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

2018 results about "Perceptron" patented technology

In machine learning, the perceptron is an algorithm for supervised learning of binary classifiers. A binary classifier is a function which can decide whether or not an input, represented by a vector of numbers, belongs to some specific class. It is a type of linear classifier, i.e. a classification algorithm that makes its predictions based on a linear predictor function combining a set of weights with the feature vector.

Shield tunneling digital twin stratum construction method and system fusing multi-source data

Disclosed in the present invention are a shield tunneling digital twin stratum construction method and system fusing multi-source data, and the method comprises: first using investigation data of drilling, geotechnical tests, in-situ tests, etc. and considering the characteristics of "sparsity", "multi-dimensional correlation" and "spatial variability" of stratum distribution and geotechnical parameters to construct a multi-layer perceptron-based stratum three-dimensional distribution model, and establish a geotechnical parameter multivariate correlation three-dimensional conditional random field based on sparse Bayesian learning technology; using the stratum distribution and the multivariate geotechnical parameter random field to establish a shield tunnel tunneling random finite element digital twin model; and, on the basis of coupling double-unscented Kalman filtering, fusing shield tunneling mechanical parameters and stratum deformation monitoring data, and performing construction feedback-based dynamic inversion on stratum distribution uncertainty and geotechnical parameter space correlation to achieve fine characterization of stratum distribution and geotechnical parameters in front of a shield tunneling surface, so as to obtain a shield tunneling dynamic digital twin stratum model.
Owner:NO 3 ENG CO LTD OF CCCC THIRD HARBOR ENG CO LTD +2

Inventory optimization method and system based on deep learning model

The invention provides an inventory optimization method and system based on a deep learning model, and relates to the technical field of deep learning, and the method comprises the steps: obtaining the multi-dimensional data of a commodity, constructing a dynamic convolution kernel through employing a graph neural network, constructing a soft clustering distribution matrix in combination with a multi-layer perceptron, and obtaining a long-term dependence feature fusing a space dimension and a time dimension. And fusing the short-term and long-term features, inputting the fused short-term and long-term features into a bidirectional long-short-term memory network to generate a sales prediction sequence, and calculating a prediction confidence interval to obtain a final sales prediction result. And calculating a safe inventory level based on a sales prediction result, generating a replenishment decision by using a dynamic planning model based on deep reinforcement learning in combination with an inventory cost function, and finally sending the decision to a supply chain execution system. The sales volume is accurately predicted through the deep learning model, the inventory management is optimized, the storage cost, the stockout cost and the overstock cost are reduced, and the supply chain efficiency is effectively improved.
Owner:QINSILK COM

Power load prediction method based on multi-source heterogeneous data feature fusion, system equipment and medium

The invention discloses a power load prediction method based on multi-source heterogeneous data feature fusion, system equipment and a medium, and relates to the technical field of power system load prediction, and the method comprises the steps: obtaining a power load prediction data set, and carrying out the preprocessing; performing input feature processing on the static data, the graph data and the time series data based on a multi-layer perceptron, a graph convolutional network and a gating loop unit network, and fusing the processed features based on a feature splicing method to obtain comprehensive feature information; based on full-connection neural network construction, taking the comprehensive features as input, inputting training set data into a model, and performing iterative optimization according to a model effect to adjust model parameters and hyper-parameters; and based on the parameter optimization adjustment model, using the evaluated optimal model to predict the power load in the future time period. The method is superior to a traditional method in precision and stability, can better adapt to complex and changeable load prediction scenes, and has wide application prospects and remarkable actual value.
Owner:LUCULENT SMART TECHNOLOGIES CO LTD

State estimation method based on adaptive space-time diagram neural network

The invention relates to a power distribution network state estimation method based on an adaptive space-time diagram neural network, and the method mainly comprises the following steps: S1, collecting historical and real-time measurement data of a power distribution network, and carrying out the preprocessing of the data, so as to guarantee the integrity of the data, provide high-quality input data for a model, and improve the estimation precision and stability of the model; s2, discrete wavelet transform is carried out on historical measurement data, multi-scale decomposition is achieved, and low-frequency and high-frequency components are extracted; a double-branch time sequence fusion module is constructed, global trend and local fluctuation features are respectively captured through a dynamic attention mechanism and a time convolution network, and the features are efficiently fused by means of adaptive weights. S3, in the real-time data processing process, branch measurement features are extracted through a multi-layer perceptron (MLP) and mapped to nodes of the whole network, dynamic integration of historical data and real-time data is achieved, and therefore the real-time performance and accuracy of state estimation of the power distribution network are improved.
Owner:SOUTHEAST UNIV +1

