260 results about "Restricted Boltzmann machine" patented technology

The invention provides a human behavior recognition method based on a depth neural network, comprising the following steps: acquiring original depth data stream of an actor; extracting human skeleton joint data from the original depth data stream of the actor; modeling the entire human body with three-dimensional coordinates corresponding to the extracted human skeleton joint data; extracting features by modeling the entire human body, sending feature data to a restricted Boltzmann machine network for preprocessing, training out a depth neural network model based on received weight initialization BP neural network parameters, and identifying a behavior from a feature extraction result; overlapping the extracted human skeleton joint data and the actual human body through multi-threaded parallel processing, and displaying the identified behavior in real time; and establishing an abnormal behavior template library and alarming for a detected abnormal behavior. The change of human behavior can be detected in real time, and alarm can be raised for abnormal behaviors (such as fall) of a human body.

The invention discloses a speaker recognition method based on depth learning. The method comprises the following steps: S1) carrying out pre-emphasis and overlapping-type framing windowing on collected voice signals; S2) carrying out endpoint detection on the collected voice signals by utilizing a dual-threshold endpoint detection method based on short-time energy and short-time zero-crossing rate, and judging and indentifying the staring moment, transition stage , noise section and ending moment of the voice; S3) carrying out feature extraction on the voice signals; S4) forming a depth belief network model based on restricted boltzmann machine hierarchy, training the established depth belief network model by utilizing layer-by-layer greedy algorithm and with speaker voice feature parameters being combined, and adding a Softmax classifier to the top layer of the depth belief network model; and S5) inputting the voice features of a speaker to the depth belief network model obtained after being subjected to training, calculating the probability that the model outputs voice features similar to the voice features of the other speakers, and selecting the speaker corresponding to the maximum probability as recognition result.

A Deep Belief Network (DBN) feature extraction-based analogue circuit fault diagnosis method comprises the following steps: a time-domain response signal of a tested analogue circuit is acquired, where the acquired time-domain response signal is an output voltage signal of the tested analogue circuit; DBN-based feature extraction is performed on the acquired voltage signal, wherein learning rates of restricted Boltzmann machines in a DBN are optimized and acquired by virtue of a quantum-behaved particle swarm optimization (QPSO); a support vector machine (SVM)-based fault diagnosis model is constructed, wherein a penalty factor and a width factor of an SVM are optimized and acquired by virtue of the QPSO; and feature data of test data are input into the SVM-based fault diagnosis model, and a fault diagnosis result is output, where the feature data of the test data is generated by performing the DBN-based feature extraction on the test data.

Training data from multiple types of sensors and captured in previous capture sessions can be fused within a physics-based tracking framework to train motion priors using different deep learning techniques, such as convolutional neural networks (CNN) and Recurrent Temporal Restricted Boltzmann Machines (RTRBMs). In embodiments employing one or more CNNs, two streams of filters can be used. In those embodiments, one stream of the filters can be used to learn the temporal information and the other stream of the filters can be used to learn spatial information. In embodiments employing one or more RTRBMs, all visible nodes of the RTRBMs can be clamped with values obtained from the training data or data synthesized from the training data. In cases where sensor data is unavailable, the input nodes may be unclamped and the one or more RTRBMs can generate the missing sensor data.

The invention proposes a rolling bearing fault prediction method based on a continuous deep belief network. The method comprises the following steps: first, extracting the time-domain characteristic quantity of vibration signals of a rolling bearing; then, fusing the extracted time-domain characteristic information using a locally linear embedding method, so as to define a new comprehensive monitoring index for better quantitative evaluation of performance degradation of the bearing; training a continuous restricted Boltzmann machine step by step to construct a continuous deep belief network prediction model; and using a genetic algorithm to optimize the structure of the continuous deep belief network so as to further improve the prediction precision. The prediction method is reliable in result, has good real-time performance, is simple and feasible, and is suitable for rolling bearing fault prediction.

