57results about How to "Improve classification recognition rate" patented technology

The invention discloses an indoor human body behavior recognition method. The method comprises the following steps that: human body three-dimensional skeleton information is obtained based on Kinect equipment; three-dimensional skeleton features in each video set are extracted; the three-dimensional skeleton features are trained, and the features are described, and the training of the three-dimensional skeleton features further includes the following steps that: online dictionary learning is performed on the features, and then, sparse principal component analysis is performed on the features, and finally, a multi-task large margin nearest neighbor algorithm and a linear support vector machine are utilized to classify the features, so that a training feature set can be obtained; three-dimensional skeleton features of test videos are extracted; and the multi-task large margin nearest neighbor algorithm and the linear support vector machine are utilized to classify the features, so that feature descriptions can be obtained, and optimum judgment is performed on the training feature set and the test features with a scoring mechanism. The indoor human body behavior recognition method of the invention has a bright application prospect in intelligent video surveillance, patient monitoring systems, human-computer interaction, virtual reality, smart home, intelligent security and prevention and athlete assistant training, and has high feasibility and great social economic benefits.

The invention discloses a gesture recognition method based on an electromyographic topographic map. The method comprises the steps of (1) data collection, wherein upper arm muscle surface electromyographic signals of different gestures are collected through array surface electromyographic electrodes; (2) data preprocessing, wherein the collected surface electromyographic signals are preprocessed; (3) generation of the electromyographic topographic map; and (4) deep convolutional neural network model training and gesture recognition for generation of a feature image of the electromyographic topographic map, wherein the electromyographic topographic map is converted into a 64*64 grayscale image first, and then ZCA whitening preprocessing is used to generate the feature image; a corresponding convolutional neural network model structure is designed according to characteristics of the electromyographic topographic map, and a model is constructed; and test set data is input into a trained network model for gesture recognition classification. Through the method, the same gesture can be made to different subjects to generate similar electromyographic topographic maps, and therefore the problem of individual difference of surface electromyographic signals is effectively solved.

The invention claims a feature recognition method of motor imaginary electroencephalogram signal based on CBLSTM algorithm model. The algorithm model comprises the following steps S1: collecting EEG signals; S2, preprocessing the original EEG signal; S3, extracting frequency domain characteristics of EEG signals by using convolution neural network; S4, extracting time domain features of EEG signals by using a two-way long-short-term network; 5, classify that EEG signals by the softmax regression method; S6: Output the final EEG signal classification result. The invention effectively improves the recognition rate of a plurality of EEG signals.

The invention relates to an electroencephalogram feature classification method based on a PSO-SVM (Particle Swarm Optimization-Support Vector Machine). The electroencephalogram feature classification method comprises the following steps: firstly, utilizing a regularizable CSP (R-CSP) (Cryptographic Service Provider) algorithm to carry out electroencephalogram feature extraction; secondly, utilizing the particle swarm optimization to optimize the penalty factor C and the nuclear parameter g of the support vector machine; and finally, training a SVM classifier by an obtained optimal parameter, and utilizing the trained classifier to carry out classification prediction on a sample. Compared with traditional SVM classification identification, a result indicates that the classification identification algorithm based on the PSO-SVM can effectively improve the classification identification rate of the electroencephalogram. Compared with the traditional classification identification method, the electroencephalogram feature classification method has obvious advantages.

The invention provides an N400 evoked potential lie detection method based on an improved extreme learning machine; random parameters of the extreme learning machine are optimized on the basis of an artificial immune algorithm, and the electroencephalogram lie detection method based on an N400 evoked potential and the improved extreme learning machine is proposed; by virtue of the improved extreme learning machine, classification recognition rates of crime group subjects and control group subjects to detection stimulation and unassociated stimulation are calculated, and the classification recognition rates of the two groups of subjects are calculated and analyzed, so that a threshold parameter for distinguishing whether a subject lies or not is found out; and detection stimulation and unassociated stimulation time domain and frequency domain characteristics of 40 channel N400 induced electroencephalogram signals are extracted, so that the extracted electroencephalogram signal characteristics are more comprehensive; therefore, shortcomings in the prior art which conducts lie detection and judgment on the basis of a few of channels and by taking induced potential waveform geometric properties as characteristic parameter are overcome; and the lie detection method disclosed by the invention has the advantage that a stable lie identification right rate is effectively guaranteed.

