Deep neural networks (DNNs) have achieved great success in many data processing applications. However, high computational complexity and storage cost make deep learning difficult to be used on resource-constrained devices, and it is not environmental-friendly with much power cost. In this paper, we focus on low-rank optimization for efficient deep learning techniques. In the space domain, DNNs are compressed by low rank approximation of the network parameters, which directly reduces the storage requirement with a smaller number of network parameters. In the time domain, the network parameters can be trained in a few subspaces, which enables efficient training for fast convergence. The model compression in the spatial domain is summarized into three categories as pre-train, pre-set, and compression-aware methods, respectively. With a series of integrable techniques discussed, such as sparse pruning, quantization, and entropy coding, we can ensemble them in an integration framework with lower computational complexity and storage. In addition to summary of recent technical advances, we have two findings for motivating future works. One is that the effective rank, derived from the Shannon entropy of the normalized singular values, outperforms other conventional sparse measures such as the $ \ell_1 $ norm for network compression. The other is a spatial and temporal balance for tensorized neural networks. For accelerating the training of tensorized neural networks, it is crucial to leverage redundancy for both model compression and subspace training.

With the extensive application of large-scale array antennas, the increasing number of array elements leads to the increasing dimension of received signals, making it difficult to meet the real-time requirement of direction of arrival (DOA) estimation due to the computational complexity of algorithms. Traditional subspace algorithms require estimation of the covariance matrix, which has high computational complexity and is prone to producing spurious peaks. In order to reduce the computational complexity of DOA estimation algorithms and improve their estimation accuracy under large array elements, this paper proposes a DOA estimation method based on Krylov subspace and weighted $ {l}_{1} $-norm. The method uses the multistage Wiener filter (MSWF) iteration to solve the basis of the Krylov subspace as an estimate of the signal subspace, further uses the measurement matrix to reduce the dimensionality of the signal subspace observation, constructs a weighted matrix, and combines the sparse reconstruction to establish a convex optimization function based on the residual sum of squares and weighted $ {l}_{1} $-norm to solve the target DOA. Simulation results show that the proposed method has high resolution under large array conditions, effectively suppresses spurious peaks, reduces computational complexity, and has good robustness for low signal to noise ratio (SNR) environment.

The warhead of a ballistic missile may precess due to lateral moments during release. The resulting micro-Doppler effect is determined by parameters such as the target’s motion state and size. A three-dimensional reconstruction method for the precession warhead via the micro-Doppler analysis and inverse Radon transform (IRT) is proposed in this paper. The precession parameters are extracted by the micro-Doppler analysis from three radars, and the IRT is used to estimate the size of targe. The scatterers of the target can be reconstructed based on the above parameters. Simulation experimental results illustrate the effectiveness of the proposed method in this paper.

Linear minimum mean square error (MMSE) detection has been shown to achieve near-optimal performance for massive multiple-input multiple-output (MIMO) systems but inevitably involves complicated matrix inversion, which entails high complexity. To avoid the exact matrix inversion, a considerable number of implicit and explicit approximate matrix inversion based detection methods is proposed. By combining the advantages of both the explicit and the implicit matrix inversion, this paper introduces a new low-complexity signal detection algorithm. Firstly, the relationship between implicit and explicit techniques is analyzed. Then, an enhanced Newton iteration method is introduced to realize an approximate MMSE detection for massive MIMO uplink systems. The proposed improved Newton iteration significantly reduces the complexity of conventional Newton iteration. However, its complexity is still high for higher iterations. Thus, it is applied only for first two iterations. For subsequent iterations, we propose a novel trace iterative method (TIM) based low-complexity algorithm, which has significantly lower complexity than higher Newton iterations. Convergence guarantees of the proposed detector are also provided. Numerical simulations verify that the proposed detector exhibits significant performance enhancement over recently reported iterative detectors and achieves close-to-MMSE performance while retaining the low-complexity advantage for systems with hundreds of antennas.

