3289 results about "Neutral network" patented technology

The invention discloses an urban water body pollution traceability system based on multi-source sensing data fusion, and the system comprises a data acquisition module which is used for deploying a multi-source water quality sensor to collect initial multi-source water body data, and carrying out the time-space unified alignment processing, and obtaining the time-space aligned multi-source time-space water body data; the pollution factor tracing module is used for constructing a pollution event deconstructor and a factor tracing reasoning engine based on a water network topological graph neural network on the basis of multi-source space-time water body data, and outputting pollution component vectors through pollution component decomposition driven by the pollution event deconstructor; inputting the pollution component vector into a tracing reason inference engine to carry out tracing reason space-time correlation to obtain a tracing reason pollution fusion map; and the traceability decision module is used for performing inversion through a reverse traceability algorithm based on the traceability pollution fusion map, calculating the probability that each upstream area is a pollution source, mapping the probability that each upstream area is the pollution source to a GIS platform, obtaining a pollution traceability confidence distribution map, and realizing accurate traceability of the urban water pollution source.

The invention relates to the technical field of land resource monitoring, in particular to a land resource dynamic monitoring and early warning method and system based on multi-source remote sensing data fusion, and the method comprises the steps: employing an unmanned plane to periodically collect optical images, SAR echoes and LiDAR point clouds, constructing a ground three-dimensional digital model, and carrying out the land parcel division; performing fusion to form a multi-dimensional feature vector, establishing an LSTM land parcel feature evolution model, and predicting a change rate interval of each feature in a current period based on a historical sequence; constructing a time sequence difference change detection algorithm, calculating a land parcel change rate, and screening potential abnormal land parcels by taking a prediction interval as an anomaly judgment threshold value; a double-branch convolutional neural network is adopted to identify crop states, growth stages and construction violation behaviors, abnormity is judged and determined, and confidence is given; spatial clustering is carried out on determined abnormal land parcels, accurate boundaries are obtained in combination with a three-dimensional model, multi-level early warning information is generated, and the decision-making efficiency and response speed of land resource monitoring are improved.

A dynamic traffic environment-oriented multi-lane driving decision-making method based on reinforcement learning, comprising: using state space, action space, and trajectory sampling information in a multi-lane driving decision-making scenario to establish a decision-making neural network model; using a comprehensive reward function to perform reinforcement learning training on the decision-making neural network model; continuously and deeply sensing the surrounding environment by means of a sensor array with which a vehicle is equipped, and capturing sensed environment information; inputting the sensed environment information into the decision-making neural network model, and, on the basis of current environment information, the decision-making neural network model predicting a vehicle trajectory and a recommended driving operation within a period of time; and converting the recommended driving operation outputted by the decision-making neural network model into a specific control instruction, and sending the instruction to a drive-by-wire chassis and an actuator of the vehicle.

A system for real-time analysis of emotional feedback during motivational speeches, consisting of: a series of multimodal sensors, including at least one visual sensor configured to capture facial expressions of spectators, at least one directional microphone configured to capture the audio responses of the audience, and optionally one or more physiological sensors configured to capture biometric signals from spectators; an edge-based processing unit that is communicatively coupled to the arrangement of multimodal sensors, wherein the edge-based processing unit comprises the following: (a) a feature extraction module configured to extract visual features from captured facial images, acoustic features from voice responses, and physiological features from biometric signals; (b) an emotion inference machine configured to process the features using a deep learning-based emotion recognition model comprising a convolutional neural network (CNN) for classifying facial expressions, a recurrent neural network (RNN) for classifying voice emotions, and a multimodal late fusion layer configured to compute a composite emotion state vector representing the aggregated emotions of the audience; (c) a timestamp and speech alignment module configured to correlate the calculated composite emotion state vector with segmented portions of a live motivational speech based on real-time speech-to-text transcription and semantic analysis; and (d) a session-based storage unit configured to log time-indexed emotional state vectors and corresponding speech segments for post-event analysis; A speaker feedback interface comprising a portable display or a podium-mounted visualization panel, wherein the interface is configured to display visual indicators of emotional feedback in real time, the indicators being derived from the emotional state vector and including at least emotional trend graphs, threshold alerts, or engagement indices.