Intelligent logistics supply chain digital management system based on data analysis

The invention relates to an intelligent logistics supply chain digital management system based on data analysis. The system comprises a demand prediction and analysis unit, an inventory optimization unit, a supplier management unit, a logistics path optimization unit, a system integration and feedback unit and a real-time logistics marketing unit. Historical orders and market data are analyzed through a recurrent neural network and a long-short-term memory network, and accurate prediction of short-term and medium-long term demands is realized. And the inventory optimization unit is combined with a Bayesian dynamic linear model and a convolutional neural network to realize dynamic management of the inventory. The supplier management unit optimizes supplier selection through a multi-layer perceptron and a fuzzy clustering algorithm. The logistics path optimization unit realizes optimal scheduling of logistics paths based on a genetic algorithm and an adaptive large-scale neighborhood search (ALNS) algorithm. According to the system, by integrating a plurality of functional units, the operation efficiency and the response speed of the logistics supply chain are effectively improved.
Owner:SHENZHEN XINGCHENG TECH CO LTD

Digital intelligence system applied to cooperative management and control of water-power engineering construction participating units

The invention relates to the technical field of management and control systems, in particular to a digital intelligence system applied to collaborative management and control of water-power engineering construction participating units, which comprises a project data management module covering water-power engineering construction full life cycle management, extracting multi-source information data from various subsystems, and constructing a project view and a project management information base; the project risk analysis module is used for constructing an intelligent risk analysis model for risk analysis and generating a dynamic evaluation result, a graded early warning notification and an auxiliary decision scheme; the project collaborative management module is used for processing graded early warning notification and auxiliary decision-making schemes by using a multi-layer perceptron model, and generating finalizing service achievements and management process records; and the project document management module is used for performing compliance automatic checking and processing on the electronic documents needing to be archived, and dynamically updating and optimizing the project management information base. Through the closed-loop management and control system, the cooperative management and control efficiency of water-power engineering construction participation units is improved.
Owner:GUODIAN DADU RIVER POWER ENG

Fire early warning method and system based on smoke image joint feature analysis

The invention provides a fire early warning method and system based on smoke image joint feature analysis, which are applied to fire early warning in an indoor scene, and the method comprises the steps: collecting smoke concentration distribution data and an infrared thermogram of an indoor environment based on a smoke sensor array and an infrared sensor array, and collecting a visible light image of the indoor environment based on a camera; extracting spatio-temporal characteristics of smoke concentration distribution by using a 3D convolutional neural network, and extracting texture and shape characteristics of the visible light image and temperature distribution characteristics of the infrared thermal image by using a 2D convolutional neural network; performing weighted fusion on the three features to generate joint feature representation; expressing the fused joint features as a feature sequence based on a time sequence, and obtaining a fire risk level of a current time window based on a trained multi-layer perceptron classification model; according to the method, the accuracy, timeliness and comprehensiveness of early warning are improved, and fire risks in various complex scenes can be better dealt with.
Owner:深圳市源流科技有限公司

Edge perception multi-prototype learning-based few-sample medical image segmentation method

The invention relates to the technical field of medical image segmentation, in particular to a few-sample medical image segmentation method based on edge perception multi-prototype learning, and the method comprises the steps: inputting support and query images into a feature encoder, and extracting support and query feature maps of different sizes; inputting into a local attention fusion prototype generator to generate a support foreground prototype; processing the support mask through dynamic corrosion operation to generate an inner boundary prototype; generating a multi-foreground local prototype through a multi-layer perceptron; local and global information is optimized through multi-scale feature extraction, and a multi-scale prototype is obtained; fusing to obtain a multi-prototype foreground prototype; dynamic calculation weighting is carried out on the multi-prototype foreground prototype by using a double-stage prototype optimization network, and automatic calibration is carried out; then prediction is carried out through a prototype prediction module, and finally collaborative optimization is carried out through a loss calculation module; the method can effectively solve the problem of edge detail loss involved in the background technology.
Owner:CHANGSHU FIRST PEOPLES HOSPITAL (CHANGSHU OCCUPATIONAL DISEASE HOSPITAL) +1

