation is generated by the proportional method and the speckle component with temporal correlation is generated by matrix transformation. Compared with previous methods, the biggest innovation of the STCPM is that it can more accurately generate K-distributed sea clutter with both temporal and spatial correlations. The comparison of the reconstructed and real data demonstrates that the method can reproduce the characteristics of real sea clutter well.

IP geolocation, which is important for the security of devices, heavily relies on the number of high-quality landmarks. As one kind of widely used Internet of Things (IoT) devices, Internet webcams are exposed to the Internet intentionally or unintentionally. While there are few researches on the methodology to extract landmarks for Internet webcams by now. In this paper, we proposed a framework GeoWAT to automatically generate landmarks from the watermarks of the webcams, which are accurate enough to improve some IP geolocation services. GeoWAT uses Optical Character Recognition (OCR) techniques to get text locations from the watermarks of public webcams on the Internet websites. Then GeoWAT queries the locations through online maps to get latitudes/longitudes of webcams as landmarks. We conducted experiments to evaluate the performance and effectiveness of GeoWAT in real world. Our results show that GeoWAT could automatically extract the locations of webcams with high precision and recall. Also, GeoWAT have got more accurate landmarks than other IP location services, such as IPIP, GeoLites2 and ipstack, on the webcams dataset we collected from the whole world.

Airborne bistatic forward-looking synthetic aperture radar (ABFL-SAR) breaks through the limitations of the conventional monostatic SAR on the forward-looking imaging. However, an ABFL-SAR is faced with the severe 2-D coupling, owing to the mechanism of translational variability, which is especially obvious in the azimuth compression compared with the conventional monostatic SAR. In this article, we improve the nonlinear chirp scalling (NCS) algorithm on the basis of polynomial fitting for ABFL-SAR with the cross trajectory. Simulation results further validate the effectiveness of the proposed algorithm.

Bistatic forward-looking SAR is a synthetic aperture radar system with an independently moving transmitter and receiver breaks through the limitations of the conventional monostatic SAR on the forward-looking imaging. However, the existence of a double hyperbola in the bistatic range equation makes the severe two-Dimension (2-D) coupling. Based on the bistatic SAR space geometrical model and the point target spectrum form the series reversion, this paper introduces the result of bistatic forward-looking SAR raw data processed using polynomial NCS algorithm is given to confirmed the applicability of mentioned algorithm. Furthermore, an analysis about the SAR image feature is discussed, then a produce is defined to slove the problem which may reduce the SNR of bistatic SAR is proposed.

In the problem of 3D imaging of air Target by shipborne ISAR, the traditional 3D ISAR imaging method based on interference technology not only has complicated hardware equipment, but also high-order phase terms caused by radar swing cannot be eliminated. A 3D imaging method for single-base shipborne ISAR was proposed. Due to the low efficiency of the conventional imaging method based on FRFT, a time-frequency analysis imaging method based on an improved FRFT is proposed. Firstly, the functional relationship is established on the high-order phase term of the single-base shipborne ISAR echo signal and the 3D coordinates of the scattering point. Then, the higher-order phase terms of the radar echo signal are estimated by an improved FRFT. Finally, Restore the coordinates of each scattering point of the target. The simulation results show that this algorithm can obtain 3D imaging of shipborne ISAR air Target with good efficiency and accuracy.

Monosatic SAR can not image targets in forward direction due to the overlapping of the 2-D resolution directions. Then bistatic forward-looking SAR can aquire high resolution 2-D image in forward direction by placing transmitter and receiver on different platforms. The diving configuration of bistatic forward-looking SAR that the transmitter flies in a straight line and the receiver dive down can be realized for one of the bistatic platforms. Compared to the traditional airborne bistatic SAR, the receiver diving configuration has a more severe 2-D coupling, so imaging processing is more difficult. This paper analyzes the 2-D resolution of the special configuration, also range and doppler formula are determined based on the gradient theory, which are used to determine parameters that affect imaging ability. The accurate form of signal spectrum is obtained by the method of series reversion. Besides, an improve NCS algorithm is used to simulated and real bistatic data acquired from bistatic forward-looking SAR experiment. The results show the success of the experiment and the feasibility of the algorithm.