The invention relates to a small sample SAR image ship classification method based on transfer learning, and belongs to the technical field of computer vision. The method comprises the following stepsof 1) preprocessing the SAR image ship slices so as to enable the ship slices to meet the requirements of the transfer learning for the input pictures, performing image enhancement on the ship slices, and synthesizing the similar ship slice images through a DCGAN network so as to meet the requirements of a CNN classification network for the data quantity; 2) extracting the image features of the images through a denoising auto-encoder, reducing the noise added when the DCGAN generates the images, and reducing the influence of different sea condition backgrounds on the classification results; and 3) carrying out transfer learning by adopting a ResNet network, and further improving the classification accuracy by adopting a fine-tune method. The small-sample SAR image ship classification method ensures that the small-sample SAR image ship classification can reach a certain accuracy.

The invention discloses a sequence deeply convinced network-based pedestrian identifying method. The method comprises the following steps of preprocessing a training image in a pedestrian database to obtain a training sample image, extracting an HOG (Histograms of Oriented Gradients) feature from the obtained training sample image, building and training a sequence restricted Boltzmann machine-based sequence deeply convinced network, using the sequence deeply convinced network to further extract features from the obtained HOG feature to form a feature vector of the training sample, inputting the obtained feature data into a support vector machine classifier, and finishing training; preprocessing a to-be-tested pedestrian image to obtain a test sample; using an HOG and the sequence deeply convinced network to extract pedestrian features from the test sample to form a feature vector of the test sample; inputting the feature vector of the test sample into the support vector machine classifier, and identifying whether the test image is a pedestrian or not. According to the method, better classification performance can be obtained, the accuracy of pedestrian identification is improved, and the robustness of a pedestrian identifying algorithm is enhanced.

The invention discloses a small sample radio signal enhancement identification method based on ACGAN. The method comprises the following steps of 1) a data preprocessing stage of converting a sample format, dividing a data set, and carrying out onehot coding on the category of the data to obtain a corresponding category label sequence; and 2) based on a signal enhancement method of a generative adversarial network, adjusting a radio signal sample to a set size, performing pixel normalization on the radio signal sample, setting the initial parameters of each network layer of the deep convolutional network, inputting the training data divided in the step 1) into the deep convolutional network, and training the network; and 3) extracting the features of the training data by using an LSTM network to construct a signal identification classifier, and classifying the test data and the verification data by using the classifier.

The invention discloses a data discretization method based on category-attribute relation dependency, belonging to the field of data mining. The method is characterized by comprising: first, based on CAIM algorithm, comprehensively considering about the influence of attribute importance and inconsistent rate of a decision table for discretization result, and providing an improved CAIM algorithm; and second, adopting a lambda correlation coefficient as discretization discriminant for evaluating category-attribute relation, and providing a new monitor discretization algorithm which does not need artificial input parameters and can automatically select discretization points. The method has the advantages that the method can maintain the high efficiency of extracting information for an original data set, balances the consideration of accuracy, and can obtain higher accuracy when in machine learning.

The invention discloses an image classification method based on combination of SRC and MFA, which is mainly used for solving the problem that the image classification result is not ideal because only the reconstruction relationship or local discriminant structure is considered and the sample information cannot be accurately described in the conventional feature extraction method. The method comprises the following steps: 1. inputting a training sample and a test sample, constructing the same kind and different kinds of sample matrixes, and initializing a projection matrix; 2. projecting the training sample, respectively taking the same kind and different kinds of samples as dictionaries, solving sparse representation coefficients of the samples, and constructing the same kind and different kinds of sparse weight matrixes; 3. constructing an objective function to solve a novel projection matrix; 4. iterating the steps 2 and 3 until the cycle index is larger than the set initial value, outputting the final projection matrix, and projecting the test samples; and 5. classifying the test samples by utilizing a sparse representation classifier. According to the method disclosed by the invention, the accuracy of image classification is enhanced, and the method can be used for discriminating identity of characters or searching objects during image shooting in a police work system.

The invention discloses a ground target classification method based on a random forest and data rejection, which comprises the following steps: (1) preprocessing a training sample set; (2) extractinga training feature matrix; (3) training a random forest classifier; (4) preprocessing the test sample; (5) extracting test feature vector; (6) calculating the output probability vector of the ground target; (7), judging whether that t sample is rejected or not; (8) if the judgment is rejected, taking the test sample as the echo signal without the fretting characteristic of the target; (9) if the judgment is not rejected, outputting the corresponding class of the maximum value in the probability vector as the ground target classification result of the test sample. The method rejects the judgment of clutter, deceptive interference and non-fretting target signal, improves the classification and recognition rate of ground moving target, and adopts a classifier with parallel processing abilityto improve the real-time performance of the method.