Knowledge distillation optimization method based on sparse mixed expert and low-rank adaptation

The invention relates to the technical field of natural language processing, and discloses a knowledge distillation optimization method based on sparse hybrid experts and low-rank adaptation, and the method comprises the steps: designing a student model according to a teacher model, training the student model, completing an open question and answer task through the trained student model, and obtaining a question and answer result; the teacher model and the student model both adopt large language models, and the parameter scale of the large language model adopted by the teacher model is larger than that of the large language model adopted by the student model; the student model is improved as follows: for each multi-layer perceptron in a backbone network of a large language model adopted by the student model, a plurality of low-rank experts and a route are added to form a low-rank hybrid expert module; and taking the SRKL divergence as a knowledge distillation loss function from the teacher model to the student model, and constructing total loss in combination with a supervised fine tuning loss function. According to the invention, through combination of sparse hybrid experts and low-rank adaptation, the student model can realize performance improvement on multiple tasks.
Owner:UNIV OF SCI & TECH OF CHINA

Hanging basket transportation safety management method and system

The invention discloses a hanging basket transportation safety management method and system, and relates to the field of damage detection. Collecting weight data of the hanging basket; establishing a steel wire rope health state prediction model by using a multi-layer perceptron (MLP) algorithm, predicting the damage degree of the steel wire rope, and obtaining a health state prediction result of the steel wire rope; according to the health state prediction result of the steel wire rope, a bidirectional long-short-term memory neural network BiLSTM is used for prediction, and a damage trend prediction result of the steel wire rope in a future period of time is obtained; comparing the collected weight data of the hanging basket with a preset safety weight range to obtain a judgment result of whether the weight of the hanging basket exceeds the limit or not; according to the health state prediction result of the steel wire rope, the damage trend prediction result and the judgment result of whether the weight of the hanging basket exceeds the limit or not, a decision tree algorithm is adopted to generate a hanging basket operation control scheme; aiming at low safety of a hanging basket in the prior art, the safety of the hanging basket is improved.
Owner:AVIC CONSTR GRP CO LTD

Fatigue driving monitoring and early warning method based on multi-dimensional feature fusion

The invention discloses a fatigue driving monitoring and early warning method based on multi-dimensional feature fusion, and relates to the field of intelligent traffic and safe driving, and the method comprises the steps: carrying out the feature extraction of a collected face image of a vehicle driver through a feature extraction model based on a convolutional neural network, and obtaining a face key point; then calculating the eye closing rate, the mouth opening rate, the head posture data and the facial muscle data to finally obtain multi-dimensional features, and fusing the multi-dimensional features by using a multi-layer perceptron to obtain fused facial features; and then, a fatigue state detection model obtained based on recurrent neural network training is utilized to detect the facial feature time sequence at a plurality of continuous sampling moments so as to detect whether a fatigue driving state occurs and trigger alarm feedback. According to the method, the fatigue state of the driver can be identified and judged more accurately through combination of multi-dimensional data fusion and a time sequence analysis algorithm, and the monitoring and early warning accuracy and reliability are improved. And the system can keep high robustness even in an illumination change or complex driving environment.
Owner:WUXI LINGWU INTELLIGENT TECHNOLOGY CO LTD

Power equipment fault prediction method and system

The invention provides a power equipment fault prediction method and system. The method comprises the steps of performing multi-modal fusion on acquired historical data of power equipment to obtain feature vectors of all modals; fusing the feature vectors by adopting principal component analysis to obtain fusion vectors; constructing the fusion vector into a graph to obtain a space-time diagram; learning spatial features of the spatial information extraction data by using a space-time diagram in a graph convolution mode to obtain a spatial feature representation vector; fusing the spatial feature representation vector in combination with the attention weight to generate an attention fusion vector; learning time sequence information by using a gating loop unit to obtain a time characteristic representation vector; performing weighted feature fusion on the spatial feature representation vector and the time feature representation vector to obtain a space-time fusion representation vector; and processing the space-time fusion representation vector by using a multi-layer perceptron, and outputting power equipment fault prediction. Based on the method, the invention further provides a power equipment fault prediction system. According to the invention, the accuracy and robustness of power equipment fault prediction are improved.
Owner:STATE GRID SHANDONG ELECTRIC POWER CO

