To improve the ability of autonomous navigation for Unmanned Surface Vehicles (USVs), multi-sensor integrated navigation based on Inertial Navigation System (INS), Celestial Navigation System (CNS) and Doppler Velocity Log (DVL) is proposed. The CNS position and the DVL velocity are introduced as the reference information to correct the INS divergence error. The autonomy of the integrated system based on INS/CNS/DVL is much better compared with the integration based on INS/GNSS alone. However, the accuracy of DVL velocity and CNS position are decreased by the measurement noise of DVL and bad weather, respectively. Hence, the INS divergence error cannot be estimated and corrected by the reference information. To resolve the problem, the Adaptive Information Sharing Factor Federated Filter (AISFF) is introduced to fuse data. The information sharing factor of the Federated Filter is adaptively adjusted to maintaining multiple component solutions usable as back-ups, which can improve the reliability of overall system. The effectiveness of this approach is demonstrated by simulation and experiment, the results show that for the INS/CNS/DVL integrated system, when the DVL velocity accuracy is decreased and the CNS cannot work under bad weather conditions, the INS/CNS/DVL integrated system can operate stably based on the AISFF method.

Under the influence of variable sea conditions, a ship will have an oscillating motion comprising six degrees of freedom, all of which are connected to each other. Among these degrees of freedom, rolling and pitching motions have a severe impact on a ship’s maritime operations. An accurate and effective ship motion attitude prediction method that makes the prediction in a short period of time is required to guarantee the safety and stability of the ship’s maritime operations. Traditional methods are based on time domain analysis, such as the autoregressive moving average (ARMA) models. However, these models have limitations when it comes to predicting the nonlinear and nonstationary characteristics of real ship motion attitude data. Many intelligent algorithms continue to be applied in nonlinear and nonstationary ship attitude prediction, such as extreme learning machines (ELMs) and the long short-term memory (LSTM) neural network, as well as other deep learning methods, showing promising results. By using the sliding window approach, the time-varying dynamic characteristics of the ship’s motion attitude can be preserved better. The simulation results demonstrate that the proposed model performs well in terms of predicting the nonlinear and nonstationary ship motion attitude.

A new DS (Dempster-Shafer) combination method is presented in this paper. As data detected by a single sensor are characterized by not only fuzziness, but also partial reliability, the development of multi-sensor information fusion becomes extremely indispensable. The DS evidence theory is an effective means of information fusion, which can not only deal with the uncertainty and inconsistency of multi-sensor data, but also handle the inevitably ambiguity and instability under noise or possible interference. However, the application of DS evidence theory has some limitations when multi-sensor data are conflicting. To address this issue, the DS evidence theory is modified in this paper. Adopting the idea of cluster analysis, we firstly introduce the Lance distance function and spectral angle cosine function to revise original evidence separately before the combination of evidence. Then, based on the modifications of original evidence, an improved conflict redistribution strategy is ulteriorly raised to fuse multi-sensor information. Finally, the numerical simulation analyses demonstrate that the improvement of the DS evidence theory available in this paper overcomes the limitations of conventional DS evidence theory, and realizes more reliable fusion with multi-sensor conflicting information compared to the existing methods.

The method proposed in this letter for synthetic aperture radar (SAR) image classification has two main stages. In the first stage, a convolutional neural network (CNN) is trained for normal SAR image classification task. After training, the sample features can be obtained by extracting the output of middle layer in the forward propagation process of CNN. In the second stage, an end-to-end metric network is trained to measure the relations between sample features. The method proposed in this letter is tested with some of the larger targets in OpenSARShip data set which is collected from Sentinel-1 satellite, and it is also tested with the MSTAR data set which is created by the U.S. Air Force Laboratory. The experimental results show that our method can get a higher recognition accuracy than normal CNN structure.

Decision-making algorithm, as the key technology for uncertain data fusion, is the core to obtain reasonable multisensor information fusion results. DS evidence theory is a typical and widely applicable decision-making method. However, DS evidence theory makes decisions without considering the sensors’ difference, which may lead to illogical results. In this paper, we present a novel decision-making algorithm for uncertain fusion based on grey relation and DS evidence theory. The proposed algorithm comprehensively takes consideration of sensor’s credibility and evidence’s overall discriminability, which can solve the uncertainty problems caused by inconsistence of sensors themselves and complexity of monitoring environment and simultaneously ensure the validity and accuracy of fusion results. The innovative decision-making algorithm firstly obtains the sensor’s credibility through the introduction of grey relation theory and then defines two impact factors as sensor’s credibility and evidence’s overall discriminability according to the focal element analyses and evidence’s distance analysis, respectively; after that, it uses the impact factors to modify the evidences and finally gets more reasonable and effective results through DS combination rule. Simulation results and analyses demonstrate that the proposed algorithm can overcome the trouble caused by large evidence conflict and one-vote veto, which indicates that it can improve the ability of target judgment and enhance precision of uncertain data fusion. Thus the novel decision-making method has a certain application value.

In this paper, information entropy and ensemble learning based signal recognition theory and algorithms have been proposed. We have extracted 16 kinds of entropy features out of 9 types of modulated signals. The types of information entropy used are numerous, including Rényi entropy and energy entropy based on S Transform and Generalized S Transform. We have used three feature selection algorithms, including sequence forward selection (SFS), sequence forward floating selection (SFFS) and RELIEF-F to select the optimal feature subset from 16 entropy features. We use five classifiers, including k-nearest neighbor (KNN), support vector machine (SVM), Adaboost, Gradient Boosting Decision Tree (GBDT) and eXtreme Gradient Boosting (XGBoost) to classify the original feature set and the feature subsets selected by different feature selection algorithms. The simulation results show that the feature subsets selected by SFS and SFFS algorithms are the best, with a 48% increase in recognition rate over the original feature set when using KNN classifier and a 34% increase when using SVM classifier. For the other three classifiers, the original feature set can achieve the best recognition performance. The XGBoost classifier has the best recognition performance, the overall recognition rate is 97.74% and the recognition rate can reach 82% when the signal to noise ratio (SNR) is −10 dB.