49 results about "Svm classifier" patented technology

The invention relates to the field of electroencephalogram signal processing and neural engineering, and discloses a multi-mode electroencephalogram feature fusion decoding method. The method comprises the following steps: carrying out noise reduction, calibration and standardization processing on an original electroencephalogram signal to generate a standard signal; extracting mu / beta rhythm time-frequency features and Hjorth time-domain features of the signals, and generating a fusion feature vector through PCA dimension reduction fusion; performing pre-classification and weight optimization by using an SVM classifier, performing space and time sequence feature extraction and classification through a CNN-LSTM network, and outputting a classification probability; model parameters are updated according to the probability and verified, and finally real-time control signals suitable for various communication interfaces are generated. According to the method, the accuracy and robustness of electroencephalogram signal decoding are improved, and efficient and self-adaptive motor imagery brain-computer interface control is realized.

The application discloses a kind of based on machine vision's grain quality index intelligent detection method, it is related to grain quality and safety detection technical field, including, using high-resolution camera to collect the upper surface and lower surface image of grain sample, pre-processing is carried out, obtains the two-dimensional image after pre-processing, utilizes convolutional neural network to extract two-dimensional feature, identifies grain external defect, and applies the physical model of light scattering theory to analyze grain internal defect, obtains preliminary quality evaluation result, the application is extracted two-dimensional feature by combining convolutional neural network to identify grain external defect, and applies the physical model of light scattering theory to analyze grain internal defect, to realize the overall evaluation of grain internal and external quality.SVM classifier is used to determine the final quality state of each grain, further improve user experience and work efficiency.

The application belongs to the field of electroencephalogram signal processing, and is a fatigue driving classification method and system based on electroencephalogram multi-scale fuzzy entropy features of CEEMDAN. The method comprises the following steps: collecting electroencephalogram data, and labeling part of the data; pre-processing the electroencephalogram signal to remove artifacts in the electroencephalogram signal; extracting features from the pre-processed electroencephalogram signal, constructing and training an SVM classifier, classifying unmarked data using the trained SVM classifier to obtain pseudo-labeled data; performing CEEMDAN processing and scale transformation processing on the pseudo-labeled data and the previously obtained labeled data to obtain electroencephalogram multi-scale fuzzy entropy features based on CEEMDAN, and establishing a fatigue state classification model to classify the electroencephalogram signal. The collection method is simple, is more suitable for application in an intelligent driving system, and has a high fatigue state recognition rate.

The invention relates to the technical field of image incremental learning, and discloses a support vector guided discriminant playback and double-alignment distillation incremental method, which can realize balanced learning of new and old knowledge without relying on original data, and can improve the learning efficiency in each task stage. The method comprises the following steps: firstly, extracting image features by using a feature extraction network fused with a triple attention mechanism, carrying out classification training by adopting a support vector machine (SVM), generating a corresponding support vector set, and in a subsequent incremental training process, firstly, designing a joint feature retention strategy to carry out discriminative playback on support vectors, and constructing a training data set; then, support vector distillation loss is constructed, and the network is updated in combination with an existing loss function so as to maintain the discrimination capability of an old category; and finally, completing an identification task by using the updated SVM classifier in a classification stage. Experimental results on data sets of CIFAR-100, Tiny-Image Net and the like show that the method is remarkably superior to the prior art in the aspects of recognition accuracy and small sample adaptability.

The application belongs to the field of mechanical fault diagnosis of disconnectors, and provides a disconnector fault diagnosis method and system. The method comprises obtaining real-time vibration signals of the disconnector, and sequentially performing singular value filtering noise reduction and hybrid modal decomposition processing on the vibration signals to extract feature vectors; and performing fault diagnosis on the disconnector according to the feature vectors and a deep weighted fusion model based on an SVM classifier; wherein the construction process of the deep weighted fusion model based on the SVM classifier is as follows: obtaining an initial weak SVM classifier according to the feature vectors of the disconnector vibration signals and a linear support vector machine with a Gaussian kernel as an initial kernel function; and iteratively optimizing the initial weak SVM classifier by means of a deep fusion weighting algorithm and optimal allocation of the weights of the disconnector vibration signal samples to obtain an SVM classifier satisfying a preset condition and serving as the deep weighted fusion model based on the SVM classifier.

