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

53 results about "Traffic generation model" patented technology

A traffic generation model is a stochastic model of the traffic flows or data sources in a communication network, for example a cellular network or a computer network. A packet generation model is a traffic generation model of the packet flows or data sources in a packet-switched network. For example, a web traffic model is a model of the data that is sent or received by a user's web-browser. These models are useful during the development of telecommunication technologies, in view to analyse the performance and capacity of various protocols, algorithms and network topologies .

Driving scene classification method based on convolution neural network

The invention discloses a driving scene classification method based on a convolution neural network, and the method comprises the following steps: collecting a road environment video image; carrying out the classification of a traffic scene, and building a traffic scene recognition database; extracting sample images of different driving scenes from the traffic scene recognition database, carryingout the feature extraction and multiple convolution training of the sample images through a deep convolution neural network, carrying out the rasterization of pixels, connecting the pixels to form a vector, inputting the vector into a conventional neural network, obtaining convolution neural network output, and achieving the deep learning of different driving scenes; carrying out the parameter optimization of a network structure of the built convolution neural network, obtaining a trained convolution neural network classifier, carrying out the adjustment of a traffic scene recognition model, and selecting an optimal mode as the standard of the traffic scene recognition model; carrying out the real-time collection of the image of a to-be-detected traffic scene, and inputting the image intothe traffic scene recognition model for the recognition of a road environment scene.
Owner:JILIN UNIV

An interactive face cartoon method based on generative adversarial networks

The invention discloses an interactive face cartoon method based on generative adversarial networks. The image to be processed is firstly subjected to interactive segmentation processing to obtain eyebrow-eye, mouth-nose, hair and face images, and then eyebrow-eye, mouth-nose and hair images are respectively input into three trained eye, mouth-nose and hair generation models to output corresponding cartoon five-feature images. Based on the cartoon processing of face image, the cartoon face can be obtained directly. Then the facial features are synthesized on the cartoon face and superimposed on the hair effect to get the final cartoon image. The invention utilizes the advantages of interactive and generating antagonistic network, obtains the five features of human hair, face shape and facethrough interactive segmentation, eliminates the difference between training samples due to different backgrounds, converts the style of each part through generating antagonistic network, and retainsas much information of eye corner, mouth corner and other detail parts as possible.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Semi-supervised intrusion detection method based on depth generation model

The invention discloses a semi-supervised intrusion detection method based on a depth generation model. The method comprises the steps of: 1, preprocessing data: converting symbol attributes in a dataset into numerical attributes, and then normalizing all the numerical attributes; 2, converting high-dimensional feature representations of labeled and unlabeled data into low-dimensional representations of a new feature space by using the variational self-encoding technology in the generation model, adding a constraint to low-dimensional feature vectors to obey Gaussian positive distribution soas to obtain a hidden variable z, and training a classifier by using the hidden variable z in combination with a labeled sample; 3, reconstructing labeled sample data: jointly generating a new labeledsample by using the hidden variable z in combination with label class information; 4, reconstructing an unlabeled sample: predicting the probability of each class of an unlabeled sample by using thehidden variable z, and then generating a new unlabeled sample in combination with the hidden variable z; and 5, calculating a reconstruction error of the model with the newly generated labeled and unlabeled samples, and training and optimizing model parameters in combination with a classification error till convergence.
Owner:CIVIL AVIATION UNIV OF CHINA

A title generation method based on a variational neural network topic model

The invention discloses a title generation method based on a variational neural network subject model, belonging to the technical field of natural language processing. This method automatically learnsthe document topic hidden distribution vector by variational self-encoder, and combines the document topic hidden distribution vector and the document representation vector learned by multi-layer neural network with attention mechanism, so as to express the comprehensive and deep semantics of the document on the topic and global level, and to construct a high-quality title generation model. Thismethod uses the multi-layer encoder to learn the more comprehensive information of the document, and improves the effect of summarizing the main idea of the full text of the title generation model; the topic implicit distribution vector of VAE learning is utilized, and the document content is represented in the abstract level of topic. The topic implicit distribution vector and the document information learned by the multi-layer encoder are combined with the deep semantic representation and context information to construct a high quality title generation model by using the attention mechanism.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY

