Optimization of Kurtosis in the Extend-Infomax Blind Signal Separation Algorithm

A kurtosis optimization method is proposed to improve the blind separated signal qualities based on the extend-infomax algorithm. The kurtosis of the hypothetical source signal was optimized based on the probability density function of sub-Gaussian signals. Obtained parameters after kurtosis optimization were then utilized to validate the effectiveness of the algorithm, which showed that the running time of the algorithm was significantly reduced, and the qualities of the separated signals were enhanced. Methods. Using kurtosis as a control variable, a one-way analysis of variance (ANOVA) was carried out on the algorithm’s performance metrics, the number of iterations, and the signal-to-noise ratio of the separated signal. Results. The results showed that there were significant differences in the above metrics under different kurtosis levels. The curves of average metric values indicate that, with the increase in kurtosis of the hypothetical source signal, the performance of the algorithm was improved.

Design and Implementation of Blind Source Separation Based on BP Neural Network in Space-Based AIS

In space-based AIS (Automatic Identification System), due to the high orbit and wide coverage of the satellite, there are many self-organizing communities within the observation range of the satellite, and the signals will inevitably conflict, which reduces the probability of ship detection. In this paper, to improve system processing power and security, according to the characteristics of neural network that can efficiently find the optimal solution of a problem, proposes a method that combines the problem of blind source separation with BP neural network, using the generated suitable data set to train the neural network, thereby automatically generating a traditional blind signal separation algorithm with a more stable separation effect. At last, through the simulation results of combining the blind source separation problem with BP neural network, the performance and stability of the space-based AIS can be effectively improved.

Evaluation of Multi-Stream Fusion for Multi-View Image Set Comparison

We consider the problem of image set comparison, i.e., to determine whether two image sets show the same unique object (approximately) from the same viewpoints. Our proposition is to solve it by a multi-stream fusion of several image recognition paths. Immediate applications of this method can be found in fraud detection, deduplication procedure, or visual searching. The contribution of this paper is a novel distance measure for similarity of image sets and the experimental evaluation of several streams for the considered problem of same-car image set recognition. To determine a similarity score of image sets (this score expresses the certainty level that both sets represent the same object visible from the same set of views), we adapted a measure commonly applied in blind signal separation (BSS) evaluation. This measure is independent of the number of images in a set and the order of views in it. Separate streams for object classification (where a class represents either a car type or a car model-and-view) and object-to-object similarity evaluation (based on object features obtained alternatively by the convolutional neural network (CNN) or image keypoint descriptors) were designed. A late fusion by a fully-connected neural network (NN) completes the solution. The implementation is of modular structure—for semantic segmentation we use a Mask-RCNN (Mask regions with CNN features) with ResNet 101 as a backbone network; image feature extraction is either based on the DeepRanking neural network or classic keypoint descriptors (e.g., scale-invariant feature transform (SIFT)) and object classification is performed by two Inception V3 deep networks trained for car type-and-view and car model-and-view classification (4 views, 9 car types, and 197 car models are considered). Experiments conducted on the Stanford Cars dataset led to selection of the best system configuration that overperforms a base approach, allowing for a 67.7% GAR (genuine acceptance rate) at 3% FAR (false acceptance rate).

APPLICATION OF BLIND SIGNAL SEPARATION TECHNIQUES FOR DETECTION OF PHASE-SHIFTED RADIO SIGNALS

Целью данной работы является исследование эффективности алгоритма слепого разделения сигналов (СРСв задаче обнаружения цифровых фазоманипулированных радиосигналов. Рассмотрены классические методы СРС и критерии независимости сигналов. Исследована модель алгоритма СРС, основанного на вычислении размешивающей матрицы, которая приводит совместные кумулянты второго и четвертого порядков к нулю. Для исключения тривиального решения накладываются дополнительные ограничения на дисперсии сигналов. Приводится система уравнений для нахождения коэффициентов размешивающей матрицы. Показан вид коэффициентов размешивающей матрицы, приводящей сигналы к некоррелированному виду. Доказана возможность аналитического решения уравнения, связанного с равенством совместного кумулянта четвертого порядка к нулю. По результатам моделирования алгоритма СРС показано, что предложенный алгоритм позволяет обеспечить прием ФМ-2 радиосигнала на фоне гауссовой помехи. Выигрыш в отношении сигнал-помеха составляет не менее 2 дБ. The purpose of this work is to study the effectiveness of the blind signal separation algorithm in the problem of detecting digital PSK radio signals. Classical methods of blind signal separation and criteria of signal independence are considered. A model of a blind signal separation algorithm based on the calculation of a mixing matrix that reduces the joint cumulants of the second and fourth orders to zero is investigated. To eliminate the trivial solution, additional restrictions are imposed on the signal variances. A system of equations for finding the coefficients of the mixing matrix is given. The view of the coefficients of the mixing matrix, which leads the signals to an uncorrelated form, is shown. The possibility of an analytical solution of the equation associated with the equality of the joint cumulant of the fourth order to zero is proved. Based on the results of the simulation of the blind signal separation algorithm, it is shown that the proposed algorithm allows receiving the PSK-2 radio signal against the background of Gaussian interference. The gain in the signal-to-noise ratio is at least 2 dB.