The invention discloses a hyperspectral remote sensing data classification method based on deep learning, and belongs to the technical field of hyperspectral data classification. The invention aims to solve a problem of low classification precision of a method for classifying hyperspectral remote sensing data with nonlinear characteristics. The hyperspectral remote sensing data classification method comprises the following steps: firstly, processing hyperspectral original data to obtain the spectral feature vector and the spatial feature information of the hyperspectral original data; then, integrating the spectral feature vector with the spatial feature information; confirming labeled samples by hyperspectral integrated data, selecting a training sample and a test sample from the labeled samples; Pre-training a multi-layer restricted Boltzmann machine which forms a deep network by the training sample; carrying out supervised learning to the network formed by the multi-layer restricted Boltzmann machine through the training sample; and inputting the test sample into the trimmed network formed by the multi-layer restricted Boltzmann machine to realize hyperspectral remote sensing data classification. The invention is used for the hyperspectral remote sensing data classification.

The invention discloses an aquatic product culture water quality prediction method based on deep learning. By building a deep learning network having three-layer limited Boltzmann machine (RBM) and a layer of BP neural network, water quality sample data is used for training three limited Boltzmann machines by specific dispersion learning for extracting the deep characteristics of the water quality sample data, deep learning network parameter is optimized through BP, so that training on the deep learning network is complete. The trained deep learning network is used to the current water quality sample data, and the water quality prediction can be obtained on an output layer. The method can obtain the characteristic relevance between different water quality factors, and the water quality prediction accuracy is increased.

The invention discloses an advanced persistent threat (APT) attack detection method based on deep belief network-support vector data description. A deep belief network (DBN) is used for feature dimension-reduction and excellent feature vector extraction; and support vector data description (SVDD) is used for the data classification and detection. At a DBN training state, the feature dimension-reduction is performed by using the DBN model after obtaining a standard data set; a low-level restricted Boltzmann machine (RBM) receives simple representation transmitted from the low-level RBM by usingthe high-level RBM so as to learn more abstract and complex representation after performing the initial dimension-reduction, and back propagation of a back propagation (BP) neural network is used forrepeatedly adjusting a weight value until the data with excellent feature is extracted. The data processed by the DBN is divided into a training set and a testing set, and the data set is provided for the SVDD to perform training and identification detection, thereby obtaining the detection result. The attack detection method disclosed by the invention is suitable for the unsupervised attack datadetection with large data size and high-dimension feature, is fit for the APT attack detection and can obtain an excellent detection result.

The invention provides a video heat prediction method based on deep belief networks. The method comprises following steps: selecting input variables according to video features; normalizing and quantifying influence factors, thus preprocessing training data; determining a single-layer restricted Boltzmann machine reconstitution dimension according to the selected input variable and feature reconstruction errors; forming the deep belief networks by multi-layer stacked restricted Boltzmann machines and a BP (Back Propagation) neural network; adjusting the deep belief networks through a global learning algorithm, thus obtaining an optimum video prediction model; placing to-be-tested video test data in the optimum video prediction model for heat prediction analysis and watching quantity prediction analysis. The invention also provides a video heat prediction system based on the deep belief networks. According to the method and the system of the invention, an online video prediction model based on the deep belief networks is provided; the deep neural network is applied in the online video prediction field; and the prediction accuracy and reliability can be improved.

This invention discloses a method for estimating man-face gestures by a dimensionality reduction method including the following steps: 1, preprocessing man-face image trained samples of different gestures, 2, carrying out PCA process to processed data, 3, initializing limited nerve network of a Boltzmann machine, 4, pre-training the limited Boltzmann machine nerve network with the data processed by PCA, 5, adjusting the limited Boltzmqnn nerve network parameters, 6, identifying gestures of new man-face images, which reduces the error rate even further compared with the present technology and reduces its dimensions greatly.

The embodiment of the invention, which relates to the technical field of the computer, provides a voice recognition method and apparatus, so that a problem of a low voice classification distinguishing degree during the voice classification process according to the existing voice recognition technology can be solved. The method comprises: at least two voice features of a to-be-recognized voice are extracted; on the basis of a multi-layer restricted Boltzmann machine (RBM), each of the at least two voice features is trained to obtain a depth voice feature corresponding to each voice feature; feature fusion is carried out on the depth voice feature corresponding to each voice feature, thereby obtaining a depth voice feature of the to-be-recognized voice; and the depth voice feature of the to-be-recognized voice is inputted into a classifier and is classified, so that a voice type of the to-be-recognized voice is obtained. The method and apparatus are applied to voice recognition.

