Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

31results about How to "Reduce redundant features" patented technology

Fused attention model-based Chinese text classification method

The invention discloses a fused attention model-based Chinese text classification method. The method comprises the following steps of: respectively segmenting a text into a corresponding word set anda corresponding character set through word segmentation preprocessing and character segmentation preprocessing, and training a word vector and a character vector corresponding to the text by adoptionof a feature embedding method according to the obtained word set and character set; respectively carrying out semantic encoding on the word vector and the character vector by taking a bidirectional gate circulation unit neural network as an encoder, and obtaining a word attention vector and a character attention vector in the text by adoption of a word vector attention mechanism and a character vector attention mechanism; obtaining a fused attention vector; and predicting a category of the text through a softmax classifier. The method is capable of solving the problem that more redundant features exist in the classification process as existing Chinese text classification methods neglects character feature information of texts, the extracted texts are single in features, all the pieces of semantic information of the texts are difficult to cover and features having obvious contribution to the classification are not focused.
Owner:中国科学院电子学研究所苏州研究院

Wireless sensor high-dimensional data real-time anomaly detection method based on deep learning

The invention discloses a wireless sensor high-dimensional data anomaly detection method based on deep learning. The method comprises the following steps: (101) obtaining historical data; (102) establishing a DBN-QSSVM hybrid model; (103) training the mixed model by using historical data of the sensor; (104) collecting test data of a sensor to be detected; (105) using a trained DBN-QSSVM hybrid model in (103) to perform abnormality detection on sensor test data; (106) outputting abnormal data in sensor test data and (106) outputting abnormal data in the sensor test data. Relevant algorithms and processes in the prior art are improved. The method for achieving online detection technology when the high-dimensional data is processed is provided, the space complexity and time complexity can begreatly reduced under the condition that the accuracy of the data exception detection method is not reduced, and therefore the method is more suitable for large-scale high-dimensional data exceptiondetection.
Owner:ANHUI AGRICULTURAL UNIVERSITY

Classification method based on kernel feature extraction early prediction multivariate time series category

The invention provides a classification method based on a kernel feature extraction early prediction multivariate time series category according to early prediction multivariate time series classification. To extract the essential features of variable time series, first the variable time series undergo feature extraction respectively, and a clustering method is adopted to reduce redundancy features, remove noise and improve classification stability; then, to improve classification efficiency, precision and early degree, a method for comprehensively evaluating feature performances is provided on the basis of accuracy rate, recall rate and the early degree and the like, and the optimal feature in each cluster is selected to serve as a kernel feature of a variable; and finally, two simple effective classifier construction methods are provided on the basis of a kernel feature set of each variable. Correctness and effectiveness of the method and an algorithm are proven through experiments, and experiment results prove that a classifier can have high accuracy rate and good early degree.
Owner:WUHAN UNIV

Space-time bone characteristic and depth belief network-based human body behavior identification method

The invention belongs to the field of computer vision and specifically relates to a space-time bone characteristic and depth belief network-based human body behavior identification method. According to the method, a bone sequence is obtained via a depth camera based on each motion; bone point time sequence characteristics are extracted from the bone sequence and comprise displacement characteristics, speed characteristics and acceleration characteristics of each bone point; a bone reference point is chosen, relative distance between each bone point and the bone reference point is calculated, space characteristics of a motion bone sequence is obtained, the bone point time sequence characteristics and the space characteristics of a motion bone sequence are subjected to clustering operation,a characteristic length is fixed, a global motion description operator is established and subjected to dimensionality reducing operation, and motion classification is finished based on cross validation and a classifier.
Owner:NORTHEAST DIANLI UNIVERSITY

Local sparse representation object tracking method based on LO regularization

The invention discloses a local sparse representation object tracking method based on LO regularization. Different from traditional L1 object tracking methods, the method herein proposes the combination between a LO norm and a structural local sparse appearance model, fully utilizes sparse coding, better differentiates objects from backgrounds in the course of tracking, and models local shielding and the like interferences by using a trivial template, and further increases the robustness of noise interference in the course of tracking. In order to enable an object model to better deal with continuous changes of the appearance of an object in the course of tracking, according to the invention, the method, through the construction of an object model set, adopts the LO norm in reconstructing the object in the course of tracking and adopts probabilistic policy in replacing a certain template in the object template set with a reconstructing result, thus realizing the update of template dynamics and further increasing the stability of the algorithm. According to the invention, the method which is directed at the NP problem of the object function optimization solution based on the LO norm, employs the APG algorithm in realizing effective solution.
Owner:JIANGNAN UNIV

