Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

345results about How to "Few parameters" patented technology

Prostate MRI image segmentation method based on Mamba-Unet

The invention relates to the technical field of prostate MRI (Magnetic Resonance Imaging) image segmentation, in particular to a prostate MRI image segmentation method based on Mamb-Unet, which realizes effective fusion of features of different scales between an encoder and a decoder, and fuses multi-scale information on a space axis by using a space attention bridge segment to fuse fusion features of different levels from the encoder, so that the segmentation accuracy of the prostate MRI image is improved. And then global and local information is captured through 1D convolution and full connection in the channel attention bridge segment, so that a channel attention map is generated, channel information is better integrated, and multi-level different-scale feature fusion is realized.
Owner:MINGDE COLLEGE OF GUIZHOU UNIV

Road defect detection method based on DRR module and SDFM

The invention discloses a road defect detection method based on a DRR module and an SDFM. The method comprises the following steps: S1, data acquisition and processing; s2, constructing a model: replacing a DWR module with a DRB module, and replacing a BottleNeck residual module of a backbone network part C2f through the DRR module; downsampling of a backbone network and a neck is replaced by an LDConv convolution module, a neck structure of an SDFM improved model is used, and features of different scales are fused to serve as input of a detection head; s3, model training: training the improved network model by using the made training set by setting training hyper-parameters; s4, model verification: setting verification parameters to verify the trained model; and deploying the verified model to a visual interface to realize real-time detection of road defects. According to the method, the model is improved, so that the detection algorithm has higher accuracy and robustness, and can adapt to different road defects and environmental conditions.
Owner:NANJING HOWSO TECH +1

Large language model parameter fine tuning method, system and device, storage medium and product

The invention discloses a large language model parameter fine tuning method, system and device, a storage medium and a product, and relates to the field of natural language processing. The fine tuning method comprises the steps that a pre-training model and a parameter matrix of the pre-training model are acquired, a parameter fine tuning module is arranged on a self-attention layer of the pre-training model, the parameter fine tuning module comprises LoRA modules of different task types and a router, each LoRA module comprises a general feature matrix and a specific feature matrix, and the general feature matrixes of the multiple LoRA modules are shared; obtaining a fine tuning data set; loading and freezing a parameter matrix of the pre-training model, and initializing parameters of a parameter fine tuning module; and performing fine tuning on the parameters of the parameter fine tuning module based on the fine tuning data set to obtain a fine-tuned large language model. Parameters of the MoE architecture are remarkably reduced, it is ensured that the model captures differences of various tasks to the maximum extent, and the cross-task generalization of the model is ensured.
Owner:BEIJING ACAD OF ARTIFICIAL INTELLLIGENCE

Power grid communication equipment fault identification method and system based on multi-source heterogeneous data representation learning

The invention discloses a power grid communication equipment fault identification method and system based on multi-source heterogeneous data characterization learning. The method comprises the following steps: firstly, collecting various complex multi-source heterogeneous data containing fault power grid communication equipment and preprocessing the complex multi-source heterogeneous data; extracting deep semantic features by using a pre-trained feature extraction network and obtaining a feature vector sequence; capturing time features of the feature vector sequence through a bidirectional long-short-term memory network, and obtaining complete sequence feature representation through a full connection layer; performing low-rank multi-modal fusion on the complete sequence feature representation in combination with cross-modal Transform to obtain three types of output splicing construction joint representation, and obtaining a fusion feature by using a self-attention mechanism; and finally, constructing a fault identification model by using the fusion features. Through innovative data preprocessing and data fusion technologies and in combination with an advanced deep learning model, fault-related characteristics can be automatically learned from multi-source heterogeneous data, and intelligent identification of the fault state of the power grid communication equipment is realized.
Owner:INFORMATION & TELECOMM COMPANY SICHUAN ELECTRIC POWER

Ship classification method based on multi-source information feature level fusion