The invention provides a cellular network flow space-time prediction method and system based on a hybrid neural network, and belongs to the technical field of intelligent communication. The method adopts a layered deep neural network architecture, and comprises a data embedding layer, a space-time coding layer, a feature fusion layer and an output layer. The data embedding layer maps a historical traffic sequence, cross-domain external data and metadata into high-dimensional features; the space-time coding layer is used for respectively fusing one-dimensional causal convolution and a Mama neural network to extract multi-scale time features and densely connecting convolution and a multi-head attention mechanism to capture multi-scale space features through time and space modeling branches; the feature fusion layer realizes adaptive weighted fusion of spatial-temporal features, cross-domain features and metadata features by using a gating fusion mechanism; and the output layer performs linear transformation on the fusion features to generate a final prediction result. According to the method, the spatial-temporal dynamic capture of the service traffic is accurate, the prediction curve is highly fit with the true value, and the accurate prediction of the multi-service traffic of the cellular network is realized.

The invention discloses a glioma T cell prediction and prognosis evaluation method based on pathological images, particularly relates to the field of patient prognosis health evaluation, and aims to solve the problems that existing pathological evaluation is difficult to combine with tumor structure heterogeneity and immune infiltration distribution, and the future progress risk of a patient cannot be predicted based on follow-up visit pathological data. A spatial heterogeneity map of a tumor core area and an invasion edge is constructed in a digital pathological section, density gradients of T cells in different areas are calculated to generate a distribution heterogeneity coefficient, interaction processing is performed on the two types of characteristics in combination with historical follow-up visit records, and a time sequence neural network constructed based on a gating structure is combined to obtain a high-efficiency characteristic of the tumor. And outputting disease progress probabilities of a plurality of follow-up visit time points in the future to form a prognosis trajectory prediction curve, calculating a quantitative recurrence risk score according to curve slope change and an immune fluctuation mode, and finally generating an individualized management scheme, thereby realizing quantitative prediction evaluation and risk management of the prognosis trend of the glioma patient.

The invention provides a hydro meteorology early warning method for an offshore oil and gas platform, and belongs to the technical field of offshore hydro meteorology. Extreme weather events are identified by adopting minimum probability abnormal event identification vectors to match abnormal characteristic parameters, and abnormal signal characteristic parameters are input into an ocean dynamics prediction model to calculate real-time sea condition parameters; calling a multi-temporal-spatial-scale early warning fusion matrix to combine with a wavelet decomposition technology and a recurrent neural network to realize multi-scale information integration, analyzing an environmental parameter change trend through a sea condition jump identification model and triggering an emergency response, dynamically adjusting system parameters according to a stability evaluation index vector, and optimizing prediction precision by adopting an early warning residual value compensation matrix. And finally, multi-level early warning information is generated and a real-time early warning notification is sent to an operator, so that the technical problem of insufficient early warning precision of an offshore oil and gas platform hydro meteorology early warning system in multi-spatio-temporal scale data fusion processing is solved.

The invention relates to the technical field of geotechnical mechanics and engineering, and particularly discloses a soft soil foundation settlement monitoring method and system based on multi-field multi-source information, and the method comprises the steps: collecting multi-source data of a target soft soil area; performing constitutive parameter inversion, data standardization and discrete Fourier transform frequency domain conversion on the data to obtain a standardized frequency domain multi-field multi-source data set; based on the data set, a soft soil constitutive parameter library and a soil mechanics physical equation, constructing an FD-PINN frequency domain physical information neural network, embedding the physical equation as a prior constraint, and training the model by adopting an alternating optimization strategy; inputting the real-time frequency domain data flow into the model, and outputting the current settlement amount, the settlement rate and the multi-physical field frequency domain distribution; and in combination with a pre-established large scale model test result, through IDFT inverse transformation, a time-space domain settlement field is reconstructed, multi-stage early warning is triggered, a targeted reinforcement scheme is recommended, the soft soil foundation settlement monitoring precision and the engineering practicability are remarkably improved, and the method is suitable for construction, operation and maintenance of infrastructures such as high-speed rails and highways.