Feature selection method and device

The invention provides a feature selection method and device. The method comprises the steps that M features are extracted from an acquired image; screening of the M features is performed by utilizing a filtering model algorithm so that N features are obtained; the N features are searched by utilizing a first packaging model algorithm so that a first feature subset is obtained, and the N features are searched by utilizing a second packaging model algorithm so that a second feature subset is obtained; and the first feature subset and the second feature subset are reorganized so that a third feature subset including K features is obtained, and the optimal feature subset of the image is selected from the first feature subset, the second feature subset and the third feature subset With application of the technical scheme, the most effective features can be selected from mass features so that the optimal feature subset can be obtained, computation complexity can be reduced, classification precision and classification performance of face recognition can be enhanced, face recognition capacity can be improved, face recognition rate can be enhanced and information security can be enhanced.
Owner:济南博观智能科技有限公司

Safety helmet real-time detection method in electric power scene

The invention provides a safety helmet real-time detection method in an electric power scene. The method comprises the following steps of: 1, acquiring an electric power monitoring video, and carryingout preprocessing and normalization of the electric power monitoring video; 2, inputting a video frame processed in step 1 into a PoseNet model to obtain skeleton information of a worker in the videoframe; 3, calculating the position of the safety helmet according to the skeleton information of the worker; 4, detecting the safety helmet wearing state of the worker by using a trained VGG16 model;5, judging whether the detection frame number reaches a set threshold value or not, if not, repeatedly executing the steps 1 to 4, and if yes, executing step 6; and 6, comprehensively analyzing the classification result of each frame by detecting a plurality of continuous video frames to obtain a safety helmet wearing detection result. According to the invention, the safety helmet wearing state of the worker can be precisely and quickly detected, and the method can adapt to various electric power working environments.
Owner:STATE GRID CORP OF CHINA +2

Text feature extraction method, device, equipment and readable storage medium

The invention discloses a text feature extraction method. The method comprises the steps of setting a target keyword collection corresponding to a target domain, obtaining an original article collection corresponding to the target keyword collection, pre-processing the articles in the original article collection, obtaining a target article collection, conducting word segmentation on each article in the target article collection to obtain a lexical collection, and calculating corresponding information gain value of each word in the lexical collection to determine a text feature collection. Themethod can obtain professional text features, facilitate the understanding and visualization of data, reduce the computing and storage capacity and the like. The invention further discloses a text feature extraction device, equipment and a readable storage medium, which have corresponding technical effects.
Owner:北京中关村科金技术有限公司

Indoor scene semantic segmentation method based on improved full convolutional neural network

The invention discloses an indoor scene semantic segmentation method based on an improved full convolutional neural network. The method comprises the steps of firstly constructing a convolutional neural network, wherein a hidden layer of the convolutional neural network comprises five neural network blocks, five feature re-extraction convolutional layer blocks, five partitioning attention convolutional blocks, twelve fusion layers and four up-sampling layers; inputting the original indoor scene image into a convolutional neural network for training to obtain a corresponding semantic segmentation prediction graph; calculating a loss function value between a set formed by semantic segmentation prediction images corresponding to original indoor scene images and a set formed by one-hot coded images processed by corresponding real semantic segmentation images to obtain an optimal weight vector and an offset term of a convolutional neural network classification training model; and inputtingan indoor scene image to be subjected to semantic segmentation into the trained convolutional neural network classification training model to obtain a predicted semantic segmentation image. The methodhas the advantage that the semantic segmentation efficiency and accuracy of the indoor scene image are improved.
Owner:ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Lower limb deep venous thrombosis thrombolysis curative effect prediction method and system based on sparse representation

The invention discloses a lower limb deep venous thrombosis thrombolysis curative effect prediction method and system based on sparse representation. The method comprises the steps: acquiring a regionof interest of lower limb deep venous thrombosis from a magnetic resonance imaging image; performing image omics feature extraction on the region of interest of the lower limb deep vein thrombosis toobtain global image omics features and sparse representation image omics features; screening out image omics features with significant differences from the global image omics features and the sparserepresentation image omics features by adopting a significance test method; and predicting the thrombolysis curative effect of the deep venous thrombosis of the lower limb by adopting a support vectormachine method according to the imaging omics characteristics with significant difference. According to the method, the thrombolysis curative effect is predicted by combining the global image omics characteristics extracted by a traditional image omics method and the sparse representation image omics characteristics extracted by a sparse representation image omics method, more effective characteristics can be covered, redundant characteristics are reduced by a significance test method, and the method can be widely applied to the field of medical image processing.
Owner:广州市番禺区中心医院 +1