The invention discloses a ship classification method based on multi-source information feature level fusion, and the method comprises the steps: firstly obtaining the HRRP and SAR original radar data of a ship target, carrying out the preprocessing of the HRRP original radar data, and generating two formats of HRRP samples; secondly, performing feature extraction on the HRRP sample in the first format to form traditional features; secondly, constructing a sequential network model branch, taking an HRRP sample in a second format as input, embedding a traditional feature, and outputting a mixed feature; a two-dimensional convolution model branch is constructed, SAR original radar data passes through a lightweight CNN network, and ship target structure features are extracted. And finally, designing a feature fusion module of an attention weighting mechanism, carrying out weighted fusion on the mixed features and ship target structure features, and outputting a ship classification result. According to the method, the problem that automatic target radar recognition is limited in recognition precision and performance based on single-modal data is solved, and the classification accuracy is improved.
Owner:HANGZHOU DIANZI UNIV

Energy output optimization scheduling method and system considering random source load virtual power plant

The invention relates to the field of short-term load prediction and power dispatching control of a power system, in particular to an energy output optimization dispatching method and system considering a random source load virtual power plant, and designs a virtual power plant double-layer optimization dispatching model. The lower-layer model constructs a user load prediction model of an improved Transform, and then a renewable energy output model is established by using a scene generation method; the upper layer model takes the power generation cost minimization of the wind-light storage and combustion virtual power plant as a target, considers constraint conditions such as gas turbine output power, ramp rate, energy storage charging and discharging power, electricity storage quantity and power balance, and proposes a single guide target function comparison algorithm considering random source load to carry out optimization solution on a virtual power plant optimization scheduling target function; and planning and deciding the output of each energy source in the next 24 hours. Experiments show that the new energy consumption level can be remarkably improved under the random source load condition, and better economic benefits are obtained while stable operation of a power distribution system is promoted.
Owner:NANTONG ELECTRIC POWER DESIGN INST CO LTD +1

Speech synthesis method and device with conditional matching stream, equipment and medium

The invention relates to artificial intelligence, and discloses a speech synthesis method and device with a conditional matching stream, equipment and a medium, and the method comprises the steps: receiving text information, coding the text information into a high-dimensional implicit vector, and obtaining a text information vector; label information is formed according to the alignment relation between the text information and the voice, and the relation between the acoustic features of the text information and the voice is predicted; performing matching in the voice data set according to the text information vector to obtain corresponding text-related voice, generating intermediate-state voice according to Gaussian noise, the text-related voice and the time step, performing noise prediction according to the intermediate-state voice and the time step by adopting a conditional matching flow model to obtain predicted noise, and outputting the predicted noise. Calculating the loss between the input Gaussian noise and the prediction noise, and combining the prediction noise with the intermediate state voice to extract and obtain the acoustic features of the text related voice; and generating a decoded speech waveform according to the obtained acoustic characteristics of the text-related speech by adopting an acoustic decoder. And the speech synthesis quality is improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Cement decomposing furnace temperature prediction control method based on KAN enhanced neural network

The invention provides a cement decomposing furnace temperature prediction control method based on a KAN enhanced neural network, and belongs to the technical field of cement calcination. A CNN-LSTM-KAN network is established as an f-CaO and Nox prediction model, and a state parameter optimization objective function is established in connection with actual production requirements; and solving an optimal solution and an optimal solution interval of the state parameters of the decomposition furnace through a multi-target particle swarm optimization algorithm. A KAN-Enhanced-Informer network is established to predict the temperature of the decomposition furnace, a target function is established by combining a state optimization result with the more accurate prediction result, the less coal consumption and the reasonable alternative fuel quantity as targets, the optimal solutions of the coal feeding quantity and the alternative fuel quantity are obtained, and the optimal solutions are applied to a control model to ensure that the temperature of the decomposition furnace reaches the optimal set value. The problems that in the actual cement production process, energy consumption is too high, the yield is not ideal, and much sewage is discharged are solved.
Owner:YANSHAN UNIV

Knowledge distillation-based target detection model training method

The invention relates to a training method of a target detection model based on knowledge distillation, and belongs to the field of target detection. Comprising the following steps: constructing a training data set and a target detection model, and training the target detection model based on the training data set to output an inference graph; calculating a first loss function to obtain a trained target detection model, and taking the trained target detection model as a teacher model; simplifying parameters of the teacher model to obtain a student model; obtaining a second training data set based on the training data set, training the teacher model and the student model based on the second training data set, and respectively outputting prediction labels; and calculating a second loss function to obtain a trained student model as a trained target detection model. According to the method, the optimal distillation temperature and loss coefficient are obtained by adopting the differential mutation algorithm, and the trained target detection model is obtained by training the student model through knowledge distillation, so that the problem of low detection precision caused by the fact that the existing target detection model is trained by a small amount of samples is solved.
Owner:BEIJING JINGHANG COMPUTING & COMM RES INST