Provided in the present invention are a power-distribution-network self-healing method and system taking photovoltaic output into consideration. The method comprises: acquiring historical operation data of a photovoltaic power station and irradiance observation data from a meteorological station; on the basis of the historical operation data of the photovoltaic power station and the irradiance observation data from the meteorological station, predicting the generated power of the photovoltaic power station by using a convolutional long-short-term memory recurrent neural network model that takes sparrow search into consideration; on the basis of the generated power of the photovoltaic power station, a segment-switch state of a power distribution network and a network topology of the power distribution network, constructing an objective function and a constraint condition for a power-distribution-network self-healing model, and obtaining the power-distribution-network self-healing model; solving the power-distribution-network self-healing model by using a propagation search algorithm, so as to obtain an optimal recovery strategy; and executing the optimal recovery strategy by means of segmented switches and node loads. The present invention can realize self-healing of a power distribution network while ensuring the minimum power generation cost of a distributed power source, the minimum network loss and the minimum node voltage deviation.

The invention relates to the technical field of geological disaster monitoring and early warning, in particular to a complex high-position landslide risk dynamic identification system based on multi-source InSAR cooperation, and the system comprises a data collection module which is used for constructing a normalized feature vector representing the state of each monitoring node; the correlation modeling module is used for quantifying the physical influence degree among the heterogeneous nodes; the state prediction module is used for iteratively updating the hidden state of each heterogeneous node by adopting a space-time diagram neural network model and interpreting the hidden state into incremental displacement; the risk assessment module is used for calculating a risk precursor index of each heterogeneous node deviating from a normal evolution mode based on the hidden state, and judging and issuing graded early warning according to a preset threshold system; according to the method, the overfitting problem of a pure data driving model during data sparsity is effectively relieved, and the generalization ability and the physical interpretability of a prediction result are remarkably improved.

The invention relates to the technical field of indoor air quality monitoring, and discloses an indoor air quality joint detection system fused with a space-time diagram neural network. The system comprises a multi-source sensor data acquisition module for acquiring multi-source air quality data flow by configuring various sensors; the space-time diagram construction module constructs space-time diagram data according to the spatial position and the time sequence of the sensor; the fusion processing module adopts a space-time diagram neural network to perform feature fusion on the space-time diagram data to generate an air quality fusion feature set; the prediction strategy module determines a prediction strategy based on the remaining duration of the current time and the end time of the prediction period, and performs air quality prediction in combination with the fusion feature set; the dynamic adjustment module analyzes the real-time change of the data, constructs the pollution change degree and tendency degree, and adjusts the detection control parameters according to the pollution change degree and tendency degree; and the joint detection output module synthesizes the prediction result and the adjustment parameters to generate an indoor air quality joint detection report. The system provides powerful support for indoor air quality evaluation.

The invention discloses a temperature and humidity adaptive control system and method for drying flower traditional Chinese medicinal materials, and the system comprises a humidity gradient monitoring module which is used for deploying a 12-channel capacitive humidity sensor spiral array and a laser radar, generating a three-dimensional humidity field thermodynamic diagram in combination with a Kriging interpolation method, calculating a humidity gradient change rate in real time, and carrying out the early warning of local abnormality; the heat-humidity ratio regulation and control module is used for integrating humidity gradient monitoring data and a real-time result of the evaporation latent heat calculation module based on a fuzzy PID algorithm, dynamically adjusting the heating power and the rotating speed of a dehumidification fan, and meanwhile, integrating a PVDF piezoelectric film sensor to monitor petal stress; the evaporation latent heat calculation module is used for predicting a future evaporation rate by combining an LSTM neural network based on an edge calculation unit and providing key parameters for the energy supply matching module; the energy supply matching module is used for outputting a combined control instruction of the heating power and the air door opening degree; and the air volume balance optimization module is used for dynamically adjusting air volume distribution according to the humidity gradient monitoring data.