A mechanical equipment fault intelligent diagnosis method based on a generation model under small sample data

The invention discloses a mechanical equipment fault intelligent diagnosis method based on a generation model under small sample data. The mechanical equipment fault intelligent diagnosis method comprises: carrying out zero-mean-value standardization preprocessing on a small number of obtained mechanical signals; Establishing a composite network for mechanical signal generation; Training a generative adversarial network model in an adversarial manner in combination with a Wasserstein distance and a gradient punishment method; Establishing a deep convolutional neural network model for classifying the operation states of the mechanical equipment by using the mechanical signals; And by combining the generative adversarial composite neural network model and the deep convolutional neural network model, training two networks by using a small amount of real mechanical signals, and finally realizing intelligent fault diagnosis of the mechanical equipment under small sample data. The method hasthe advantages of being good in mechanical signal feature extraction effect, high in state classification accuracy and good in mechanical signal data expansion performance.
Owner:XI AN JIAOTONG UNIV

Traffic sign detection method based on convolutional neural network

The invention relates to a traffic sign detection method based on a convolutional neural network. The method comprises the following steps: step 1, constructing a traffic sign detection network with classification and positioning separated based on the convolutional neural network; 2, in the training stage, training the constructed traffic sign detection network by adopting an enhanced iterative training method to obtain a traffic sign detection model; and step 3, in the use stage, carrying out target detection on the input image by adopting a separation and fusion prediction method to obtaina traffic sign detection result. According to the method, rapid and accurate traffic sign detection is realized in a complex traffic monitoring scene, the robustness to the environment is high, and the detection accuracy for small-size traffic signs is relatively high.
Owner:UNIV OF SCI & TECH OF CHINA

Diabetic retinopathy fundus photography standard image generation method

The invention provides a diabetic retinopathy fundus photography standard image generation method, which comprises the following steps: 1) enabling a collected non-standard fundus image to be generated into a new sample image through a generation model; 2) carrying out local feature extraction on the new sample image; and 3) comparing local features of the non-standard image with local features of a standard image in a discrimination model, if the local features are consistent, outputting the new sample image, that is, the generated standard image, and if the local features are not consistent, adjusting the new sample image. The provided method is simple and effective; the definition of the generated standard image reaches requirement of an intelligent aided diagnosis system; and accuracy of diagnosis is improved.
Owner:HUZHOU TEACHERS COLLEGE

A traffic sign detection method in automatic driving based on a YOLOv3 network

The invention discloses a traffic sign detection method in automatic driving based on a YOLOv3 network, and belongs to the field of traffic sign detection. The method solves the problems that an existing YOLOv3 network target detection algorithm is not high in detection precision and the detection speed cannot meet the real-time requirement. According to the invention, an improved loss function isprovided, so that the influence of a large target error on a small target detection effect is reduced, and the detection accuracy of a small-size target is improved. An improved activation function is provided, a negative value is reserved, meanwhile, changes and information propagated to the next layer are reduced, and the robustness of the algorithm to noise is enhanced. The real frames in thetraffic sign data set are clustered by using a K-means algorithm to realize the pre-fetching of a target frame position and accelerate convergence of the network. The detection precision mAP of the traffic sign detection model on a test set reaches 92.88%, the detection speed reaches 35FPS, and the requirement for real-time performance is completely met. The method can be applied to the field of traffic sign detection.
Owner:BEIJING INFORMATION SCI & TECH UNIV

