Aiming at the problem of the present mainstream adversarial attack algorithm that the attack invisibility is reduced by disturbing the global image features, an untargeted attack algorithm named PS-MIFGSM (Perceptual-Sensitive Momentum Iterative Fast Gradient Sign Method) was proposed. Firstly, the areas of the image focused by Convolutional Neural Network (CNN) in the classification task were captured by using Grad-CAM algorithm. Then, MI-FGSM (Momentum Iterative Fast Gradient Sign Method) was used to attack the classification network to generate the adversarial disturbance, and the disturbance was applied to the focus areas of the image with the non-focus areas of the image unchanged, thereby, a new adversarial sample was generated. In the experiment, based on three image classification models Inception_v1, Resnet_v1 and Vgg_16, the effects of PS-MIFGSM and MI-FGSM on single model attack and set model attack were compared. The results show that PS-MIFGSM can effectively reduce the difference between the real sample and the adversarial sample with the attack success rate unchanged.
In order to solve the problems of having nonlinear observation equations and being susceptible to initial value of filtering in bearings-only target tracking, a range-parameterized hybrid coordinates Square Root Cubature Kalman Filter (SRCKF) algorithm was proposed. Firstly,it applied the SRCKF to hybrid coordinates,obtained better tracking effect than the SRCKF under Cartesian coordinates. And then it combined the range parameterization strategy with the SRCKF under hybrid coordinates, and eliminated the impact of unobservable range. The simulation results show that the proposed algorithm can significantly improve the accuracy and robustness although the computational complexity increases slightly.
Time-interval sequential pattern mining was used to discover frequent subsequences as patterns from sequence database of flowing industry. Firstly, the large history database were analyzed by fuzzy theory and the exceptional equipment parameters were found. After scattering exceptional parameters by Time-window approach, a new time-interval sequential database was got by dealing with time intervals. In order to find time-interval sequential pattern, TimeSeq_PrefixSpan algorithm is developed from the conventional PrefixSpan algorithm and implemented in flowing industry's production. Then the models can monitor faults when the equipments circulating.