The invention provides a zero sample image classification method based on a relative attribute random forest. An attribute ranking score model is built for an image with an unknown class according to the relative relationship between image classes and image attributes, the attribute ranking score models for all images serve as training samples to train a random forest classifier, and finally, according to an attribute ranking score for a tested image and the random forest classifier obtained through training, the label of the tested image is predicted. The method of the invention can realize zero sample image classification and has the advantages of high classification recognition rate, strong model stability and the like.

The invention discloses an image characteristics extracting method based on combination of SRC-DP and LDA. The image characteristics extracting method mainly solves the problems that an existing characteristics extracting method only takes reconstitution relation or distinguish relation into consideration, cannot accurately describe sample information and is not ideal in image classifying results. The image characteristics extracting method comprises the step 1 of inputting training sample, calculating out an intra-class dispersion matrix and a between-class dispersion matrix of the sample and initializing a projection matrix, the step 2 of projecting the training sample and sequentially solving sparse representation coefficients of the projection matrix, the step 3 of respectively calculating out an intra-class reconstitution dispersion matrix and a between-class reconstitution dispersion matrix of projection sample, the step 4 of constructing a target function and solving a new projection matrix, and the step 5 of carrying out iteration on the step 2 to the step 4 until the cycle index is larger than a given initial value and outputting a final projection matrix. The image characteristics extracting method enhances image classifying accuracy, improves the classification recognizing rate and can be applied to distinguishing character identities in a police system or searching articles in image shooting.

The invention relates to the technical field of data processing, and provides a method and device for obtaining micro-motion characteristics. The method for obtaining the micro-motion characteristicscomprises the steps that radar echo signals of a warhead target are acquired; the time-frequency analysis of the radar echo signals is carried out to obtain a signal energy distribution function; according to the signal energy distribution function and the radar echo signals, at least one micro-motion characteristic of the warhead target is extracted; and a SVM classifier is used for filtering theextracted micro-motion characteristics, and an optimal feature subset including at least one of the micro-motion characteristics is obtained. The device for obtaining the micro-motion characteristicsincludes an acquisition unit, a time-frequency analysis unit, a characteristic extraction unit and a characteristic filtering unit. According to the method and device for obtaining the micro-motion characteristics, the micro-motion characteristics can be obtained from the radar echo signals.

The invention discloses a motor imagery electrocorticogram (EEG) signal classification method based on independent component analysis, which comprises the following steps: S1, collecting the EEG signals and preprocessing the EEG signals, and randomly dividing the preprocessed EEG signals into a training set and a test set; S2, sequentially selecting the training set data to carry out independent component analysis and calculation on the single test sample data, and automatically identifying and acquiring the motion related component based on the spatial distribution pattern of the source; S3:classification and recognition of motor imagery based on zero training classifier; S4: optimizing the selection of leads by using the training set data, substituting the optimized leads into the testset, and looping the steps S2 and S3 to obtain the final classification recognition rate. The invention can reduce the spatial model matching problem caused by the difference between the collected EEGdata, and has high recognition accuracy to the motor imagery EEG signals.

The invention discloses a hyperspectral data dimensionality reduction method based on ultra-pixel and maximum boundary distribution, which overcomes a defect of high inter-band correlation for lack of enough spatial and spectral domain information in the prior art. The hyperspectral data dimensionality reduction method comprises the steps of (1) dividing a sample set; (2) generating a regular matrix; (3) generating a judgment matrix; (4) solving an optimal projection matrix; and (5) carrying out projection dimensionality reduction. The hyperspectral data dimensionality reduction method has the advantages of abilities of maintaining the consistency in space and spectrum of neighboring samples and reducing redundant bands, and can be applied to dimensionality reduction of hyperspectral remote sensing images.

The invention discloses an observation vector difference based method for classifying SAR image textures. The method mainly solves the problem of terrain classification of SAR images. The method comprises the steps of (1) randomly selecting r images from a training set for partitioning processing, converting to obtain a column vector difference matrix P; (2) observing the P with an observation matrix to obtain a texture observation vector difference matrix X, and conducting clustering on the X to obtain a texture dictionary D; (3) calculating images of the training set according to Step (2) to obtain an observation vector difference matrix Xtr; (4) projecting the Xtr onto the texture dictionary D to form a training image texture column diagram h; (5) representing images of a test set by a test image texture column diagram he; (6) calculating the distance between the he and the h, and determining the classification to which the he belongs according to the distance; and (7) calculating all test images according to Step (6) to obtain a final classification rate. According to the method, the latest compressed sensing theory is applied, the process is simple, the classification identification rate is high, and the method is applicable to terrain texture classification of SAR images.

