Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

22results about How to "Increase feature dimension" patented technology

Lower limb movement gait recognition method and system based on feature fusion

The invention discloses a lower limb movement gait recognition method and system based on feature fusion, and belongs to the technical field of gait recognition. Comprising the following steps: acquiring a surface electromyogram signal and a motion inertia signal of a to-be-predicted object; carrying out feature extraction on the surface electromyogram signal and the motion inertia signal by utilizing wavelet transform, obtaining gait features and screening an optimal feature combination; and processing the optimal feature combination through the trained gait recognition model to obtain a gait recognition result. Complex multi-modal data can be effectively processed and analyzed, so that high-precision gait recognition and evaluation are realized; the problem that the accuracy of gait evaluation needs to be improved due to the fact that single signal processing is difficult to comprehensively reflect a complex gait dynamic process in the prior art is solved.
Owner:SHANDONG UNIV

Target identification method based on sonar image segmentation and computing device

The invention belongs to the technical field of sonar image processing, and relates to a target identification method based on sonar image segmentation and a computing device.The target identification method based on sonar image segmentation comprises the following steps that 1) a data set of existing sonar images is acquired; 2) building a target identification model composed of an encoder and a decoder; 3) inputting the data set into the target recognition model from the encoder, and performing initial training on the target recognition model; 4) performing sample augmentation on categories with a small number of samples in the data set to obtain an augmented feature domain data set; 5) using the augmented feature domain data set to carry out fine tuning training on the target identification model; and 6) after the target identification model is finely adjusted and trained, inputting a newly obtained sonar image into the target identification model to obtain a segmentation image of the target. The method can achieve the accurate recognition of a target.
Owner:BAOLI TIANTONG INSTR CORP +1

Traffic small target detection method, device and equipment for high-speed driving vehicle and medium

The invention relates to a traffic small target detection method and device for a high-speed driving vehicle, equipment and a medium, and relates to the field of image processing, and the method comprises the steps: inputting a traffic scene image frame into a second traffic small target detection model which is trained to a convergence state, and carrying out the detection of a traffic scene image frame in a plurality of multi-layer stacked recursive Star Block modules of a StarNet lightweight network, performing element-by-element multiplication on image features corresponding to the traffic scene image frames by adopting star operation to exponentially increase implicit feature dimensions in the traffic scene image frames so as to determine high-dimensional image features of the traffic scene image frames; and inputting the high-dimensional image features into a detection head network in a traffic small target detection model to obtain a plurality of traffic small targets in the traffic scene image frame so as to complete traffic small target detection of the high-speed driving vehicle. According to the method, the small traffic target can be accurately and quickly detected in a traffic scene in high-speed driving, and higher target detection performance can be realized in a resource-limited environment such as high-speed driving vehicles.
Owner:SOUTH CHINA UNIV OF TECH

Day-ahead time-sharing electric quantity prediction method and device based on feature fusion and medium

The invention discloses a day-ahead time-sharing electric quantity prediction method and device based on feature fusion and a medium, and relates to the technical field of electric quantity prediction, and the method comprises the steps: constructing a three-dimensional electric quantity matrix based on historical electric quantity data; screening the characteristic variables influencing the electric quantity prediction based on a machine learning and evidence optimization combination algorithm to obtain a dominant characteristic set; performing dimension reduction on the three-dimensional electric quantity matrix according to the dominant feature set to obtain a time-sharing electric quantity three-dimensional matrix; constructing a time-sharing electric quantity prediction model based on the pyramid ConvLSTM; and a time-sharing electric quantity prediction model based on pyramid ConvLSTM is adopted to predict a time-sharing electric quantity value of the next day according to the time-sharing electric quantity three-dimensional matrix. According to the feature fusion-based day-ahead time-sharing electric quantity prediction method and device and the medium provided by the invention, accurate prediction of day-ahead time-sharing electric quantity consumption can be realized.
Owner:NORTH CHINA ELECTRIC POWER UNIV +1

Optimized SVM-based analog circuit fault diagnosis method and system, and storage medium