Traffic flow completion and prediction method

The invention discloses a road traffic flow prediction method, and the method comprises the steps: sampling the historical traffic information of a road condition, and constructing a traffic network model; providing a missing data complementation method based on historical traffic information, building a reachable matrix according to travel time, carrying out the graph convolution through employing the reachable matrix as a convolution kernel, and extracting features; training a recurrent neural network according to the extracted features and the collected traffic data to obtain a flow prediction model; based on real-time sampling traffic data, inputting a pre-trained prediction model, obtaining a new error result in the process, and dynamically training the model.The reachable matrix canreduce unnecessary space search, the space-time relationship mining efficiency is improved, and the road traffic flow prediction accuracy under the conditions of more missing of road traffic flow dataand longer prediction duration is improved.
Owner:ZHEJIANG UNIV OF TECH

Form data privacy protection method fusing differential privacy GAN model and PATE model

The invention relates to a form data privacy protection method fusing a differential privacy GAN model and a PATE model. The method comprises the steps of 1, training a differential privacy generationmodel by using original table data; 2, training a teacher classifier under the differential privacy budget by using the original table data; Step 3, generating 'false' table data by using the generation model, predicting labels of the 'false' table data by using a teacher classifier, selecting data with consistent prediction labels and generated labels, defining an 'available' data set, and training a student classifier by using the 'available' data set; and step 4, releasing the generation model and the student classifier, synthesizing data by using the generation model, selecting the data by using the student model, and finishing a data analysis task. According to the method, privacy protection is carried out on the table data in the data release stage, a data analyst cannot restore original training data through a generation model and cannot speculate the original training data through a student model, protection on the original table data is achieved, and the requirement of the data analyst for the data is met.
Owner:FUZHOU UNIV

Hydropower station hydropower dispatching plan generation and simulation method based on GIS technology

The invention relates to a hydropower station hydropower dispatching plan generation and simulation method based on the GIS technology. The hydropower station hydropower dispatching plan generation and simulation method is characterized by including the steps of firstly, setting up a local terrain spatial database based on a GIS platform; secondly, forecasting a reservoir inflow / outflow amount-time curve based on the expected generating capacity of an upstream hydropower station; thirdly, adjusting the forecasted inflow / outflow amount-time curve based on real-time information such as the water level, the rain condition and the flow and through combination with meteorological and hydrological forecast information and spatial information stored in the first step; fourthly, generating a dispatching plan through the forecasted reservoir inflow / outflow amount-time curve, through combination with hydropower station working condition data and hydropower station dispatching rules, and according to the preset dispatching plan generation model in the system; fifthly, generating the optimal dispatching plan. By means of the hydropower station hydropower dispatching plan generation and simulation method, benefits of different dispatching plans are evaluated for workers, and the method plays a role in assisting the management layer in making a decision.
Owner:SICHUANG TECH CO LTD

Underwater acoustic target recognition method based on deep convolutional generative adversarial network

The invention relates to an underwater acoustic target recognition method based on a deep convolution generative adversarial network, and belongs to the field of underwater acoustic target recognition. The method comprises the following steps: constructing a generation model and a discrimination model; normalizing the original underwater acoustic signals with the category information and the original underwater acoustic signals without the category information, and framing; setting generation model parameters; setting hyper-parameters; constructing a convolutional neural network in the discrimination model; taking the signal data as the input of a convolutional neural network, and calculating and outputting the signal data through the network to obtain a classification result; and countingclassification errors, returning the errors by using a BP algorithm, and updating the weight parameters of the network in the three steps, including the weight between the convolution kernel and thefull connection layer, until the iteration frequency is reached. The method has the advantages that the extracted features completely depend on the data, parameters related to the data do not need tobe set manually, the extracted features are effective to a certain extent for the data, and the data can be effectively utilized to mine distribution information existing in the data.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Harbour district traffic flow forecasting method under reserved harbour concentration mode

The invention relates to a harbour district traffic flow forecasting method under a reserved harbour concentration mode, which belongs to the technical field of harbour district traffic control and comprises the following steps of: dividing traffic generation and attraction areas to obtain the time-interval distribution rule of the historical traffic volume of each traffic generation area and each traffic attraction area to determine the traffic attraction area and the traffic volume; determining a corresponding back-up yard after a forwarder and a cargo collection style are obtained by issuing dynamic information, thereby obtaining the traffic generation area and the traffic volume; forecasting the harbour concentration time-interval traffic volume of each current area; calculating the harbour concentration vehicle OD distribution of the generation areas and the attraction areas, and adding the commuting OD of historical statistics to obtain total OD which corresponds to the generation areas and the attraction areas; and estimating the distribution of the traffic volume on each road section. The invention can basically reflect the condition of the actual traffic flow, can be used for forecasting the development tendency of the traffic flow and carry out traffic control and dispersion in advance, thereby preventing jam points from being generated and jam areas from extending.
Owner:TIANJIN MUNICIPAL ENG DESIGN & RES INST

Automatic text generation method based on deep learning

The invention discloses an automatic text generation method based on deep learning. The method includes a stage of obtaining a text generation model and a stage of calling the text generation model. The first stage includes the steps of preprocessing data, constructing a deep learning algorithm model, training a deep learning model and obtaining the text generation model. The second stage includesthe steps of accepting text input by a user, extracting feature information of the text input by the user, calling the text generation model and generating text matched with the feature information of the text input by the user. The first stage adopts the deep learning algorithm model to make the training process more automated, redundant manual intervention is eliminated, and a series of training strategies are used in the training process to make the text generated by the text generation model more readable. In the second stage, the user input information is classified, the intention of theuser is identified, and the text desired by the user is generated according to the intention of the user. The method is relatively easy to implement and has high applicability and great application especially in the aspect of article generation.
Owner:GUILIN UNIV OF ELECTRONIC TECH

Traffic scene generation method, device and system, computer equipment and storage medium

The invention relates to the technical field of automatic driving simulation, in particular to a traffic scene generation method, system and device, computer equipment and a storage medium. The traffic scene generation method is applied to an on-site terminal and comprises the following steps: acquiring road on-site dynamic traffic data; And processing the dynamic traffic data to obtain dynamic traffic element semantic description information and dynamic traffic element motion information, and transmitting the dynamic traffic element semantic description information and the dynamic traffic element motion information to a cloud. The traffic scene generation method is applied to a cloud end and comprises the following steps: acquiring dynamic traffic element semantic description informationand dynamic traffic element motion information transmitted by a field end; And generating a dynamic traffic scene according to preset static traffic scene data, the virtual dynamic traffic elements and the dynamic traffic element motion information. According to the method, the dynamic simulation site is generated by collecting the data of the road site, and a more real dynamic traffic scene can be provided for the automatic driving simulation system, so that the effectiveness of the automatic driving simulation system is improved, and the road test mileage is greatly reduced.
Owner:上海车右智能科技有限公司

Abstract automatic generation method based on concept pointer network

The invention relates to an abstract automatic generation method based on a concept pointer network, and belongs to the technical field of natural language processing. The method comprises: on the basis of a pointer network, providing a concept pointer network, and finding out a plurality of concepts of input text words firstly; then, selecting the most appropriate concepts according to currentlyinput text semantic information, text word information and concept information, and giving appropriate output probabilities to the concepts; and finally, adding the concept pointer network into the encoding-decoding attention-increasing model, and optimizing the model by using reinforcement learning and remote supervision modes on the basis of the cross entropy training model in combination with apointer-generator mechanism, thereby finally generating an abstract. According to the method, the document content is expressed in a deeper level on the abstract level of the concept, and the model is trained by utilizing a remote supervision strategy, so that the abstract generation model has stronger adaptability and generalization ability, and a high-quality abstract generation mode is constructed.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY

A vehicle big data computing and unloading method based on a fog network

ActiveCN109947574ALess number of task failuresLess number of failed tasksResource allocationParticular environment based servicesReliable computingFog computing
The invention discloses a vehicle big data computing and unloading method based on a fog computing network. According to the invention, a more efficient and reliable computing environment can be provided for analyzing vehicle big data. Firstly, a fog computing network system architecture is provided, a network delay model is further established, then a task generation model is established, a fog computing resource optimization model is established, and finally a load balancing computing resource effective task unloading algorithm is used. Efficient Task Offloading Algorithm with Load Balancing, CRETOA) is used for managing computing resources for load balancing of the fog computing network, and a road vehicle terminal request computing task is allocated to the optimal fog computing resources.
Owner:NANJING UNIV OF POSTS & TELECOMM