The invention belongs to the related technical field of brain image processing, and provides an Alzheimer's disease classification method and system based on topology perception and a group hypergraph in order to solve the problem of inaccurate classification of the Alzheimer's disease in the prior art. Constructing a dynamic function connection network sequence through a sliding window strategy; a local topology perception encoder and a global topology perception encoder are respectively used for extracting local topology features and global topology features of each time window, deep interaction and fusion are carried out, and comprehensive feature representation of a tested level is generated; according to the method, each subject is used as a hypergraph node, hyperedges are constructed on the basis of comprehensive feature representation of a subject level and by combining feature similarity calculated by diffusion tensor imaging features and clinical embedded features of the subject, then a group hypergraph is constructed, a classification result is obtained by using a hypergraph neural network, and the early classification diagnosis accuracy of the Alzheimer's disease is effectively improved.

The invention discloses an intelligent regulation and control method for a tea fermentation process and a regulation and control system based on microbial activity monitoring, and relates to the technical field of tea processing. According to the method, microbial activity and environmental parameters are monitored in real time, and a microbial metabolism model and a neural network algorithm are combined, so that dynamic optimization and accurate regulation and control of the tea leaf fermentation process are realized, firstly, microbial activity data and environmental parameters in a fermentation environment are collected by utilizing a sensor array; the method comprises the following steps: firstly, calculating a metabolite generation rate and a concentration change trend through a microbial metabolism model, accurately identifying abnormal fluctuation in a fermentation process, secondly, adjusting fermentation conditions in real time based on the metabolite concentration change trend and a dynamic regulation and control algorithm to ensure the stability of the fermentation process, and finally, carrying out real-time fermentation. Tea quality parameters after fermentation condition adjustment are predicted through a neural network algorithm, a regulation and control strategy is optimized, and stable improvement of tea quality is achieved.

The invention provides an underground water environment automatic monitoring super station state supervision method and system. The method comprises the following steps: collecting a multi-source dynamic time sequence data set and carrying out time-space alignment; generating a dynamic characteristic index set by using a nonlinear dynamic characteristic extraction method; based on the index set, constructing a self-adaptive cooperative measurement network to perform anomaly monitoring, and generating an anomaly detection result and a cooperative control instruction; generating real-time monitoring and early warning information by using a dynamic threshold adjustment algorithm; and generating an adaptive control instruction and a dynamic resource allocation scheme by using a neural network adaptive control strategy and a resource scheduling optimization algorithm. According to the method, a dynamic characteristic index set is generated, a C-C method is adopted to reconstruct a high-dimensional phase space, a Wolf algorithm and a G-P algorithm are combined to calculate related indexes and dimensions, and a multi-scale fractal mode is analyzed through an R / S analysis method and wavelet transform. The methods capture complex dynamic behaviors of the underground water system, and solve the problem that the traditional method is insufficient in non-linear feature extraction capability.

The invention discloses a fuel gas intelligent valve with point type laser methane sensors, and relates to the field of fuel gas intelligent valves, and the fuel gas intelligent valve comprises an equipment installation module which is used for installing three point type laser methane sensors and collecting interface methane concentration values; the data acquisition module is used for acquiring pipeline parameters and environment parameter data inside and outside the interface; the risk assessment module is used for calculating the methane concentration change rate according to the methane concentration value and assessing whether gas leakage exists at each interface; the fuel gas leakage positioning module is used for constructing a fuel gas leakage positioning model based on a neural network and acquiring the probability of the fuel gas leakage risk at each interface; the valve self-adjusting module is used for determining whether the gas leakage point is a leakage point or not according to the gas leakage risk probability; and the historical data analysis module is used for calculating the precision ratio, the recall rate and the F1-Score value by using the historical data and the field actual measurement result. The leakage risk of the gas pipeline is effectively diagnosed and positioned, and the opening degree of the valve is intelligently controlled.

The invention discloses a systemic lupus erythematosus assessment method and device based on multi-modal medical map and medical knowledge fusion, terminal equipment and a medium, and relates to the technical field of medical artificial intelligence. The method comprises the following steps: acquiring multi-dimensional medical indexes of a patient, and constructing a multi-modal medical knowledge graph of the patient associated with the indexes; pre-training the self-supervised graph neural network to obtain a patient and medical index embedding vector; grouping and constructing a feature subset combination according to medical knowledge, and training and selecting an optimal sub-model; dynamically weighting and fusing the prediction probabilities of the sub-models to obtain a comprehensive prediction probability; and screening the key indexes based on the embedded vector and quantifying the activity evaluation contribution degree of the key indexes to obtain an activity comprehensive score. The systemic lupus erythematosus evaluation method improves the accuracy and robustness of preliminary evaluation of systemic lupus erythematosus, solves the problems of data missing and sample imbalance, and is explainable in output evaluation, adaptive to primary medical treatment and capable of supporting hierarchical diagnosis and treatment.