The invention discloses an analog circuit fault diagnosis method and system for optimizing an SVM (Support Vector Machine) and a storage medium. An SVM algorithm is optimized by adopting a fused particle swarm algorithm and an improved grey wolf algorithm. Comprising the following steps: extracting time domain features and wavelet packet features of various fault sample signals of an analog circuit, and fusing the two features as a final fault feature sample set; dividing the fault feature sample set into a training set and a test set according to a certain proportion; optimizing a kernel function and a penalty factor of the SVM by using a fusion particle swarm algorithm and an improved grey wolf algorithm, and constructing a PSO-IGWO-SVM model; and training and testing the PSO-IGWO-SVM model by using the test set, and outputting a fault diagnosis result of the analog circuit. By combining the advantages of the two algorithms, the classification effect and diagnosis precision of the SVM are improved. Meanwhile, by introducing a nonlinear convergence factor and a proportional weight dynamic adjustment strategy, the search efficiency and convergence speed of the algorithm are further improved.
Owner:HEBEI CREATE INSTR TECH CO LTD

Image information extraction method and device, computer equipment and storage medium

The embodiment of the invention provides an image information extraction method and device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence and the field of digital medical treatment. The method comprises the following steps: segmenting an original image into a plurality of sub-images, and determining a target image feature corresponding to each sub-image; determining a description text corresponding to the original image, and determining a target text feature corresponding to the description text; splicing the target text feature with each target image feature to obtain a target image-text feature corresponding to each sub-image; inputting the target image-text features and the target image features into a trained decoding model, and outputting a target sub-image related to the description text; and extracting an entity corresponding to the description text according to the target sub-image, wherein the trained decoding model is obtained based on corresponding loss training between the prediction sub-sample image and the label sub-image. According to the embodiment of the invention, the accuracy of extracting the entity in the image can be improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Skin state classification system based on multi-modal feature fusion

The embodiment of the invention discloses a skin state classification system based on multi-modal feature fusion. A specific implementation mode of the system comprises a patient state text information input device, a skin image acquisition device, a main control chip and a classification result display, wherein the patient state text information input device inputs a patient state structured text information sequence and a patient state unstructured text information sequence; the skin image acquisition device acquires a skin lesion image of a patient; the main control chip is configured to obtain an initial first state text feature vector and an initial second state text feature vector sequence; performing image feature extraction processing on the skin lesion image of the patient to obtain an initial skin lesion region feature vector; inputting the initial first state text feature vector, the initial second state text feature vector sequence and the initial skin lesion region feature vector into a skin state classification model; and the classification result display displays the skin state classification result. According to the embodiment, the classification accuracy of the skin state can be improved.
Owner:AIR FORCE MEDICAL CENT PLA

Data enhancement model-based transformer fault diagnosis method and related equipment

The invention discloses a transformer fault diagnosis method based on a data enhancement model and related equipment, and the method achieves the training process optimization of a CTGAN through introducing a CRS module under the condition of considering different data types of a data column, achieves the high-quality generation of DGA table data, and improves the efficiency. Evaluating the quality of the generated data by using a KS index and a CNN model; dGA data features are amplified and screened based on full-type gas ratios and a random forest algorithm, and large-scale abundant and effective screening of gas ratio features is achieved under the original background that only part of empirical features are selected. The effectiveness of the data dimension amplification method is verified by using a CNN model subsequently, and the feature expressive power is improved while feature dimension amplification is realized; through the data processing operation, the problems of poor data generation quality and low transformer fault diagnosis precision in the prior art are solved.
Owner:XIAN HIGH VOLTAGE APP RES INST CO LTD

A texture segmentation and enhancement method and system for seismic profile images

The present invention relates to a texture segmentation and enhancement method and system for a seismic profile image, and relates to the technical field of image processing, wherein the method comprises: preprocessing the seismic profile image to obtain the preprocessed seismic profile image; performing a first texture segmentation on the preprocessed seismic profile image through a plurality of texture segmentation algorithms to obtain a plurality of first texture segmentation results; performing a second texture segmentation on the preprocessed seismic profile image based on the plurality of first texture segmentation results through a texture segmentation model to obtain a second texture segmentation result; obtaining a plurality of segmentation sub-images based on the second texture segmentation results; for each segmentation sub-image, determining a texture enhancement model corresponding to the segmentation sub-image based on the texture features of the segmentation sub-image, and performing texture enhancement on the segmentation sub-image through the texture enhancement model corresponding to the segmentation sub-image, which has the advantage of improving the clarity and recognizability of texture information in the seismic profile image.
Owner:XI'AN PETROLEUM UNIVERSITY