Sparse point cloud completion method based on multi-view fusion

The invention belongs to the technical field of computer vision, and discloses a sparse point cloud completion method based on multi-view fusion, which comprises the following steps: (1) inputting point cloud data, extracting point cloud features, and obtaining an overlapping region of the point cloud data; (2) calculating a similarity matrix of inter-frame point clouds in the overlapping region, and solving inter-frame rigid transformation by using a weighted singular value decomposition algorithm; (3) realizing accurate registration of multi-view point clouds through an accumulative registration strategy; (4) performing coarse-grained completion on the point cloud by using a 3D convolutional mesh residual network module, and further fusing 3D voxel features by using a multi-layer perceptron and completing fine-grained accurate point cloud completion; and (5) optimizing the weight of the model by calculating a loss function, and improving the overall effect and precision of completion. According to the invention, the accuracy and robustness of vehicle detection are improved by fusing a multi-view registration technology and a coarse-to-fine modular point cloud completion method.
Owner:NANJING UNIV OF POSTS & TELECOMM

Multi-modal sentiment analysis and interactive adjustment method and system based on large model

The invention discloses a multi-modal sentiment analysis and interactive adjustment method and system based on a large model, and relates to the technical field of artificial intelligence and natural language processing. Comprising the steps of 1, collecting dialogue video data and preprocessing the video data, 2, respectively carrying out image feature extraction, voice feature extraction and text feature extraction according to video frames, audios and texts, 3, carrying out interactive fusion on every two modal features through a cross attention mechanism, and step 4, generating a corresponding dialogue strategy according to the emotion label in the recognition result and the requirement of appointed emotion adjustment, and carrying out interaction according to the dialogue strategy, so as to obtain the emotion recognition result of the multi-layer perceptron after the feature after the interaction fusion is subjected to average pooling processing and then is input into the multi-layer perceptron to carry out emotion classification, and obtaining a classification corresponding to the highest probability as the emotion label recognition result. Dynamically adjusting a dialogue strategy according to the change of the emotion label; the method is suitable for enhancing the emotion understanding and response ability of the intelligent dialogue system and improving the user experience.
Owner:SHANDONG INSPUR SCI RES INST CO LTD

Opportunity network link prediction method based on time sequence diagram neural network

The invention discloses an opportunity network link prediction method based on a time sequence diagram neural network, and particularly relates to the technical field of the time sequence diagram neural network, and the method comprises the following steps: S1, data collection and network snapshot generation; s2, weighting feature coding clusters; s3, GAT and LSTM combined processing embedding is carried out; s4, the probability is calculated through a multi-layer perceptron; s5, constructing a loss function according to the link; s6, drawing sets and training parameters; and S7, multi-index evaluation of the optimal model. The method accurately captures the spatial-temporal characteristics of nodes, collaboratively operates embedding, coding and decoding layers, improves the accuracy and stability of link prediction, stabilizes the reliability of network communication and the success rate of data transmission, innovates a loss function and an optimization strategy, solves the problems of data sparseness and over-fitting, enhances the generalization ability, adapts the model to a multi-field network, and improves the data transmission efficiency. And links are accurately predicted in scenes such as intelligent traffic and disaster rescue, resource configuration and communication efficiency are optimized, and innovative development of multi-industry network application is powerfully promoted.
Owner:INNER MONGOLIA UNIVERSITY +2

Interference resource planning method based on knowledge graph and space-time diagram convolutional neural network, medium and equipment

