141results about How to "Improve fitting ability" patented technology

The invention discloses a high-precision granary volume calculation method and system, and relates to the technical field of laser radar technology and point cloud processing, and the method comprises the following steps: data collection; laser radar equipment is used for carrying out omnibearing scanning on a target object, and a laser point cloud data set is obtained; preprocessing the data; performing point cloud segmentation; object recognition; point cloud precision compensation: performing precision compensation on the point cloud data, the precision compensation including error compensation of laser radar precision along with distance and temperature changes; volume calculation: performing volume calculation on the recognized regular object by adopting a volume calculation formula; for the recognized irregular object, a three-dimensional grid model of the object is created through a three-dimensional model reconstruction algorithm, the grid model is adjusted, and then the volume of the grid model is calculated; according to the method, optimization is carried out from the two aspects of radar distance and temperature compensation, an error model is established, in the model, primary functions are designed from the two aspects of temperature and distance, and the precision is improved from the two aspects at the same time.

The invention discloses a craniocerebral injury degree diagnosis auxiliary system based on a medical image, and relates to the technical field of medical treatment, a primary judgment module can accurately judge whether a patient has the risk of interstitial encephaledema or not by analyzing the accumulation degree of interstitial fluid in white matter and quantitatively calculating a penetration anomaly coefficient Syxs, the ability of early risk screening is provided, and the risk of interstitial encephaledema can be accurately judged. Potential problems can be recognized in time before disease deterioration, a clinician is prompted to intervene rapidly, and therefore the prognosis effect of a patient is remarkably improved. When the risk of interstitial encephaledema exists, the type diagnosis module further distinguishes lesion types (such as brain contusion or other injuries) by extracting related distinguishing features in a multi-modal feature set, calculates a locking coefficient Sdxs, and provides a scientific quantitative basis for diagnosis of lesion types based on specific features of the lesions. According to the accurate type diagnosis method, diagnosis errors can be reduced, and reliable support is provided for clinical decision making.

The invention discloses a model training method and an infrared weak and small target detection method, a trained model takes a Yolov3 model as a framework, and a detection layer corresponding to a large-size feature map in the Yolov3 model is cut off, so that the model focuses on small and medium targets of an image; a channel attention mechanism and a space attention mechanism are further utilized, shallow layer features extracted from a backbone network of a Yov3 model are regarded as effective features, the shallow layer features are utilized to guide middle layer features, the model selectively pays attention to more important features when weak and small targets are detected, effective features of other layers are embedded, detail information of images is effectively utilized, and the detection accuracy of the weak and small targets is improved. The fitting capability and the detection performance of the model are enhanced; in addition, a joint loss function is established, the scale sensitivity of weak and small target position regression on similarity measurement is relieved, multiple measurement modes make up each other, a position prediction frame is guided from multiple angles, and the accuracy of prediction of the model on the final position of the target is optimized.

The invention discloses an end-to-end automatic driving decision planning model and device combining a vectorized map and multi-task feature embedding. The end-to-end automatic driving decision planning model comprises six task branches of different modules such as perception, decision and control. An end-to-end automatic driving framework is utilized to reduce errors between different model transmissions, and a multi-task constraint mode is utilized to improve the fitting ability of the model. Vectorized map and aerial view target detection are combined to serve as perception representation of a multi-task model, dynamic and static target information needed in aerial view space is provided, environment perception information and decision navigation point output are unified to the same space, and model prediction precision is improved. Information transmission is performed by using a cross attention mechanism between different tasks, training conflicts caused by simple sharing of feature maps in a traditional multi-task model are overcome, efficient coupling between different tasks is realized, and model prediction precision is improved.

The invention discloses a water supply network flow prediction method based on time-invariant feature extraction, relates to the technical field of water supply network flow prediction, and provides a water supply network flow prediction model based on time-invariant feature extraction. Acquiring a time-invariant signal and a time-varying signal based on the high-frequency signal and the low-frequency signal; then a feature extraction module obtains time-invariant features and time-varying features based on the time-invariant signals and the time-varying signals; the flow prediction module obtains predicted water supply network flow based on the time-invariant features and the time-varying features; the time-varying features and the time-invariant features are processed separately, so that the respective features of the time-varying features and the time-invariant features can be captured more accurately; according to the method, the frequency domain signals are extracted from the time domain signals by using fast Fourier transform and inverse transform thereof, and are divided into the time-varying signals and the time-invariant signals, so that the performance of the model is improved, and the accuracy of flow prediction of the water supply network is improved.