Model lightweight application deployment method based on knowledge distillation and related device

The invention belongs to the technical field of model deployment, and discloses a model lightweight application deployment method based on knowledge distillation and a related device. The model lightweight application deployment method comprises the following steps: acquiring a student network and a trained teacher network; based on the trained teacher network, an improved knowledge distillation algorithm is adopted to train and update the student network, a preset convergence condition is reached, and a trained target student network is obtained; the step of improving the knowledge distillation algorithm comprises the steps of exchanging roles of a teacher network and a student network based on an adversarial game, taking the student network as a teacher model, and taking the teacher network as a student model; and generating an adversarial teacher model through the KL divergence between the teacher model and the student model, and training the student network by taking the adversarial teacher model as a teacher guiding model of the student network. According to the technical scheme, lightweight application deployment of the model can be realized, and the recognition precision of the lightweight model can be effectively improved.
Owner:CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +3

Rock pore three-dimensional reconstruction method and system based on adaptive hierarchical cube algorithm, and storage medium

PendingCN119131290ADeepen the depthincrease capacityImage analysisBiological modelsMobile CubeAlgorithm
The invention discloses a rock pore three-dimensional reconstruction method and system based on an adaptive hierarchical cube algorithm, and a storage medium, relates to the technical field of rock structure measurement, and aims to solve the problems of low extraction execution efficiency, ambiguity and poor reconstruction precision of an existing moving cube algorithm. According to an image segmentation model based on RefineNet, the model adopts three 3 * 3 convolution cascading to replace 7 * 7 convolution, and a coordinate attention mechanism is introduced behind each block of an encoder to improve the segmentation precision and efficiency of a key area; dividing the cube into tetrahedrons by adopting a saddle point-adaptive layered downward subdivision method, solving intersection point coordinates and normal vectors, and constructing a triangular patch index; determining the contour surface shape penetrating through the cube by adopting a cube lookup table, and merging triangles of all tetrahedrons to form a complete contour surface; and creating a new triangular patch by using the vertex of the edge of the hole and the newly generated vertex, and repairing the hole to obtain the accurately reconstructed three-dimensional hole of the rock.
Owner:HEILONGJIANG BAYI AGRICULTURAL UNIVERSITY

Transient damping control method based on virtual synchronous generator

The invention discloses a transient damping control method based on a virtual synchronous generator, and belongs to the field of new energy converter technology control. The method comprises the following steps: firstly, sampling output voltage and current of a converter, and calculating instantaneous active power and reactive power output by a virtual synchronous generator through the sampled voltage and current; then, an output phase instruction value and a voltage control instruction value are obtained through an active outer loop algorithm and a reactive outer loop control algorithm of the virtual synchronous generator with angular frequency feedforward compensation; and finally, a PWM modulation signal is obtained through voltage and current double-closed-loop control, so that the control of the virtual synchronous generator is realized. According to the invention, the angular frequency is set to feed forward after passing through the transient link and the gain link, the overall damping of the system is transiently compensated, the overshoot and oscillation of the system are suppressed on the premise of not losing the steady-state characteristic of the system, and the stability of the system is improved.
Owner:HEFEI UNIV

Power model deployment method and device based on federated learning and knowledge distillation

The invention discloses an electric power model deployment method and device based on federated learning and knowledge distillation, and the method comprises the steps: carrying out the data division of a common data set, and obtaining a training set; constructing a teacher model, and training the teacher model through the training set; constructing a student model, and training the student model through the training set and the teacher model; and descending the student model to a power distribution network edge node based on a federated learning framework, training the student model through a local data set, deploying the student model to the power distribution network edge node for operation, and updating the student model regularly. The method and the device provided by the invention not only can effectively reduce model parameters to realize lightweight deployment of the power distribution network, but also can ensure the security of the model during data sharing.
Owner:TIANJIN UNIV +4