The application provides a kind of mood recognition method, device, equipment and storage medium, it is related to artificial intelligence, the method comprises: according to frame level feature, the statistical feature of audio data is acquired;Frame level feature is input to deep neural network, and first emotion score is obtained;Wherein, deep neural network includes DNN layer, BLSTM model, attention layer, DNN layer and softmax layer in order from input side to output side;Attention layer carries out weighted average calculation to the output of BLSTM model at different time points, and first emotion representation is acquired;Statistical feature and first emotion representation are input to SVM classifier model, and second emotion score is obtained;According to first emotion score and second emotion score, emotion recognition result is obtained;Emotion recognition result is used to represent the emotional state identified from audio data.The application can balance and utilize frame level and sentence level emotional information in audio segment, can obtain the emotion recognition result with higher robustness, improve the precision of emotion recognition.

The application discloses a bearing fault diagnosis method and system based on a CS-SHAP model, bearing operation signals are collected through acceleration, temperature and acoustic emission multi-sensor, multi-dimensional fault features are extracted from time domain, frequency domain and time-frequency domain after wavelet transform or EMD algorithm denoising to complete preprocessing, feature data is divided into similar clusters by K-means clustering, SHAP values are calculated cluster by cluster and weighted according to cluster data density or diagnosis influence degree to obtain feature importance score, a SVM classifier based on RBF kernel function is trained with screened key features, model parameters are optimized through 5-fold cross validation, new collected data is preprocessed and input into the trained model to obtain diagnosis results, feature SHAP values are calculated and visualized by using the CS-SHAP model, and key factors of faults are analyzed. The application realizes accurate diagnosis of bearing faults and interpretability of diagnosis results, and provides technical support for intelligent operation and maintenance of industrial equipment.

The application discloses an image recognition method and device based on chroma domain positioning and topological constraint, relates to the technical field of data processing, and comprises the following steps: after an input image is preprocessed, an initial mask is generated in combination with contrast criteria and darkness criteria, pseudo targets are removed through hole-preserving connected domain analysis and Euler number filtering; rendering is performed by using an artificial color embedding technology, chroma domain positioning is performed in an HSV space, and an MRZ region is extracted; an inclination angle is estimated based on edge line direction consistency, and a maximum inscribed rectangle cutting is performed to obtain an MRZ cutting region; character segmentation is performed based on format constraint, an uncertainty conduction scheduling mechanism is adopted to adjust segmentation parameters and a retry strategy, and multiple single-character images are output; HOG features are extracted from the single-character images, a character classification is performed by using an SVM classifier, and preliminary recognition results and classification scores of each character are obtained; a final recognition score is fused based on structure prior scores and classification scores, and complete MRZ text is output.

The invention relates to the technical field of medical image processing, and particularly discloses a medical image processing method and a medical image processing system, which are characterized in that pixels are divided by dynamically calculating an adaptive threshold, a Gaussian mixture model is used for denoising, an image is enhanced by a multi-scale Retinex enhancement algorithm, and a tissue boundary is highlighted. And constructing a U-Net network model combined with an attention mechanism, training by using a large amount of annotation data, optimizing by using a cross entropy loss function and a stochastic gradient descent algorithm, inputting a preprocessed image, and outputting a segmentation result. And extracting multiple types of features for the segmented tissues, constructing a diagnosis model by combining an SVM classifier with multi-modal features, determining parameters through a grid search method and cross validation, and inputting new image features to assist doctors in diagnosis. According to the method, the adaptive threshold is dynamically calculated to remove noise, the U-Net network model combined with the attention mechanism is utilized to perform image segmentation and construct the disease diagnosis model, the quality of medical image processing and the accuracy of disease diagnosis are improved, and more reliable diagnosis assistance is provided for doctors.

The application relates to an image recognition method for multiple types of underwater targets. When a support vector machine (SVM) is used to classify and recognize underwater image targets, a transductive support vector machine (TSVM) and a multi-SVM are combined to establish a double-layer structure image recognition system. Firstly, a classifier constructed by the TSVM is used to preliminarily classify according to the geometric properties of the target, and the set (which is a subset in the sample set and is composed of multiple samples with similar geometric properties) to which the target belongs is determined; then, a multi-SVM classifier corresponding to the set is used to classify according to the texture features of the target, the specific type of the target is confirmed, and target recognition is realized. The method reduces the number of types learned by the multi-SVM, and reduces the influence of the number of target types on the recognition rate.

