12results about How to "Address imbalances" patented technology

The invention relates to the technical field of medical image analysis, in particular to a training method and system for a cataract recognition model and a storage medium. The method comprises the following steps: acquiring cataract eye image samples and non-cataract eye image samples in different stages; lesion region segmentation and image synchronous simulation enhancement are carried out on the cataract eye image samples and the non-cataract eye image samples in different stages to obtain cataract lesion enhanced image samples and non-cataract enhanced image samples; extracting local detail features of the lesion and extracting structural features of a mask pair, and constructing a multi-task convolutional neural network learning framework to train a cataract recognition model and optimize focus weighted loss; and obtaining a cataract related key feature set and carrying out online incremental learning updating to generate a cataract recognition online incremental updating model. According to the invention, the accuracy and robustness of cataract recognition model training can be improved.

The invention belongs to the technical field of diabetes diagnosis, and particularly relates to a diabetes prediction model construction method based on ensemble learning and a prediction system. The method comprises the following steps: step 1, carrying out preprocessing and feature screening on a data set; 2, dividing a training set and a test set; 3, searching and extracting positive samples in the training set, randomly generating positive samples obeying normal distribution according to the mean vector and the covariance matrix of the positive samples in the training set, adding the newly generated positive samples into the training set, and continuously repeating until the proportion of the negative samples to the positive samples is balanced; and 4, learning the model by using the processed training set machine. The invention also provides a diabetes prediction system constructed by using the machine learning model. The method can effectively improve the prediction performance of the prediction model through the balance of the sample data and the integrated learning of the single classifier, and has a good application prospect.

The application relates to the technical field of deep learning, in particular to a traffic scene image small target detection method and device, equipment and a storage medium. The method comprises the following steps: acquiring a traffic scene image and a detection result of a small target in the traffic scene image, generating a training data set according to the traffic scene image and the detection result of the small target in the traffic scene image; constructing a convolutional neural network based on a feature extraction module, a feature fusion module, a sample distribution module and a positioning classification module, and optimizing the sample distribution module and the positioning classification module of the convolutional neural network to obtain an optimized convolutional neural network; training the optimized convolutional neural network by using the training data set, updating network parameters of the optimized convolutional neural network based on gradient back propagation, and stopping the training until a preset training stop condition is met; and detecting small targets in the traffic scene image by using the trained convolutional neural network. Thus, the problems of small target sample imbalance and poor positioning capability in the related art are solved.

The invention discloses a near-infrared nonlinear discrimination method for fruit sorting, and relates to the technical field of artificial intelligence, and the training process of a classification discrimination model comprises the steps: obtaining a spectral data set of fruits, carrying out the preprocessing, carrying out the moving smoothing of the preprocessed spectral data set, and carrying out the classification discrimination. Mixing the preprocessed spectral data set with the spectral data set after moving and smoothing to serve as a sample data set; performing random sampling on the sample data set by using a Monte Carlo method so as to divide a training set and a first test set, training the discrimination model based on the training set, obtaining a classification result of random sampling, and performing statistics on a classification error rate of each sample; constructing a sample weight coefficient based on the probability density value corresponding to the chemical value of each sample and the classification error rate of each sample; constructing a non-linear discrimination model by using the sample weight coefficient, and optimizing the non-linear discrimination model; according to the near-infrared nonlinear discrimination method, the accuracy and reliability of fruit sorting are improved.

This invention discloses an abnormal driving recognition method based on pedal data and facial expression multimodal data. The process is as follows: Step 1: Collect vehicle driving data and facial video data, and label real facial abnormal expressions to obtain original multimodal data composed of multiple original multimodal samples; Step 2: Train an original abnormal driving model based on the original multimodal dataset; Step 3: Perform noise diffusion on each original multimodal sample to obtain diffused multimodal samples, and select effective multimodal samples from the diffused multimodal samples to construct a multimodal dataset; Step 4: Process the multimodal dataset using the original abnormal driving model, and select prediction-consistent multimodal samples to construct a prediction-consistent multimodal dataset; Step 5: Train the original abnormal driving model again using the prediction-consistent multimodal data to obtain an abnormal driving recognition model; Step 6: Use the abnormal driving recognition model to predict the abnormal driving prediction result.

According to the network intrusion detection enhancement method based on the diffusion model provided by the invention, noise is gradually added to training data through the diffusion model, and then a denoising process is learned to model data distribution. Based on this, the method can enhance the training sample by synthesizing the virtual sample, especially the category with a small number of enhanced samples, thereby solving the problem of low detection precision caused by sample imbalance. Meanwhile, the method can enhance the adversarial samples, and introduces a certain degree of change to synthesize more diversified adversarial samples while maintaining the core features of the adversarial samples, thereby enhancing the defensiveness of the detection model to unseen adversarial samples. An existing diffusion model is improved to be suitable for intrusion detection data, and the data synthesis effect of the diffusion model is improved through adaptive nonlinear noise. Furthermore, an optimal diffusion model is provided, the random noise of the diffusion model adopts self-adaptive nonlinear noise, and the noise level is dynamically adjusted according to time.