Network background flow generation method and system based on conditional generative adversarial network

ActiveCN109889452ACoping with complexityCoping with DiversityError preventionData switching networksAlgorithmGenerative adversarial network
The invention relates to a network background flow generation method based on a conditional generative adversarial network, which comprises the following steps: a data acquisition step: acquiring network flow data and conditional information, and vectorizing the acquired network flow data and conditional information into real flow; a model generation step: obtaining an initial generation model anda discrimination model according to the real flow, and training the initial generation model by using the discrimination model through a conditional generative adversarial network to obtain a generation model; and a flow generation step of generating simulated background flow by using a random vector through the generation model.
Owner:INST OF COMPUTING TECH CHINESE ACAD OF SCI

Targeted work generation method and system based on big data

The invention relates to a targeted work generation method and system based on big data. On the basis of a big data method, big data analysis is carried out on knowledge structures and learning processes and states of a great number of students, learning rules of different kinds of students are grasped; targeted precise works are arranged for the students according to the rules on the basis of learning history and thought characteristics of the students; and the students are assisted in learning. Through continuously accumulated samples, comprising continuously collected learning state data and generated targeted works, a work generation model is trained and updated, so the work generation model can be updated along with the real-time levels of the students, thereby obtaining the precise targeted works all the time. According to the method and the system, the learning state data of the students is collected, and teaching information, such as teaching audios / videos and blackboard-writings of teachers, is collected synchronously, so the correspondence between the learning states of the students and the explaining content, explaining modes, content and details of the teachers is learned, thereby helping the teachers to adjust teaching methods and content.
Owner:耀灵人工智能(浙江)有限公司

Establishment method of dark web traffic recognition model based on SVM machine learning

The invention discloses an establishment method of a dark web traffic recognition model based on SVM machine learning. The method comprises the following steps: constructing a traffic detection model based on the SVM machine learning; performing machine learning on a parameter in the traffic detection model to obtain four feature values of pure anonymous traffic and pure non-anonymous traffic; substituting four feature values of the pure anonymous traffic and the pure non-anonymous traffic into a traffic detection model to perform the operation so as to obtain a parameter of the traffic detection model. Compared with the prior art, the establishment method disclosed by the invention has the advantages as follows: a mathematic model for anonymous data traffic recognition can be accurately depicted by use of the method disclosed by the invention, the method can be applied to the anonymous network data traffic detection, the detection accuracy rate is high, the operation is simple and efficient; after the anonymous network is upgraded, the new anonymous network data traffic can be detected only needing to relearning the upgraded anonymous network by use of the algorithm based on the machine learning.
Owner:NO 30 INST OF CHINA ELECTRONIC TECH GRP CORP

Application encrypted traffic generation method and system based on generative adversarial network

The invention discloses an application encrypted traffic generation method and system based on a generative adversarial network. An encrypted traffic packet (including a data packet header) of a realapplication is extracted into decimal data and intercepted to a fixed length (insufficient bits are supplemented by 0) and separated by comma, each row is one piece of traffic data, the traffic data is sent to a GAN (Generative Adversarial Network) for feature extraction, and after a generator and a discriminator of the GAN tend to be stable, a small amount of encrypted traffic of a real application is input into the generator of the GAN to generate any number of encrypted traffic containing the traffic characteristics of the application. According to the method, the features in the encryptedtraffic are ingeniously abstracted through the GAN, the traffic does not need to be decrypted, the decryption work is reduced, meanwhile, the privacy of a user is effectively protected, and the cost for obtaining a sample is greatly reduced. The method is suitable for all encrypted traffic recognition scenes based on deep learning, and the recognition rate is low due to the fact that encrypted traffic samples are difficult to obtain.
Owner:NANJING UNIV OF POSTS & TELECOMM

Image description generation method based on conditional generative adversarial network