Universal multi-level fusion attention model for urban coast SAR image ship detection

The invention relates to a universal multi-level fusion attention model for urban coast SAR image ship detection, which comprises the following steps: establishing sub-modules DFEM, CMAFM and SMAFM: firstly designing the DFEM to extract rich features with different resolutions and semantic information for multi-scale ship detection; then designing CMAFM and SMAFM to fuse channel attention blocks and space attention blocks on different levels of feature maps so as to better learn dependency features from channel and space dimensions to enhance feature representation; and finally, inputting the fused feature map into an existing ship detection network to obtain a detection result. According to the method, more important part of information in an input image can be focused, the position information of the ship is enhanced, unimportant feature information is weakened, the model performance is improved through a small number of additional parameters, and the precision of identifying large and small ships under the complex urban coast background is improved.
Owner:ZHEJIANG COLLEGE OF SECURITY TECH +2

Power grid abnormal situation awareness method and system

The invention discloses a power grid abnormal situation awareness method and system. The method comprises the following steps: acquiring power grid data in real time and calculating different power grid situation evaluation indexes; weighting each power grid situation assessment index, correcting the weight of an abnormal index, and then performing linear weighting on all the power grid situation assessment indexes to obtain a situation assessment value; constructing a prediction model with a double-layer gating recurrent neural network, an attention layer and an output layer cascade, inputting historical data of a power grid situation assessment index, and outputting a future situation assessment prediction value; and inputting new historical data of the power grid situation assessment index into the trained prediction model to obtain a corresponding future situation assessment prediction value, and matching the future situation assessment prediction value with a pre-divided security level to determine whether an abnormality occurs. According to the method, a deep learning framework is utilized, the model for predicting the power grid operation situation of the double-layer gating recurrent neural network based on the attention mechanism is constructed, and a better prediction effect and higher accuracy are achieved.
Owner:STATE GRID HUNAN ELECTRIC POWER COMPANY LIMITED +2

Fractional order thermal network model modeling and parameter identification method of IGBT module

The invention discloses a fractional order thermal network model modeling and parameter identification method for an IGBT module, and the method is characterized in that the method comprises the following steps: S1, building a fractional order thermal network model of the thermal impedance of the IGBT module based on the mathematical function operation relation between the heat transfer mechanism of the IGBT module and the fractional order calculus; s2, based on a junction-shell transient thermal impedance curve given in a data manual of an IGBT module of any model, identifying a fractional order thermal capacity C, an order alpha, a thermal resistance R and a time constant tau in the fractional order thermal network model; the fractional order thermal network model provided by the invention can accurately describe a time-varying curve of thermal impedance of the IGBT module, so that a reference basis can be provided for design and reliability analysis of a circuit system containing such elements.
Owner:CHINA THREE GORGES UNIV

Power transmission line fire smoke identification method based on improved YOLOv9

The invention relates to a power transmission line fire smoke identification method based on improved YOLOv9. The method comprises the following steps: constructing a fire smoke image data set; constructing a power transmission line fire smoke detection model; inputting the training set into the power transmission line fire smoke detection model for training, and storing the optimal power transmission line fire smoke detection model obtained through training; and inputting a to-be-identified power transmission line fire smoke picture into the optimal power transmission line fire smoke detection model to obtain a power transmission line fire smoke picture detection result. According to the method, depth separable convolution is introduced, so that the calculation amount can be reduced, parameters are reduced, and the network detection speed is increased; a parallel weighted mixed domain attention module is adopted to enhance extraction of target features in the fire smoke image; the up-sampling content perception feature recombination network structure CARAFE has a larger receptive field, the perception of important content is enhanced, and the lightweight level of the model can be kept due to the fact that the operation amount is small.
Owner:ANHUI NANRUI JIYUAN POWER GRID TECH CO LTD