This invention relates to the field of power quality analysis technology, specifically providing a power quality evaluation method and apparatus based on multi-source data fusion. The method includes: acquiring power quality parameters at the power supply end, performing wavelet transform on these parameters to obtain the information entropy corresponding to the power quality parameters; using the information entropy as input to a pre-trained SVM classifier to obtain the power quality assessment level of the power supply end output by the pre-trained SVM classifier; acquiring power quality parameters at the user end, using these parameters as input to a pre-built PCNN model to obtain the power quality assessment level of the user end output by the pre-built PCNN model; and determining the power system power command assessment result based on the power supply end power quality assessment level and the user end power quality assessment level. The technical solution provided by this invention can effectively reflect the overall power quality of the power system.

The utility model relates to pipeline safety monitoring technical field, and disclose a kind of sensing pile device of monitoring oil and gas pipeline periphery construction behavior, including equipment column, equipment lower shell is fixedly connected in equipment column by bolt, the upper fixedly connected equipment upper shell of equipment lower shell, the shell base is fixedly connected in equipment lower shell by bolt;Through the setting of pickup unit, collect sound and extract MFCC feature, utilize SVM classifier to distinguish construction and environmental noise, while starting wide-angle camera to record video when meeting trigger condition, target detection and behavior analysis are carried out through AI data processing unit, form the dual verification mechanism of voiceprint and video, effectively reduce false alarm rate to below 5%, avoid relying on single sensor, it is difficult to distinguish construction noise and environmental noise, lead to high false alarm rate.

The application relates to the field of fault diagnosis, and is specifically a kind of aero-engine fault diagnosis method, system, terminal and medium based on deep auto-encoder transfer learning technology, wherein a source domain basic model is trained by using a data set of a certain type of object, and on this basis, when the fault of the same type of object of different types needs to be diagnosed, only a small amount of target domain data set is needed, and the source domain basic model can be fine-tuned by combining the transfer learning technology, so that a target domain deep auto-encoder transfer learning model is obtained, the deep features of the target domain data are extracted, and finally, the fault diagnosis is realized by using an SVM classifier for classification. Compared with the traditional engine fault diagnosis method, the method has the advantages of easy migration of the diagnosis object, low requirement for the fault sample amount, high diagnosis precision and the like.

The application discloses a kind of finger vein image recognition methods based on multi-index fusion pre-evaluation, comprising: obtaining image quality evaluation index, carrying out normalization processing to evaluation index, generating sample vector, determining classifier core parameter and generating SVM classifier, evaluating and screening picture to generate database to image, carrying out HOG feature extraction and gray level co-occurrence matrix feature extraction to the image processed, fusion two kinds of features form fusion vector, identity matching.The application can effectively reduce the problems such as recognition rate reduction caused by uneven image quality.

The application discloses a kind of based on multi-sensor fusion's aero-engine test bed performance parameter synchronous acquisition and analysis system;System is through the hierarchical linkage of sensor layer, data acquisition layer, data processing layer and analysis decision layer, integrates multiple types of high-precision sensors, adopts the dual time alignment mechanism of hardware synchronous trigger and software compensation combination, fuses the multi-modal algorithm of Kalman filter, SVM classifier, deep neural network (DNN) and D-S evidence reasoning, with double-layer inverse Broyden iteration and online learning adaptive model, realize the accurate synchronous acquisition of engine temperature, pressure, vibration and other key parameters, real-time analysis and fault early warning.System is compatible with multiple aviation buses, with redundant transmission and anti-interference design, visual interface supports multidimensional data linkage and playback, can adapt to the engine test demand under different conditions, provides reliable technical support for aero-engine research and development, maintenance and performance optimization.

