Abstract：This paper introduces a way to realize the supervised neural network algorithms based on memristive characteristics on Field Programmable Gate Array(FPGA) for the problem that how to take the memristors into artificial neural networks and hardware implement. This design uses memristors module as weight store module in neural network to build supervised learning with error feedback mechanism. The memristive neural networks are used in pattern recognition and their hardware resource and processing speed are optimized. Experiment results show that the performance of pattern recognition is quite good. Further, the hardware resource occupancies and training time are 11 773 logic elements(LEs) and 0.33 ms on Cyclone II：EP2C70F896I8, respectively, and the test time of images is 10 μs, which gives a useful reference for combination of memristors and neural networks.
Abstract：The ambient noise at any two different sensors, in practice, may correlate with each other, and the spatial distribution of ambient noise intensity may be directional because of wind and shipping noise sources. A linear harmonic noise model is considered in this paper to appropriately describe the ambient noise. By applying l2-norm penalization of fitting the source covariance model to the estimated spatial covariance and the linear harmonic noise model, super-resolution direction of arrival(DOA) estimation algorithm based on sparse spectrum fitting is proposed. Then, the influence of the regular parameters and the number of linear noise model on the performance of the algorithm is discussed by computer simulations. The performance of the proposed algorithm is verified by the data processing of the sea trial data.
Abstract：When high resolution range profiles(HRRP) are used to recognize radar target, few traditional recognition methods analyse the sparseness of HRRP samples. In order to overcome the tedious analysis problems and simplify the recognition procedure, sparse representation is an effective way to compress HRRP samples and extract the target features. Thus, a federated redundant dictionary and a fast sparse representation algorithm are introduced to implement radar target recognition here. Moreover, a sparse decomposition parameter is adjusted by SNR in order to suppresses noise. The simulation results show that compared with the same kind of RATR algorithms, the algorithm in the paper is practicable, simple and efficient. In contrast to the traditional dimension reduction recognition method, it has better noise robustness and higher recognition ratio.
Abstract：The stability problem of memristor may affect the performance of memristive neural network. In order to explore it, a memristive back propagation(BP) neural network, in which the memristors are the synapses, is constructed based on the equivalent resistance topology memristor model. And it’s trained and tested on the MNIST dataset. The stability problem of memristor is simulated by setting fluctuations of the parameters in the model. Finally, it is found that the performance fluctuation of the memristor to a certain extent will promote the convergence of the neural network, but the excessive fluctuation will reduce the convergence speed of the network. To characterize this criticality, the maximum fluctuation range of each parameter in the model is obtained. Meanwhile, the fluctuations’ ranges of device parameters are obtained by tracing back to the memristor model. The result provides a reference for the fabrication and selection of memristor devices during hardware application.
Abstract：In ultrasonic measuring distance technology, traditional signal processing algorithms are difficult to analyze signals with long distances and weak echoes, and it is also impossible to measure the distance of multiple obstacles at the same time. In order to solve this problem, an ultrasonic measurement distance method based on random forest is proposed in this paper. Firstly the time domain characteristics of the signal—the relative peak amplitude and frequency domain characteristics—the relative area of the spectrum are extracted to judge the number of obstacles in the detection area by random forest method, and then calculates distance of obstacles. After the experiment, the algorithm can effectively measure the distance of multiple obstacles within 10 meters, and the measurement error is within 3 cm, which satisfies the practical application and has high practical value and theoretical reference significance.