Deep forged audio detection method based on attention and double features

The invention discloses a deep forged audio detection method based on attention and double features, which comprises a training stage and a testing stage, and is characterized in that training data is acquired and preprocessed in the training stage, and a double-feature deep forged audio detection model is constructed; inputting the manual acoustic features and the original waveform features of the training data into respective detection branches for model training; attention blocks are added to feature extraction modules of the two models respectively, each attention block is composed of spatial local attention and spectrum global attention, the spatial local attention is used for focusing a local sensitive area of the features, the spectrum global attention is used for capturing cross-channel correlation between the features, namely, the long-range dependency relationship of the captured features, and the spatial local attention is used for focusing the local sensitive area of the features. Splicing, fusing and outputting the images, and inputting the images into a classification module for true and false classification; and finally, the detection model is trained in the test stage, authenticity detection of real voice and synthetic voice is completed, and high-quality deep forged audio detection is realized.
Owner:NANJING UNIV OF POSTS & TELECOMM

Noninvasive blood pressure prediction method based on signal dimension expansion and lightweight network

The invention discloses a non-invasive blood pressure prediction method based on signal dimension extension and a lightweight network, which comprises the following steps: firstly collecting PPG blood pressure data and ABP data, then denoising the collected PPG blood pressure data and ABP data, and cleaning the denoised data. The processed data is used for data signal dimension expansion, a PPG blood pressure measurement model is constructed, and the PPG blood pressure measurement model comprises a basic convolution layer and a residual grouping convolution module Group ResidualBock; and then deploying the constructed PPG blood pressure measurement model into the wearable device to obtain the wearable blood pressure monitoring device. And finally, measuring the processed PPG signal by using wearable blood pressure monitoring equipment to obtain a blood pressure value. According to the method, the PPG signal dimension is expanded, the data processing link is optimized, and the model blood pressure prediction accuracy is improved; and meanwhile, a lightweight algorithm architecture is adopted, so that resource occupation is reduced, the system can be deployed in wearable embedded equipment, and the security of personal privacy data is guaranteed.
Owner:SOUTH CHINA UNIV OF TECH

Hollow fresh soybean detection method and sorting device based on machine vision

The invention discloses a machine vision-based hollow fresh soybean detection method and a sorting device. The method comprises the following steps: acquiring a fresh soybean RGB image with transmission information and surface information; extracting a single fresh soybean image through an edge detection algorithm, and constructing a fresh soybean data set with center coordinates; marking the fresh soybean data set, and dividing the fresh soybean data set into a training set, a verification set and a test set; constructing an improved YOLOv8 classification model by using the labeled fresh soybean data set; the improved YOLOv8 classification model is used for conducting hollow fresh soybean judgment on the fresh soybeans on the conveying line, and the hollow fresh soybeans are separated out. The sorting device comprises a material conveying mechanism, an illumination mechanism, an image acquisition unit, a central controller, a sorting mechanism and the like, an improved YOLOv8 classification model is embedded in the central controller, light-weight and high-accuracy classification of fresh soybeans is realized, a multi-target detection task is converted into a single-target classification task, characteristics of the fresh soybeans are maximized, and the sorting efficiency of the fresh soybeans is improved. And the classification accuracy is improved.
Owner:CHINA NAT PACKAGING & FOOD MACHINERY +1

Field-level rice yield remote sensing estimation method based on high-resolution total primary productivity and dynamic harvest index

The invention provides a field-level rice yield remote sensing estimation method based on high-resolution total primary productivity and a dynamic harvest index, and the method comprises the following steps: firstly, obtaining a rice growth season time sequence Sentinel-2 image based on a remote sensing cloud platform, calculating a leaf area index, and obtaining meteorological data EAR5 products and CO2 data; then, a self-service sampling method and a multi-model process sensitivity analysis method are used for analyzing the influence rule of the rice growth season environment factors on the GPP, an improved double-leaf light energy utilization rate model is constructed, and high-resolution rice GPP high-precision estimation is achieved. And finally, forming an HIDYM method in combination with the dynamic harvest index to realize the yield estimation of the field-level rice in Jiangsu province for many years. The method can be used for quickly and accurately estimating the yield of the large-range field-level rice.
Owner:NANJING AGRICULTURAL UNIVERSITY

High arch dam deformation state fractional order numerical analysis method and module