The invention provides a monocular camera visibility estimation method and a monocular camera visibility estimation device in order to effectively estimate the road visibility by using a monocular video image. According to the method, day and night scene division is carried out, and day and night judgment is carried out on an input image by using a support SVM classifier. For a daytime scene, estimating a smooth transmissivity graph based on an atmospheric scattering model by combining color ellipsoid prior and a guided filtering method; for a night scene, the RGB image is converted into a normalized grey-scale map which is used as an illumination map. And inputting the image into the trained depth estimation network, outputting a single-channel depth map, and carrying out linear normalization processing on the single-channel depth map. For a daytime scene, reversely deducing a transmission coefficient graph by combining the transmissivity graph and the depth graph according to a Koschmieder formula, and estimating global visibility after removing an extreme value; and for a night scene, according to the depth map and the illumination map, constructing a simplified illumination model to carry out global visibility estimation.

The invention discloses a single-phase earth fault reason identification method and system based on multi-dimensional robust Fisher feature selection and a multi-support vector machine, and the method comprises the steps: firstly extracting multi-dimensional time domain, frequency domain and time-frequency domain features from fault recording data, and constructing a fault feature candidate set; the method comprises the following steps: firstly, carrying out multi-dimensional robust Fisher feature selection on each feature fusion Fisher score, mutual information and a robustness index so as to screen out an optimized feature vector with the highest distinction degree and anti-interference capability, and finally, in order to solve the problems of complexity and sample imbalance of multi-class fault identification, carrying out multi-dimensional robust Fisher feature selection on the feature fusion Fisher score, the mutual information and the robustness index. A multi-support vector machine identification mechanism based on a priority judgment strategy is constructed, a plurality of independent SVM classifiers are trained by optimizing feature vectors, and step-by-step judgment is performed by using the trained SVM classifiers. According to the method, the identification capability of various single-phase earth fault reasons is remarkably improved.

The invention relates to a multi-modal feature-based network construction type energy storage fault diagnosis method and system, and the method comprises the steps: collecting the operation data of an energy storage system, and carrying out the preprocessing of the operation data; performing feature extraction including a time domain and a frequency domain on the preprocessed operation data to obtain feature vectors of different modes; dividing the feature vectors of different modes into feature groups according to a physical domain, calculating the abnormality of each feature group, mapping the abnormality into a weight coefficient of each feature group through a full connection layer, and carrying out the weighted fusion of each feature group based on the weight coefficient, thereby obtaining a final fusion feature vector; and inputting the final fusion feature vector into an SVM classifier designed based on an adaptive kernel function, and carrying out fault type identification. According to the method, the problems of low diagnosis accuracy, poor real-time performance and high false alarm rate due to too single data of the existing diagnosis method are solved.

The invention discloses a children education strategy generation method and system based on multi-modal perception, and a medium, and relates to the technical field of children education strategies and interaction. Comprising the following steps: acquiring first modal behavior data and second modal behavior data of a child in a teaching process; according to the first modal behavior data, a ResNet-18 model is adopted to recognize the facial emotion of the child, and a first emotion classification result is obtained; according to the second modal behavior data, adopting an SVM classifier to classify the voice emotion to obtain a second emotion classification result; based on a D-S evidence theory, fusing the first emotion classification result and the second emotion classification result to obtain a final emotion classification result; according to the final emotion classification result, the development stage, the age interval, the symbolization ability and the logical reasoning threshold value, a four-dimensional evaluation matrix is constructed, and a teaching strategy suitable for the current state of the child is generated. According to the invention, the teaching content is dynamically matched with the children cognitive development stage.

The application discloses a method, system, device and medium for building a data visualization large screen based on an improved ResNet algorithm, and the method comprises the following steps: constructing a training data set, training an improved ResNet18 model by using the training data set; removing two full connection layers of the trained improved ResNet18 model to serve as a feature extractor; extracting features of the training data set by using the feature extractor, training an SVM classifier by using the extracted features; cutting a large design graph to obtain a plurality of small graphs, inputting features of the small graphs into the trained SVM classifier after applying the feature extractor to extract the features of the small graphs, classifying the small graphs, matching components from a component library according to the categories of the small graphs, and rendering the components to a large screen according to the information of the small graphs; and configuring and adjusting the components and page attributes of the large screen according to data, display and event requirements of the large screen, so as to obtain a complete data visualization large screen. The application has a higher chart image classification accuracy than existing models, and reduces the design complexity of the large screen through low-code components, thereby avoiding a repeated configuration process.