With more flexibility and higher generality, translational variant BFSAR has extensive potential applications in self-handing and navigation. However, the current BFSAR imaging algorithms mostly focus on bistatic configuration without velocity of altitude which would product azimuth position error. In this paper, we propose a new nonlinear chirp scaling (NCS) imaging algorithm that using frequency focusing position to remove spatially variability of Doppler parameters. Finally, simulation results further validate the effectiveness of the method.

In order to reconstruct the quadratic frequency modulated (QFM) signal, such as radar signal due to the complexity. A novel method for the parameter estimation of multi-component QFM signal based on a modified product kernel function (MPKF) is proposed in this paper. The method has fewer external cross-terms and light computational burden because of non-iterative operations. Moreover, it is robust against additive noise. Finally, simulated and real data results confirm the proposed method.

The three-axis velocity and acceleration of platform not only reduce the accuracy of the traditional bistatic equivalent range model in the missile-borne bistatic synthetic aperture radar (BiSAR) with arbitrary configuration and curved track but also make the imaging algorithm based on the uniform linear track model inapplicable any more. In addition, due to the influence of space-variant motion errors introduced by double platform acceleration, the traditional 2-D subblock compensation method will cause discontinuities between image subblocks, and thus affect the subsequent image matching application. In view of these problems, this paper proposes a new BiSAR imaging algorithm, the space-variant phase filtering imaging algorithm (SVPFIA), which is based on the modified bistatic equivalent range model. SVPFIA constructs the combined compensating filter of space-variant phase error and geometric distortion and adopts inverse mapping interpolation. This makes it possible to achieve the local joint compensation of motion error, wavefront bending, and geometric distortion in the process of oblique conversion, and consequently yield the SAR ground image without distortion to facilitate the subsequent image matching process. Finally, the effectiveness of the proposed algorithm is examined through simulation experiments.

Agility radar with the carrier frequency random hopping and the pulse repetition frequency (PRF) staggering from pulse to pulse achieves superior performance against the electromagnetic jamming. This novel scheme leads to the discontinuity of phase in a coherent processing interval, thus the fast Fourier transform-based method is no longer a valid way to estimate the velocity of a target. A novel sparse optimisation method based on compressed sensing is proposed for high-resolution range-Doppler reconstruction from random frequency hopping and PRF-jittering pulses. The performance of moving target detection of the proposed method for frequency agile and PRF-jittering radar is analysed by comparing it with parameters-fixed pulse Doppler radar. Both simulation and field experimental results demonstrate the effectiveness of the proposal.

The aim of bankruptcy prediction is to help the enterprise stakeholders to get the comprehensive information of the enterprise. Much bankruptcy prediction has relied on statistical models and got low prediction accuracy. However, with the advent of the AI (Artificial Intelligence), machine learning methods have been extensively used in many industries (e.g., medical, archaeological and so on). In this paper we compare the statistical method and machine learning method to predict bankruptcy with utilizing China listed companies. Firstly, we use statistical method to choose the most appropriate indicators. Different indicators may have different characteristics and not all indicators can be analyzed. After the data filtering, the indicators are more persuasive. Secondly, unlike previous research methods, we use the same sample set to conduct our experiment. The final result can prove the effectiveness of the machine learning method. Thirdly, the accuracy of our experiment is higher than existing studies with 95.9%.