The invention discloses an unmanned aerial vehicle intelligent inspection system based on AI vision and a detection switch cabinet, and relates to the technical field of unmanned aerial vehicle intelligent inspection, the unmanned aerial vehicle intelligent inspection system comprises an unmanned aerial vehicle inspection platform, and the unmanned aerial vehicle inspection platform is in communication connection with the following modules: an unmanned aerial vehicle end, which is used for collecting and preprocessing video stream data of an inspection area; extracting a key frame from the preprocessed video stream data; and the AI visual analysis module is used for analyzing the extracted key frame by using an AI visual algorithm and identifying key information and abnormal fragments in the key frame. According to the invention, through the AI vision algorithm based on the convolutional neural network model, abnormal features can be automatically learned and identified, the abnormal types and specific conditions can be rapidly determined through deep analysis of the key frames, accurate positioning of abnormal segments and comparison with the preset abnormal feature database, compared with manual detection, the accuracy is greatly improved, and the detection efficiency is improved. Tiny abnormal changes can be found in time, and potential faults can be warned in advance.

The invention relates to the technical field of artificial intelligence and new energy management, in particular to a battery pack intelligent health management method, device and equipment based on a dynamic space-time diagram neural network and a computer storage medium. According to the battery pack intelligent health management method based on the dynamic time-space diagram neural network, multi-source and multi-mode data in the operation process of the battery pack are fully fused, a dynamically evolved diagram structure is constructed to describe a complex coupling relation and a degradation propagation path between battery cells, a GRU mechanism is introduced to model state evolution characteristics in a time dimension, and the battery pack intelligent health management method based on the dynamic time-space diagram neural network is obtained. The method adapts to different battery working conditions through a'pre-training-fine tuning 'migration strategy, and is finally deployed in a battery management system (BMS) to realize online health monitoring and intelligent fault early warning. The method effectively improves the precision, stability and generalization ability of health assessment of the battery pack, and overcomes the technical bottlenecks that a traditional method cannot dynamically sense the state evolution of the battery cell and is difficult to adapt to a complex operation environment.

The invention provides a highway situation awareness method and system, and the method comprises the following steps: collecting camera video stream data to extract traffic flow data and parking data, and inputting the traffic flow data into a graph neural network to construct a traffic flow propagation model; constructing an abnormal event influence evaluation model based on the recurrent neural network and the long-short-term memory network; and through an abnormal event influence evaluation model, outputting influence range data including an affected road segment set and predicted abnormal recovery time, integrating the data and outputting the data to a visual interface. According to the method, the traffic flow state of the expressway is accurately evaluated by collecting, processing and analyzing the video stream data of the roadside camera, and a reliable situation awareness model is constructed in combination with toll station entrance and exit data, portal snapshot data and the like, so that real-time and accurate monitoring and prediction of the traffic condition of the expressway are realized, powerful decision support is provided for traffic management, and the traffic flow state of the expressway is accurately evaluated. And the operation efficiency of the expressway is improved.

The invention discloses a subway service robot real-time path planning method based on a graph neural network, and the method comprises the following steps: scanning the environment in a subway station, completing the map construction, and obtaining basic environment data; performing target detection and personnel statistics to form an environment and passenger flow fusion map; taking the fused map as input, setting a starting point and a target position, and outputting a global path search initial state; calling an improved A * algorithm to carry out node expansion, calculating a cost estimation function, and generating candidate paths; performing redundant node deletion and arc smoothing processing on the candidate path, performing step length dynamic adjustment, and outputting an optimized global path; performing local path planning by adopting an improved dynamic window method, and outputting an update path in real time; a passenger evacuation scheme is generated and is output through a display screen and voice broadcast, evacuation is guided, and passing is guaranteed. According to the invention, real-time path planning of the subway service robot is realized.

