45results about How to "Feature extraction is simple" patented technology

The invention discloses a method for automatic identifying steel slab coding and a steel slab tracking system. The method is characterized in that: from the starting of a first frame original image, automatic identification of slab coding is successively carried out on each frame of original image by the following steps: step 1, carrying out image preprocessing on the original image; step 2, carrying out binarization processing on the image after the preprocessing and carrying out slab coding detection and coding position positioning on an obtained binary image, wherein the slab coding detection and coding position positioning employ a projection processing method; and step 3, splitting the original image according to a boundary coordinate that is obtained by the coding position positioning to obtain a plurality of single character images and carrying out character identification on the each single character image, thereby completing slab coding identification on the original image ofthe current frame; and then returning to the step 1. According to the invention, the method for automatic identifying steel slab coding and the steel slab tracking system have characteristics of highautomation degree and high coding identification efficiency.

The invention discloses a graph-structured-data generation method based on deep convolutional generative adversarial networks (DCGAN), and belongs to the field of big-data technology. The method of the invention applies the deep convolutional generative adversarial networks to the generation field of graph-structured data. According to the method of the invention, firstly, actual graph-structureddata are converted into grid structure pictures with uniqueness; then learning of a generation model is carried out through the deep convolutional generative adversarial networks; and finally, specific-scale simulated graph-structured data are generated through the generation model, which is obtained by learning, according to input parameters and requirements. According to the graph-structured-data generation method based on the deep convolutional generative adversarial networks of the invention, features are extracted mainly from the actual graph-structured data to construct the model, and thus attributes which the generated simulated graph-structured data have are enabled to more accord with the actual graph-structured data.

The invention discloses a lower limb movement recognition method based on a pressure and acceleration sensor. The specific implementation steps of the method are as follows: firstly, the pressure sensor signal of the lower limb movement of the human body is collected in real time, and after preprocessing the pressure sensor signal, according to the pressure sensor data rising The edge and falling edge mark the start and end of the lower limb movement. When the rising edge of the pressure is detected, the three-axis acceleration signal of the acceleration sensor will be collected and stored. When the falling edge of the pressure is detected, the three-axis acceleration signal of the acceleration sensor will be collected. The three-axis signal of the acceleration sensor collected between the edge and the falling edge is called the acceleration signal segment. Then the frequency domain features and statistical features are extracted from the acceleration signal segment extracted in the previous step. After the features are extracted, the data dimensionality reduction is performed on the extracted features. Finally, the trained classifier is used to classify the feature data after dimension reduction, and the classification result of the action pattern is obtained.

The invention discloses a graph-structured-data generation method based on deep convolutional generative adversarial networks (DCGAN), and belongs to the field of big-data technology. The method of the invention applies the deep convolutional generative adversarial networks to the generation field of graph-structured data. According to the method of the invention, firstly, actual graph-structureddata are converted into grid structure pictures with uniqueness; then learning of a generation model is carried out through the deep convolutional generative adversarial networks; and finally, specific-scale simulated graph-structured data are generated through the generation model, which is obtained by learning, according to input parameters and requirements. According to the graph-structured-data generation method based on the deep convolutional generative adversarial networks of the invention, features are extracted mainly from the actual graph-structured data to construct the model, and thus attributes which the generated simulated graph-structured data have are enabled to more accord with the actual graph-structured data.

The invention discloses a signal identification method based on extraction of signal power spectrum fitting characteristic, and belongs to the field of the wireless communication. The signal identification method comprises the following steps: firstly dividing power spectrum data into a training set and a testing set, intercepting data sample fragments with equal length from the power spectrums corresponding to service class signals of different types in the training set; performing polynomial fitting on one data sample fragment A by using the least square linear regression algorithm to construct a cost function J, and minimizing the cost function J to acquire a parameter of the fitting polynomial; respectively selecting different polynomial orders, repeating w times of polynomial fittingand extracting the highest order item parameter, and acquiring all elements in a characteristic vector of the data sample fragment A; repeating the above steps to obtain a characteristic vector set Fof the service class signal, thereby constructing a training set matrix; and finally constructing a multi-layer neural network classifier model, searching an optimal solution by adopting a self-adaptive moment estimation algorithm, and identifying and classifying power spectrum signals in the testing set. Through the signal identification method disclosed by the invention, the characteristic extraction is simple and efficient, the signal identification rate is high, and the computing complexity is reduced.

The invention discloses a method for automatic identifying steel slab coding and a steel slab tracking system. The method is characterized in that: from the starting of a first frame original image, automatic identification of slab coding is successively carried out on each frame of original image by the following steps: step 1, carrying out image preprocessing on the original image; step 2, carrying out binarization processing on the image after the preprocessing and carrying out slab coding detection and coding position positioning on an obtained binary image, wherein the slab coding detection and coding position positioning employ a projection processing method; and step 3, splitting the original image according to a boundary coordinate that is obtained by the coding position positioning to obtain a plurality of single character images and carrying out character identification on the each single character image, thereby completing slab coding identification on the original image of the current frame; and then returning to the step 1. According to the invention, the method for automatic identifying steel slab coding and the steel slab tracking system have characteristics of high automation degree and high coding identification efficiency.

The invention belongs to the technical field of signal detection and estimation, and discloses a triangular linear frequency modulation continuous signal parameter estimation method based on differential envelope detection. A receiver samples an observed triangular linear frequency modulation continuous wave signal from the radar to obtain a sampling sequence; the receiver carries out differentialoperation, Hilbert transform and low-pass filtering on the sampling sequence to obtain a denoising envelope sequence; the receiver calculates according to the denoising envelope sequence to obtain signal characteristic parameters including a positive modulation frequency, a negative modulation frequency, a frequency modulation signal period, a minimum frequency in a sweep frequency interval and amaximum frequency in the sweep frequency interval. The triangular linear frequency modulation continuous signal parameter estimation method based on differential envelope detection has the advantagesof characteristic extraction and calculation in the time domain and lower time complexity, and can be used for solving the parameter estimation problem of the triangular linear frequency modulation continuous signal; the characteristic parameters of the triangular linear frequency modulation continuous signal can be obtained by utilizing the sequence difference and the envelope detection, and a parameter estimation value is calculated according to the envelope slope and the change time of the envelope slope.

The present disclosure provides a malicious domain name processing method, device, device and machine-readable storage medium. The method includes: acquiring training samples that meet preset requirements, extracting sample features from the training samples according to preset dimensions; and according to the extracted sample features , perform sample clustering on the training samples, and use BiLstm to train and generate a classifier; use the classifier to process the features extracted according to the domain name to be determined, and determine whether the domain name to be determined belongs to the DGA domain name; the preset dimensions include : Domain name length, initial proportion, numerical proportion, domain name entropy. Through the technical solution of the present disclosure, the initials of pinyin are used as one of the dimensions of the training model, and the algorithm model obtained can effectively reduce the false alarm rate of domestic websites. At the same time, the training method provided by the present disclosure has simple and efficient feature extraction, and can determine the DGA domain name. High accuracy and low resource consumption.

The technical solution of the present invention includes a GRNN-based identity recognition method, which is used to realize: obtain an ECG signal sample data set including multiple cycles of heartbeat data of multiple users, and use wavelet transform to remove the ECG signal noise; the denoised signal is segmented to construct the morphological features of the ECG signal, and the heartbeat feature database of the training set and the heartbeat feature database of the test set are respectively constructed; the singular value decomposition method is used to remove the redundancy in the ECG signal. Additional features; using linear discriminant analysis to reduce the dimensionality of the heart beat feature data set; training a generalized regression neural network classifier, and outputting the identity information of the individual according to the principle of multi-heart beat voting. The beneficial effects of the present invention are: the redundant information in the electrocardiogram signal is effectively removed, and the accuracy rate of subsequent identification is improved, while the reduction of the feature dimension of the heartbeat by LDA and the use of the GRNN neural network as a classifier greatly improve the identification speed.

The invention discloses a method for estimating the abundance of a hyperspectral image end member. The method for estimating the abundance of the hyperspectral image end member comprises a first step of extracting the image end from an image and selecting mixed pixel points, conducting linear decomposition and obtaining a corresponding abundance value, a second step of evaluating a normalized spectral characteristic value which corresponds to the end member, a third step of tracing points under a rectangular coordinate system, a fourth step of conducting curve fitting and obtaining a quadratic curve expression, a fifth step of obtaining the abundance of the rest points by means of mapping the spectral characteristic value, and a sixth step of evaluating the root mean square error RMSE between an estimated value and an actual value and judging whether the RMSE meets the evaluated precision. According to the method for estimating the abundance of the hyperspectral image end member, an abundance value is rapidly predicted through establishment of certain relationship between the spectral feature value and the abundance of the end member, the defect that the corresponding abundance can be obtained when the liner decomposition is conducted on all mixed pixel points is overcome. In actual application process, due to the fact that the linear decomposition is conducted on only a small amount of pixel points which are evenly distributed, the abundance value which corresponds to end members of all pixel points can be obtained, and the time of decomposition of the pixel points can be effectively shortened.