The invention discloses an interference resource planning method based on a knowledge graph and space-time diagram convolutional neural network. A head entity, a relation and a tail entity gt; constructing an interference pattern decision knowledge graph in a triple form; constructing an interference pattern decision knowledge graph embedding representation model, and generating embedding features representing semantic association; constructing interference pattern decision knowledge fusion based on a multi-layer perceptron, and combining attribute characteristics of interference pattern decision with a historical space-time network interference efficiency evaluation sequence; constructing a space-time diagram convolutional neural network to model embedded features, extracting space correlation characteristics between nodes, capturing a time evolution rule of node attributes, and dynamically predicting interference efficiency; and reasoning an optimal interference pattern in combination with the interference efficiency prediction result and the real-time situation information of the target equipment. The method can effectively predict the interference efficiency evaluation of different interference devices, significantly reduces the prediction error of the interference efficiency evaluation, and improves the prediction precision and model stability.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Point cloud classification and segmentation method based on point cloud channel attention feature fusion mechanism

The invention discloses a point cloud classification and segmentation method based on a point cloud channel attention feature fusion mechanism, and the method builds a deep learning model, comprises a down-sampling module which carries out the re-sampling of points through a farthest point sampling algorithm, employs K neighbors for each sampling point, and carries out the segmentation of the points. Aggregation is carried out through maximum pooling, and local points are converted into normal distribution through a geometric mapping module; a double-branch input structure is constructed, one branch inputs a multi-layer perceptron layer with residual connection to perform weight learning on neighborhood features of each point of a point cloud, the other branch inputs a multi-scale channel attention fusion module, and channel attention is extracted through two branches with different scales. A multi-scale channel attention mechanism model is designed, local and global features are combined, and an attention mechanism is adopted in a feature space to fuse multi-scale information of point cloud features. According to the method, a channel attention fusion model is designed to solve the problem that the capability of capturing a remote dependency relationship by using convolution in a traditional point cloud classification and segmentation task is limited, a double-branch input network structure is adopted in a feature extraction stage, and dimension reduction operation is performed on a channel during input; the method has the advantages that the accuracy of classification and segmentation tasks can be improved, and meanwhile, the calculation amount is reduced. The method has great advantages in point cloud classification and point cloud segmentation application tasks.
Owner:GUANGDONG UNIV OF TECH

Scientific and technological achievement intelligent matching and transaction recommendation method and system based on knowledge graph

The invention provides a scientific and technological achievement intelligent matching and transaction recommendation method and system based on a knowledge graph, and relates to the technical field of science and technology, and the method comprises the steps: extracting a technical gene sequence based on a scientific and technological achievement data set, generating a technical state vector, constructing a technical association intensity matrix and a technical iteration path graph, and calculating a technical potential energy distribution field; and forming an initial knowledge graph. And monitoring the fluctuation of the knowledge graph state feature set through the intelligent sensor, and dynamically optimizing the knowledge graph according to the fluctuation condition. Converting technical requirements of a user into a query state, performing state similarity calculation with the knowledge graph, identifying an optimal technical unit combination, predicting a state evolution trajectory, evaluating a regional adaptation degree, and generating a technical implementation scheme. By dynamically optimizing the knowledge graph and accurately matching the user demands, the efficiency and accuracy of scientific and technological achievement matching and transaction recommendation can be effectively improved, and scientific and technological achievement conversion is promoted.
Owner:HEBEI XIONGAN HONGZE TECHNOLOGY CO LTD

Electric drive transmission system comprehensive life prediction method based on AI

The invention relates to the technical field of electric drive transmission system service life prediction, and discloses an AI-based electric drive transmission system comprehensive service life prediction method, which comprises the following steps: acquiring electric drive system operation parameters and mechanical part degradation data; arranging the data into a system operation full-period input tensor and a component degradation full-period input tensor, and respectively extracting multi-order feature tensors through a bidirectional recurrent neural network and a gated time convolutional network; performing cross-modal fusion by using a cross attention fusion network in combination with physical constraints to obtain a system-component degradation fusion feature vector; and after dimension reduction, inputting a multi-layer perceptron network output life prediction value, and generating a residual service life interval with confidence in combination with historical cases. The method integrates multi-source data, realizes cross-domain feature dynamic association and physical constraint fusion, improves the precision and reliability of life prediction, is suitable for intelligent operation and maintenance of the electric drive system, and provides a scientific basis for equipment maintenance.
Owner:HUNAN INSTITUTE OF ENGINEERING