The invention discloses a horror video identification method based on discriminant instance selection and multi-instance learning. The method comprises the steps of extracting the video shot of each video in a training video set and selecting an emotional representative frame and an emotional mutation frame for each video shot to show the shot, extracting the audio and video characteristics of the shots as video instances to form a video instance set, selecting a discriminant video instance from the video instance set, calculating the similarity distances between the video instances and the discriminant video instance in the training video set to obtain a characteristic vector set, carrying out sparse reconstruction on the characteristic vector of the video to be identified and the characteristic vector set corresponding to the training video set, and identifying the class of the video according to reconstruction errors. The novel horror video identification method based on the discriminant instance selection and the multi-instance learning is applied to horror film scene identification, is of great academic significance and social significance and has wide application prospects.

The invention provides an electronic nose signal feature fusion method based on the separability degree and the dissimilarity degree and belongs to the technical field of electronic noise signal and information processing. The method comprises a step one of subjecting an electronic nose signal to feature extraction, a step two of performing feature selection and a step three of performing feature weighted fusion. The invention reserves classification information to the greatest degree while reducing dimensions and eliminating redundancy, and thus the classification identification rate is greatly improved, and the classification identification performance of an electronic nose is improved further.

The invention provides a communication emitter signal classification and identification method under the condition of Gaussian white noise channel, which comprises the following steps of transmittingand receiving the communication emitter signal; extracting envelope information from the received signal of the communication emitter; constructing the characteristic data set dictionary of communication emitter signal; classifying and identifying the received signals from untagged communication emitters. On the premise that the labeled signal characteristic dictionary database is artificially continuously supplemented and perfected, the invention can realize very good classification and identification of the communication emitter signal under the condition of Gaussian white noise channel.

The invention discloses a PSO-SVM (Particle Swarm Optimization-Support Vector Machine)-based classification and identification method for the surface defects of a bridge inhaul cable. The method comprises the following steps: S1, acquiring surface image information of an inhaul cable to be detected; S2, extracting to-be-detected surface defect feature information from the to-be-detected inhaul cable surface image information; and S3, inputting the feature information of the surface defects to be detected into the PSO-SVM classifier to obtain surface defect classification and identification information of the inhaul cable to be detected. In view of the unique advantages of the support vector in solving small-sample, nonlinear and high-dimensional mode recognition, the SVM algorithm is applied to inhaul cable surface defect detection. The SVM model parameters are optimized by adopting the particle swarm optimization algorithm, so that the classification recognition rate is further improved.

The invention relates to a continuous attribute discretization method based on Chi2 statistics, which belongs to the field of data mining, and is characterized in that Chi2 series algorithm is analyzed, a discretization standard is re-defined, and continuous attributes are discretized more reasonably and more effectively; and a difference sequence interval combination method serves as a standard, so that all adjacent areas have fair combination opportunities, thereby well solving the problem of unfairness. In addition, the imprecise Eji value in Chi2 statistics is analyzed, and two improving schemes are presented. The continuous attribute discretization method based on Chi2 statistics has the advantages and the benefits that the high efficiency in extracting information from original data, the discretization process is more precise, and higher accuracy is realized in machine learning.

The invention discloses a human-vehicle classification and identification method for low-resolution radar ground targets, and relates to target classification and identification of ground radars in the field of radio measurement. The method mainly comprises the processing steps of target multi-dimensional feature extraction, feature smoothing and selection, speed coarse classification, probabilityadjustment, SVM classifier, D-S evidence pushing, threshold judgment and the like. According to the method, the moving targets forming the stable track are classified, and ground moving target classification with high recognition probability and low cost is realized. The method has the characteristics of high target recognition probability, target rejection outside the library, high calculation speed and simple engineering implementation, solves the problem that a low-resolution radar system does not have the target classification and recognition capability or is poor in recognition performance, and is particularly suitable for the ground pedestrian and vehicle target classification and recognition process of ground surveillance radar and battlefield reconnaissance radar.

The invention discloses a pedestrian recognition method based on positive-negative generalized max-pooling. The method comprises: preprocessing acquired traffic videos to obtain required training sample images, extracting local features of the training sample images by means of gradient-based HOG local descriptors, encoding the local features by the depth hierarchical encoding method which is completed via a spatial aggregating restricted Boltzmann machine, forming feature encoding vectors of training samples, obtaining high-level image feature representation vectors by adopting the positive-negative generalized max-pooling method, and inputting feature data obtained to a support vector machine classifier to finish the training; preprocessing to-be-tested pedestrian images to obtain test samples, and obtaining feature representation vectors of the test samples by the same method; inputting the feature representation vectors of the test samples to the support vector machine classifier which is already trained, and identifying whether test images are pedestrian images or not. The invention improves the accuracy of pedestrian recognition and enhances the robustness of the pedestrian recognition algorithm.

