10 results about "Classification rate" patented technology

The invention discloses a thermal power equipment fault diagnosis method based on artificial intelligence, and relates to the technical field of artificial intelligence. The method comprises the steps of thermal power equipment training data acquisition, thermal power equipment fault diagnosis, thermal power equipment training data labeling and thermal power equipment fault diagnosis. A comprehensive method of band-pass filtering and wavelet packet transformation is adopted for vibration signal preprocessing, information loss caused by a single method is avoided, key fault features can be extracted in multiple frequency bands and time domain ranges, the problem that a traditional filtering method is prone to failure in a multi-working-condition coupling vibration environment is solved, and the complete retention capacity of a fault mode is improved; the dynamic penalty factor based on the misclassification rate and the iteration process is adopted, penalty is reduced in the early stage of training, convergence difficulty is avoided, penalty is gradually enhanced in the later stage, the correction capacity of misclassification samples is improved, the problem that a traditional fixed penalty coefficient or a simple attenuation strategy is difficult to adapt to requirements of different training stages is solved, and model training is more stable and efficient.

According to the corn seed form classification method based on the residual network model, the residual network model is designed, input is allowed to be directly transmitted to a subsequent layer through jump connection, and the problem of gradient disappearance is avoided. A corn seed image sample is generated by combining active learning and a conditional generative adversarial network, and the problems of data imbalance and insufficient diversity are effectively solved. A residual network pre-trained through an ImageNet data set is introduced as a reference model, and the model adapts to a corn seed classification task through fine tuning. Dropout, an L2 regularization technology and an early stop method are combined, and the over-fitting risk of the classification model is reduced. And an RMSprop optimizer is used for dynamically adjusting the learning rate according to the change of the training process, so that an ideal optimization effect is achieved. A classification result shows that the corn seed classification model provided by the invention has remarkable advantages in the aspects of overall accuracy, balanced performance of all categories, low misclassification rate and the like.

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.

This invention discloses a robustness quantitative analysis method for intelligent image classification systems based on compressed sensing technology, belonging to the field of artificial intelligence. The method comprises the following steps: 1: collecting original image data and modifying labels; 2: training an intelligent image classification system to be tested using an original image training set and an adversarial image training set with modified labels; the intelligent image classification system comprises a transmitter, a receiver based on a compressed sensing algorithm, and an image classification end; and 3: testing the trained original intelligent image classification system and the adversarial intelligent image classification system using an original image test set, statistically calculating the misclassification rate of adversarial category images, and calculating the robustness score of the intelligent image classification system; a higher score indicates higher system robustness. The invention aims to provide guidance for the secure application of compressed sensing technology in intelligent image classification systems.

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.

The invention relates to the technical field of data processing, in particular to a VR simulation data intelligent classification method. According to the scheme, the multiple keywords in the historical VR simulation scene can be obtained, the corresponding features of the keywords are obtained so as to calculate the similarity between the keywords, the corresponding features and the membership degree between the keywords are obtained, the classification weight of each keyword is obtained by using the corresponding features and the membership degree between the keywords, and the classification efficiency of the keywords is improved. The method comprises the steps of obtaining classification weights of current simulation data, obtaining decision tree importance through the classification weights to train an XGboost model, and inputting the current simulation data into the trained XGboost model to realize classification of the current simulation data. According to the method, the final classification result of the simulation data in the current VR simulation scene is determined according to the similarity between the simulation scene keyword prepared in the current VR simulation scene and the keyword obtained by the XGboost model, so that the classification rate and accuracy of the VR simulation data are effectively improved.

The present application relates to the technical field of data processing, and particularly relates to a VR simulation data intelligent classification method; the scheme of the present application can acquire a plurality of keywords in a historical VR simulation scene, acquire corresponding features of the keywords, calculate the similarity between the keywords, obtain the membership between the corresponding features and the keywords, obtain the classification weight of each keyword by using the membership between the corresponding features and the keywords, train an XGboost model by using the classification weight to obtain the importance of a decision tree, input current simulation data into the trained XGboost model, and realize classification of the current simulation data. The present application determines the final classification result of simulation data in the current VR simulation scene according to the similarity between the simulation scene keywords in the current VR simulation scene and the keywords obtained by the XGboost model, effectively improving the classification rate and accuracy of VR simulation data.

The invention discloses a time sequence remote sensing image land cover classification method based on a multi-prototype cooperation mechanism, and mainly solves the problem that an existing large-scale remote sensing charting method neglects crop growth diversity in a region, and consequently the error classification rate is too high, and the scheme comprises the steps that 1, feature mapping is conducted on an input time sequence image; 2) learning a plurality of prototypes for each category by using a method based on multiple prototypes, and capturing subtle differences under different growth distributions through a time sequence measurement perception mechanism; 3) based on a distance measurement penalty strategy, realizing accurate modeling of a feature space through multiple optimization targets; and 4) by using an adversarial learning strategy, through constructing a game optimization process between the feature extractor and the domain discriminator, realizing alignment of different subclass spatial features, and obtaining a final classification result. According to the method, the problem of inconsistent distribution caused by time sequence change can be effectively relieved, the model generalization ability is improved, and the method is easy to deploy and popularize in an agricultural actual scene with limited resources.