Unmanned aerial vehicle identity recognition method based on deep learning radio frequency fingerprints

ActiveCN119004268AReduce false positivesAchieving Classification AccuracyBiological modelsLow noiseRF front end
An unmanned aerial vehicle identity recognition method based on deep learning radio frequency fingerprints belongs to the field of signal recognition and unmanned aerial vehicle identity recognition, an RF front end collects radio frequency signals when an unmanned aerial vehicle flies, signal preprocessing is performed through a low-noise amplifier, a band-pass filter and a pre-amplifier, an IQ signal is obtained through digital down-conversion, the amplitude of the IQ signal is calculated, and the amplitude of the IQ signal is calculated; and further dividing and splicing the amplitude sequence to obtain final input data of the deep learning network. If the process is a model training process, data annotation is needed, and one-hot codes are generated according to the type of the unmanned aerial vehicle. The deep learning network model is composed of ViT blocks with different patch sizes, and each ViT block comprises a multi-head attention mechanism and a multi-layer perceptron. By performing weighted summation on the output of all ViT blocks, a vector which is used for predicting the type of the unmanned aerial vehicle and is consistent with the label dimension can be obtained. The method has the characteristics of high calculation speed, high unmanned aerial vehicle identity recognition accuracy and no information leakage.
Owner:ZHEJIANG UNIV OF TECH

Real-time ship navigation route planning method based on augmented reality

The invention provides a real-time ship navigation route planning method based on augmented reality, and the method comprises the steps: collecting various environmental data around a ship in real time, and carrying out the preprocessing of the various environmental data; processing video data through a convolutional neural network, extracting environment features, extracting dynamic features through a long-short-term memory network, extracting spatial features through the convolutional neural network, extracting meteorological features by using a two-layer multi-layer perceptron, and fusing to obtain fused features; a generative adversarial network is utilized to generate various sea conditions and meteorological scenes, risk assessment is carried out, a risk map is generated, an avoidance strategy is generated, and a route is adjusted to avoid a high-risk area; in combination with the real-time environment perception data and the historical navigation data, dynamically adjusting the navigation route by adopting a reinforcement learning algorithm to obtain an optimized navigation route; the display is performed through real-time synchronization of AR display and a navigation system in combination with augmented reality technology superposition. According to the scheme, the safety and navigation efficiency of the ship are improved.
Owner:GUANGZHOU SHANGSAI ELECTRONIC TECH CO LTD

Video sequence segmentation method based on selective scanning visual state space model

The invention relates to the technical field of deep learning semantic segmentation, in particular to a video sequence segmentation method based on a selective scanning visual state space model, which comprises the following steps of: inputting an image sequence into an overlapped feature block division layer, and dividing the input image sequence into an image feature block sequence; inputting the image feature block sequence into a state space model encoder based on selective scanning vision to extract thickness feature sequences on different scales; inputting the coarse and fine feature sequences on different scales into a multi-layer perceptron layer for effective fusion of multi-level features to obtain a feature sequence; inputting the feature sequence into a lightweight de-wharf prediction segmentation mask based on a convolutional neural network, and performing visual visualization to generate a semantic segmentation map; in this way, the technical problems that in the prior art, the acceptance range of a traditional convolutional neural network is limited, and a self-attention-based network has extremely high calculation complexity in the aspect of constructing long-term dependence, so that the image sequence segmentation effect is poor are solved.
Owner:HARBIN INST OF TECH AT WEIHAI +1

Deep learning traffic flow prediction method based on time perception hypergraph

The invention discloses a deep learning traffic flow prediction method based on a time perception hypergraph, and the method comprises the steps: constructing a mixed hypergraph through traffic flow data, so as to describe the space structure information of a traffic network, including the position information of nodes and the high-order relation between the nodes; and constructing a time-aware hypergraph to represent the dynamic periodic characteristics of the traffic flow data. Secondly, in combination with space structure information and dynamic periodic characteristics of a traffic road network, a time module based on a time encoder and a time attention network is used for extracting and mining a time dependency relationship in traffic flow data; a spatial module based on a spectral domain spatial hypergraph encoder and a hypergraph attention network is used for deeply mining a spatial dependency relationship in traffic flow data, and a multi-layer perceptron feature fusion device is used for fusing various time and spatial features into a space-time dependency relationship. And finally, mapping the space-time dependency relationship into a future traffic flow predicted value by using a predictor based on a full connection layer.
Owner:BEIJING UNIV OF TECH