Social network text sentiment analysis method based on deformable self-attention mechanism

The invention discloses a social network text sentiment analysis method based on a deformable self-attention mechanism, which is used for analyzing the sentiment of a user utterance. The method comprises the following steps: segmenting each sentence in user utterance text data into words, and expressing each word with a word vector; inputting the word vector sequence into a bidirectional recurrentneural network (Bi-LSTM) to obtain a coded representation of each word; utilizing a deformable self-attention mechanism to convert the coding representation of the words into a plurality of sentencecoding representations with different context ranges; fusing the plurality of sentence code representations to obtain a sentence code representation; inputting the fused sentence code representation into a feed-forward neural network (FFN) for classification, and outputting a result; according to a model output result and a data real result, iteratively training a model updating parameter by minimizing a cross entropy loss function; and inputting the social network text to be classified into the trained model to obtain an emotion analysis result.
Owner:SOUTH CHINA UNIV OF TECH

A cross-dataset facial expression recognition model construction and recognition method

ActiveCN109145749AStrengthen the role of important featuresReduce redundant featuresAcquiring/recognising facial featuresData setSelf adaptive
The invention discloses a method for constructing a cross-data set facial expression recognition model and a recognition method, wherein, the reconstruction error of a training expression image is constrained by an adaptive non-negative weighting matrix, the function of important features in image data representation is strengthened, and the useless features with significant reconstruction error are reduced. In addition, by projecting the training set into the appropriate subspace through the mapping matrix, the intrinsic similarity between the cross-data set image samples can be better revealed, so that the subspace based on the low-rank and sparse representation can learn the robust reconstructed image in order to realize the final cross-data set facial expression recognition.
Owner:CHANGAN UNIV

Escape vehicle rapid identification and tracking method based on vehicle-mounted unmanned aerial vehicle

ActiveCN112863186AOvercome the defect of poor real-time performanceShorten the time of tracking and predictionDetection of traffic movementNeural architecturesFeature extractionIn vehicle
The invention discloses an escape vehicle rapid identification and tracking method based on a vehicle-mounted unmanned aerial vehicle. The method specifically comprises the steps of (1) constructing a prediction model for the position of a road section where an escape vehicle is located, and taking the first three areas with the largest probability values as candidate areas; (2) scanning vehicles in the three candidate areas and uploading the vehicles to a cloud end through a 5G network; (3) establishing a lightweight escape vehicle re-identification model based on the improved DenseNet121, and performing vehicle feature extraction and re-identification on a picture of each candidate area based on the escape vehicle to be queried; and (4) transmitting the position information of the candidate area where the picture with the highest escape vehicle re-identification rate is located to an on-duty person, and completing tracking of the hit-and-run vehicle. The unmanned aerial vehicle can rapidly and reliably re-identify the escape vehicle, and the case solving efficiency is improved.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Filter characteristic selection method based on subclass problem classification ability measurement

The present invention discloses a Filter characteristic selection method based on subclass problem classification ability measurement. The main difference between the method and the most existing methods is that a single value is not used as a classification ability evaluation standard of characteristics, the classification ability of each subclass problem by the characteristics and weighted average values thereof are used for measurement, and the classification abilities of the subclass problems by the characteristics are specially valued. According to the method, the characteristic having a strong total classification ability can be ensured to be selected, the characteristic having a strong subclass problem classification ability and a not strong total classification ability can also be ensured to be selected, so that more accurate ordering evaluation on characteristic classification abilities is obtained, better characteristic subsets are also obtained, redundant characteristics are effectively reduced, and classification prediction accuracy is increased. The method can be used for classification prediction of cancer data sets, prediction accuracy is improved, cancer markers can be found, and therefore early diagnosis of cancers and development of targeted drugs for treating the cancers are promoted.
Owner:TIANJIN NORMAL UNIVERSITY

Traditional Chinese medicine image classification and retrieval method based on pyramid network

The invention designs a traditional Chinese medicine image classification and retrieval method based on a pyramid network, and is used for solving various problems that traditional neural network classification focuses on global semantic information such as contours and shapes, and a lot of information is lost due to multiple down-sampling operations. In order to achieve an ideal classification effect, multi-scale feature fusion is realized through a pyramid structure of a feature pyramid, and the requirement that shallow-layer and deep-layer spatial and semantic information needs to be fused in traditional Chinese medicine decoction piece image classification is met. Aiming at the problems that a multi-scale feature fusion mode can cause a large number of redundant features and neural network training can be interfered by redundant information, an SE-Net model is used, the redundant features are reduced, a sampling strategy and triple loss are combined, a multi-task learning framework is used for classifying and retrieving images at the same time, and more compact and accurate traditional Chinese medicine image feature information can be obtained.
Owner:NANJING UNIV OF TECH