For air-missile borne bistatic forward-looking beam-steering synthetic aperture radar (BFLBS-SAR), the receiver platform moves along a curve track due to the existence of accelerations. Besides, transmitting and receiving antenna beams rotate around a certain rotary center during the process of data collection to extend or shorten synthetic aperture time. These characteristics imply that the echo signal suffers serious range–azimuth coupling and aliasing problems of azimuth spectrum. Worse still, the echo process has problems of double-radical sign and high-order terms, which makes the rotary beam center unable to be obtained directly, and thus, the traditional polar formation algorithm (PFA) cannot be applied directly to BFLBS-SAR. To solve these problems, this paper proposes a generalized PFA (GPFA) for air-missile borne BFLBS-SAR. The algorithm uses the equivalent bistatic linear range model first to separate platform acceleration errors. By equating the bistatic mode to the monostatic one, an equivalent rotary center is obtained, and a new azimuth Deramp function is introduced to eliminate aliasing. Then, spectrum utilization and azimuth sampling rate are improved by spectral rotation and interpolation, and the image format is changed. In the azimuth focusing phase, azimuth aliasing is avoided by means of azimuth scaling, which makes azimuth focusing possible eventually. Numerous simulation experiments verify the effectiveness of the proposed GPFA.

Most of the deep neural machine translation (NMT) models are based on a bottom-up feedforward fashion, in which representations in low layers construct or modulate high layers representations. We conjecture that this unidirectional encoding fashion could be a potential issue in building a deep NMT model. In this paper, we propose to build a deeper Transformer encoder by properly organizing encoder layers into multiple groups, which are connected via a grouping skip connection mechanism. Here, each group is further appropriately fed into subsequent groups to build a deep Transformer encoder. In this way, we successfully build a deep Transformer encoder with up to 48 layers. Moreover, we can share the parameters among groups to extend the encoder (virtual) depth even without introducing additional parameters. Detailed experimentation on the large-scale WMT (workshop on machine translation) 2014 English-to-German, English-to-French translation, WMT 2016 English-to-German, and WMT 2017 Chinese-to-English tasks demonstrates that our proposed deep Transformer model significantly outperforms the strong Transformer baseline. Furthermore, we carry out linguistic probing tasks to analyze the problems existing in the original Transformer model and explain how our deep Transformer encoder improves the translation quality. One particularly nice property of our approach is that it is incredibly easy to implement. We make our code available on Github https://github.com/liyc7711/deep-nmt .

This paper addresses the problem of ground moving target relocation (GMTR) for airborne dual-channel wide-area radar systems. The monopulse technique can be utilized to perform GMTR. However, in real conditions, the GMTR performance degrades greatly due to the effect of channel mismatch. To tackle this problem, prior knowledge of the antenna pattern information is fully utilized to improve the GMTR performance, and a knowledge-aided GMTR algorithm (KA-GMTR) for airborne dual-channel wide-area radar is proposed in this paper. First, the GMTR model for the two receiving channels is analyzed. The channel mismatch model is constructed, and its expression is derived. Then, the channel mismatch phase error is well estimated by exploiting the prior antenna pattern information based on the least squares (LS) method. Meanwhile, the knowledge-aided monopulse curve (KA-MPC) is derived to perform the direction of arrival (DOA) estimation for potential targets. Finally, KA-GMTR, based on the KA-MPC, is performed to estimate the azimuth offsets and relocate the geometry positions of the potential targets when channel mismatch occurs. Moreover, the target relocation performance is analyzed, and the intrinsic reason that degrades the target relocation accuracy is figured out. The performance assessment based on airborne real-data, also in comparison to the conventional GMTR method, has demonstrated that our proposed KA-GMTR algorithm offers preferable target relocation results under channel mismatch scenarios.

Aiming at the problem of that the standard salp swarm algorithm has low result precision and slow convergence velocity in the evolutionary process, an improved salp swarm algorithm optimization based on memory mechanism and boundary collision processing is proposed. Firstly, a Chebyshev chaotic map was used to initialize the salps to make them distribute more evenly in search space. Secondly, adding the memory mechanism introduces the individual history optimum of salps into the optimizing strategy of individual salps, which accelerates the convergence speed of the algorithm. Finally, the boundary collision rebound mechanism is introduced to ensure the effectiveness and diversity of the population. The improved algorithm is simulated on 12 types of benchmark test functions in this paper, and compared with other intelligent optimization algorithms under the same conditions. The results show that the improved algorithm has not only a obvious improvement in convergence speed and convergence accuracy, but also has better optimization performance.