The invention discloses a high arch dam deformation state fractional order numerical analysis method and module, and relates to the technical field of hydraulic structure service state analysis and computational mechanics. The method comprises the following steps: establishing a high arch dam body and dam foundation fractional order rheological mechanical element model by constructing a fractional order characterization method of attenuation rheological, steady-state rheological and accelerated rheological in a three-dimensional stress state; calculating an internal stress increment, a viscoelastic strain increment, a viscoplastic strain increment and a deformation increment in a delta tn time period by adopting a front difference formula according to the stress, the viscoelastic strain, the viscoplastic strain and the deformation at the tn moment by virtue of an increment finite element method, so as to obtain the stress, the strain and the deformation at the tn + 1 moment; and repeatedly calculating to obtain the stress, strain and deformation of the high arch dam in the analysis time period. According to the method, the nonlinear rheological effect of the dam body and the dam foundation of the high arch dam is objectively described, scientific deformation property numerical value quantitative analysis is achieved, technical support is provided for safety monitoring and dangerous case early warning of the in-service high arch dam, and the method has wide application prospects and market prospects.
Owner:NORTH CHINA UNIV OF WATER RESOURCES & ELECTRIC POWER +1

Terahertz gyrotron traveling wave tube low-speed scattered magnetic control injection electron gun and design method

The invention discloses a gyrotron traveling wave tube low-speed scattered magnetic control injection electron gun and a design method, and belongs to the field of vacuum electronic devices. The electron gun comprises a cathode and an anode. The cathode comprises a cathode bottom table, a rear forming pole, an emission band and a front forming pole, the radius of the cathode bottom table is larger than that of the rear forming pole, the generatrix of the emission band is an arc curve, and the overall surface of the front forming pole is an arc surface; besides, in the design of the cathode, through two times of modeling and respective simulation optimization of partial parameters, the parameters in the one-time simulation optimization process are reduced, the optimization target is clearer, the design difficulty is effectively reduced, and the design time is shortened. The problem that the electric field of the gun area of the electron gun is too high due to the fact that the size of the cathode is too small is effectively solved, meanwhile, the adverse effect of the abrupt change structure of the cathode on the surface electric field of an emission band is avoided, and speed scattering of the electron gun is effectively reduced.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Dam disaster point identification method based on improved DeepLabV < 3 + >

The invention relates to a dam disaster point identification method based on improved DeepLabV < 3 + >, and the method comprises the following steps: Step 1: data preprocessing: changing a data set composed of dam images into a size which can be trained by a network according to the demands; step2, establishing a dam disaster point identification model based on the improved DeepLabV < 3 + >, applying a lightweight network MobileNetV2 in the model, optimizing the expansion rate of a cavity space pyramid pooling module, and introducing a channel attention mechanism and a space attention mechanism, and Step3, training by using the dam disaster point identification model based on the improved DeepLabV < 3 + >, and obtaining a dam disaster point image segmentation result. According to the algorithm, the recognition precision of dam disaster points is improved by introducing an adaptive attention mechanism, a feature extraction module in the algorithm adopts specific cavity convolution configuration, the capture capability of small-scale disaster features is enhanced, and a decoder structure is improved, so that more efficient feature fusion is realized, and the accuracy of semantic segmentation is improved.
Owner:NANJING NORMAL UNIVERSITY

Method for analyzing and predicting drug-target interaction by using deep learning

The invention discloses a method for analyzing and predicting drug-target interaction by using deep learning, which comprises the following steps: encoding a drug and a target protein, and extracting the characteristics of the drug and the target protein for interaction; inputting the interaction characteristics of the drug and the target protein into a multi-head cross attention mechanism, and extracting the interaction characteristics of the drug and the target protein; obtaining independent characteristics of the drug and the target protein; fusing and re-classifying the independent characteristics of the drug, the independent characteristics of the target protein and the interaction characteristics of the drug and the target protein, and predicting drug-target interaction; the invention provides a network based on feature extraction between global molecules and local feature molecules of a drug-target, and the DTIs of the drug-target is predicted; according to the method, the interaction features of the drug target are extracted by adopting a cross attention mechanism, and the independent features of the drug target are extracted by using GAT and CNN, so that rich drug-target information is obtained, and the prediction performance is improved.
Owner:ANHUI UNIV