ActiveCN110287357ASolving problems that require a large amount of labeled informationImprove performanceDigital data information retrievalNeural architecturesData setDescent algorithm
An image description generation method based on a conditional generative adversarial network comprises the following steps of 1, constructing a network, wherein a conditional generative adversarial network framework is composed of a generation model and a judgment model, the generation model and the judgment model are similar in structure, but the parameters are independently trained and updated; 2, preprocessing a data set; 3, performing network training, wherein the process comprises 3.1, initializing the parameters of a genearation model and a discrimination model by using the random weights; 3.2, training the generation model; 3.3, training a discrimination model; 3.4, minimizing a loss function by using an RMSprop descent algorithm; and 4, testing the precision, generating the description of the test picture through the operation of the above steps. The image description generation method based on the conditional generative adversarial training is better in robustness and lower in requirement for training data.
Owner:ZHEJIANG UNIV OF TECH

Intelligent household electrical appliance data encryption method based on neural network

The invention discloses an intelligent household electrical appliance data encryption method based on a neural network. A first communication end, a second communication end and a stealing end are included, a first neural network, a second neural network and a third neural network are established at the first communication end, the second communication end and the stealing end, the first neural network and the second neural network are used for encrypting data, and the third neural network is used for decrypting the data. The method comprises steps of establishing a generation model of the first neural network and the second neural network; establishing a discrimination model of a third neural network; and inputting the encrypted data of the second communication end of the first communication end into a generation model, training the generation model, inputting the encrypted data obtained by the stealing end into a judgment model, training the judgment model, inputting the training data of the generation model into the judgment model, judging and decrypting by the judgment model, and training for multiple times to obtain the minimum probability of decryption. According to the method, the neural network is used for encrypting the intelligent household appliances which communicate with one another, a powerful decryption algorithm is defended, and the privacy security of user datais protected.
Owner:FOSHAN VIOMI ELECTRICAL TECH +1

Multistate-network-based transmission time reliability measuring method

InactiveCN106850253AIncrease authenticityThe expression is simple and straightforwardData switching networksState modelEngineering
A method for reliability measurement of transmission time based on a multi-state network, which relates to the technical field of reliability detection of power communication transmission network, and is characterized in that it comprises the following steps: establishing a state model of a network node, establishing a parameter model, establishing a network topology model, Establish a flow generation model and a node transmission model. The invention has convenient operation, high efficiency and reliable method.
Owner:李敏 +2

Network monitoring device

InactiveUS20130322272A1Discriminates power discontinuityImprove perceptionPower managementError preventionAccess timeEngineering
A zero traffic state that is a non-communication state derived from any fault is discriminated from a no-operation state derived from, power discontinuity, and a communication device that is in the zero traffic state is efficiently sensed in consideration of a zero traffic period that is normally observed in a certain installation place or use environment. A network monitoring device cyclically notifies a maintenance person of a communication device, for which a time difference between a final access time and a finally passed traffic generation time exceeds a threshold calculated by multiplying a previously observed maximum, value of the time difference between the final access time and the finally passed traffic generation time by a coefficient that is a safety factory as a device that is In a zero traffic suspected state.
Owner:HITACHI LTD

Method and device for establishing text generation model, medium and computing equipment

The embodiment of the invention provides a method for establishing a text generation model. The method comprises the following steps: inputting at least one training sample generated based on real data sampling into a discriminator to obtain a reward score of the training sample; and training a generator based on the training sample and the reward score thereof. According to the method, the generator is trained through the training sample obtained based on the real data and the reward score output by the discriminator, so that the training process is more stable, and the quality of the generated text is remarkably improved. In addition, the embodiment of the invention provides a device for establishing the text generation model, a medium and computing equipment.
Owner:TSINGHUA UNIV

Signalized intersection traffic demand estimation method affected by traffic stream