The purpose of the aspect-level sentiment analysis task is to analyze the sentiment orientation expressed by different aspects in the text. It has more fine-grained sentiment evaluation objects and is more in line with actual needs. Therefore, it has received extensive attention in recent years. At present, the model that combines the attention mechanism with the Recurrent Neural Network and its variants has gradually become the main method to solve aspect level sentiment analysis tasks. However, this type of method is limited by the deficiencies of the RNN itself, the training time is too long and the dependence between words decreases with the increase of distance. Even if the attention mechanism is added, the above problems will still exist. Therefore, this paper introduces the multi-head attention mechanism into the GCAE model (Gated Convolutional network with Aspect Embedding), and then proposes the GCAE-MHA model (Improved GCAE model based on Multi-Head Attention mechanism). This model models the context and specific aspects of the text sequence at the same time, and learns the interactive relationship between them. And finally uses the two together as the basis for sentiment classification. At the same time, in order to make up for the problem that the convolutional neural network can only extract the dependencies between local words, the GCAE-MHA model also uses the Dilated Convolutional Neural Network to replace it, which can extract the semantic information between long-distance words, and by setting different dilation rate to obtain a richer semantic feature. Finally, experiments are carried out on the SemEval2014 dataset and Twitter dataset. The experimental results show that the GCAE-MHA model can effectively improve the effect of aspect level sentiment analysis while ensuring the simplicity of the model network structure.

Chaotic-based random stepped frequency signal is applied in the multiple-input-multiple-output through-the-wall detection radar (MIMO-TWDR)recently. When the frequency modulation (FM) sequence of transmission signal is controlled by the chaotic signal, the single-frequency interference such as the power harmonics sneaking into the phase detector becomes periodical and therefore can be filtered in frequency domain. However, the target echo signal becomes random after chaotic modulation, where the matched filter usually is unable to be realised by Fourier transform and consequently the envelope of direct wave after the phase detector varies stochastically and is difficult to be eliminated by an analogue filter. The FM sequence of random disorganising cannot meet the demand of filtering out the single-frequency interference and direct wave simultaneously. Therefore, a new method of FM sequence optimisation of chaotic-based random stepped frequency signal based on genetic algorithm is proposed to solve these problems in this study. Simulations show that the optimised stepped frequency signal possesses the advantages of both chaotic-based random and linear stepped frequency signal. The proposed scheme achieves excellent performance on direct wave and single-frequency interference suppression and target detection. Moreover, it can avoid the interference between transmission antennas of MIMO radar.

This paper investigates a new and special imaging mode, bistatic forward-looking high-speed maneuvering platform synthetic aperture radar, in which both platforms travel curvilinear trajectories with high velocities and accelerations. A thorough understanding of its new properties of motion, 2-D resolution, and echo signal coupling is given. Applicability of gradient method neglecting time dependence of gradient to this special configuration is addressed. Moreover, 2-D coupling characteristic of echo signal at different imaging distances is investigated.

In order to reconstruct the linear frequency modulated (LFM) signal, such as radar signal due to the complexity. A novel parameter estimation method based on a modified convolution kernel function (MCKF) is proposed for multi-component LFM signal in this paper. The method has fewer external cross-terms and light computational burden because of non-searching operations. Moreover, it is robust against additive noise. Finally, simulated and real data results confirm the proposed method.

Small and medium-sized users with distributed generators or flexible demand response resources desire to participate in market transactions solely, rather than aggregated by aggregators. The commonly used decentralized bookkeeping mode, blockchain-based trading schemes can now realize uniform clearing of decentralized transactions with the help of smart contracts. However, there are still risks of excessive disclosure of information and privacy leakage caused by incomplete decentralization. To solve this problem, we propose a decentralized optimization-based market clearing model, which can be applied on blockchain. The model has three advantages: ① limited access to the consumers’ or generators’ private data, ② convenient calculation methods that can be deployed on the smart contract and ③ pure decentralization to realize transparent on-chain market clearing. Moreover, considering the insufficient throughput of the existing blockchain, a blockchain network, which can process the quotation calculation in parallel with various sub-chains, is also designed to support the proposed market clearing model. Finally, the effectiveness of proposed models is validated and tested on the Ethereum private blockchain.