Non-uniform low-illumination image enhancement method and system

The invention belongs to the technical field of image processing, and particularly relates to a non-uniform low-illumination image enhancement method and system. The method comprises the following steps: step 1, constructing a network model: constructing a non-uniform low-illumination image enhancement network model, wherein the model comprises a Retinex network, an illumination image enhancement network, a reflection image enhancement network and a multi-scale enhancement network; step 2, preparing a data set: dividing a training set and a test set by using an LOL-v1 data set, and preprocessing the training set and the test set; and performing fine adjustment on the model by the LOL-v2 data set. According to the invention, based on deep learning, an efficient two-way feature enhancement network is designed and is used for improving the performance of image features. On the basis of Retinex network decomposition, an input image is decomposed into an illumination image component and a reflection image component, and the characteristics and channel dimensions of the illumination image component and the reflection image component are modulated respectively, so that the characteristics of a low-illumination image are effectively enhanced. According to the method, the quality and definition of the image can be remarkably improved, and illumination and reflection details are brighter.
Owner:CHANGCHUN UNIV OF SCI & TECH

Bionic large-field-of-view cross aperture cooperative monitoring method and model, computer program product and terminal equipment

The invention relates to a target monitoring method and model, in particular to a bionic large-view-field cross aperture cooperative monitoring method and model, a computer program product and terminal equipment. In order to overcome the defects that in the prior art, due to the fact that missing detection and equipment faults occur in the movement process of monitoring equipment in a wide-area range, capturing, detecting, recognizing and tracking of a target in the large-view-field range are difficult, the bionic large-view-field cross-aperture cooperative monitoring method comprises the steps that firstly, model training is conducted through an original compound eye image; the method comprises the steps of obtaining a large-field-of-view cross-aperture collaborative monitoring model, performing target monitoring by using the model, reconstructing a sub-eye image into a large-field-of-view image, and calculating to obtain a prediction frame and collaborative confidence of a target in the large-field-of-view image. Meanwhile, the invention further provides a monitoring model for realizing the monitoring method, and a small target detection module capable of improving the detection efficiency and accuracy is added in the monitoring model.
Owner:XIAN INST OF OPTICS & PRECISION MECHANICS CHINESE ACAD OF SCI

Linear relation accurate zero-knowledge proving method with hidden product

The invention discloses an accurate zero-knowledge proof method for a linear relation with a hidden product. The method comprises the following steps: converting a linear relation with the hidden product on an incomplete split ring # imgabs0 # into a linear relation on # imgabs1 #; an attached additional condition is converted into a gradual component product relation on # imgabs2; the secret evidence # imgabs4 # on the # imgabs3 # is inversely transformed into # imgabs6 # elements xi on the # imgabs5 # through NTT, and a uniform and random matrix and a plurality of vectors are selected on the # imgabs7 #; generating a commitment of the first stage, sampling a vector from discrete Gaussian distribution, and determining a public vector; selecting first challenge information; generating a new commitment, a blind element and a redundant item through the first challenge information; randomly sampling second challenge information c from the challenge space C; and c, determining a vector # imgabs9 # for blinding # imgabs8 # to verify whether the vector # imgabs10 # meets a preset condition or not through c, checking whether a series of equations are established or not, if all equations are established, accepting certification, and otherwise, refusing to accept.
Owner:GUANGZHOU INSTITUTE OF TECHNOLOY XIDIAN UNIVERSITY

Electroencephalogram signal automatic sleep staging method based on residual network and multi-level attention

The invention relates to an electroencephalogram signal automatic sleep staging method based on a residual network and multi-level attention, and belongs to the technical field of sleep monitoring, and the method comprises the following steps: S1, constructing a sleep data set, and carrying out data preprocessing; s2, building a single-channel electroencephalogram automatic sleep staging network model based on deep learning; s3, training the model by using a gradient descent method; s4, sleep staging of the single-channel electroencephalogram signals is achieved through the sleep staging model with the optimal parameters. According to the method, multi-scale feature extraction is realized by using convolution kernels of different sizes, signal features are extracted more comprehensively by combining a style pooling-based recalibration module with a space attention module, and time sequence information is captured and important sequences are highlighted by using a gated loop network fused with a self-attention mechanism. And finally, the sleep staging accuracy is improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM