5results about How to "Effective feature extraction" patented technology

The application provides a negative sample enhancement APT attack detection method based on graph structure learning, mainly solving the problem that the existing data set compatibility, edge information utilization and insufficient negative samples of the data set lead to poor detection effect. The scheme comprises the following steps: 1) obtaining a heterogeneous data set and constructing a visual traceability graph; 2) preprocessing the traceability graph, dividing it into snapshots according to the time stamp, and constructing a training set and a test set; 3) designing an encoder and a decoder of the graph neural network, taking the time window, the node feature, the adjacency matrix and the edge feature as the input of the encoder, and generating the reconstructed adjacency matrix through the decoder; 4) designing a loss function, and training the graph neural network through RNN; and 5) inputting the to-be-detected data into the trained model, identifying abnormal attack traffic, and completing the detection. The application can effectively improve the accuracy and robustness of APT attack detection, and can be used for the development and deployment of the APT attack detection and defense system in the network security field.

The present application relates to the technical field of detection of Dendrobium polysaccharide content, and discloses a system and method for rapid nondestructive detection of Dendrobium polysaccharide content, which comprises the following steps: collecting spectral reflection data in the 600 nm-1700 nm band by using a FLA6800 spectrometer, and performing data preprocessing, feature extraction, machine learning model training and prediction to rapidly and accurately predict the Dendrobium polysaccharide content, and finally generating a visual report and performing grading. The present application combines near-infrared spectroscopy technology with a machine learning model to realize efficient, accurate and nondestructive detection of the Dendrobium polysaccharide content, significantly improves the detection speed and accuracy, and provides real-time and reliable quality control basis.

The application provides an avalanche disaster road influence evaluation method and device based on deep learning, and relates to the technical field of deep learning. Firstly, avalanche dynamic information and road real-time response information in the evolution process of the avalanche disaster are dynamically captured to form an avalanche road dynamic interaction set. Then, a dynamic response simulation process is constructed to generate an avalanche road co-evolution feature set. Then, the avalanche road co-evolution feature set is input into a deep learning co-evolution network to generate an avalanche road evolution correlation feature set. Then, a cross-stage influence transmission simulation process is constructed based on the avalanche road evolution correlation feature set to generate a cross-stage influence transmission feature set. Finally, a dynamic evaluation result is generated through multi-dimensional co-evaluation operation. The application can comprehensively, dynamically and accurately evaluate the influence of the avalanche disaster on the road.

This invention relates to a method for locating defects in forgings, aiming to improve the efficiency and accuracy of defect identification. The method first involves grinding the surface of the forging to ensure its smoothness and flatness. Next, an ultrasonic flaw detector with low-frequency and high-frequency emission capabilities is used to emit ultrasonic waves and acquire signals. Wavelet transform technology is used to process and analyze the acquired signals, extracting amplitude, phase, and frequency features to form a feature set. In the defect feature identification stage, feature vectors are constructed and input into a trained support vector machine (SVM) model, outputting the probability of various defects. The defect type is determined based on a set threshold; if the probability exceeds the threshold, the defect is considered to exist. Finally, samples are cut and subjected to tensile tests based on the detection results to confirm the defect characteristics. This invention combines wavelet transform and machine learning techniques, not only achieving precise location of forging defects but also improving detection efficiency, demonstrating promising application prospects and economic value.

The invention belongs to the technical field of digital image watermarking, and provides a robust watermarking method based on multi-scale attention to solve the problem that an existing deep learning digital image robust watermarking scheme is insufficient in performance under attacks of JPEG, cutting and the like. An encoder-noise layer-decoder structure is adopted, and the encoder realizes feature extraction and cross-group fusion by designing an MSCAF module; meanwhile, constructing a space attention mask layer to guide the watermark to adaptively adjust the embedding strength according to the image features; the decoder uses the MSCAF to extract the multi-scale features so as to improve the watermark extraction precision. Experimental results show that under JPEG attack training of different quality factors, the PSNR and the watermark extraction error rate of the coded image are both superior to those of an existing comparison algorithm; under combined noise attack training, the average peak signal-to-noise ratio of a coded image generated by the method reaches 38.6738 dB, the watermark extraction error rate is lower than 0.6%, and the method is superior to an existing comparison algorithm.