The invention relates to a method for re-identifying persons on the basis of deep learning encoding models. The method includes steps of firstly, encoding initial SIFT features in bottom-up modes by the aid of unsupervised RBM (restricted Boltzmann machine) networks to obtain visual dictionaries; secondly, carrying out supervised fine adjustment on integral network parameters in top-down modes; thirdly, carrying out supervised fine adjustment on the initial visual dictionaries by the aid of error back propagation and acquiring new image expression modes, namely, image deep learning representation vectors, of video images; fourthly, training linear SVM (support vector machine) classifiers by the aid of the image deep learning representation vectors so as to classify and identify pedestrians. The method has the advantages that the problems of poor effects and low robustness due to poor surveillance video quality and viewing angle and illumination difference of the traditional technologies for extracting features and the problem of high computational complexity of the traditional classifiers can be effectively solved by the aid of the method; the person target detection accuracy and the feature expression performance can be effectively improved, and the pedestrians in surveillance video can be efficiently identified.

The invention discloses an emotion analysis method for Chinese texts based on computer information processing technology. Comments on Chinese products are subjected to word segmentation. By utilizing a bag-of-words model, vector representations of product comments are generated. The vector of every comment is inputted to a visible unit of a limited Boltzmann machine (RBM) in deep learning. Sentimental characteristics of Chinese texts are extracted by the RBM and the extracted emotional characteristics are inputted to a SVM for text emotion classification. The emotion analysis method for the Chinese texts based on computer information processing technology is capable of improving relevance of emotional semantics of characteristics while the SVM is capable of improving accuracy of emotion classification of comments on Chinese products.

The invention provides a mixed recommendation method based on a factorization condition limitation Boltzmann machine. The method includes: constructing a target user feature vector; building a target user grading matrix set; building a target user training sample; building a factorization condition limitation Boltzmann machine model; grading and predicting to recommend results to a target user. The problems of user interest expression inaccuracy caused by pure recommendation based on content and data sparsity caused by recommendation based on behavior are effectively solved.

The invention provides an aero-engine main bearing residual life prediction method based on digital twinning. The method comprises: firstly, using a plurality of restricted Boltzmann machines and a regression algorithm to construct a main bearing health monitoring model; comparing the main bearing actual measurement vibration signals with main bearing health state information extracted from the digital twinning model, adjusting and correcting the digital twinning model by utilizing a comparison result, and finally predicting the residual life of the main bearing by utilizing the updated digital twinning model. According to the aero-engine main bearing residual life prediction method based on digital twinning, a digital twinning technology is introduced into the field of main bearing residual life prediction, so that a main bearing digital twinning model applied to the method can be updated in real time along with the change of the working condition of the main bearing of the aero-engine, and a more accurate residual life prediction result can be obtained.

The invention relates to a mammary gland image feature fusion method based on a restricted Boltzmann machine. The method first obtains the high-level semantic feature of a mammary gland molybdenum target and a mammary gland B-scan ultrasonography by stacked self-encoder deep learning, and then uses a restricted Boltzmann Machine model to extract the shared feature representation of different modes of image of the mammary gland B-scan ultrasonography and the mammary gland molybdenum target. The mammary gland image feature fusion method based on the restricted Boltzmann machine obtains the united distribution between different modal statistical attributes of the mammary gland B-scan ultrasonography and mammary gland molybdenum target by a unsupervised training mode, and can fully utilize a large amount of unlabeled data, compensates a defect of excessive reliance on sample class labels of a lot of conventional feature fusion method, and has strong practicality.

