No abstract

The class imbalance problem has been reported to exist in remote sensing and hinders the classification performance of many machine learning algorithms. Several technologies, such as data sampling methods, feature selection-based methods, and ensemble-based methods, have been proposed to solve the class imbalance problem. However, these methods suffer from the loss of useful information or from artificial noise, or result in overfitting. A novel double ensemble algorithm is proposed to deal with the multi-class imbalance problem of the hyperspectral image in this paper. This method first computes the feature importance values of the hyperspectral data via an ensemble model, then produces several balanced data sets based on oversampling and builds a number of classifiers. Finally, the classification results of these diversity classifiers are combined according to a specific ensemble rule. In the experiment, different data-handling methods and classification methods including random undersampling (RUS), random oversampling (ROS), Adaboost, Bagging, and random forest are compared with the proposed double random forest method. The experimental results on three imbalanced hyperspectral data sets demonstrate the effectiveness of the proposed algorithm.

The accuracy of low probability of intercept (LPI) radar waveform recognition is an important and challenging problem in electronic warfare. Aiming at the problem of the difficulty in feature extraction and the low recognition rates of the LPI radar signal under a low signal-to-noise ratio, and inspired by the symmetry theory, we propose a new approach for the LPI radar signal recognition method based on a dual-channel convolutional neural network (CNN) and feature fusion. Our new approach contains three main modules: the preprocessing module that converts the LPI radar waveforms into two-dimensional time-frequency images using the Choi–Williams distribution (CWD) transformation and performs image binarization, the feature extraction module that extracts different features obtained from the images, and the recognition module that utilizes a multi-layer perceptron (MLP) network to fuse these features and distinguish the type of LPI radar signals. In the feature extraction module, a two-channel CNN model is proposed that extracts Histogram of Oriented Gradients (HOG) features and deep features from time-frequency images, respectively. Finally, the recognition module recognizes the radar signals using a Softmax classifier based on the fused features from two channels. The experimental results from 12 types of LPI radar signals prove the superiority and robustness of the proposed model. Its overall recognition rate reaches 97% when the signal-to-noise ratio is −6 dB.

No abstract

The Synthetic Aperture Radar (SAR) echo simulation is to obtain the SAR original echo signal by performing reverse operation on the pre-set SAR image. The traditional platforms used to implement the simulation algorithms like central processing unit (CPU) + graphic processing unit (GPU) and digital signal processor (DSP) + field programmable gate array (FPGA) have disadvantages such as high power consumption or complicated programming. In order to make up for these shortcomings, the implementation structure of the SAR echo simulation algorithm was improved to be applicable on the heterogeneous embedded platform with the basic SAR simulation algorithms digitized and decomposed. Base on the improved structure, a mobile GPU based heterogeneous computing platform with one multiprocessor system-on-chip (MPSoC) and multiple GPUs was designed to implement SAR echo simulation algorithm. The platform can simultaneously utilize the real-time nature of register transfer level (RTL) design and the ease of programming on GPU. It can achieve relatively faster computing power at lower power consumption and has the characteristics of miniaturization and mobility.