Coding and decoding structure-based crowd counting and positioning method

The invention discloses a crowd counting and positioning method based on a coding and decoding structure, relates to the field of computer vision, and solves the problems that in the prior art, characteristics are not fully utilized, and a tag graph cannot well give consideration to counting and positioning tasks. A multi-scale feature fusion module is introduced into the deep layer of the network, a space-channel attention up-sampling module is introduced into a re-decoding part, and the multi-scale feature fusion module captures features of multiple scales by using cavity convolution with different expansion rates and performs feature fusion, so that the robustness of the network to deal with scale change is improved; the space-channel attention up-sampling module guides superficial layer features to perform high-efficiency fusion through high-level high-level semantics, so that interference of redundant features and picture backgrounds is reduced; secondly, a new label graph is provided, and the label graph has the advantage of simple counting of a density graph and also has the positioning performance of an FIDT graph.
Owner:SOUTHWEST JIAOTONG UNIV

Support vector machine electrical network intrusion detection system and method based on feature selection

The invention discloses a support vector machine electrical network intrusion detection system and method based on feature selection. The system comprises an intrusion information database, a data preprocessing module and a data analysis module, wherein the intrusion information database, the data preprocessing module and the data analysis module are connected through network equipment; the intrusion information database is used for storing intrusion information data packets; the data preprocessing module comprises a data filling module and a data normalization module; the data filling moduleand the data normalization module are in communication connection through a data bus; the data analysis module comprises a feature selection module and a support vector machine detection module; the feature selection module and the support vector machine detection module are in communication connection through a data bus. Missing value filling, normalization, feature selection and intrusion behavior detection are carried out on network data to achieve the purposes of high detection of the network data and more accurate judgment of the smart power grid.
Owner:CHINA SOUTHERN POWER GRID COMPANY

Classification method based on kernel feature extraction early prediction multivariate time series category

The invention provides a classification method based on a kernel feature extraction early prediction multivariate time series category according to early prediction multivariate time series classification. To extract the essential features of variable time series, first the variable time series undergo feature extraction respectively, and a clustering method is adopted to reduce redundancy features, remove noise and improve classification stability; then, to improve classification efficiency, precision and early degree, a method for comprehensively evaluating feature performances is provided on the basis of accuracy rate, recall rate and the early degree and the like, and the optimal feature in each cluster is selected to serve as a kernel feature of a variable; and finally, two simple effective classifier construction methods are provided on the basis of a kernel feature set of each variable. Correctness and effectiveness of the method and an algorithm are proven through experiments, and experiment results prove that a classifier can have high accuracy rate and good early degree.
Owner:WUHAN UNIV

Deep learning wafer welding spot detection method based on improved YOLOV5

The invention discloses a deep learning wafer welding spot detection method based on improved YOLOV5. The method comprises the following steps: 1) making a wafer welding spot data set; the method comprises the following steps of (1) constructing an attention mechanism module CCANET, (2) constructing a YOLOV5 network integrated with an attention mechanism, (4) introducing a Ghost module, and (5) training and improving the YOLOV5 network.According to the method, under the condition that fewer network parameters are used, the wafer welding spot detection precision is improved, and under the same condition, more wafer welding spots can be detected, and shielded wafer welding spots can also be detected.
Owner:GUANGXI NORMAL UNIV

A ddnn based on cloud-edge collaborative computing and its construction method and application

The invention discloses a DDNN based on cloud-edge collaborative computing and its construction method and application, which are applied to object classification under multi-view images of the Internet of Things. DDNN includes: an edge side, which adopts a feature bag model to extract multiple features The similarity of the image is measured and the histogram vector of each view is obtained statistically; the feature weighted fusion is performed on the histogram vector of each view, and the classification of the edge side target is obtained based on the fused histogram vector. If the classification accuracy is not enough, the extracted The feature images of each viewing angle are transmitted to the cloud; the cloud is used to carry out feature weighted fusion of all feature images, perform convolution and classification operations on the fused feature images, and obtain the target classification in the cloud. The present invention introduces a feature bag model on the edge side to reduce the amount of parameters; in addition, multi-view weighted feature fusion reduces multi-view redundant features and increases the effectiveness of feature expression capabilities. The invention reduces the amount of parameters of DDNN and the traffic of cloud-edge communication and improves the overall performance of DDNN.
Owner:HUAZHONG UNIV OF SCI & TECH