Single-lead electrocardiogram arrhythmia detection method and system based on adaptive attention

The invention discloses a single-lead electrocardiogram arrhythmia detection method and system based on adaptive attention. The method comprises the following steps: preprocessing electrocardiogram data; extracting spatial features and time sequence features of the electrocardiosignals through a multi-scale parallel spatial-temporal feature extraction module; weighting processing is carried out on the time sequence features through an adaptive attention mechanism; splicing and fusing the spatial features and the weighted time sequence features, and carrying out cross-channel information integration to obtain space-time fusion features; the time-space fusion feature outputs a classification result through a classifier comprising stacked BiLSTM and a multi-layer perceptron; and iteratively training and optimizing parameters of the whole network to obtain an optimal classification effect. The system comprises a preprocessing module, a multi-scale parallel spatial-temporal feature extraction module, a weighting module, a splicing fusion module, a classifier module and an iterative optimization module. According to the method, the arrhythmia classification accuracy of the single-lead electrocardiogram data is improved, and misdiagnosis conditions are reduced; the real-time performance of the portable wearable device is improved, and the portable wearable device can be widely applied to multiple fields such as remote medical monitoring, family health management and sports health tracking.
Owner:NANJING UNIV OF SCI & TECH

Hearth temperature field prediction method and equipment fusing actual measurement point data mechanism model

The invention belongs to the related technical field of coal-fired boiler detection, and discloses a hearth temperature field prediction method and equipment fused with an actual measurement point data mechanism model, and the method comprises the following steps: completing the installation of a radiation temperature measurement device based on a determined hearth radiation temperature measurement point, and obtaining the hearth radiation temperature data of each measurement point on line, inputting the current unit operation parameters and the hearth radiation temperature data into a hearth temperature field machine learning model, and outputting a hearth temperature field by the hearth temperature field machine learning model; wherein the hearth temperature field machine learning model based on the multilayer perceptron neural network is established, and the training data set is utilized to train the hearth temperature field machine learning model to obtain the hearth temperature field machine learning model. The method solves the problem that the prediction precision of an existing machine learning model on the hearth temperature field is low.
Owner:HUAZHONG UNIV OF SCI & TECH

Medical image generation method and device based on bimodal fusion, equipment and medium

The invention discloses a medical image generation method and device based on bimodal fusion, equipment and a medium, and the method comprises the steps: respectively extracting the visual features of a medical image and the semantic features of text description through an image encoder and a text encoder; mapping the two types of features to a shared semantic space by adopting comparative learning to realize cross-modal alignment; a first path captures hierarchical semantic information through a convolutional neural network, a second path retains local significant features through maximum pooling, and two paths of outputs are fused layer by layer to construct spatial context features; projecting the cross-modal features into a spatial feature map through a multi-layer perceptron, splicing the spatial feature map with coding features, and inputting the spliced spatial feature map into a decoder for up-sampling reconstruction; and performing joint optimization on the comparison loss and the structural similarity loss to realize end-to-end training. And finally, the SSIM index of the generated medical image is improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Road monitoring multi-mode sensing method and system adapting to dynamic environment

The invention provides a road monitoring multi-mode sensing method and a road monitoring multi-mode sensing system adapting to a dynamic environment, and belongs to the field of road monitoring. Performing multi-modal weighted fusion to obtain a feature set after weighted fusion; performing classification processing on the fusion features by using a multi-layer perceptron network; generating a comprehensive evaluation result; dynamically adjusting the working priority of each sensor; alignment is carried out in time and space; automatically adjusting a data fusion strategy; and carrying out data cooperative processing by utilizing edge computing and cloud computing to generate a local model generated by the edge computing and a global model and an optimization result generated by the cloud computing. According to the method, the defects of a traditional road monitoring system in the aspects of environmental adaptability, sensor fusion, calculation efficiency and compatibility are overcome, the overall performance and reliability of the system in a complex and changeable environment are remarkably improved, and the method has wide application prospects especially in the fields of automatic driving and intelligent traffic.
Owner:SHENZHEN ZHONGTING TECH CO LTD +1