A personality analysis method, device and medium based on multi-feature electroencephalogram signals

The present invention discloses a personality analysis method, device and medium based on multi-feature electroencephalogram (EEG) signals, and relates to the technical field of electroencephalogram (EEG) signal processing. The method comprises: obtaining the original electroencephalogram (EEG) signals of a target subject; preprocessing the original electroencephalogram (EEG) signals to remove power frequency interference and artifacts to obtain preprocessed electroencephalogram (EEG) signals; extracting features from the preprocessed electroencephalogram (EEG) signals to obtain EEG features of different frequency bands, and using a multi-layer perceptron to fuse the EEG features of different frequency bands to obtain multi-dimensional EEG features; using a sparsity criterion linear discriminant analysis with L1 regularization to reduce the dimension of the multi-dimensional EEG features to obtain the EEG features after the dimension reduction; using a deep learning model to learn deeper temporal features and spatial features from the EEG features after the dimension reduction and classify them to determine the personality category of the target subject; the deep learning model is a model in which multiple sub-deep network models are fused. The present invention improves the accuracy and efficiency of personality recognition.
Owner:NANCHANG HANGKONG UNIVERSITY

Demand prediction method based on machine learning

The invention discloses a demand prediction method based on machine learning, and relates to the technical field of data-driven decision making of machine learning, and the method comprises the specific steps: extracting product attribute features and prediction features; constructing a product cluster according to the product attribute features; performing preliminary screening on the prediction features to obtain a product important feature set; performing secondary screening according to the product important feature set in combination with the product cluster to form a secondary screening feature set; and inputting the secondary screening feature set into a machine learning model for demand prediction. According to the method, the products are classified into different product clusters, and secondary feature selection is carried out by means of feature information of other products in the same category, so that the problem of feature screening failure can be effectively solved on the basis of avoiding learning model failure, the feature dimension is reduced, the demand prediction effect of high feature dimension and small sample size is improved, and the prediction efficiency is improved. And the prediction error cost is reduced.
Owner:ZHEJIANG UNIV +1

A bearings-only target motion analysis method and system for surface trajectory planning

ActiveCN114692678BNon-linear mapping is reliableIt is not easy to reduce the accuracy of the solution and even divergeNeural architecturesNeural learning methodsState predictionTarget Motion Analysis
The present invention discloses a pure bearing target motion analysis method and system for surface track planning; wherein the analysis method comprises: a preprocessing step, a target predicted position acquisition step, and a target predicted position correction value acquisition step; the present invention uses a target position prediction model based on a time convolutional network to obtain a target predicted position, and compared with a traditional positioning method, the target position prediction model has a higher prediction accuracy; the present invention uses a set empirical mode decomposition method to decompose an initial signal, and uses a target position prediction model to obtain a target predicted position, thereby not prone to problems of reduced solution accuracy or even divergence; the present invention constructs a motion state equation of a target, and on this basis uses a recursive least squares method to correct the target predicted position output by the target position prediction model, so that all observation information in the observation process is utilized, and the accuracy and stability of the target motion state prediction are further improved.
Owner:NO 719 RES INST CHINA SHIPBUILDING IND +1

A sea surface small target detection method based on multi-domain multi-dimensional feature combination

The application discloses a sea surface small target detection method based on multi-domain multi-dimensional feature combination, and adaptively extracts deep features of sea clutter and target echo signals by using a stack sparse auto-encoder, so that the feature dimension is improved to ensure the feature feasibility. Since the feature extraction is a complete adaptive process, the complexity of the model is reduced. Meanwhile, aiming at the problem that the feature distinction degree of the sea clutter and target echo data in a single domain is low, a time-frequency domain feature combination method is provided to improve the feature difference and ensure the stable and efficient detection performance of the detector. Through an adaptive genetic algorithm, the convergence process of the super parameter group optimization is accelerated, and the local optimization of the super parameter is prevented to a certain extent, so that the final detection probability is effectively improved. The experimental results show that the detector provided by the application has better detection effect on high sea state data, the detection probability is improved by 27.6%, and the sea surface small target detection under high sea state can be coped with.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Small traffic target detection method, device, equipment and medium for high-speed vehicles