In recent years, the proposal of neural network has provided new idea for solving natural language processing, and at the same time, neural machine translation has become the frontier method of machine translation. In low-resource languages, due to the sparse bilingual data, the model needs more high-quality data, and the translation quality fails to achieve the desired effect. In this paper, experiments on neural network machine translation based on attention are conducted on Tibetan-Chinese language pairs, and transfer learning method combined with back translation method is used to alleviate the problem of insufficient Tibetan-Chinese parallel corpus. Experimental results show that the proposed transfer learning combined with back translation method is simple and effective. Compared with traditional translation methods, the translation effect is significantly improved. From the analysis of translation, it can be seen that the citation of Tibetan-Chinese neural machine translation is smoother, which is greatly improved compared to the translation without back translation. At the same time, there are common deficiencies in neural machine translation such as inadequate translation and low translation loyalty.

As a basic tool for signal processing in Synthetic Aperture Radar (SAR), raw data simulation plays a significant role in those complicated configurations in which the real raw data is difficult to obtain. For the new and special configuration in Bistatic Forward-looking High-speed Maneuvering-platform SAR (BFHM-SAR), the double square roots and high-order terms in range history caused by high velocities and accelerations from both platforms make it difficult to gain the corresponding 2-dimensional frequency spectrum (2-D FS) effectively. In addition, space variances in phase terms of 2-D FS owing to curvilinear trajectories and different traveling directions of two platforms influence the accuracy of echo data significantly. In this paper, a fast and effective scene raw data simulator is developed based on the effectual access of 2-D FS with high precision and quantificational analysis and correction of phase space variance of it. As the inverse process of imaging, raw signal can be reconstructed and generated by this method more efficiently than traditional approaches nearly without sacrificing accuracy. Plenty of simulation results for scattering targets and real scene verify its validity and effectiveness. Moreover, our method can be applied for handling the simulation in the conventional airborne platform of bistatic SAR besides BFHM-SAR. Bistatic Forward-looking High-speed Maneuvering platform SAR is introduced.There exist double square roots and high order terms in the range history.Space variance should be considered and corrected to design raw data simulator.An effective approach is achieved from the precise access of frequency spectrum.The accurate raw data is generated more efficiently without sacrificing precision.

This paper investigates a new imaging algorithm for high-maneuverability synthetic aperture radar (HM-SAR) travels with high velocities and time-variant accelerations. To be specific, a more precise acceleration-separation-based equivalent range model (ASERM) is established, which can separate time-variant acceleration errors from the ideal linear range model. After 2-D spectral interpolation, a joint compensation method based on inverse-mapping and local filtering is constructed for compensating the space-variant motion error (ME) and image distortions caused by the time-variant acceleration.

Tibetan-Chinese neural machine translation (NMT) is facing serious resource scarcity problem. This paper compares the application effect of multiple neural network optimization algorithms under the condition of resource scarcity, and proposes an optimization method which is suitable for resource scarcity languages. Then, by which it improving the performance of the Tibetan-Chinese NMT. Experimental results show that when choosing a suitable optimization algorithm, the Tibetan-Chinese NMT can still exceed the traditional statistical machine translation (SMT) and achieve better translation performance.

In [1] , the result of Fig. 13(b) was incorrectly provided. Now, we provide the corrected result, as shown in Fig. 1 .

With the rapid development of distributed renewable energy (DRE), demand response (DR) programs, and the proposal of the energy internet, the current centralized trading of the electricity market model is unable to meet the trading needs of distributed energy. As a decentralized and distributed accounting mode, blockchain technology fits the requirements of distributed energy to participate in the energy market. Corresponding to the transaction principle, a blockchain-based integrated energy transaction mechanism is proposed, which divides the trading process into two stages: the call auction stage and the continues auction stage. The transactions among the electricity and heat market participants were used as examples to explain the details of the trading process. Finally, the smart contracts of the transactions were designed and deployed on the Ethereum private blockchain site to demonstrate the validity of the proposed transaction scheme.