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

75 results about "Continuous training" patented technology

Continuous Training, also known as continuous exercise or steady state training, is any type of physical training that involves activity without rest intervals. Continuous training can be performed at low, moderate, or high exercise intensities, and is often contrasted with interval training, often called high-intensity interval training. Some training regimens, such as Fartlek, combine both continuous and interval approaches.

Static electrocardiogram analysis method and device based on artificial intelligence self-learning

The embodiment of the invention relates to a static electrocardiogram analysis method and device based on artificial intelligence self-learning. The static electrocardiogram analysis method comprisesthe steps of data preprocessing, heart beat detection, heart beat classification based on a deep learning method, heart beat checking, heart beat waveform characteristic detection, electrocardiogram event measurement and analysis and final automatic report data outputting and achieve a complete and quick static electrocardiogram process. By adopting the static electrocardiogram analysis method, modification information of automatic analysis results can be also recorded, modified data is collected and fed back to a deep learning model for continuous training, and the accuracy rate of an automatic analysis method is constantly improved.
Owner:SHANGHAI LEPU CLOUDMED CO LTD

A binocular depth estimation method based on depth neural network

The invention relates to a binocular depth estimation method based on a depth neural network, which comprises the following steps: 1) preprocessing the input left and right viewpoint images to enhancedata; 2) constructing a multi-scale network model for binocular depth estimation, wherein the model comprises a plurality of convolution layers, an activation layer, a residual connection, a multi-scale pooling connection and a linear upsampling layer; 3) Designing the loss function to minimize the results in the continuous training process, so as to obtain the optimal network weights; 4) inputting the image to be processed into the network model to obtain the corresponding depth map, and repeatedly repeating the above steps until the network converges or reaches the training times. The invention adopts the idea of unsupervised learning, and only the left and right viewpoint images obtained by the binocular camera are used as network input. The adaptive design of the network sets the internal and external parameters of the camera as a single model parameter, so it can be applied to multiple camera systems without modifying the network.
Owner:浙江七巧连云生物传感技术股份有限公司

A license plate recognition method based on convolution neural network

The invention discloses a license plate recognition method based on a convolution neural network. Firstly, the license plate image is preprocessed to construct the license plate training sample set; then the Faster R-CNN network model consisting of CNN convolution network layer, RPN candidate region extraction layer, ROI pooling layer and discriminant layer is constructed; continuous training through multitasking loss The model generates a Faster R-CNN network model with high accuracy. Finally, the trained Faster R-CNN network model is used to identify the license plate, obtain the location information and category information of the license plate character frame, and then use the prior knowledge to determine the position of the character, sorting and integrating the recognized license plate characters, and outputting the license plate recognition result. The method of the invention utilizes the convolution neural network to complete the license plate recognition, can complete the license plate recognition more quickly and accurately, and avoids the error accumulation problem caused by too many steps in the traditional algorithm.
Owner:MELUX TECH CO LTD

LSTM network-based treatment and convalesce combined health monitoring method

InactiveCN108597609AAccurate Health MonitoringPrecise early warning serviceHealth-index calculationSpecial data processing applicationsPersonalizationNerve network
The invention discloses an LSTM network-based treatment and convalesce combined health monitoring method. The method comprises the following steps that by means of health detection equipment, intelligent home and an HIS system, comprehensive health information data of people aged 60 years and above is collected and obtained and then stored in a cloud database; collected and obtained data waveformsare subjected to denoising processing by adopting an adaptive notch filter of LMS; processed and classified data serves as a training sample, a pervasive health model of people aged 60 years and above is generated by adopting LSTM network training and learning; for an existing pervasive health model, after personal data is obtained, continuous training and personalized adjustment are conducted while the model is identified, and abnormal early warning of the corresponding situation is given. Accordingly, a traditional statistical model algorithm and a neural network are organically combined, comprehensive health monitoring is performed on people aged 60 years or above, efficient and accurate personalized health prediction and early warning are achieved, and a solid foundation is laid for building intelligent health pension service.
Owner:EAST CHINA NORMAL UNIV