The present application relates to a method, device, equipment and medium for detecting small traffic targets of high-speed vehicles, which relates to the field of image processing. The method includes: inputting a traffic scene image frame into a second small traffic target detection model that has been trained to a convergence state, and in a plurality of Star Block modules of a multi-layer stacked recursion of a StarNet lightweight network, using a star operation to perform element-by-element multiplication of image features corresponding to the traffic scene image frame to exponentially increase the implicit feature dimension in the traffic scene image frame to determine the high-dimensional image features of the traffic scene image frame; inputting the high-dimensional image features into a detection head network in a small traffic target detection model to obtain a plurality of small traffic targets in the traffic scene image frame to complete the small traffic target detection of high-speed vehicles. The present application can accurately and quickly detect small traffic targets in a high-speed traffic scene, and can achieve higher target detection performance in a resource-constrained environment such as a high-speed vehicle.
Owner:SOUTH CHINA UNIV OF TECH

A geomagnetic road positioning method, system and storage medium combining coarse and fine matching

The present invention provides a geomagnetic road positioning method, system and storage medium combining coarse and fine matching, which relates to the field of intelligent driving, and is to solve the problem that the existing method has a large amount of calculation, and the characteristic dimension of geomagnetic data is small, which makes the algorithm susceptible to measurement noise. It includes: step one, obtaining the geomagnetic scalar, three-axis geomagnetic vector, and three-axis attitude angle information of the vehicle along the path, and establishing a spatial sequence geomagnetic reference library; step two, sampling the reference library, obtaining a training set pair to train a pre-built random forest classifier, and obtain a coarse matching model; step three, obtaining a training set pair to train a pre-built multi-scale twin neural network, and obtain a fine matching model; step four, obtaining the spatial sequence of geomagnetic intensity and attitude angle when the vehicle is driving; step five, using the coarse matching model to determine the road where the current vehicle is located, and using the fine matching model to determine the position of the current vehicle in the road; step six, repeating steps four to five until the positioning is completed.
Owner:HARBIN INST OF TECH AT WEIHAI

Model training method, control device and computer-readable storage medium

This invention relates to the field of deep learning technology, specifically providing a model training method, control device, and computer-readable storage medium, aiming to solve the problem of ensuring model evaluation performance while ensuring rapid model transfer. To this end, the invention obtains a trained first linear model, and creates a second linear model based on the first linear model, wherein the feature dimension of the second linear model is greater than that of the first linear model. Features are padded on a first dataset used to train the first linear model, and the padded first and second datasets are used to train the second linear model, resulting in a trained second linear model. This allows for rapid transfer based on the first linear model, and the second linear model, by using a dataset with more feature fields, achieves higher performance with higher feature dimensions.
Owner:北京宏瓴科技发展有限公司

An image-based proppant transport condition prediction method and system

ActiveCN122157162BRealize organic integrationRealize synergy
The application provides a proppant migration state prediction method and system based on images, and relates to the technical field of oil and gas development.The method comprises the following steps: processing and predicting a real-time image sequence currently collected by using a prediction neural network model to obtain current placement form prediction data of the proppant in a complex fracture; obtaining a regulation instruction based on the current placement form prediction data, and sending the regulation instruction to a field fracturing construction control unit to close-loop control the proppant migration process.The application realizes accurate prediction and closed-loop control of the proppant migration state through downhole image collection, preprocessing, segmentation correction, multi-source data fusion modeling and real-time prediction and regulation.
Owner:HENAN TIANXIANG NEW MATERIALS +1

Method for dynamic filtering of liquid medicine extraction timing signal and concentration prediction