Method and system for predicting power load of rural power grid user based on liquid neural network

The invention discloses a rural power grid user power load prediction method and system based on a liquid neural network. The method comprises the following steps: firstly, collecting rural power grid user power load historical data including multi-dimensional features such as weather and agricultural modes, and carrying out data preprocessing; then constructing liquid neurons based on biological neuron dynamics, and modeling the state of the liquid neurons through a differential equation; thirdly, constructing a liquid neural network based on liquid neurons, improving the characterization capability of multi-scale time sequence data through multi-level time constant setting and time gating residual connection, and supplementing network initial information in combination with a multi-layer perceptron architecture; completing model training by using the time sequence data set; the actual application performance of the model is tested based on the test data and the actual application scene; and finally, deploying the model to practical application, and carrying out power load prediction on rural power grid users. According to the method, the expression capability of the model for the multi-scale time sequence data is improved, and high-precision rural power grid user power load prediction is realized.
Owner:INST OF ECONOMIC & TECH STATE GRID HEBEI ELECTRIC POWER

Techniques for multi-view neural object modeling

Techniques are disclosed for generating photorealistic images of objects, such as heads, from multiple viewpoints. In some embodiments, a morphable radiance field (MoRF) model that generates images of heads includes an identity model that maps an identifier (ID) code associated with a head into two codes: a deformation ID code encoding a geometric deformation from a canonical head geometry, and a canonical ID code encoding a canonical appearance within a shape-normalized space. The MoRF model also includes a deformation field model that maps a world space position to a shape-normalized space position based on the deformation ID code. Further, the MoRF model includes a canonical neural radiance field (NeRF) model that includes a density multi-layer perceptron (MLP) branch, a diffuse MLP branch, and a specular MLP branch that output densities, diffuse colors, and specular colors, respectively. The MoRF model can be used to render images of heads from various viewpoints.
Owner:DISNEY ENTERPRISES INC +1

Drug target activation and inhibition relation prediction method based on depth map neural network

The invention discloses a drug target activation and inhibition relation prediction method based on a depth map neural network, and aims to improve the modeling precision and prediction performance of an activation or inhibition action mechanism between a drug and a target. According to the method, on the basis of a fine-grained graph interaction modeling mechanism, multi-scale structural characteristics of drug molecules and three-dimensional space structural information of protein residue levels are fused, and a heterogeneous interaction graph between drugs and proteins is constructed. The method comprises the following steps: firstly, acquiring a drug-target sample with an activation / inhibition tag through a public database, predicting a protein structure by utilizing AlphaFold2, and constructing a protein residue map and a drug molecular map; multi-scale structure semantic representation is obtained through sub-graph decomposition, atomic-scale feature extraction and graph neural network coding of drug graph features; protein graph node features are combined with context embedding generated by a pre-training language model, DSSP coding, secondary structure spectrum and atomic structure features are constructed, and edge features are designed based on the geometrical relationship between residues. Then, based on constraints such as spatial distance and biochemical similarity, a fine-grained mapping relation between drug atoms and protein residues is established, an interaction graph is constructed, and coding is carried out through a GraphSAGE network; and finally, fusing the interacted multi-source embedding, and completing the prediction of the activation / suppression relationship through a multi-layer perceptron. A cross entropy loss function, an Adam optimizer and hyper-parameter grid search are adopted in model training; in the evaluation stage, five-fold cross validation and an independent test set are adopted, and indexes such as the accuracy rate, the recall rate, the F1 score, the specificity and the Morse correlation coefficient are used for comprehensively evaluating the performance of the model. Experimental results show that compared with an existing method, the method has the advantages that the prediction accuracy and mechanism interpretability are remarkably improved, and the method has good generalization ability and application prospects and is suitable for multiple fields of drug action mechanism research, new drug discovery and the like.
Owner:GUILIN UNIV OF ELECTRONIC TECH