The application discloses a kind of based on Internet of Things's carrying thing security detection management system and method, it is related to carrying thing safety detection technical field, the present application is based on the sensor combination of carrying thing type label selection, collects the multimodal sensing data of carrying thing, vehicle and driver;Uniform timestamp and space coordinates are applied to multimodal data Generation spatiotemporal correlation dataset;Filter spatiotemporal correlation dataset constitutes core feature set, the operation characteristic analysis fusion weight of vehicle is combined, and optimization feature is generated based on fusion weight;Optimized features and corresponding category labels are used to train SVM classifier, and the local data of each vehicle is used to train LSTM model;Analysis source domain and target domain MMD distance;Fusion multi-source evidence analysis joint trust degree, based on dynamic safety evaluation triggers abnormal early warning.Adaptive fusion multi-source feature, dynamically adjust threshold, adapt to different time periods risk fluctuation, improve early warning sensitivity.

The present application relates to the technical field of rolling contact fatigue detection, and particularly relates to a rolling contact fatigue detection method based on a hybrid neural network, which comprises the following steps: constructing a corresponding hybrid neural network model as a fatigue prediction model based on a neural network and an SVM classifier; training the fatigue prediction model; inputting vibration data of a test sample to be detected into the trained fatigue prediction model, performing feature extraction and feature classification prediction by the neural network and the SVM classifier respectively, and then outputting corresponding fatigue prediction class probabilities; and taking the fatigue prediction class probabilities output by the fatigue prediction model as fatigue detection results of the corresponding test sample to be detected. In the present application, feature extraction can be accurately and effectively realized through the fatigue prediction model, and the generalization ability of the fatigue prediction model can be improved, so that the accuracy and effect of rolling contact fatigue detection are improved.

This invention belongs to the technical field of image classification and discloses a medical image classification method based on Lie group kernel learning. The method includes acquiring low-level image features and representing them as a Lie group matrix; obtaining the model parameters of an SVM classifier and the pivot point for each class through a training image set; and selecting either an SVM or KNN classifier to classify the images based on the geodesic distance between the class pivot point and each image to be classified, calculated using the Lie group kernel function on the Lie group manifold. This invention outperforms traditional image classification methods in terms of classification accuracy. Compared to artificial neural network methods, it has less dependence on training data and processes, and exhibits stronger generalization and deployability.

The application discloses a system intrusion detection method based on SAE and FSVM, step one, setting a listening system at the network port of the recruitment platform, step two, processing historical data, and using the processed data for rule learning of the intrusion detection model, step three, preprocessing the real-time data obtained by interception in step one, and using the self-encoder model obtained in step two for dimension reduction processing of the real-time data, and using the model generated in step two for classification of the processed data, step four, putting the abnormal data and part of the normal data in step three into a historical database, step five, separating and filtering the real-time data according to the marking in step three, and giving response measures for the abnormal data. The application can effectively improve the learning speed and learning rate of the SVM classifier by reducing the size of the sample data through the feature processing of the network data by SAE, so that the efficiency of the intrusion detection is improved.

The invention discloses an SVM (Support Vector Machine) cooperative spectrum sensing method and system based on PSO (Particle Swarm Optimization), and relates to the technical field of cognitive radio. The system at least comprises a cognitive user, an authorized user and a fusion center, an authorized user, namely a primary user (PU), transmits a signal in an authorized frequency band, and the signal is influenced by path loss and fading in a propagation process; a cognitive user is a secondary user SU, a plurality of SUs are randomly distributed in a network, energy sampling is periodically carried out on a target frequency band, and local observation data are obtained; the fusion center, namely, FC, receives observation data uploaded by each SU and is used for unified judgment; and a PSO module and an SVM judgment module are deployed at the fusion center. According to the method, a hyper-parameter automatic optimization module based on particle swarm optimization (PSO) is introduced into a fusion center, so that a kernel parameter and a penalty factor of an SVM classifier can be adaptively adjusted under the conditions of a dynamic channel and different signal-to-noise ratios, and a better compromise is obtained among detection precision, robustness and calculation efficiency.

