374 results about "Signal prediction" patented technology

The invention discloses an intelligent early warning method for pipeline blockage of a slurry circulation system of a slurry shield, which relates to the field of intelligent early warning, and comprises the following steps of: performing spatial-temporal feature analysis on a standardized multi-dimensional data stream, constructing a blockage feature knowledge graph based on pipeline position and time sequence correlation analysis, and generating a blockage feature vector through a graph neural network; based on the blockage feature vector, analyzing the dynamic change trend of particle distribution through a long-short-term memory network and predicting the particle blockage risk in combination with an acoustic signal, then performing adaptive judgment by fusing geological conditions and construction stage information to obtain a risk assessment result, and inputting the risk assessment result and the blockage feature vector into digital twinborn simulation to obtain the particle blockage risk. A blockage scene is predicted based on fluid dynamics and a particle sedimentation model, early warning parameters are adjusted through Bayesian optimization, and graded early warning signals are generated; according to the invention, by generating the blockage feature vector, the recognition capability of the early local abnormal propagation trend is enhanced, and a reliable basis is provided for accurately predicting the blockage risk.

The invention discloses an intelligent multi-gas detection module data processing system and method based on NDIR, and relates to the technical field of gas detection.The method comprises the steps that a multi-wavelength NDIR sensor is used for obtaining light intensity changes of a gas sample under different wavelengths, and original spectral signals are generated; performing denoising processing on the spectral signal by adopting wavelet transform, and performing zero calibration and dynamic baseline deduction; based on the Beer-Lambert law in combination with environmental factors, establishing a relation model between gas absorption and spectral signals; updating model parameters by using a recursive least square algorithm, and continuously optimizing gas concentration prediction; separating gas signals by adopting a non-negative matrix factorization algorithm, and predicting the concentration of each gas; and the edge end operates the lightweight model in real time, and regularly uploads the model to the cloud end for global optimization and federated learning. The method can effectively improve the condition that the precision is insufficient when the model is used for a long time in the prior art.

The invention relates to a vehicle vibration response prediction method based on multi-modal feature depth fusion, which belongs to the field of computer vision and signal processing, and is characterized by comprising the following steps: constructing a vehicle vibration excitation and response triple data set based on multi-modal data; constructing a vehicle vibration response prediction model based on multi-modal feature deep fusion; training, verifying and testing the vehicle vibration response prediction model; and predicting a vehicle vibration response signal. According to the method, the problems that the traditional road excitation measurement precision is relatively poor and the calculation complexity and the structure fineness are difficult to balance by vibration signal prediction are solved, and the image feature extraction advantage of an EfficientNet framework and the time sequence feature extraction advantage of a Transformer framework are applied to the regression prediction of the vehicle vibration response signal; multi-modal features are fused through a bidirectional cross attention mechanism obeying Dirichlet distribution, and high prediction accuracy is obtained. And a method with relatively high prediction accuracy is provided for the field of vehicle vibration response signal prediction.

The invention discloses a head-mounted brain body workability assessment method based on a space-time dynamic fusion network, belongs to the technical field of artificial intelligence and human body signal acquisition, and solves the problems that an existing method cannot comprehensively reflect the comprehensive state of an individual, and interaction and potential risks among multiple factors are difficult to reveal. The method comprises the steps that physiological parameter signals are collected based on wearable equipment, and an attention and fatigue prediction result is output by an LSTM prediction model; according to the method, the graph structure data packet is analyzed and processed based on the pre-constructed space-time dynamic fusion network model, the working state signal characteristics of the plateau high-risk operating personnel can be accurately evaluated, the space-time graph neural network (STGNN) can capture the complex relation, the high-dimensional topological characteristics are extracted, and the high-risk working personnel can be accurately evaluated. The dynamic event-driven pulse neural network (deSNN) can convert the pulse sequence features into pulse sequence features so as to describe feature values more accurately, iterative optimization enables the pulse sequence features and the pulse sequence features to cooperate, and the accuracy and reliability of time-space dynamic fusion network model evaluation are improved.