The invention discloses a submarine pipeline vortex-induced vibration analysis method based on multiple Fourier characterization PINN, and the method comprises the steps: constructing a physical information neural network, determining a loss function of an initial condition, a boundary condition and a partial differential equation (PDEs) according to a submarine pipeline vortex-induced vibration model, and adding an anchor point to correct the network, so as to improve the fitting capability of the network; a Fourier transform technology is adopted, the key frequency of vibration and the frequency value of the key frequency are accurately identified, a Fourier mapping # imgabs0 # function is introduced, and a multiple Fourier mapping network is constructed to carry out refined mapping decomposition and feature extraction on vibration signals; according to the number and the value of the key vibration frequency, the mapping times and the hyper-parameter are dynamically adjusted to overcome the limitation of the PINN in processing complex vibration signals; integrating the spatial-temporal characteristics through point-by-point multiplication, and outputting a vibration learning result; according to the method, the analysis precision is improved, the capability of processing various high and low frequency superposition vibrations is enhanced, and the problem of spectrum deviation during high-frequency information learning is effectively solved.

The invention provides a soil quick-acting potassium measuring method and system and a medium, and relates to the technical field of soil data measurement, and the method comprises the following steps: extracting near infrared spectrum data of soil to be measured; solving Euclidean distances between one row and other rows in the spectrum matrix, and taking the number of distances smaller than a preset threshold value as the number of neighbors of the row; traversing the spectrum matrix, constructing a neighbor number array, normalizing a density vector, and transposing and assigning the density vector as an initial weight of a competitive adaptive reweighted sampling (CARS) method; determining an optimal regularization parameter through a Bayesian optimization method, fitting a Lasso model, obtaining a coefficient matrix of the Lasso model, and determining a regression coefficient of each spectral feature; and screening spectral features with non-zero regression coefficients in the near infrared spectral data of the soil to be detected to form an effective feature matrix. According to the method, the calculation complexity of the CARS method is reduced, parameter setting is simplified, overfitting is prevented, the model fitting precision is improved, and the prediction performance of soil available potassium measurement is improved.

According to the missile-target matching planning method and device based on deep reinforcement learning and the medium, the deep reinforcement learning algorithm based on the DQN is provided for the characteristics of large solution space, discretization, dynamic performance, nonlinearity and the like of a firepower-target distribution problem, the six-layer full-connection feedforward neural network is combined with the Q-learning algorithm, and the firepower-target distribution problem is solved. According to the method, the perception ability of deep learning and the decision-making ability of reinforcement learning are fully exerted, through model performance test comparison, the method is high in fitting ability, high in convergence speed and small in variance jitter, the distribution result conforms to combat expectation, and a certain reference can be provided for commander firepower attack problem decision making. The method has remarkable advantages in solving the problem of dynamic resource scheduling and distribution, the ammunition-target distribution efficiency can be effectively improved, and the overall combat benefit is maximized.

The invention relates to the field of artificial intelligence, in particular to a collagen peptide absorptivity prediction method. Comprising the following steps: acquiring a collagen peptide sample data matrix, and constructing a convolutional neural network and a recurrent neural network to obtain a molecular structure feature vector and a time sequence feature vector; constructing a prediction neural network, inputting the molecular structure feature vector and the time sequence feature vector into an interactive feature fusion layer, and obtaining a fused feature vector by using an interactive feature fusion algorithm; inputting the fused feature vector into a self-adaptive decoupling layer, and calculating by using a self-adaptive feature decoupling algorithm to obtain a decoupled feature vector; and inputting the decoupled feature vector into an output layer to obtain a predicted value of the collagen peptide absorptivity. The technical problems that the molecular structure feature extraction capacity is insufficient, the complex interaction relation between local molecular structures cannot be flexibly captured, feature extraction is not deep enough, and the accuracy of collagen peptide absorptivity prediction is affected are solved.