Method and system for implementing single carrier frequency domain equilibrium

The invention discloses a single carrier frequency domain equilibrium realizing method with low cost and a system thereof, comprising three parts of channel estimation, equalizer and channel tracking. A data frame adopted by the method / system comprises a training sequence part and a data transmission part. The training sequence part is arranged in the front part and comprises two same continuous training blocks. The data transmission part is arranged in the back part and comprises a plurality of continuous Fourier transforming blocks, namely FFT blocks. The length of every FFT block is the size of FFT. Any complete FFT block comprises a data block and a UW block. And the data block is in front, and the UW block is at back. The method / system utilizes the data of the two same training blocks for the channel estimation. Compared with a traditional continuous data format, the cost of useless data can be lowered. A noise prediction decision feedback equilibrium algorithm is adopted for the equilibrium treatment and a recursive least squares algorithm is adopted for the channel tracking treatment.
Owner:北京韦加航通科技有限责任公司

Deep learning palm vein recognition system and method based on cloud side cooperative computing

The invention discloses a deep learning palm vein recognition system based on cloud side cooperative computing. The system is mainly composed of a cloud computing layer, an edge computing layer and aterminal layer. The calculation and storage capabilities of the whole identification system are determined through the combination of three layers; the system specifically comprises a cloud storage module, palm vein acquisition and identification equipment and a client; the cloud storage module can provide computing resources required by training for the model and transmits the trained model to anedge calculation module of the palm vein acquisition equipment; the terminal collects the recognition condition of the deep convolutional neural network model, and feeds back the recognition condition to the deep convolutional neural network model chip on the cloud storage module through the edge calculation module.Continuous training, application, feedback and retraining are performed, and the accuracy of the finally obtained palm vein recognition model is greatly improved through repeated effective iterative training. The rear-end cloud storage module can also realize rapid deployment and unified management of the palm vein recognition system according to the resource configuration and management capability of the cloud platform.
Owner:WUHAN UNIV

Automatic driving vehicle microscopic decision-making method based on reinforcement learning

The invention discloses an automatic driving vehicle microcosmic decision-making method based on reinforcement learning. According to the method, a reinforcement learning A3C algorithm is adopted, driving behaviors are output by an Actor network, the flexibility is high, and the complexity of logic judgment is not affected by state space and behavior space. According to the method, a two-stage training solving process is adopted. In the first stage, an automatic driving microcosmic decision model suitable for all road sections is obtained through training so as to guarantee driving safety. Inthe second stage, the overall model in the first stage is deployed to each road section, and each road section trains a single-road-section model on the basis of the overall model and has transportability. Meanwhile, the continuous training of the second stage enables the method to adapt to the influence of various real-time factors. Finally, distributed communication architecture based on a realInternet of Vehicles system structure is elaborated, and distributed calculation in the solving process can be completed, so that the method can adapt to different road features and dynamic driving environments, and has wide applicability and robustness.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Seismic wave recognition algorithm based on convolution neural network

The invention discloses an image recognition and feature extraction method based on a convolution neural network, which mainly comprises the following steps: selecting a sufficient amount of seismic and non-seismic data capable of supporting network training; de-noising and intercepting at the starting point being used to ensure the usability of the data; a convolution neural network being built according to the requirement, and the number of layers and some important parameters being adjusted continuously according to the need and effect in the process of debugging and testing; dropout, BatchNormalization and other methods being used to prevent over-fitting; the seismic data being transmitted to the network in the form of three-component and three-channel for continuous training and debugging, and the network model being tested after many times of training. According to the results, the composition proportion of the training data, the iteration times and the size of the data amount are adjusted. By using this method, we can get 97.17% accuracy of seismic wave recognition.
Owner:NORTHEASTERN UNIV LIAONING

Multi-feature-learning-based adversarial network training method

The invention, which belongs to the field of the deep learning neural network, discloses a multi-feature-learning-based adversarial network training method. The method comprises the following steps: S1, constructing a deep convolutional generative adversarial network (DCGAN) model; S2, constructing a plurality of convolution kernels for a determination device; S3, initializing random noises and inputting the processed noises into a generator; S4, with the plurality of constructed convolution kernels with different sizes, carrying out conversion processing on all images received by the determination device to obtain a plurality of characteristic patterns; and S5, outputting a mean value of loss functions of the plurality of characteristic patterns into the generator for continuous training.According to the method disclosed by the invention, the training method after picture receiving by the determination device is changed and thus the convolution process of the determination device iscarried out in parallel, so that a plurality of characteristics of the images generated by the generator are learned simultaneously and several kinds of characteristics in a data set are learned rapidly and thus images matching the characteristics of the data set are generated efficiently.
Owner:SOUTH CHINA UNIV OF TECH

Substation electric quantity trend predictive analysis method based on machine learning