The invention provides a high-voltage cable partial discharge mode recognition method, and the method comprises the following steps: obtaining training data through laboratory data, dividing the training data into a training set and a test set, and collecting onsite to-be-recognized data; respectively inputting the training set into a plurality of classifiers for training, respectively inputting the test set into the trained classifiers for testing, and inputting to-be-identified data acquired on site into the trained classifiers to obtain a preliminary identification result; taking the preliminary identification result as input data, constructing a partial discharge mode identification model by adopting a learning method taking a support vector machine as a classifier, and then inputtingthe input data into the partial discharge mode identification model for testing to obtain a tested partial discharge mode identification model; and inputting to-be-identified data acquired on site into the tested partial discharge mode identification model, and outputting to obtain a high-voltage cable partial discharge integrated mode identification result.

The invention discloses a small sample hyperspectral classification method based on data enhancement. The method comprises the following steps: inputting hyperspectral image data to obtain a sample set; dividing N neighborhood regions with different sizes for each sample point in the sample set; enabling each sample point to obtain N neighborhood sample sets, processing the neighborhood sample sets to obtain corresponding newly-added sample points, combining all the corresponding newly-added sample points into an amplified data set of the sample points, and traversing the sample sets to obtain enhanced image data; using the original hyperspectral image data and the enhanced image data for training a classifier; and carrying out classification identification on the to-be-identified sample points enhanced by using the data in the above steps in the hyperspectral image by using a voting method or an optimization method by using the trained classifier. According to the invention, the data enhancement of the hyperspectral image data is realized, the problem of small samples is solved to a certain extent, a better classifier is trained through the amplified training samples, and the classification recognition rate of the hyperspectral data is obviously improved under similar conditions.

The embodiment of the invention provides a rehabilitation prediction method and system of a deaf patient after a CI operation based on machine learning, and relates to the field of computer signal processing. The method comprises the steps of obtaining multiple electroencephalogram signals of the patient with congenital deafness, and pre-processing the obtained electroencephalogram signals; extracting characteristic quantities of the electroencephalogram signals from the preprocessed electroencephalogram signals; conducting normalization preprocessing on all electroencephalogram signal data; selecting a kernel function; selecting a training set and a testing set from the electroencephalogram signal data; loading the training set and the testing set into a support vector machine, and conducting rehabilitation prediction. The rehabilitation prediction method and system of the deaf patient after the CI operation based on machine learning have the advantages of being high in recognition rate, accuracy rate, practicability and the like.

The invention belongs to the technical field of intelligent robots, and discloses an intelligent cooking robot system and a control method. The intelligent cooking robot system comprises an energy supply module, a control module, a display module, a collection module, a central processing module, an operation module and a conveying module. The central processing module adopts a support vector machine (SVM) and a mixed signal control processor for data processing. The SVM adds regularization items into a solver system so as to reduce structure risks and is a classifier with sparsity and robustness, wide application to the portrait discrimination and text classification is achieved, the mixed signal control processor is utilized for signal processing, and an intelligent cooking robot can complete multiple commands at the same time.

The invention discloses a polycrystalline diamond compact surface defect classification and recognition method. The problems of manual detection such as strong subjectivity, low efficiency and the fact that accuracy and reliability of classification results cannot be guaranteed are solved, and high-efficiency, high-precision and automatic classification recognition of three kinds of defects, i.e.,a surface crack, a white point and a white edge of a polycrystalline diamond compact can be achieved.

The invention discloses a pedestrian recognition method based on a sequence deep belief network, comprising the following steps: preprocessing the training images in the pedestrian database, obtaining training sample images, performing HOG feature extraction on the obtained training sample images, constructing and training Based on the sequence deep belief network of the sequence restricted Boltzmann machine, the obtained HOG features are further extracted with the sequence deep belief network to form the feature vector of the training sample, and the obtained feature data is input into the support vector machine classifier to complete Training; preprocessing the pedestrian image to be tested to obtain a test sample, using HOG and sequence deep belief network to extract pedestrian features from the test sample to form the feature vector of the test sample; input the feature vector of the test sample into the support vector machine classifier, Recognize whether the test image is pedestrian or non-pedestrian. The invention can obtain better classification performance, improve the accuracy rate of pedestrian identification, and enhance the robustness of pedestrian identification algorithm.