The invention relates to the technical field of modern precision machining and optical scanning, and discloses a motion control method and system of a laser galvanometer. The method comprises the steps that a real-time position signal is collected and preprocessed, and a filtered position signal is obtained; the deviation between the trajectory model and a preset trajectory model is calculated, when the deviation exceeds a threshold value, the trajectory model is identified as a complex trajectory segment, offset vector data is generated, and an offset compensation demand signal is generated accordingly; driving an instruction device in combination with historical data to obtain compensation parameters; when the deviation is lower than an updating threshold value, updating the trajectory model; a stable control signal is generated based on the optimization model and filtering signal prediction, and the environmental interference is calibrated and the signal smoothness is enhanced through the stable control signal; and finally, comparing the enhanced signal with the optimization model, and repeating the compensation process when the deviation exceeds the standard to obtain a final stable control signal. According to the method, through multi-level deviation processing and iterative optimization, the control precision and the anti-interference performance of the laser galvanometer in complex track movement are improved.

The invention belongs to the field of game joystick reset, and discloses a reset sensitivity setting method of a game joystick, a gamepad and a storage medium. Comprising the steps that a key parameter set is designed, the reset sensitivity of the game joystick is judged, the state of the game joystick is obtained, and a corresponding program is started; carrying out primary processing on the real-time data set to obtain a quality-improved data set; if the state of the game joystick is noise abnormity, dynamic center point calibration is carried out by using a quality increase data set; if the state of the game joystick is sensor drift abnormity, signal filtering and noise suppression are carried out by using a quality-increasing data set; if the state of the game joystick is that the response speed is abnormal, signal prediction compensation is carried out by using the quality increase data set; and if the rocker is recognized to return to the ideal center point, the maintenance processing is stopped, and if the rocker is recognized not to return to the ideal center point, the above steps are repeated until the rocker returns to the ideal center, and sensitivity adjustment of game rocker resetting is achieved.

The invention relates to the technical field of physiological signal prediction, in particular to a preoperative risk assessment method for the department of cardiology, which comprises the following steps: sliding window segmentation time sequence data to calculate a baseline offset, dynamic time warping alignment parameter fluctuation rate to generate an abnormal mark, and standard deviation comparison amplitude threshold triggering risk signals. K-means clustering multi-dimensional data mapping risk levels, isolated forest detection abnormal fluctuation and electrocardiogram and myocardial zymogram cross validation are combined, and a preoperative risk assessment conclusion is output. According to the method, individual differences and interferences are eliminated through a sliding window algorithm, a time difference problem is solved by aligning a multi-parameter fluctuation rate through dynamic time warping, a quantitative evaluation standard is established by comparing a standard deviation with an amplitude threshold value to avoid limitation of a single threshold value, and objective grading is realized by combining K-means clustering with an Euclidean distance. The isolated forest algorithm, the electrocardiogram ST segment and myocardial zymogram cross validation form a multi-modal evaluation system, and the risk evaluation sensitivity and specificity are improved in a complete closed-loop mode.

The invention relates to the technical field of mechanical arm control, and discloses a bionic self-adaptive variable-stiffness mechanical arm joint control method. The method comprises the steps that multi-source biological signals such as electromyographic signals, tendon tension signals and joint angle signals during joint operation are collected; constructing a stiffness feature vector based on the myoelectricity and tendon tension signals, and generating a motion trail sequence according to the joint angle signals; extracting a corresponding stiffness feature vector for each track point, and calculating stiffness sensitivity; constructing a bionic stiffness reference model containing a mapping relation between the stiffness feature vector and a joint angle signal, and dynamically weighting and adjusting the mapping relation by using stiffness sensitivity; predicting a joint stiffness change sequence based on the adjusted model and the real-time signal, and fusing the sequence with the current joint angle signal to generate a dynamic stiffness parameter; and calculating a driving torque correction amount according to the dynamic stiffness parameter and a preset safety threshold range, iteratively updating the model weighting parameter until the correction amount meets a convergence condition, and outputting a driving torque instruction to an execution mechanism.

The invention relates to the technical field of spraying control, in particular to an anti-corrosion steel pipe inner spraying track self-adaptive control system based on multi-sensor fusion. The feed-forward prediction module generates a feed-forward correction signal through a model compensator and a self-adaptive compensator and predicts and compensates system errors, the feedback control module comprises a track generator and a disturbance observer, a feedback control instruction is generated by comparing a correction track with an original track, an execution mechanism is dynamically adjusted, and the system error is predicted and compensated. The signal driving module adopts a frequency domain decoupling fusion technology, combines a feedforward correction signal and a feedback control instruction, generates a composite control instruction, and ensures the accuracy of trajectory tracking control. According to the invention, through a double-loop control architecture combining feedforward prediction and feedback disturbance suppression, high-precision and strong-robustness self-adaptive control of a spraying track under a complex working condition is realized.