The invention discloses a deep learning-based fraud transaction recognition method, a fraud transaction recognition system and a storage medium. The method comprises the following steps: acquiring training samples, wherein the training sample is composed of transaction data used for establishing a fraud transaction detection model; constructing a stacked restricted Boltzmann machine RBM neural network structure, training the RBM neural network structure, and carrying out dimensionality reduction and clustering treatment on the training sample through the trained RBM neural network structure soas to divide the training sample into a plurality of groups; calculating the mass center of each of all the groups, and respectively calculating the hamming distance between each group and the mass center; determining the fraud probability of each group according to the calculated hamming distance so as to establish a fraud transaction detection model; acquiring to-be-detected transaction data, and analyzing the to-be-detected transaction data according to the fraud transaction detection model so as to obtain the fraud probability of the to-be-detected transaction data. In this way, the fraudtransaction is recognized. By means of the method and the device, the accuracy and the rationality of fraud transaction recognition can be improved.

The invention provides a natural gas pipeline tiny leakage detection method based on a sound signals. By taking the sound signal fluctuating most intensely during pipeline tiny leakage as a main signal, and temperature, pressure and flow rate signals as secondary signals, a deep convolution neural net based on multiparameter is established, and the probability of tiny leakage of a natural gas pipeline is determined through studying data of the main signal and the secondary signals; in addition, a deep restricted boltzmann machine model is designed specifically for the isomerism of multiparameter data, the multiparameter data is subjected to pre-training, an optimal weight value matrix and an optimal offset value are obtained and act as a weight initial value and an offset value initial value of a deep convolution neural net model. With the adoption of the method, an accuracy rate of pipeline tiny leakage accident judgment is increased greatly, the probability of a large safety accident is reduced, and the rescue efficiency of a natural gas pipeline accident is improved.

The invention discloses an isolated digit speech recognition classification system and method combining a principal component analysis (PCA) with a restricted Boltzmann machine (RBM). First of all, a Mel frequency cepstrum coefficient (MFCC) is employed for combination with a one-order difference MFCC, and a voice dynamic characteristic of an isolated digit is preliminarily drawn off; then, linear dimension reduction processing is carried out on an MFCC combination characteristic by use of the PCA, and dimensions of a newly obtained characteristic are unified; accordingly, nonlinear dimension reduction processing is performed on the obtained new characteristic by use of the RBM; and finally, finishing recognition classification on a digit voice characteristic after nonlinear dimension reduction by use of a Softmax classifier. According to the invention, PCA linear dimension reduction, unification of the dimensions of the characteristic and RBM nonlinear dimension reduction are combined together, such that the characteristic representation and classification capabilities of a model are greatly improved, the isolated digit voice recognition correct rate is improved, and an efficient solution is provided for high-accuracy recognition of isolated digit voice.

The invention relates to a risk identification method and system based on transfer deep learning. The risk identification method comprises the steps of generating vectors for all possible features through prescribed preprocessing, enabling the vector set to act as visible layer input of a first RBM ((Restricted Boltzmann Machine) so as to build an RBM layer; performing transfer learning by using known fraud samples, and carrying out transfer weighted BP tuning on the RBM layer built in RBM building step; and judging whether the RBM meets prescribed conditions or not after BP tuning, if the RBMmeets the prescribed conditions, not requiring to increase an RBM layer and continuing the following step, and if the RBM does not meet the prescribed conditions, repeating the steps of RBM buildingand transfer weighted BP tuning. A judgment model can be built more accurately and emerging fraud means can be better dealt with according to the invention.

Embodiments of the present invention provide an enhanced Restricted Boltzmann Machine (RBM) system with a novel regularization term to generate features automatically that are suitable for predicting remaining useful life (RUL) of engineered systems such as machines, tools, apparatus, or parts. The system improves the trendability of the output features, which may better represent the degradation pattern of such systems. The disclosed system has been demonstrated to improve trendability and RUL prediction accuracy, offering improved predictive power earlier in the life cycle of the machine, tool, or part. During operation, the system implements an RBM including a loss function. The system then extracts a set of features from a degradation measurement via the RBM. The system fits a rate-of-change slope for a respective feature and adds a regularization term to the loss function based on the fitted slope. The system then selects a subset of the enhanced features based on a measure of monotonic trending and aggregates the subset into a health value. The system then predicts a RUL as a weighted average of features best matching a historical degradation pattern in the health value.