The invention discloses a comprehensive energy operation and maintenance management system based on a smart park, which belongs to the technical field of energy operation and maintenance management and comprises a data acquisition and exchange module, a data analysis and prediction module, an auxiliary decision module, an intelligent scheduling module, a micro-grid management module, an operation and maintenance simulation module, an operation and maintenance management module and a real-time feedback module. Characteristics related to the energy demand are selected through the Pearson's correlation coefficient matrix of the data analysis and prediction module, the model is constructed through the technologies of difference, autoregression, moving average and the like, the trend and periodic changes of the energy demand can be effectively captured, the weighted model result can accurately predict the future energy demand, and the prediction accuracy is improved. The park energy management is facilitated, various decision-making schemes are generated through the auxiliary decision-making module according to the result of the data analysis and prediction module and through predefined decision-making rules and logics, the schemes are evaluated according to preset evaluation standards, decisions are provided for park managers, and the decision-making efficiency and quality are improved.

The invention discloses a false data injection attack detection method and device. The method comprises the steps that power grid measurement data are acquired, and the power grid measurement data comprise multiple types of power data; power grid measurement data are analyzed through an ensemble classification detection model, an output vector value is obtained, and the ensemble classification detection model is obtained through machine learning training of multiple sets of data; each group of data in the multiple groups of data comprises historical power grid measurement data and a label for indicating whether the historical power grid measurement data is false data injection attack data; and determining whether the power grid measurement data is attacked or not according to the size of the output vector value, and processing the attacked data. The technical problems that in the prior art, a false data injection attack detection method for power system state estimation is insufficient in fitting capacity, and the polluted power grid state quantity cannot be accurately recognized are solved.

The invention belongs to the technical field of remote sensing image classification, and particularly relates to a hierarchical progressive hyperspectral image classification method based on FKAN. The method comprises the following steps: S1, dividing a hyperspectral image data set with labels into a training set and a test set, and processing the training set to obtain a global-level sample, a local-level sample and a pixel-level scale sample; s2, constructing a hierarchical progressive fusion network model, wherein the hierarchical progressive fusion network model comprises a global information branch, a local feature extraction branch and a pixel-level feature extraction branch; s3, training the hierarchical progressive fusion network model by using the total loss function to obtain a trained hierarchical progressive fusion network model; and S4, inputting the test set into the trained hierarchical progressive fusion network model to obtain a corresponding prediction classification result. According to the method, the artificial weight distribution of the multi-branch network is reserved, so that actual classification scenes with different requirements on spectral information and spatial information are flexibly adapted.

The invention discloses a carbon nanotube mechanical property analysis method based on machine learning molecular dynamics, and relates to the technical field of carbon nanotube mechanical property analysis. The diameter, the length and the defect proportion serve as variables to construct a structure parameter library; the temperature and the strain rate serve as supplementary variables to establish a tensile model parameter library; carrying out molecular dynamics simulation analysis on tensile mechanical properties; drawing a stress-strain curve and extracting key parameters; establishing a parameter association library between the structural parameters and the mechanical properties by using a machine learning method; selecting a machine learning algorithm to predict mechanical properties; and extracting a function relationship through the trained machine learning model to establish a fitting function. Starting from the relationship between different diameters, lengths, defect proportions, temperatures and strain rates and the mechanical properties of the carbon nanotubes, the optimal structure parameters of the carbon nanotubes under specific conditions are obtained through machine learning, the calculation amount is greatly reduced, the experiment cost is saved while the effectiveness of the model is ensured, and the research efficiency is remarkably improved.

The invention provides an intelligent early warning method and system for underground engineering dynamic disasters, and relates to the technical field of underground engineering dynamic disaster early warning, and the method comprises the steps: obtaining the microseismic historical monitoring data of underground engineering; preprocessing the micro-seismic historical monitoring data, obtaining related time sequence parameters, and obtaining a reconstruction signal; acquiring a plurality of rolling statistical characteristics of the reconstructed signal; selecting a preset number of rolling statistical features according to the importance degrees to form a rolling statistical feature matrix; constructing an underground engineering dynamic disaster prediction model; inputting the rolling statistical feature matrix data set into an underground engineering dynamic disaster prediction model for training; acquiring real-time micro-seismic monitoring data; extracting a real-time rolling statistical feature matrix data set; and inputting the real-time rolling statistical feature matrix data set into the trained underground engineering dynamic disaster prediction model, and outputting a disaster early warning result. According to the invention, efficient, accurate and intelligent early warning of underground engineering dynamic disasters is realized.