The application discloses a reinforcing cage hoisting device for pile testing of a cast-in-place pile and relates to the field of hoisting devices.The reinforcing cage hoisting device comprises a hoisting vehicle, a movable hoisting frame is installed on the hoisting vehicle, and a counterweight is movably installed on the movable hoisting frame; further comprising a counterweight moving device, the counterweight moving device is installed on the hoisting vehicle, the movable hoisting frame and the counterweight are both installed on the counterweight moving device, and the counterweight moving device is used for moving the counterweight.It should be noted that in the embodiment of the application, when the hoisting vehicle is pulled up, the counterweight is automatically extended to the lifting side to form an active balance moment without external power, and meanwhile, the counterweight frame is rotated and unfolded to further shift the center of gravity of the hoisting vehicle; in addition, the earth boring motor drives the drill rod to rotate and drill into the ground to provide additional pulling force, effectively solving the problems of unbalance and overturning of the hoisting vehicle and bringing about remarkable effects of safety, economy and convenient operation.

The application discloses a matchstick person posture intelligent monitoring method based on orthogonal amplification, collects a monitoring scene video, extracts human key points, generates a non-private matchstick person skeleton sample, extracts four types of features of a skeleton structure, motion, support contact and data distribution, adaptively matches a plurality of Hadamard, DCT and Wavelet orthogonal sampling matrices for different skeleton states, realizes sample amplification through point-by-point multiplication of the matrices, and adds a skeleton semantic check to remove invalid samples; and a BiGRU-Attention, TCN or Transformer time sequence model is used to complete fall and long-time lying risk identification. The application solves the problems of traditional monitoring privacy leakage, high-risk posture sample scarcity and random amplification to generate invalid skeleton samples, and is applicable to home, nursing ward and old-age care institution scenes.

The present invention relates to the field of cable processing technology, specifically to a cable processing device, which includes a device base, a hot melt mechanism and a molding mechanism; a feed hopper is provided on the upper side of the device base, and a control panel is provided on the front side of the device base; the hot melt mechanism includes a hot melt outer shell and a hot melt inner shell arranged in the hot melt outer shell, the lower end of the feed hopper extends into the hot melt inner shell, the outer wall of the hot melt inner shell is provided with a plurality of main electric heating rings, and an extrusion screw is arranged in the hot melt inner shell; the molding mechanism includes a molding outer shell and a molding assembly, the molding outer shell is located on the right side of the hot melt outer shell, the molding outer shell includes a transverse tube and a longitudinal tube, the transverse tube is assembled and connected to the discharge port of the hot melt inner shell by bolts; the molding assembly is located in the longitudinal tube. The present invention discloses a method for simplifying the steps required for disassembly and assembly of the molding mechanism while ensuring the sealing effect between the hot melt mechanism and the molding mechanism.

The embodiment of the present invention provides a method for de-anonymizing unbalanced trajectory data based on Granger causality, which belongs to the field of data processing technology, and specifically includes: step 1, for the problem of unbalanced multi-source trajectory data, data balancing processing is performed on anonymous and non-anonymous trajectory data sets; step 2, the trajectory data set processed by balancing is input into the improved bidirectional long short-term memory model, and anonymous trajectory representation and non-anonymous trajectory representation are obtained respectively; step 3, the non-anonymous trajectory representation is input into the causal learning module, and the causal structure existing in the trajectory data is extracted; step 4, the causal structure is input into the user ID balanced prediction module, and trained under the optimization of the loss function; step 5, the anonymous trajectory representation is input into the trained model, and the user and trajectory link result of the anonymous trajectory is obtained, so as to realize the de-anonymization of the trajectory. Through the scheme of the present invention, the accuracy of the de-anonymization effect is improved.

This invention proposes a method for detecting fake reviews based on big data, comprising: acquiring a review dataset, wherein the data in the review dataset includes review texts from multiple users and corresponding user behavior data, and performing data preprocessing; extracting review text features from the review dataset, and extracting user behavior features and review behavior features from the user behavior data; defining relationship categories based on the review text and user behavior features, and constructing a multidimensional relationship enhancement graph (MREGC) based on multiple relationships; using a dynamic adaptive feature enhancement graph neural network to learn features on the MREGC relationship graph, obtaining the embedding representation of each node in the multidimensional relationship enhancement graph, and aggregating the embedding representations; inputting the aggregated features into a classifier to determine whether a review is a fake review, and outputting a fake review label if the review is classified as a fake review; this invention, by fusing residual networks and multi-relationship review graphs, fully considers the multidimensional relationships and deep features between reviews, enabling the model to more accurately identify fake reviews, and significantly improving the accuracy and robustness of fake review detection.

This invention belongs to the field of data processing technology and provides a method and system for processing job application data for overseas recruitment. The method includes: analyzing job request texts uploaded by recruiting users to derive multiple key dimensions for judging job-person suitability, generating a job requirement feature vector; analyzing the relationships between these key dimensions and constructing a dynamic weight allocation network using a graph neural network; parsing each job request text in the set of uploaded job request texts to generate a job text feature vector; based on the dynamic weight allocation network, using semantic bridging to perform multi-dimensional joint similarity calculation between the job text feature vector and the job requirement feature vector to obtain the comprehensive suitability of each job request text; and removing job request texts with a comprehensive suitability below a preset threshold as content that does not belong to the requested business type. This invention enables intelligent and precise filtering of massive amounts of business texts.