The invention discloses a deep neural network training method based on multiple pre-training. According to the method, the pre-training process of a deep neural network is completed by performing pre-training with a restricted Boltzmann machine and a denoising auto-encoder acting as models in turn. With application of the method, the result of pre-training, i.e. the initial value of the deep neural network parameters, is enabled to have the characteristics of different models so that a better initial model is provided for later training. The method only restricts the value of the parameters of the beginning of different pre-training phases so that the method can be extended to other layer-by-layer pre-training models, such as the auto-encoder and a contraction auto-encoder, etc.

The invention discloses a deep neural network-based SAR (Synthetic Aperture Radar) texture image classification method, and aims to mainly solve the problem of low accuracy of SAR texture image classification with a larger number of samples and more characteristic dimensions in the prior art. The method is implemented by the following steps: (1) extracting low-level characteristics of an SAR image; (2) training the low-level characteristics of the SAR image to obtain advanced characteristics of the image by virtue of a first layer of RBF (Radial Basis Function) neural network of a deep neural network; (3) training the advanced characteristics to obtain more advanced characteristics of the image by virtue of a second layer of RBM (Restricted Boltzmann Machine) neural network of the deep neural network; (4) training the more advanced characteristics to obtain image texture classification characteristics by virtue of a third layer of RBF neural network of the deep neural network; (5) comparing texture classification characteristics of an image test sample with a test sample tag, and regulating parameters of each layer of the deep neural network to obtain the optimal test classification accuracy. The method is high in classification accuracy, and can be used for target identification or target tracking.

This invention relates to Boltzman neutral network for human face identification method in image identification technique field, which comprises the following steps: a, pre-processing human images training samples with different positions; b, initiating limited Boltzman neutral network; c, pre-training limited Boltzman neutral network; d, adjusting limited Boltzman neutral network parameters; e, identifying new human face position. This invention relates to human face testing, mode sorting, human face position identification for re-establish three dimensional human faces and identification.

In a method and apparatus for training a computer system for use in classification of an image by processing image data representing the image, image data are compressed and then loaded into a programmable quantum annealing device that includes a Restricted Boltzmann Machine. The Restricted Boltzmann Machine is trained to act as a classifier of image data, thereby providing a trained Restricted Boltzmann Machine; and, the trained Restricted Boltzmann Machine is used to initialize a neural network for image classification thereby providing a trained computer system for use in classification of an image.

The invention provides a pest image automatic recognition method based on a high-reliability network. The method includes the following steps that preprocessing is carried out on multiple collected training images to obtain multiple training samples, and HOG feature extraction is conducted on the training samples to form joint image feature vectors of the training samples; the high-reliability network based on a restricted boltzmann machine is constructed, the joint image feature vectors of the training samples are input to the constructed high-reliability network, and training on the high-reliability network is completed; preprocessing is conducted on pest images to be tested to obtain test samples, and HOG feature extraction is carried out on the test samples to form joint image feature vectors of the test samples; the joint image feature vectors of the test samples are input to the high-reliability network after training is finished, and categories of past images to be tested are obtained through recognition. According to the method, the accuracy rate of pest recognition can be improved, and robustness of a pest recognition algorithm is enhanced.

The invention relates to a method for analyzing and predicating the content of heavy metals in soil based on LIBS and a stacked RBM deep learning technology. The defect of slow detection speed of the content of the heavy metals in soil in the prior art is overcome in the invention. The method comprises the following steps: obtaining and preprocessing a soil sample; constructing a prediction model based on the stacked restricted Boltzmann machine deep learning technology; carrying out unsupervised training on the prediction model; carrying out supervised training on the predication model; and analyzing and predicating the content of the heavy metals in the soil. The content of the heavy metals in the soil is analyzed and predicated by using the mapping relationship between a laser induced breakdown spectrum and the content of the heavy metals in the soil and combining with the stacked RBM deep learning technology.