PendingCN122508053ABalanced level of inhibitionWeaken superimposed interference
This invention discloses a method for dynamic filtering and concentration prediction of drug extraction time-series signals, belonging to the field of drug signal detection technology. The method includes acquiring an original time-series signal sequence containing subsequences of pressure fluctuations, temperature drift, and conductivity changes. Dynamic noise features are extracted to separate the periodic vibration noise component of the equipment from the random noise component of fluid turbulence. An adaptive filtering kernel function is constructed and convolutionally processed to obtain the initial filtered signal. Baseline drift is corrected using a weighted baseline estimate based on the temperature drift subsequence, resulting in a dynamically corrected signal sequence. Signal feature inflection points are detected and marked, and single extraction cycle segments are segmented. Peak amplitude sequences and inter-peak time interval sequences are extracted and input into a pre-trained model to output predicted drug concentration values. This method can adaptively adapt to complex noise environments, correct signal baseline shifts, accurately divide extraction cycles, effectively mine time-series signal features, and optimize drug concentration prediction performance.
Owner:WEIFANG GERUN PHARM CO LTD

Audio emotion recognition method and device, equipment and medium

The invention belongs to the field of artificial intelligence, and relates to an audio emotion recognition method, which comprises the following steps: acquiring original audio data of a target object; preprocessing the original audio data to obtain preprocessed audio data; performing feature extraction on the audio data by adopting a pre-trained self-supervised model to obtain audio feature information of the audio data; performing dimension reduction processing on the audio feature information to obtain an emotion feature vector of the audio data; based on the emotion feature vector, performing emotion classification on the audio data by adopting a preset emotion classification model to obtain an emotion classification result; and determining an emotion type represented by the audio data according to an emotion classification result. The invention further provides a device, equipment and a medium. In addition, the invention also relates to a block chain technology, and the original audio data can be stored in a block chain. The accuracy of audio emotion recognition can be improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Radar signal processing system based on complex field pulse neural network

The invention provides a radar signal processing system based on a complex field spiking neural network. The system is a complex field spiking neural network composed of a plurality of layer units. And the structure of each layer unit is that a layer of LIF neurons is superposed on the complex field spiking neural network layer. The complex number field spiking neural network layer is constructed based on a spiking neural network, input signals of the complex number field spiking neural network layer and weights of the spiking neural network are both in a complex number form, and the multiplication calculation of the input signals and the weights of the complex numbers during the forward propagation calculation of the spiking neural network is converted into the following steps: splitting real parts and imaginary parts of the input signals; and respectively multiplying by the real part and the imaginary part of the complex weight, then forming a new real part and a new imaginary part through addition and subtraction operation, and synthesizing the new real part and the new imaginary part into complex output. The method can improve the feature recognition precision of the complex field radar signals.
Owner:PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV

Multispectral image segmentation method, device, electronic device and storage medium

ActiveCN113327256BIncrease feature dimensionImproving Image Segmentation AccuracyImage enhancementImage analysisImage segmentationMultispectral image
The present application provides a multispectral image segmentation method, device, electronic device, and computer-readable storage medium; the method comprises: performing image segmentation on the multispectral image to be processed through a first segmentation submodel included in an image segmentation model to obtain a corresponding first segmentation feature image; based on the multispectral image and the first segmentation feature image, performing feature expansion on the multispectral image through a first feature extension submodel included in the image segmentation model to obtain a corresponding feature extension image; performing image segmentation on the feature extension image through a second segmentation submodel included in the image segmentation model to obtain a first target segmentation image corresponding to the multispectral image. Through the present application, the segmentation accuracy of the multispectral image can be improved.
Owner:WEBANK (CHINA)

Complete time sequence feature extraction method for environmental sound recognition

The invention discloses a complete time sequence feature extraction method for environmental sound recognition, and belongs to the technical field of time sequence feature extraction for environmental sound signal recognition. According to the invention, the problem that the time sequence information contained in the time sequence representation obtained by the existing method is limited is solved. According to the method, the complete semantic representation subspace which is higher in feature dimension and does not have redundant information can be obtained, information contained in the obtained complete semantic representation subspace is effective for completely depicting event time sequence information, and due to the fact that time sequence information between audio segments is introduced in the learning process, the time sequence information can be effectively depicted. The complete semantic representation subspace contains sufficient time sequence information, so that the performance of environment sound recognition is improved, and the recognition efficiency is greatly improved. In addition, the model structure of the method is simple, and the requirement for software and hardware resources is low. The method can be used for complete time sequence feature extraction of environmental sound signals.
Owner:CHONGQING JIAOTONG UNIV