53 results about "Traffic generation model" patented technology

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.

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.

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.

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.

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.

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.

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.

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.

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.