The invention relates to the technical field of forklift control, and discloses a refrigeration house unmanned forklift anti-skid control method and system based on multi-sensor fusion, and the method comprises the steps: synchronously collecting wheel angular velocity, vehicle body inertia data, motor current, vibration and acoustic signals through a multi-mode sensor, and carrying out the time alignment and feature extraction; inputting a time-space diagram neural network to estimate the friction coefficient and the optimal slip rate of each wheel in real time; and in combination with model predictive control, four-wheel independent torque distribution is optimized in a rolling manner under the condition that physical constraints are met, so that high-precision tracking and dynamic stability are realized. The system comprises a data acquisition module, a data processing module, a friction estimation module, a torque distribution module and an execution module. The attachment change can be sensed in advance, and the safety, efficiency and operation precision of the unmanned forklift in the wet and slippery refrigeration house environment are improved.

The invention discloses a lithium battery thermal runaway monitoring method and a related device, and relates to the field of lithium battery thermal runaway monitoring, and the method comprises the steps: obtaining a multi-sensing parameter time sequence of a target lithium battery; the multi-sensing parameter time sequence comprises a battery temperature time sequence, a battery voltage time sequence, an in-battery gas concentration time sequence and a battery deformation time sequence; inputting the multi-sensing parameter time sequence into a monitoring model to obtain the spatial-temporal characteristics of each sensing parameter; the monitoring model comprises a convolutional neural network, an LSTM network and an attention mechanism module which are connected in series; and monitoring the thermal runaway state of the lithium battery according to the spatial-temporal characteristics of the sensing parameters and the corresponding dynamic thresholds. According to the invention, the thermal runaway state of the lithium battery can be accurately monitored in real time, the occurrence of thermal runaway can be predicted in advance, and an early warning signal can be sent out in time.

The invention relates to the technical field of building monitoring, and provides an early warning method and system for pile foundation health state analysis. The method comprises the steps that a monitoring platform receives and processes various monitoring data from a multi-source sensor in real time, and data fusion and dynamic trend analysis are carried out on the various monitoring data by combining a graph neural network and a lightweight multi-head attention sequential network with a building structure of a target building to obtain an initial pile foundation evaluation result; uploading the initial pile foundation evaluation result of the target building in each geographic area and various monitoring data to a cloud data processing center; the cloud data processing center stores the initial pile foundation evaluation results of the target buildings in the geographic areas, and comprehensively evaluates the correlation trend between the target buildings in the geographic areas to obtain correction parameters; and the correction parameters are issued to a monitoring platform, the monitoring platform dynamically combines the correction parameters to update the pile foundation health state of the target building in each geographic area, and a target pile foundation evaluation result of the target building is obtained.

The invention relates to the field of traditional Chinese medicine diagnosis, and discloses a traditional Chinese medicine intelligent diagnosis system based on multi-source data fusion and an AI technology, and the system comprises a tongue picture collection and classification unit which is used for collecting tongue picture data of a patient through imaging equipment, carrying out the feature extraction of the tongue picture data, and obtaining a tongue picture feature data set; performing tongue picture pathological mode classification on the tongue picture feature data set based on a deep convolutional neural network to obtain tongue diagnosis identification result data; and the face diagnosis feature correlation analysis unit is used for inputting the tongue diagnosis identification result data into a multi-modal data fusion engine and carrying out face diagnosis pathological feature correlation analysis based on a graph attention network to obtain face diagnosis identification result data. The deep semantic understanding is realized by introducing a plurality of data acquisition modes such as three-dimensional imaging, thermal imaging, micro-expression recognition, spectral information and pulse condition harmonic analysis and combining advanced models such as a graph neural network, U-Net and Bi-LSTM.

The invention discloses a tuna pond culture strategy optimization method and system based on meteorological influence analysis, and the method comprises the steps: collecting regional meteorological data and pond culture monitoring data, and constructing a multi-modal pond ecological feature vector; establishing a weather-water body dynamic coupling model by using a space-time diagram neural network, and generating water body situation response prediction information; a breeding regulation and control strategy is made based on the prediction information, and strategy self-adaptive optimization is achieved through real-time monitoring data; evaluating the anti-disaster capability of the tuna after the meteorological influence is finished, screening high-quality germplasm resources by combining genetic analysis, and generating an anti-disaster breeding scheme. According to the method, full-chain optimization from meteorological early warning to culture regulation and control to genetic breeding is achieved, and the climate toughness and economic benefits of tuna pond culture are comprehensively improved.