The invention discloses an electrocardiosignal prediction method, system and device for an acute heart failure patient and a medium, and the method comprises the steps: obtaining a historical electrocardiosignal of the acute heart failure patient, generating a multi-modal signal comprising a feature enhanced electrocardiosignal, a dynamic feature and a power spectrum density, and constructing an acute heart failure sample data set; obtaining a pre-trained ECG signal prediction model, and training the model by using the acute heart failure sample data set based on transfer learning to obtain an acute heart failure ECG signal prediction model; the method comprises the following steps: acquiring an electrocardiosignal of a patient with acute heart failure in real time and preprocessing the electrocardiosignal to obtain a real-time multi-mode signal, and taking the real-time multi-mode signal as an input to predict an ECG signal within a future preset duration; by extracting a multi-modal signal as model input, the prediction precision and robustness of the ECG signal are remarkably improved; based on transfer learning, efficient and accurate ECG signal prediction is realized in an acute heart failure scene.

The invention discloses a digital pre-distortion method, system and device and a storage medium, and relates to the technical field of aerospace communication. The method comprises the following steps: acquiring a first input signal and a first actual output signal of the power amplifier, and acquiring a thermal state characteristic; constructing a three-dimensional dynamic baseline; superposing the detection sequence into the first input signal to obtain a second input signal, obtaining a corresponding second actual output signal, and predicting an ideal output signal of the second input signal; extracting a harmonic component generated after the detection sequence passes through a power amplifier, and determining a distortion early warning moment; recording a third input signal after the distortion early warning moment; constructing a virtual test signal according to the third input signal, and predicting to obtain a reference output signal; and comparing the difference between the distortion output signal and the reference output to obtain a distortion feature vector, constructing a dynamic increment compensation function, and correcting the signal processing flow of the power amplifier based on the dynamic increment compensation function. And the accuracy of digital pre-distortion is improved.

The invention relates to the technical field of artificial intelligence, particularly provides wearable equipment and an operation method thereof, a wearable intelligent system and a storage medium, and aims to solve the problem of how to timely and accurately obtain sentences which are not talked out by a user due to jamming and prompt the sentences. The method provided by the invention comprises the steps of collecting an electroencephalogram signal of a user and a target voice signal in an environment where the user is located, wherein the target voice signal comprises a first voice signal of the user; analyzing the speaking state of the user according to the first voice signal; when the speaking state is a pause state, according to the electroencephalogram signal and the target voice signal, predicting a missing utterance of the user during pause, and outputting prompt information; or, the electroencephalogram signal and the target voice signal are sent to the server, prompt information sent by the server is received and output, and the prompt information is generated by the server according to the utterance missed by the user during the jamming. By means of the method, the sentences which are not taught by the user due to jamming can be timely and accurately obtained and prompted.

The invention discloses a power distribution network fault early warning method and system based on online monitoring, and relates to the field of fault early warning, and the method comprises the steps: continuously collecting real-time electrical signals; signal waveform prediction of the real-time electrical signal is completed according to the real-time signal prediction result, and whether an early fault signal exists in the target power distribution network is judged; if the target power distribution network has the early fault signal, obtaining power distribution network information, environment prediction data and geographic position data; constructing a topological structure of the power distribution network, and extracting early fault information of the target power distribution network; constructing an icing evolution model of the target power distribution network; completing fault risk coupling between the icing evolution model and the early fault information; and carrying out risk accumulation analysis on the topological structure of the power distribution network, and outputting fault early warning information of the target power distribution network according to a risk accumulation analysis result. According to the invention, the power distribution network fault early warning precision and efficiency can be effectively improved.

The invention provides a power regulation method and device based on load feedforward, a medium and a product, and relates to the technical field of power regulation, and the method comprises the steps: carrying out the real-time monitoring of the working condition state of a target load, so as to obtain a load state signal, and the load state signal is used for representing the actual control information of the target load; the load state signal is input to a preset logic classifier to obtain a load type output by the preset logic classifier, and the load type is the type of a target load output after the preset logic classifier classifies the load state signal; predicting the state change trend of the target load according to the load type and the load state signal to obtain a load feedforward signal; and performing a power regulation operation according to the load feed-forward signal. According to the invention, the technical problem of low power regulation efficiency of the generator set in the case of load fluctuation in the prior art is solved, and the technical effect of improving the power regulation efficiency of the generator set in the case of load fluctuation is achieved.