The invention discloses a forest fire point detection method based on a KAN network and multi-sensor fusion. The forest fire point detection method comprises the following steps: S10, configuring a plurality of sensors in fire point detection equipment for data acquisition; s20, transmitting the acquired data to a multi-sensor fusion model based on a KAN network for data fusion, and fusing the data into one piece of data as decision data for forest fire point detection; and S30, performing fire point generation early warning processing by using the decision data of forest fire point detection. According to the method, the detection of the fire points in a large forest can be more accurately realized.

The invention discloses an arbitrary-scale image super-resolution reconstruction method based on local features. According to the invention, two efficient plug-and-play modules are designed and can be combined with an existing fixed-scale super-resolution network so as to realize a super-resolution task of any scale. Wherein the scale perception feature adaptive module (SLFAM) solves the problem of lack of adaptability to the scale and the local structure of an image in the feature extraction process by generating a scale perception feature adaptive dynamic convolution kernel; the local feature adaptive up-sampling module (LFAUM) fuses scale information, projection position coordinates, local features, receptive field offset and other information in the up-sampling reconstruction process to generate a deformable up-sampling convolution kernel, and the function of up-sampling reconstruction of any scale is achieved. The method is mainly applied to the technical field of image super-resolution reconstruction, and has wide application prospects in the fields of remote sensing satellite images, medical images, security monitoring and the like.

The invention discloses a deep learning-based abrupt slope bridge stability evaluation method and system. The method comprises the following steps of S1, obtaining bridge area DEM data, bridge displacement data and bridge stress data; s2, constructing a bridge stability evaluation network, and extracting bridge region DEM features based on a convolutional neural network; s3, extracting internal structure features of the bridge based on the recurrent neural network; s4, fusing the DEM features of the bridge region and the features of the internal structure of the bridge based on an attention mechanism; and S5, setting input, output and optimization targets of the network, and optimizing parameters of the bridge stability evaluation network based on an adaptive learning rate optimization algorithm. According to the scheme, the problem of insufficient bridge stability evaluation accuracy is solved.

The invention relates to the technical field of picture processing, and discloses an astronomical image splicing method and device based on deep learning, equipment and a medium, and the method comprises the steps: carrying out the key point detection of a preprocessed original image based on an XFat neural network, and obtaining the pixel coordinates of a corresponding key point; wherein the original image comprises a first image and a second image; feature extraction is carried out based on the pixel coordinates, and key point feature descriptor vectors are output; matching the nearest neighbor of each key point feature descriptor vector in the first image in the second image, generating a matching candidate set of rough matching, and performing offset prediction based on the matching candidate set of rough matching; optimizing and adjusting the matching result based on the predicted offset to obtain a finely matched key point pair set; calculating a homography matrix based on the key point pair set; and carrying out image transformation and fusion based on the homography matrix. The key points of the astronomical image can be accurately extracted and matched, and the splicing quality and effect are improved.

The invention provides a single-valued transient electromagnetic apparent resistivity calculation method based on deep learning, and the method comprises the following steps: a), carrying out the normalization processing of an actually-measured induced voltage, and obtaining a normalized induced magnetic field; b) a deep neural network model comprising an input layer, a plurality of hidden layers and an output layer is constructed, the input layer receives the normalized induced magnetic field, and the output layer outputs transient field parameters; c) training the deep neural network model by using a Nadam optimization algorithm, wherein a training sample set comprises multiple groups of actually measured induced voltages and transient field parameters corresponding to the actually measured induced voltages; and d) inputting the actually measured induced voltage to be measured into the trained deep neural network model, obtaining the output transient field parameters, and calculating the apparent resistivity according to the theoretical formula of the transient electromagnetic field. Compared with a traditional method, the method has the advantages that the fitting capacity of nonlinear data is higher, and the transient electromagnetic apparent resistivity can be solved more accurately.

The invention discloses a rehabilitation training data processing method and device, and relates to the technical field of medical information data processing, and the rehabilitation training data processing method comprises the following steps: 1, data acquisition and preprocessing: collecting and preprocessing physiological, log and video data of a to-be-rehabilitated user, and integrating the physiological, log and video data into a multi-source data set; 2, high-performance model construction and knowledge distillation: selecting and training a teacher network model, constructing a student network model, and obtaining a model with relatively good performance and high calculation efficiency through knowledge distillation; step 3, differential evolution algorithm optimization: defining differential evolution algorithm parameters, and obtaining an optimized student network model through iterative optimization; and step 4, deep reinforcement learning parameter adjustment: utilizing the optimized student network model to generate feature data, and adjusting rehabilitation training parameters through reinforcement learning. The data processing efficiency and accuracy are remarkably improved, and the complexity is reduced.