A real-time badminton action detection system, consisting of: a video recording module configured to continuously record video images at a frame rate of at least thirty frames per second; a pose estimation processing unit configured to detect and output two-dimensional skeletal landmark coordinates for a variety of body joints, including at least wrists, elbows, shoulders, hips, knees and ankles, from each video frame; a Motion Bidirectional Encoder Representation Transformer (Motion-BERT) configured to receive sequential skeleton landmark coordinates over a defined time window and encode motion trajectories using multi-head self-attention mechanisms across past and future frames; and a classification controller module operationally coupled to the Motion-BERT, wherein the classification controller module comprises a dense neural network with a softmax output layer configured to generate real-time probability distributions over a variety of badminton-specific action classes, the end-to-end system being configured to produce recognition results with a processing latency of less than 100 milliseconds; and wherein the video recording module comprises a high-speed digital camera with a wide-angle lens positioned at a point on the perimeter of the court, the camera being calibrated with intrinsic and extrinsic parameters for perspective correction, and wherein the system includes a calibration routine that aligns detected skeletal landmarks with a reference badminton court coordinate system.

The invention discloses a wind power plant energy management system and a dispatching optimization system, and belongs to the field of wind power generation. The system comprises a data acquisition module, a wind speed prediction module, a wake effect analysis module, a power prediction and distribution module, an optimization scheduling module, a dynamic adjustment module, an energy efficiency evaluation module and a communication control module which work cooperatively. Through multi-source data fusion and dynamic collaborative optimization, the comprehensive performance of the wind power plant is remarkably improved, on the operating efficiency level, the system combines the space-time convolutional neural network and the multi-target optimization algorithm, high-precision prediction of minute-level wind speed and optimal distribution of whole-field power are achieved, energy loss caused by the wake effect is effectively reduced, and the wind power generation efficiency is improved. The output strategy is dynamically adjusted according to the health state of the fan, and the fatigue loss of the equipment is delayed while the generating capacity is maximized; on the power grid adaptability level, a self-learning mechanism based on the frequency disturbance qualified rate is introduced, and frequency modulation response parameters are optimized in real time.

The invention relates to the technical field of cable asset health management and predictive maintenance, and discloses a cable discharge signal blind separation and enhancement processing method based on an adversarial network, and the method comprises the steps: building a multi-modal monitoring data set through collecting mixed signals and environment data in cable operation; blind separation of discharge signals is realized by using the generative adversarial network, and prior information is not needed; identifying the number of potential signal sources through covariance analysis and double-criterion estimation; iterative optimization and signal enhancement are carried out in combination with a graph neural network and variational reasoning; and finally, through multiple cross validation and quality correction, an enhanced signal with high reliability is output. According to the method, the signal processing technology is deeply fused with asset management, risk prediction and operation and maintenance decision, weak discharge signals can be effectively separated and enhanced under the condition of low signal-to-noise ratio, the accuracy and reliability of cable early fault diagnosis are improved, and credible data support is provided for cable asset health state assessment, risk prediction and operation and maintenance decision.

The invention relates to the technical field of medical image classification, in particular to a myopic macular traction lesion grading method and system. The method comprises the following steps: taking a convolutional neural network, a direction perception attention module and a classifier which are connected in sequence as an MTM classification model; a direction perception attention module extracts weight information of a space position through a direction perception space attention module, and a channel attention module is used for extracting weight information of a channel; an MTM classification model is used as a backbone network, direction perception attention modules and auxiliary branches which are connected in sequence are arranged after first M-1 feature coding stages of a convolutional neural network, and a self-distillation model is constructed; by combining a structural knowledge distillation strategy based on multi-stage feature fusion, a historical knowledge distillation strategy based on a linear growth mechanism and a category perception comparison learning strategy, multi-angle feature information interaction is fully utilized, multi-angle information collaborative optimization is realized, and the classification precision of the MTM classification model is effectively improved.