Existing specific emitter identification (SEI) methods based on hand-crafted features have drawbacks of losing feature information and involving multiple processing stages, which reduce the identification accuracy of emitters and complicate the procedures of identification. In this paper, we propose a deep SEI approach via multidimensional feature extraction for radio frequency fingerprints (RFFs), namely, RFFsNet-SEI. Particularly, we extract multidimensional physical RFFs from the received signal by virtue of variational mode decomposition (VMD) and Hilbert transform (HT). The physical RFFs and I-Q data are formed into the balanced-RFFs, which are then used to train RFFsNet-SEI. As introducing model-aided RFFs into neural network, the hybrid-driven scheme including physical features and I-Q data is constructed. It improves physical interpretability of RFFsNet-SEI. Meanwhile, since RFFsNet-SEI identifies individual of emitters from received raw data in end-to-end, it accelerates SEI implementation and simplifies procedures of identification. Moreover, as the temporal features and spectral features of the received signal are both extracted by RFFsNet-SEI, identification accuracy is improved. Finally, we compare RFFsNet-SEI with the counterparts in terms of identification accuracy, computational complexity, and prediction speed. Experimental results illustrate that the proposed method outperforms the counterparts on the basis of simulation dataset and real dataset collected in the anechoic chamber.

Classical localization methods use Cartesian or Polar coordinates, which require a priori range information to determine whether to estimate position or to only find bearings. The modified polar representation (MPR) unifies near-field and far-field models, alleviating the thresholding effect. Current localization methods in MPR based on the angle of arrival (AOA) and time difference of arrival (TDOA) measurements resort to semidefinite relaxation (SDR) and Gauss-Newton iteration, which are computationally complex and face the possible diverge problem. This paper formulates a pseudo linear equation between the measurements and the unknown MPR position, which leads to a closed-form solution for the hybrid TDOA-AOA localization problem, namely hybrid constrained optimization (HCO). HCO attains Cramér-Rao bound (CRB)-level accuracy for mild Gaussian noise. Compared with the existing closed-form solutions for the hybrid TDOA-AOA case, HCO provides comparable performance to the hybrid generalized trust region subproblem (HGTRS) solution and is better than the hybrid successive unconstrained minimization (HSUM) solution in large noise region. Its computational complexity is lower than that of HGTRS. Simulations validate the performance of HCO achieves the CRB that the maximum likelihood estimator (MLE) attains if the noise is small, but the MLE deviates from CRB earlier.

Beamspace super-resolution methods for elevation estimation in multipath environment has attracted significant attention, especially the beamspace maximum likelihood (BML) algorithm. However, the difference beam is rarely used in super-resolution methods, especially in low elevation estimation. The target airspace information in the difference beam is different from the target airspace information in the sum beam. And the use of difference beams does not significantly increase the complexity of the system and algorithms. Thus, this paper applies the difference beam to the beamformer to improve the elevation estimation performance of BML algorithm. And the direction and number of beams can be adjusted according to the actual needs. The theoretical target elevation angle root means square error (RMSE) and the computational complexity of the proposed algorithms are analyzed. Finally, computer simulations and real data processing results demonstrate the effectiveness of the proposed algorithms.

In order to extract the richer feature information of ship targets from sea clutter, and address the high dimensional data problem, a method termed as multi-scale fusion kernel sparse preserving projection (MSFKSPP) based on the maximum margin criterion (MMC) is proposed for recognizing the class of ship targets utilizing the high-resolution range profile (HRRP). Multi-scale fusion is introduced to capture the local and detailed information in small-scale features, and the global and contour information in large-scale features, offering help to extract the edge information from sea clutter and further improving the target recognition accuracy. The proposed method can maximally preserve the multi-scale fusion sparse of data and maximize the class separability in the reduced dimensionality by reproducing kernel Hilbert space. Experimental results on the measured radar data show that the proposed method can effectively extract the features of ship target from sea clutter, further reduce the feature dimensionality, and improve target recognition performance.