The invention discloses a substation electric quantity trend predictive analysis method based on machine learning. The method comprises the steps that influence factors of substation electric quantitytrend prediction are analyzed, and a characteristic quantity type needed for model construction is determined; a multidimensional characteristic quantity dataset is constructed based on collected electric quantity data and the characteristic quantity type; and a GBDT and Adaboost integrated prediction model is constructed, and a value of a root-mean-square error is adopted to compare prediction effects of evaluation models. Through the substation electric quantity trend predictive analysis method based on machine learning, characteristic factors possibly influencing the prediction effects arefully considered, so that predictive analysis is more accurate; and by the adoption of the regression-based GBDT and Adaboost integrated learning algorithm, data over-fitting is prevented, and continuous training, analysis and optimization of the prediction model can be realized.
Owner:CHENGDU SIHAN TECH

Face detection method and device and computer readable storage medium

The invention discloses a face detection method and device and a computer readable storage medium. The method comprises the steps of model training and face detection, wherein in the training process,multiple deep quadratic trees are constructed by the adoption of a positive sample image, a negative sample image and standard pixel difference features of the images, and then face detection tracking is performed through a random forest formed by the deep quadratic trees; in the training process, testing is performed every time the random forest is obtained to check whether a face can be correctly detected, and the image with a detection error is updated to a corresponding training set and subjected to continuous training learning till the random forest with a detection effect conforming toan expectation is obtained; and during detection, features of a to-be-detected image are input into the random forest, judgment is performed through each quadratic tree of the random forest, statistical analysis is performed on judgment results of all the quadratic trees, and whether the image is a face image is judged according to the statistical result. The method has the advantages that a detection model with high precision is obtained by use of a small quantity of training samples, and the method is particularly suitable for detection of a face with occlusion.
Owner:SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV

Pedestrian attribute recognition method based on image and attribute joint guidance

A pedestrian attribute recognition method based on image and attribute joint guidance includes: obtaining image features and attribute features; build an image-attribute mutual guidance mechanism, including constructing the features of image guiding attributes and pedestrian attributes guiding images; inputting the feature of image guide attribute and the feature of pedestrian attribute guide image into a short-and long-term memory model, and obtaining a pedestrian attribute recognition model in which the image and attribute guide each other; obtaining the pedestrian attribute result and optimizing the pedestrian attribute result by continuous training using cross-entropy objective function. The method can make the model learn the relationship between the image feature and the attribute feature better through the mutual guidance between the image feature and the attribute feature, and adds the attention mechanism in the attribute recognition process, so that the model can further improve the distribution of the two features to improve the accuracy of the pedestrian attribute recognition.
Owner:TIANJIN UNIV

Process and equipment for recognition of a pattern on an item presented

Apparatus and method for improving recognition of patterns such as alphanumeric characters. A known recognition system is expanded to further include a complementary recognition system which is linked with the primary recognition system. An image that can not be positively recognized by the primary recognition system is passed on to the complementary recognition system and any characters not positively recognized by the complementary recognition are again passed on to a correction system. At the correction system, an operator classifies unrecognized characters which are then used to teach the complementary recognition system. Thus, the classified data of the correction system provide the training data for a continuous training process which is coupled with the correction system by a pattern adaptation system.
Owner:IBM CORP

Method for detecting characteristics of video object in finite complex background

InactiveCN101609552AAnti-Background DisturbanceImage analysisState of artSample image
The invention provides a method for detecting the characteristics of a video object in a finite complex background by studying color-based and gradient-based background models. The method comprises the following steps: 1, taking a background scene graph, conducting continuous training on a background sample image to obtain a color-based background model of mixed Gaussian distribution. If the background model conforms to the mixed Gaussian distribution, the gradient distribution functions of various combinations need to be calculated, and if a certain pixel belongs to any gradient distribution, the background model is supposed to conform to the gradient background model; 2, calculating the gradient distribution functions of each image to be detected, and establishing a color- and gradient-based background model; and 3, updating the parameters and weight of Gaussian distribution according to the ambient changes, such as illumination, wind strength and the like, and further updating thecolor-based models and the color- and gradient- based models. Compared with the prior art, the invention has the characteristics of background disturbance resistance and adaption to changes in environmental illumination.
Owner:ZHEJIANG GONGSHANG UNIVERSITY

Method for efficiently utilizing cloud center quantum computer resources

The invention particularly relates to a method for efficiently utilizing cloud center quantum computer resources. According to the method for efficiently utilizing the cloud center quantum computer resource, a quantum cloud center creates a task for a quantum computing application program, and after testing, simulating, simulating, evaluating and optimizing the program, the task enters a physicalquantum computer execution program queue to wait for execution; the quantum cloud center comprehensively executes historical data generated by similar quantum computing application programs, a multiplexing result is selected, the quantum cloud center dynamically selects the programs and loads the programs to the physical quantum computer, and the use efficiency of the quantum computer is improved.The invention discloses a method for efficiently utilizing cloud center quantum computer resources, resources can be distributed more reasonably and efficiently, the use efficiency of the physical quantum computer is improved, the quantum program task selection model and the evaluation model can be optimized through continuous training, the rationality of quantum computing application program selection is continuously improved, and then the operation efficiency of the physical quantum computer is improved.
Owner:JINAN INSPUR HIGH TECH TECH DEV CO LTD

Test case generation system based on neural style migration

The invention discloses a network protocol test case generation system based on neural style migration, which comprises an original data collection module, an encoding module, a neural style migrationmodule and a reverse encoding module. The original data collection module collects the traffic data in the industrial control network system and classifies the collected data by clustering algorithm.The encoding module encodes the classified data into a picture form; The neural style transfer module takes the pictures and style pictures output by the encoding module as the input, and transformsthe neural style based on the neural style transfer method. In the process of transforming, the degree of the style transformation is controlled by continuous training iteration. The inverse coding module converts the two-dimensional image output by the neural style transformation module into one-dimensional sequential form as a test case. This test case can be directly injected into the target network for attack testing. This system can intelligently learn the protocol format, reduce the artificial learning process, and improve the efficiency of testing.
Owner:EAST CHINA NORMAL UNIV

Asynchronous distributed deep learning training method, device and system

The invention discloses an asynchronous distributed deep learning training method, device and system. The method is applied to a computing node k, the computing node performs the forward propagation through the local model parameters and the local data to obtain the loss values, then the gradient updating is obtained via the backward propagation, and only the values with larger information amount in the gradient updating vectors are sent by using the sparse function, so that the communication traffic from the computing node to the parameter server is effectively reduced. On the basic concepts of the asynchronous random gradient descent and a parameter server, the gradient of the computing node is returned via the parameter server, the communication compression is carried out, the compression rate of the communication is effectively guaranteed. The compression rate of communication is continuously increased along with the continuous training, and a better compression effect and a higher communication speed can be achieved.
Owner:SUN YAT SEN UNIV

Intermittent leg rehabilitation training frame for orthopedics department

The invention relates to the technical field of orthopedic training frames, in particular relates to an intermittent leg rehabilitation training frame for the orthopedics department which comprises ahorizontal plate and support legs, the support legs are fixed at four corners of the horizontal plate; two shank sliding grooves are formed in the left end of the upper surface of the horizontal plate. A first wall groove is formed in the outer side wall of the shank sliding groove; a shank sliding block is slidably arranged in the shank sliding groove, a connecting block moving left and right along the first wall groove is arranged on the outer side face of the shank sliding block, a shank containing groove is formed in the upper surface of the shank sliding block, a foot sole limiting plateis arranged at the left end of the shank containing groove, and a groove is formed in the middle section of the upper surface of the horizontal plate; through the meshing effect between a moving frameand an incomplete gear, the legs of a patient are subjected to rehabilitation training in the bent, pause and straightened states, continuous training in the bent and straightened states all the timewhen an existing rehabilitation training device is used for training the legs of the patient is effectively avoided, and the rehabilitation training effect of the rehabilitation training frame is better.
Owner:界首泰谷工业设计有限公司

A white balance proofreading method based on white objects

The invention discloses a white balance proofreading method based on a white object, which comprises the following steps: a white object contrast model is established by using a large number of acquired white object samples through continuous training and learning; The white object contrast model is applied to the scene capture, and the pixel mean value and color gain value are calculated by identifying the image and extracting the white object region in the image, so as to adjust the color to realize the white balance proofreading of the image; The invention has the advantages of simple realization principle, low resource cost, fast operation time, ideal and accurate white balance effect. The paper towel identification technology adopted by the invention is based on convolution neural network algorithm, learning from the large sample data, extracting the high-level features of the image gradually, classifying the features and completing the recognition can deal with the offset, scalechange and deformation of the paper towel to a certain extent, ensure the strong separability of the features, have an ideal recognition effect on the feature classification, reduce the dependence ofthe recognition on external conditions, and reduce the complexity of the model.
Owner:GUANGDONG MATVIEW INTELLIGENT SCI & TECH CO LTD

