4 results about "Classification rate" patented technology

The invention discloses a grid sorting abnormal code management method and system based on special rule sorting, and relates to the technical field of intelligent logistics, and the method comprises the following steps: S1, collecting package sheet information, and analyzing and extracting key information, including a receiving address, a package type and a delivery requirement; s2, the analyzed key information is matched with a predefined abnormal code rule base, whether an abnormal code is triggered or not is judged, and the abnormal code rule base comprises triggering conditions, processing measures and associated grid information of the abnormal code. According to the lattice sorting abnormal code management method and system based on special rule sorting, accurate coverage of a complex sorting scene is achieved by deeply optimizing an existing abnormal code rule, the recognition accuracy and processing efficiency of abnormal parcels are remarkably improved, an intelligent recognition engine is combined with a machine learning algorithm, and the recognition efficiency of the abnormal parcels is improved. The problem of fuzzy information processing is effectively solved, and the error classification rate is reduced.

The invention discloses a deep signature network based on a triple attention mechanism and distribution-dependent attacks, which comprises the following steps: firstly, acquiring an off-line handwritten signature original image, preprocessing the off-line handwritten signature original image and inputting the preprocessed off-line handwritten signature original image into an agent model integrated with the triple attention mechanism, and the triple attention mechanism can respectively capture three inter-dimension interactions so as to accurately capture signature features; and aiming at the problem of sample imbalance, real and forged signature weights are adjusted to train signature images, and a substitution model is finely adjusted to adapt to a dichotomy task. A distribution-related attack method is introduced to generate adversarial disturbance, disturbance is added to an offline handwritten signature image through a projection gradient descent algorithm to generate an adversarial sample, finally the generated adversarial sample attacks a target model after being processed by defense measures, and the attack effect of the target model is evaluated according to the misclassification rate of the target model. And a target model is used for extracting features to train an SVM (Support Vector Machine) to carry out signature identification, and multiple probabilities are counted to evaluate the attack success rate, so that target-free and target attacks on an offline handwritten signature image can be effectively realized.

The present application belongs to the technical field of multi-rotor unmanned aerial vehicle target recognition, and particularly relates to a feature extraction method for multi-rotor unmanned aerial vehicle and flying bird targets. The present application firstly performs distance-preserving dimension reduction preprocessing on the target micro-Doppler spectrum, and then extracts locally preserving orthogonal optimization projection features from the preprocessed spectrum data, so as to realize classification and recognition of multi-rotor unmanned aerial vehicle and flying bird targets. Since the distance-preserving dimension reduction method not only reduces the dimension size of the target spectrum and avoids "dimension disaster", but also retains the original distance information between targets, the distance weight coefficient can better reflect the distribution structure of the target data. At the same time, the locally preserving orthogonal optimization projection vector has mutual orthogonality, which can reduce the redundancy in the target features and reduce the overlap between the target feature regions, thereby improving the correct classification rate of the unmanned aerial vehicle and flying bird targets. The experimental results verify the effectiveness of the method of the present application.

The application relates to the technical field of satellite communication and discloses an open domain radiation source individual identification method and system based on deep learning, which comprises the following steps: acquiring a monitoring signal of a communication satellite and pre-processing the monitoring signal; inputting the pre-processed monitoring signal into a deep learning network for feature extraction to obtain a deep feature vector; training an individual identification classification network based on the deep feature vector; in the training process, a decision threshold value of an open set and a closed set is determined by combining a prediction score output of known category and unknown category data with an open set classification rate calculation criterion; the to-be-tested monitoring signal is pre-processed and feature-extracted, and a prediction score is output by using the trained individual identification classification network; the maximum value of the prediction score is compared with the decision threshold value; if the maximum value of the prediction score is greater than or equal to the decision threshold value, a corresponding known category label is output; otherwise, an unknown category label is output. The application improves the identification accuracy of unknown categories under the premise of ensuring the closed set performance.