Three-dimensional (3D) synthetic aperture radar (SAR) extends the conventional 2D images into 3D features by several acquisitions in different aspects. Compared with 3D techniques via multiple observations in elevation, e.g. SAR interferometry (InSAR) and SAR tomography (TomoSAR), holographic SAR can retrieve 3D structure by observations in azimuth. This paper focuses on designing a novel type of orbit to achieve SAR regional all-azimuth observation (AAO) for embedded targets detection and holographic 3D reconstruction. The ground tracks of the AAO orbit separate the earth surface into grids. Target in these grids can be accessed with an azimuth angle span of 360°, which is similar to the flight path of airborne circular SAR (CSAR). Inspired from the successive coverage orbits of optical sensors, several optimizations are made in the proposed method to ensure favorable grazing angles, the performance of 3D reconstruction, and long-term supervision for SAR sensors. Simulation experiments show the regional AAO can be completed within five hours. In addition, a second AAO of the same area can be duplicated in two days. Finally, an airborne SAR data process result is presented to illustrate the significance of AAO in 3D reconstruction.

This paper systematically introduces and reviews a scientific exploration of reliability called the belief reliability. Beginning with the origin of reliability engineering, the problems of present theories for reliability engineering are summarized as a query, a dilemma, and a puzzle. Then, through philosophical reflection, we introduce the theoretical solutions given by belief reliability theory, including scientific principles, basic equations, reliability science experiments, and mathematical measures. The basic methods and technologies of belief reliability, namely, belief reliability analysis, function-oriented belief reliability design, belief reliability evaluation, and several newly developed methods and technologies are sequentially elaborated and overviewed. Based on the above investigations, we summarize the significance of belief reliability theory and make some prospects about future research, aiming to promote the development of reliability science and engineering.

Autonomous umanned aerial vehicle (UAV) manipulation is necessary for the defense department to execute tactical missions given by commanders in the future unmanned battlefield. A large amount of research has been devoted to improving the autonomous decision-making ability of UAV in an interactive environment, where finding the optimal maneuvering decision-making policy became one of the key issues for enabling the intelligence of UAV. In this paper, we propose a maneuvering decision-making algorithm for autonomous air-delivery based on deep reinforcement learning under the guidance of expert experience. Specifically, we refine the guidance towards area and guidance towards specific point tasks for the air-delivery process based on the traditional air-to-surface fire control methods. Moreover, we construct the UAV maneuvering decision-making model based on Markov decision processes (MDPs). Specifically, we present a reward shaping method for the guidance towards area and guidance towards specific point tasks using potential-based function and expert-guided advice. The proposed algorithm could accelerate the convergence of the maneuvering decision-making policy and increase the stability of the policy in terms of the output during the later stage of training process. The effectiveness of the proposed maneuvering decision-making policy is illustrated by the curves of training parameters and extensive experimental results for testing the trained policy.

Natural events have had a significant impact on overall flight activity, and the aviation industry plays a vital role in helping society cope with the impact of these events. As one of the most impactful weather typhoon seasons appears and continues, airlines operating in threatened areas and passengers having travel plans during this time period will pay close attention to the development of tropical storms. This paper proposes a deep multimodal fusion and multitasking trajectory prediction model that can improve the reliability of typhoon trajectory prediction and reduce the quantity of flight scheduling cancellation. The deep multimodal fusion module is formed by deep fusion of the feature output by multiple submodal fusion modules, and the multitask generation module uses longitude and latitude as two related tasks for simultaneous prediction. With more dependable data accuracy, problems can be analysed rapidly and more efficiently, enabling better decision-making with a proactive versus reactive posture. When multiple modalities coexist, features can be extracted from them simultaneously to supplement each other’s information. An actual case study, the typhoon Lichma that swept China in 2019, has demonstrated that the algorithm can effectively reduce the number of unnecessary flight cancellations compared to existing flight scheduling and assist the new generation of flight scheduling systems under extreme weather.

In the context of big data, many large-scale knowledge graphs have emerged to effectively organize the explosive growth of web data on the Internet. To select suitable knowledge graphs for use from many knowledge graphs, quality assessment is particularly important. As an important thing of quality assessment, completeness assessment generally refers to the ratio of the current data volume to the total data volume. When evaluating the completeness of a knowledge graph, it is often necessary to refine the completeness dimension by setting different completeness metrics to produce more complete and understandable evaluation results for the knowledge graph. However, lack of awareness of requirements is the most problematic quality issue. In the actual evaluation process, the existing completeness metrics need to consider the actual application. Therefore, to accurately recommend suitable knowledge graphs to many users, it is particularly important to develop relevant measurement metrics and formulate measurement schemes for completeness. In this paper, we will first clarify the concept of completeness, establish each metric of completeness, and finally design a measurement proposal for the completeness of knowledge graphs.