Parkinson's disease voice data classification system based on sample and feature double transformation

The invention relates to the technical field of voice classification, and particularly discloses a Parkinson's disease voice data classification system based on sample and feature double transformation, which comprises a sample input module, a sample transformation module, a data set division module, a feature transformation module, a model generation module and a voting module. The system is based on the characteristic that the number of existing PD voice samples is small, and transformation is particularly carried out on two dimensions of samples and features: for sample transformation, hierarchical structures of different PD voice samples are mined through an iterative mean value clustering method, and new samples are generated; for feature transformation, PD voice feature dimension transformation is carried out through different feature kernels. The sample transformation not only can reduce the influence of abnormal samples on the classifier boundary and the influence of the samples with high correlation on the training time and the storage space, but also can reflect the hierarchical structure information of the samples in the samples. Dimension reduction is carried out on PD voice samples through feature transformation, the complexity of a classification model is reduced, and high-performance classification is achieved.
Owner:CHONGQING UNIV

Iris recognition method based on KNN classification model

The invention relates to iris recognition, in particular to an iris recognition method based on a KNN classification model, and the method comprises the steps: determining the position of an iris, and carrying out the image preprocessing of an iris image; extracting a feature vector of the preprocessed iris image through a circular symmetry filter; carrying out dimension reduction processing on the extracted feature vectors; training a KNN classifier by using the feature vector after dimension reduction, and identifying the iris image to be identified by using the trained KNN classifier; according to the technical scheme provided by the invention, the defects that the recognition precision is difficult to guarantee and the recognition efficiency is relatively low in the prior art can be effectively overcome.
Owner:HEFEI INNOVATION RES INST BEIHANG UNIV

Optimal Feature Subset Selection Method Based on Structural Vector Complementary of Classification Ability

The present invention proposes a new optimal feature subset selection method based on the complementarity of classification capability structure vectors, aiming at the classification capability evaluation criteria in which single values ​​are used as features or feature subsets in most existing methods. This method defines the feature classification ability structure vector and the complementary features of the classification ability structure vector in binary form, and uses the dichotomy method to calculate the threshold of feature classification and discrimination ability in each subcategory problem, and on this basis, according to the different characteristics of the selected feature subset The principle of structural complementarity maximization and greedy strategy are used to select the optimal feature subset. This method not only fully considers the different evaluations of each feature on the classification ability of different categories, but also follows the principle of maximizing the structural complementarity of the classification ability in the process of feature selection. It not only conforms to the natural law of complementary advantages, but also maximizes the feature classification information, so as to obtain a better feature subset, effectively reduce redundant features, and improve the accuracy of classification prediction.
Owner:TIANJIN NORMAL UNIVERSITY

YOLOv5 marine fish target detection method based on attention mechanism and DropBlock

The invention discloses a YOLOv5 marine fish target detection method based on an attention mechanism and DropBlock. The YOLOv5 marine fish target detection method comprises the following steps: step 1, obtaining a target fish data set; step 2, labeling and dividing the obtained data set; step 3, constructing a YOLOv5 marine fish target detection model added with an attention mechanism and DropBlock; and 4, performing fish detection by adopting the constructed marine fish target detection model. The objective of the invention is to solve the problems that according to an existing fish detection method, due to the fact that the activity range of marine fishes is large and various living environments exist, the fishes shot underwater deform, clear fish targets cannot be captured, the fish detection accuracy is affected, and the fish detection efficiency is affected. And extraction of fish features by a single convolutional neural network is susceptible to interference of image noise, and fishes cannot be rapidly detected, so that the speed and precision of a target detection method are affected.
Owner:CHINA THREE GORGES UNIV

A Method of Intrusion Detection Based on Semi-Supervised Learning

The invention discloses an intrusion detection method based on semi-supervised learning. The implementation steps include: selecting a mixed sample set initially containing labeled samples and unlabeled samples to be tested, calculating the information gain of each feature value in the feature space and completing the process based on The feature selection of information entropy, and then screen the labeled samples based on the feature selection of information entropy, and use the new training data obtained by screening for the semi-supervised training of the classifier based on LapSVM, and use the trained classifier to be tested. The samples are classified, the best evaluation value of the detection index is determined according to the detection index, and the classification result corresponding to the evaluation value of the best detection index is output. The present invention adopts the method of feature selection to deal with the redundancy phenomenon that is easy to appear in the network environment data, and uses a small number of labeled samples and a large amount of unlabeled data to create a semi-supervised learning model, while reducing the false alarm rate and improving the detection rate, It can reduce data redundancy and improve detection efficiency.
Owner:CHANGSHA UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products