The invention discloses an integrated circuit worst performance processing method, and relates to the field of integrated circuits, and the method comprises the steps: employing a corrected normal distribution cumulative distribution function CDF to describe the nonlinearity between the failure rate and the circuit performance, and introducing a skewness parameter and a kurtosis parameter; and carrying out weight calculation on the sampling points, highlighting important samples near the failure boundary, and constructing a local linear model in a local region by adopting weighted least square regression. On the global scale, logarithmic transformation is carried out on a sampling matrix, feature distribution is converted from nonlinearity to approximate linearity, an orthogonal matching pursuit algorithm is adopted to construct a sparse global linear model, and the generalization ability and interpretation of the model are improved. Finally, according to the method, a circuit performance predicted value at 6 sigma calculated by a corrected Gaussian function is taken as a target, a global or local linear model is flexibly selected as a constraint condition according to the position of a worst performance point, an optimal solution is iteratively solved, and the estimation precision and the calculation efficiency are effectively balanced.

The invention provides a logistics state prediction method based on spatial-temporal characteristics. The method comprises the following steps: acquiring historical production logistics time sequence data, historical production logistics state sequence data and historical logistics states from a workshop information system; analyzing the workshop layout description file of the production workshop system to generate a workshop layout topological structure; based on the workshop layout topological structure, performing feature extraction on historical production logistics time sequence data and historical production logistics pattern sequence data to obtain historical logistics time features and historical logistics space features; the production logistics state space-time model predicts the logistics state based on the historical logistics time features and the historical logistics space features to obtain a predicted logistics state; and according to the historical logistics state and the predicted logistics state, optimizing model parameters of the production logistics state space-time model until a training ending standard is reached.

The invention belongs to the technical field of remote sensing, and relates to a multi-source data fused high-spatial-resolution vegetation leaf area index estimation method. The method comprises the steps of generating a modeling data set based on a physical radiation transmission model, constructing an LSTM-PGeff model, constructing an LSTM-TLeff model and an LSTM-TLtrue model which are subjected to migration training, and packaging, converting, splicing and storing an LAI remote sensing estimation model. According to the method, simulation data is generated by using a radiation transmission model, migration measured data set knowledge is used for deep learning training to increase physical constraints, the fitting ability of an LAI remote sensing estimation model to a complex nonlinear regression relationship is improved, and the model precision is effectively improved; the generated LAI product has high spatial resolution, the uncertainty caused by the problem of mixed pixels in a coarse spatial resolution algorithm is reduced, and the accuracy of LAI remote sensing estimation is greatly ensured.

The invention relates to a resource allocation method and system based on cloud edge collaboration. Historical to-be-processed data is acquired and input into a data prediction model for training; the data prediction model predicts the to-be-processed data of each terminal device, pre-splits the predicted to-be-processed data, matches the corresponding edge nodes according to the data type and data volume involved in the pre-split information, collects the to-be-processed data of each terminal device in real time, compares the real-time to-be-processed data with the predicted to-be-processed data, and determines the to-be-processed data of each terminal device. When the real-time to-be-processed data exceeds the prediction, the exceeding part is split again, otherwise, different data units are obtained through direct splitting, and the same type of data units obtained through splitting are packaged and transmitted to matched edge nodes; and each edge node generates a result after processing, returns the result to the relay node, splits each processing result data packet, integrates the processing result data packet according to the processing result of the same data source, and returns the integrated processing result data packet to the equipment terminal. And collaboration between cloud side resource allocation and data generated by large-scale terminal equipment is realized.