To solve the problem of risk identification and quantitative assessment for human-computer interaction (HCI) in complex avionics systems, an HCI safety analysis framework based on system-theoretical process analysis (STPA) and cognitive reliability and error analysis method (CREAM) is proposed. STPA-CREAM can identify unsafe control actions and find the causal path during the interaction of avionics systems and pilot with the help of formal verification tools automatically. The common performance conditions (CPC) of avionics systems in the aviation environment is established and a quantitative analysis of human failure is carried out. Taking the head-up display (HUD) system interaction process as an example, a case analysis is carried out, the layered safety control structure and formal model of the HUD interaction process are established. For the interactive behavior “Pilots approaching with HUD”, four unsafe control actions and 35 causal scenarios are identified and the impact of common performance conditions at different levels on the pilot decision model are analyzed. The results show that HUD’s HCI level gradually improves as the scores of CPC increase, and the quality of crew member cooperation and time sufficiency of the task is the key to its HCI. Through case analysis, it is shown that STPA-CREAM can quantitatively assess the hazards in HCI and identify the key factors that impact safety.

As the “engine” of equipment continuous operation and repeated operation, equipment maintenance support plays a more prominent role in the confrontation of symmetrical combat systems. As the basis and guide for the planning and implementation of equipment maintenance tasks, the equipment damage measurement is an important guarantee for the effective implementation of maintenance support. Firstly,this article comprehensively analyses the influence factors to damage measurement from the enemy’s attributes, our attributes and the battlefield environment starting from the basic problem of wartime equipment damage measurement. Secondly, this article determines the key factors based on fuzzy comprehensive evaluation (FCE) and performed principal component analysis (PCA) on the key factors. Finally, the principal components representing more than 85% of the data features are taken as the input and the equipment damage quantity is taken as the output. The data are trained and tested by artificial neural network (ANN) and random forest (RF). In a word, FCE-PCA-RF can be used as a reference for the research of equipment damage estimation in wartime.

Based on the wave attack task planning method in static complex environment and the rolling optimization framework, an online task planning method in dynamic complex environment based on rolling optimization is proposed. In the process of online task planning in dynamic complex environment, online task planning is based on event triggering including target information update event, new target addition event, target failure event, weapon failure event, etc., and the methods include defense area reanalysis, parameter space update, and mission re-planning. Simulation is conducted for different events and the result shows that the index value of the attack scenario after re-planning is better than that before re-planning and according to the probability distribution of statistical simulation method, the index value distribution after re-planning is obviously in the region of high index value, and the index value gap before and after re-planning is related to the degree of posture change.

In this study, the problem of measuring noise pollution distribution by the intertial-based integrated navigation system is effectively suppressed. Based on nonlinear inertial navigation error modeling, a nested dual Kalman filter framework structure is developed. It consists of unscented Kalman filter (UKF) master filter and Kalman filter slave filter. This method uses nonlinear UKF for integrated navigation state estimation. At the same time, the exact noise measurement covariance is estimated by the Kalman filter dependency filter. The algorithm based on dual adaptive UKF (Dual-AUKF) has high accuracy and robustness, especially in the case of measurement information interference. Finally, vehicle-mounted and ship-mounted integrated navigation tests are conducted. Compared with traditional UKF and the Sage-Husa adaptive UKF (SH-AUKF), this method has comparable filtering accuracy and better filtering stability. The effectiveness of the proposed algorithm is verified.