InactiveCN108417039AAccurately estimate traffic demandGood effectDetection of traffic movementResourcesData setStream data
The invention belongs to the technical field of intelligent transportation control, relates to a signalized intersection traffic demand estimation method affected by a traffic stream, and is applicable to trunk lines and regional road systems. Various vehicle types and platoon dispersing characteristics are considered, intersection entrance stop lines and an upstream section of an intersection entrance, a plurality of traffic stream data sets are acquired, and platoon dispersing coefficient calibration method is provided based on the data sets, so that a traffic demand estimation model is built. Besides, technical application processes of the model and the method are given and explained by a use case according to computer programming software MATLAB and traffic simulation software VISSIM.The results show that a new method can accurately estimate signalized intersection lane group traffic demands according to traffic streams formed by various vehicle types.
Owner:DALIAN UNIV OF TECH

Network attack traffic generation method based on auxiliary classification type generative adversarial network

The invention discloses a network attack traffic generation method based on an auxiliary classification type generative adversarial network, and the method can generate a malicious traffic sample which can cheat and escape from the detection of a defense system according to an existing network attack traffic data set sample by utilizing the principle of the generative adversarial network. The system comprises: a multi-source heterogeneous data fusion processing module which is responsible for defining a unified data format; a generator network which is responsible for generating a network statistical flow sample according to Gaussian noise and feedback from the discriminator; a discriminator network which is responsible for analyzing the attack traffic sample generated by the generator and the original network traffic sample, including authenticity analysis and attack traffic category analysis; and a classification fine tuning module which is responsible for debugging the performance of the generation model for generating specific types of traffic samples. According to the method, the network attack traffic generation model based on the auxiliary classification type generative adversarial network is constructed, the network attack traffic sample of a specific type can be generated according to the type of the network attack when the network traffic is generated, and the network attack can be simulated by generating the adversarial sample to detect the robustness of the existing intrusion detection system, and a new thought is provided for the existing traffic generator.
Owner:BEIJING UNIV OF POSTS & TELECOMM +2

Urban rail transit receiving and transporting public transportation scheduled departing time generation method

The invention discloses an urban rail transit receiving and transporting public transportation scheduled departing time generation method, which comprises the steps of acquiring scheduled arrival time of rail transit trains and the rated passenger carrying capacity of receiving and transporting public transportation vehicles according to a rail transit scheduled time table and receiving and transporting public transportation vehicle model configuration data provided by an operating enterprise; estimating the volume of rail transit transfer passengers based on historical passenger flow data, estimating the average transfer walking time of the passengers based on field research, and mastering an arrival pattern of non transfer passengers of surrounding block regions; setting virtual trains to act as carriers for the non transfer passengers, and sorting the virtual trains and actual trains according to the arrival time; building a receiving and transporting public transportation scheduled departing time generation model considering passenger carrying capacity constraints of the vehicles; and designing a genetic algorithm embedded with an enumeration process to acquire an optimal / an approximately optimal scheduled departing time scheme. The method disclosed by the invention is used for determining the urban rail transit receiving and transporting public transportation scheduled departing time which gives consideration to the passenger cost and the enterprise cost, reduces the waiting time of the passengers and reduces the operation cost of enterprises.
Owner:SOUTHEAST UNIV

Blood vessel enhancement method of color fundus image

ActiveCN109859139AExcellent blood vessel enhancement effectEffective approachImage enhancementFluorescenceDeep level
The invention discloses a blood vessel enhancement method for a color fundus image. The method comprises the steps of obtaining and processing training data; inputting the data into a generation modelto train the generation model and obtain a final generation model; acquiring and processing data to be enhanced; and inputting the data into a final generation model to generate a blood vessel enhanced color fundus image. According to the invention, the generation model is established; a deep neural network is used for learning blood vessel imaging characteristics of a fluorescence contrast image, information deeper than gray level textures and the like can be learned, the blood vessel enhancement effect of an eye fundus image is more remarkable, and a generated image can be effectively closer to a target image through design of a loss function; therefore, the method can effectively generate the blood vessel enhanced color fundus image according to the existing color fundus image, and ishigh in reliability, good in safety and wide in application range.
Owner:CENT SOUTH 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