The application provides an airport low-altitude flight track playback analysis method and system, and relates to the technical field of air traffic management. The method comprises the following steps: acquiring low-altitude flight track data, constructing a hybrid neural network model to filter and process the low-altitude flight track data to generate intermediate flight track data; identifying key track feature data and non-key track data in the intermediate flight track data through an SVM classifier and respectively performing lossless compression and lossy compression to generate playback flight track data; designing a collaborative computing framework of CPU, GPU and FPGA, and distributing the playback flight track data to multiple track computing nodes for collaborative processing; adopting a storage architecture based on consistent hashing to partition and store the playback flight track data, and designing a multi-level index mechanism to support the retrieval of the playback flight track data, so that the track playback precision can be improved, the data processing efficiency can be optimized, and the system storage and computing cost can be reduced.

The application discloses a mechanical rotating component fault diagnosis method based on non-stationary nonlinear feature cancellation, and pre-acquires mechanical rotating component vibration signals under normal and fault states. i The original intrinsic mode component is obtained by using empirical mode decomposition to process the original signal, then a step parameter h is set, multi-step reconstruction is carried out, the reconstructed component is obtained, energy features are calculated, and a data set is established; an optimal kernel function is selected, a kernel matrix is constructed; the data is input into the kernel matrix, the kernel matrix is centralized, the characteristic value is calculated, the characteristic vector is sorted in size order, and the data set is reconstructed; the reconstructed data set is input into the SVM, the SVM classifier is trained by using the training set, the trained classifier is tested by using the test set, and precise fault classification is realized. The kernel principal component algorithm proposed in the application combines the empirical mode decomposition method, and can realize precise classification of mechanical rotating component faults for non-linear and non-stationary signals.

This invention discloses a multi-radar cooperative target recognition method, relating to the field of radar target recognition technology. It solves the problems of complex target recognition algorithm system design, large data processing volume, and single-target recognition limitations in existing technologies. The method includes: acquiring multiple static RCS data of multiple targets to be identified; obtaining the motion trajectories of multiple targets using motion equations; calculating and adding variable micro-motion features to the corresponding static RCS data to obtain multiple dynamic RCS data; adding noise to the multiple dynamic RCS data; extracting statistical features from the multiple final RCS data and inputting them into an SVM classifier to obtain multiple recognition results; and fusing the multiple recognition results to obtain fused data. This method achieves a simple design, overcomes the curse of dimensionality and nonlinear separability problems when calculating large amounts of data, and significantly increases the target recognition rate.

The application relates to a CSP-CPSO-SVM electroencephalogram decoding algorithm and a brain-controlled lower-limb exoskeleton system, wherein the algorithm adopts a CSP algorithm to extract features of electroencephalogram signals to obtain an initial feature set; adopts a CPSO algorithm to intelligently search and filter and optimize the initial feature set, and obtains a feature subset which is strong in discrimination and low in redundancy; the feature subset is input into an SVM classifier for recognition, and an intention category label is output, the combination of CSP-CPSO-SVM has obvious advantages in improving feature discrimination and classification accuracy, and provides a reliable method for efficient recognition of motor imagery electroencephalogram signals. The system comprises a sensing unit, an intention transmission unit and an execution unit, the system integrates the CSP-CPSO-SVM electroencephalogram decoding algorithm, establishes a complete mapping link from intention recognition of electroencephalogram signals to motion control of a lower-limb exoskeleton, and realizes closed-loop control from intention recognition to trajectory following. The system can stably follow an expected trajectory according to a motion intention, and has good robustness.

The application relates to the field of motor fault identification, and discloses a permanent magnet synchronous motor fault identification method, which comprises a preset permanent magnet synchronous motor fault prediction model comprising a quantum heuristic neural network module, a double-flow convolutional neural network module and an SVM classifier connected in sequence. Through the quantum heuristic neural network mode, the weak features of early faults of the permanent magnet synchronous motor can be effectively mined, the feature expression capability is enhanced by unique rotation and entanglement operations of the quantum heuristic neural network, the feature extraction and fusion capability of the double-flow convolutional neural network module and the accurate classification capability of the SVM classifier are combined, the detection sensitivity of early weak faults is significantly improved, the fault degree of the permanent magnet synchronous motor is more accurately distinguished, and the fault type is effectively identified, so that reliable guarantee is provided for stable operation of the permanent magnet synchronous motor.