Tracking the fast-moving object in occlusion situations is an important research topic in computer vision. Despite numerous notable contributions have been made in this field, few of them simultaneously incorporate both object’s extrinsic features and intrinsic motion patterns into their methodologies, thereby restricting the potential for tracking accuracy improvement. In this paper, on the basis of efficient convolution operators (ECO) model, a speed-accuracy-balanced model is put forward. This model uses the simple correlation filter to track the object in real-time, and adopts the sophisticated deep-learning neural network to extract high-level features to train a more complex filter correcting the tracking mistakes, when the tracking state is judged to be poor. Furthermore, in the context of scenarios involving regular fast-moving, a motion model based on Kalman filter is designed which greatly promotes the tracking stability, because this motion model could predict the object’s future location from its previous movement pattern. Additionally, instead of periodically updating our tracking model and training samples, a constrained condition for updating is proposed, which effectively mitigates contamination to the tracker from the background and undesirable samples avoiding model degradation when occlusion happens. From comprehensive experiments, our tracking model obtains better performance than ECO on object tracking benchmark 2015 (OTB100), and improves the area under curve (AUC) by about 8% and 32% compared with ECO, in the scenarios of fast-moving and occlusion on our own collected dataset.

Detumbling operation toward a rotating target with nutation is meaningful for debris removal but challenging. In this study, a deformable end-effector is first designed based on the requirements for contacting the nutating target. A dual-arm robotic system installed with the deformable end-effectors is modeled and the movement of the end-tips is analyzed. The complex operation of the contact toward a nutating target places strict requirements on control accuracy and controller robustness. Thus, an improvement of the tracking error transformation is proposed and an adaptive sliding mode controller with prescribed performance is designed to guarantee the fast and precise motion of the effector during the contact detumbling. Finally, by employing the proposed effector and the controller, numerical simulations are carried out to verify the effectiveness and efficiency of the contact detumbling toward a nutating target.

This study presents a kinematic calibration method for exoskeletal inertial motion capture (EI-MoCap) system with considering the random colored noise such as gyroscopic drift. In this method, the geometric parameters are calibrated by the traditional calibration method at first. Then, in order to calibrate the parameters affected by the random colored noise, the expectation maximization (EM) algorithm is introduced. Through the use of geometric parameters calibrated by the traditional calibration method, the iterations under the EM framework are decreased and the efficiency of the proposed method on embedded system is improved. The performance of the proposed kinematic calibration method is compared to the traditional calibration method. Furthermore, the feasibility of the proposed method is verified on the EI-MoCap system. The simulation and experiment demonstrate that the motion capture precision is significantly improved by 16.79% and 7.16% respectively in comparison to the traditional calibration method.

An algorithm to track multiple sharply maneuvering targets without prior knowledge about new target birth is proposed. These targets are capable of achieving sharp maneuvers within a short period of time, such as drones and agile missiles. The probability hypothesis density (PHD) filter, which propagates only the first-order statistical moment of the full target posterior, has been shown to be a computationally efficient solution to multitarget tracking problems. However, the standard PHD filter operates on the single dynamic model and requires prior information about target birth distribution, which leads to many limitations in terms of practical applications. In this paper, we introduce a nonzero mean, white noise turn rate dynamic model and generalize jump Markov systems to multitarget case to accommodate sharply maneuvering dynamics. Moreover, to adaptively estimate newborn targets’ information, a measurement-driven method based on the recursive random sampling consensus (RANSAC) algorithm is proposed. Simulation results demonstrate that the proposed method achieves significant improvement in tracking multiple sharply maneuvering targets with adaptive birth estimation.

Angles-only relative orbit determination for space non-cooperative targets based on passive sensor is subject to weakly observable problem of the relative state between two spacecraft. Previously, the evidence for angles-only observability was found by using cylindrical dynamics, however, the solution of orbit determination is still not provided. This study develops a relative orbit determination algorithm with the cylindrical dynamics based on differential evolution. Firstly, the relative motion dynamics and line-of-sight measurement model for near-circular orbit are established in cylindrical coordinate system. Secondly, the observability is qualitatively analyzed by using the dynamics and measurement model where the unobservable geometry is found. Then, the angles-only relative orbit determination problem is modeled into an optimal searching frame and an improved differential evolution algorithm is introduced to solve the problem. Finally, the proposed algorithm is verified and tested by a set of numerical simulations in the context of high-Earth and low-Earth cases. The results show that initial relative orbit determination (IROD) solution with an appropriate accuracy in a relative short span is achieved, which can be used to initialize the navigation filter.