The invention discloses a workpiece surface roughness prediction method, system and device and a storage medium, and relates to the technical field of workpiece surface roughness prediction, and the method comprises the steps: obtaining a machining section signal in an original vibration signal of a workpiece; calculating the characteristics of the processing section signal; based on a random forest method, screening out important features with high relevancy with the surface roughness; performing feature dimension reduction on the related important features through a principal component analysis method to obtain a low-dimensional feature matrix; combining the low-dimensional feature matrix with a corresponding surface roughness index to obtain a data set, and removing data with abnormal values in the data set to obtain a normal data set; and training the MKL-SVR model by using the normal data set so as to predict the surface roughness of the workpiece. According to the method, a small sample condition optimized feature screening and dimension reduction method is adopted, the number of features can be reduced to a great extent, data information is reserved, and the model effect is improved.

The invention discloses a power grid optimization scheduling method and device based on wind power prediction model dynamic selection, and the method comprises the steps: obtaining a prediction error probability density function of each wind power prediction model based on a plurality of wind power prediction models; acquiring real-time meteorological data of the wind turbine generator, performing power prediction based on a plurality of wind power prediction models to obtain a plurality of wind power real-time prediction values, and generating a wind power real-time prediction scene set in combination with a corresponding prediction error probability density function; and on the basis of a plurality of wind power real-time prediction scene sets, real-time control strategies corresponding to the scene sets are generated through a random unit combination model, and the real-time control strategy with the lowest sum of wind curtailment and load loss of wind power in a plurality of real-time control strategies is selected as a control strategy after optimization of the wind turbine generator. And carrying out random unit combination on the basis of scene sets generated by the multi-prediction model, generating a plurality of real-time control strategies in combination with the influence of meteorological factors, and finally selecting a strategy with the lowest value of the sum of wind curtailment and loss load of wind power as an optimization control strategy.

The invention provides a ship detection method based on a ViT architecture and a visual state space model, and the method comprises the steps: improving a backbone network: designing a brand-new visual Transform block, employing a part of convolution as a token mixer, and fusing different spatial position information at lower cost; and feature enhancement is improved: a VSS Attention block based on a visual state space is designed, and the VSS Attention block is composed of a state space model series with a feed-forward network and is used for enhancing global and local features through residual connection, so that the feature fusion module better fuses the features. According to the method, a Backbone network output feature is processed by adopting a VSS Attention block based on an SSM, and nonlinear transformation is carried out on a fused global feature through a forward network, so that the fitting capability of a model is improved. Meanwhile, an experimental verification result shows that the detection effect of the method is greatly improved compared with that of an algorithm before optimization no matter in ship target detection under complex background, multi-scale and dense arrangement scenes.

The invention belongs to the technical field of information recommendation, and particularly relates to an intelligent image recognition and commodity classification system. Comprising an image acquisition module, an image processing and feature extraction module, a deep learning model training module, a commodity classification and identification module, a user interface module, a database module, a system integration and deployment module, an update and maintenance module and a security module. The invention provides an intelligent image recognition and commodity classification system, and a multi-layer perceptron is adopted as a feature representation unit in the intelligent image recognition and commodity classification system, so that the system can capture a more complex nonlinear relationship in an image. Therefore, abstract features in the image can be better expressed, and the recognition capability of the system on complex modes is improved.

The invention discloses a drilling pump pressure prediction method based on an artificial neural network, and the method comprises the following steps: S1, data collection; s2, data preprocessing; s3, constructing a neural network model; s4, model training and optimization; and S5, model verification and deployment. According to the method, multi-channel data fusion and time synchronization optimization are innovatively adopted, so that the data quality and consistency are improved; in combination with a deep neural network and a self-adaptive optimization strategy, the precision and generalization ability of pump pressure prediction of the drilling pump are improved; and an online updating mechanism is introduced, so that the model can be dynamically optimized according to real-time data, the defects of low prediction precision, poor adaptability and difficulty in real-time updating of a traditional method are overcome, and an efficient and reliable prediction means is provided for intelligent drilling control.

The invention discloses a performance state evaluation method and device based on a space-time attention mechanism and electronic equipment, and the method comprises the steps: converting equipment operation monitoring performance degradation data into three-dimensional time series data through employing a detection data sliding window reconstruction method; according to the relationship between the physical layout of the sensor and the equipment structure, the performance monitoring sensor is graphically expressed as a graph neural network adjacency matrix; constructing a space-time attention graph-based convolution STAGCN model, and inputting the three-dimensional time sequence data and the graph neural network adjacency matrix into the STAGCN model for training to obtain a trained STAGCN model; and performing performance state evaluation on to-be-evaluated equipment based on the trained STAGCN model.