Ankle-joint rehabilitation training assisting device

ActiveCN104014108AImprove and improve mobilityPromote recoveryGymnastic exercisingMuscle forceFoot supports
The invention relates to an ankle-joint rehabilitation training assisting device. Other people need to assist a patient with the dysfunctional ankle joint of the lower limb in carrying out rehabilitation, and the patient cannot complete rehabilitation training independently. The ankle-joint rehabilitation training assisting device is provided with a base which is provided with a rotary pedal, one end of the rotary pedal is fixed to the base through a connection shaft, and the other end of the rotary pedal is fixed to a telescopic adjustable moment part arranged on the base. The rotary pedal is provided with a foot support, guide posts are fixed to the two sides of the rotary pedal, each guide post is fixedly provided with a leg support, and the patient carries out rehabilitation by stamping on the rotary pedal. Through the ankle-joint rehabilitation training assisting device, without the help of other people, the patient can independently control the training time sequence and the training progress at the right moment according to requirements of the patient, the action capability of the joint and muscle force for relevant control can be improved and enhanced through continuous training, and rehabilitation is facilitated.
Owner:陕西福音假肢有限责任公司

A method for auditing the content of bad information buffered by CDN and CACHE

The invention discloses a method for auditing the content of bad information buffered by CDN and CACHE. The method comprises the following steps of A acquiring a data packet through a data transmission interface; B carrying out the data format of a file analysis module; C using that file analysis module to generate URL to be scanned and transmit the URL to the web page content grabbing module; D using the data processing module to use the intelligent image recognition model to recognize the specific image of the picture, and complete the process of identifying and auditing the CDN / cache content. Compared with the prior art, the invention improves the service coverage range of the content audit, supports the bad information audit of the CDN / webcache service, and the crawler module can directly read the URL to be scanned through the file to carry out content crawling and obtain the web page content. By using the depth learning algorithm and simulating a human brain neural network, a model with high-level expressive force is constructed. Through the continuous training of big data and the frequent iteration, the precision can reach 99.5%.
Owner:CHENGDU SIWEI CENTURY TECH

Pilot frequency distribution method and pilot frequency distribution device of multi-antenna system

An embodiment of the invention provides a pilot frequency distribution method and a pilot frequency distribution device of a multi-antenna system. The pilot frequency distribution method comprises the following steps of: determining the number of pilot frequencies to be distributed and the number of training periods according to the number of users of each cell; and determining a pilot frequency distribution scheme of each cell according to the number of pilot frequencies and the number of training periods, wherein determining the pilot frequency distribution scheme of each cell comprises the following steps of: determining the pilot frequency for each training period, which is distributed by each user of lth cell, and distributing the pilot frequency of at least kth user of the lth cell to different users of other cells in the system in each training period. According to the pilot frequency distribution method and the pilot frequency distribution device, which are provided by the embodiment of the invention, the pilot frequencies distributed to the expected users are distributed to different users in each training period, so that the pilot pollution in different continuous training periods is randomized for providing a foundation for carrying out later accurate channel estimation.
Owner:BEIJING ZHIGU RUI TUO TECH

Environmental protection intelligent law enforcement emergency traceability scheduling management method based on big data

ActiveCN107679743AIntuitive and effective meansClear and effective meansArtificial lifeResourcesNonlinear dimensionality reductionPersonalization
The invention provides an environmental protection intelligent law enforcement emergency traceability scheduling management method based on big data. The environmental protection intelligent law enforcement emergency traceability scheduling management method based on big data includes the steps: 1) establishing a customized triangle environment processing efficiency acquisition and assessment model for a law enforcement object, the law enforcement time and a law enforcement officer; 2) performing self-adaption layered classified dimensionality reduction on the air pollution data; and 3) by means of the customized triangle environment processing efficiency acquisition and assessment model for the law enforcement object, the law enforcement time and the law enforcement officer, according tothe air pollution data after self-adaption layered classified dimensionality reduction, performing continuous training subdivision by combining with the big data ant colony algorithm.
Owner:河北百斛环保科技有限公司

A PDF document content text paragraph aggregation method based on a neural network

The invention discloses a PDF document content text paragraph aggregation method based on a neural network, and the method comprises the steps: defining dozens of features of a row of texts, converting the features into multi-dimensional vectors, generating a sample data set, designing an algorithm model, carrying out the continuous training of the model, and finally outputting the trained algorithm model. For two input lines of texts, the algorithm model is used to accurately determine whether the two lines of texts should be merged into the same paragraph. Based on an artificial intelligencetechnology of a neural network, a research and development application program automatically aggregates line characters extracted from PDF into paragraphs, original sentences and paragraph structureinformation of the characters are restored, and repeated utilization of PDF content data is facilitated. The automatic aggregation efficiency of the artificial intelligence program cannot be achievedthrough manual processing, manual work is replaced by machines, the labor cost is saved, and the efficiency is greatly improved.
Owner:武汉汉王数据技术有限公司

Outdoor sports comprehensive warm-up fitness training all-in-one machine

The invention relates to the technical field of fitness equipment, provides an outdoor sports comprehensive warm-up fitness training all-in-one machine, and aims to solve the problems that a common outdoor training device is low in applicability and cannot perform comprehensive training according to requirements of users, and during training, a trainee cannot have continuous training power and desire. The all-in-one machine comprises a horizontally-arranged bottom plate and a machine body vertical shell arranged on the bottom plate. A machine body top shell is mounted at the top of the machinebody vertical shell in a penetrating manner, and the machine is characterized in that a transverse mounting part extends from one side of the lower part of the machine body vertical shell, a leg exercising mechanism is arranged in the transverse mounting part, a cushion is mounted at the top end of the transverse mounting part through an adjusting frame, and a waist massaging mechanism is arranged in the middle of the side wall of the machine body vertical shell; and the leg exercising mechanism comprises a counterweight flywheel which is rotatably inserted into the transverse mounting part.The all-in-one machine is particularly suitable for outdoor sports comprehensive training and has high social use value and application prospects.
Owner:EAST CHINA UNIV OF TECH

A Test Case Generation Method Based on Neural Style Transfer

ActiveCN109062811AReduce labor costsAvoid the disadvantages of time-consuming and labor-intensive generationSoftware testing/debuggingCluster algorithmAlgorithm
The invention discloses a network protocol test case generation method based on neural style migration, which comprises a raw data collection step, an encoding step, a neural style migration step anda reverse encoding step. The original data collection step collects the traffic data in the industrial control network system and classifies the collected data by clustering algorithm. The encoding step encodes the classified data into a picture form. The neural style transfer step takes the encoded picture and the style picture as the input, and transforms the neural style based on the neural style transfer method. The degree of the style transfer is controlled by continuous training iteration in the process of transforming. The inverse coding step converts the two-dimensional image output from the neural style transformation step into one-dimensional sequential form as a test case. The test case can be directly injected into the target network for attack testing. The method can intelligently learn the protocol format, reduce the artificial learning process, and improve the efficiency of testing.
Owner:EAST CHINA NORMAL UNIV

Marine noise signal identification method based on deep neural network (DNN)

The invention discloses a marine noise signal identification method based on a deep neural network (DNN). According to the method, a deep-neural-network model is established, continuous training and updating of forward operating and back propagation are carried out on weight values of each layer of neurons in the model to obtain classification weight values capable of distinguishing different types of ocean noise signals, and thus identification on the different types of ocean noise signals is realized. According to the identification method of the invention, a deep belief network is utilizedto carry out initial weight value training of the deep neural network, obtained weight values are used as initial weight values of training of the deep neural network, then training is carried out ondata, thus identification on the different types of ocean noise signals is realized. According to the method, the deep neural network and the initial values trained by the deep belief network are utilized to enable accuracy of test results to be high, and high-precision identification requirements can be met.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Supervised image classification method based on self-paced constraint mechanism

The invention discloses a supervised image classification method based on a self-paced constraint mechanism. The method comprises the following steps: dividing difficult types of training samples; establishing a sparse representation model, and substituting samples into the sparse representation model for training; obtaining an image classification model and a prediction model; constructing a category decision-making device, wherein the training sample difficult type comprises a training easy sample and a training difficult sample, and the division training sample difficultly-easy types are divided by adopting a self-step constraint matrix. According to the invention, the training samples are divided through the self-paced constraint matrix; the easy training sample and the difficult training sample are sequentially substituted into a defined sparse representation model for continuous training; a specific self-step constrained image classification scheme can be formed, more judgment information can be conveniently utilized, robustness is achieved on sample noise, and therefore the problem that a supervised dictionary learning mechanism is not suitable for complex samples containingnoise and huge intra-class changes can be solved, and the image recognition effect is improved.
Owner:JIANGNAN UNIV
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