The invention discloses a hydroelectric generating set vibration signal trend prediction method and system, and the method comprises the steps: S1, collecting vibration signals of key parts in the operation process of a hydroelectric generating set, and generating a vibration time sequence sample with a unified structure; s2, applying an EEMD (ensemble empirical mode decomposition) algorithm to each section of preprocessed vibration time sequence; s3, dividing the constructed data set into a training set and a test set; s4, constructing a time sequence prediction model based on BiLSTM and an attention mechanism; s5, training the model on the training set, using a mean square error as a loss function, and adopting an Adam optimizer to optimize network parameters; calculating a mean value and a standard deviation based on prediction errors of the training set, and setting upper and lower threshold values of early warning judgment; s6, applying the trained model to a test set, predicting an unknown vibration sequence, and if a prediction error exceeds a set threshold range, regarding that the trend is abnormal; according to the method, the problems of insufficient feature extraction capability, poor modeling effect and low prediction precision in the existing hydroelectric generating set vibration signal prediction are solved.

The invention discloses a multi-rotor unmanned aerial vehicle broken propeller fault rapid diagnosis and fault-tolerant stable control system and method, belongs to the technical field of unmanned aerial vehicle flight control, and aims to solve the problems that traditional broken propeller detection is high in cost and unreliable, power compensation robustness is insufficient and return flight logic is lacked. According to the system and the method, on the basis of a high-order nonlinear observation theory, rapid and accurate identification of the abnormal state of the unmanned aerial vehicle power system is realized by constructing a multi-modal signal prediction and residual evaluation system; the method effectively prevents the out-of-control, rolling and even crash of the unmanned aerial vehicle caused by power asymmetry, solves the problem that a traditional fixed control strategy is difficult to adapt to fault working conditions, and adapts to dynamic changes under complex working conditions such as hovering and cruising. Finally, closed-loop control from fault detection to safe return can be realized, the autonomous safe return capability of the unmanned aerial vehicle under the condition of the fault of the propulsion system is ensured, and the method is suitable for unmanned aerial vehicle application scenes with high reliability requirements, such as logistics transportation and inspection monitoring.

The invention discloses an optical communication network adaptive entropy loading method and device based on transfer learning, and belongs to the technical field of optical communication, and the method specifically comprises the steps of entropy loading model building, synthetic signal generation and model pre-training, experimental signal generation and model transfer learning, and adaptive entropy loading. In the whole process, the entropy distribution process of traditional entropy loading is replaced by the neural network, and the entropy approaching the channel capacity is predicted according to the received signal. A large number of synthetic signals are used for pre-training an entropy loading model, transfer learning is combined, the entropy loading model predicts the entropy of an unknown channel in the optical communication network in a self-adaptive mode, dependence of an existing entropy loading algorithm on the channel state is reduced, and therefore self-adaptive entropy loading of the optical communication network is achieved.

The invention discloses a sensor signal prediction method, system and equipment for a humanoid robot. The method comprises the following steps: acquiring a multi-source sensor training sample of the humanoid robot; training the heterogeneous neural network fusion model according to the multi-source sensor training sample through a signal amplitude loss function, a frequency loss function and a transient characteristic loss function to obtain a signal prediction model; obtaining current sensor signals of the humanoid robot, wherein the current sensor signals comprise at least two of a joint angle signal, a motor current signal or an acceleration signal; and inputting the current sensor signal into the signal prediction model, and outputting a predicted sensor signal which is a force sense signal or a torque signal. Through multi-source sensor signal fusion and multi-domain feature learning, accurate prediction of key sensor signals is realized, the number of deployed sensors is reduced, the cost is reduced, the system reliability is improved, and the method can be widely applied to the technical field of robots.

The invention discloses a control method and system for a vertical three-in-one production line used for PCB production, and relates to the technical field of PCB production control. Vibration signals on the production line are acquired, historical vibration data of the production line are utilized, a prediction model of the vibration signals is established through a long-short term memory network, and the vibration signals are predicted; predicting a future vibration signal of the current production line in PCB production according to the vibration signal, and adjusting and optimizing production process parameters according to a vibration signal prediction result and the real-time vibration signal; calculating an optimization effect coefficient after the process parameter adjustment is completed, and judging and evaluating whether the process parameter optimization is effective or not; if the technological parameter optimization is effective, the vibration signal of the production line is obtained again, whether the technological parameter needs to be continuously optimized or not is judged according to the vibration signal prediction result and the vibration signal of the production line, vibration of the production line is controlled, the possibility of potential influence on equipment of the production line is reduced, and the production quality of the PCB is improved.

The invention provides a Rowland time delay signal prediction method and system, electronic equipment, a program product and a storage medium. The method comprises the following steps: acquiring an initial Rowland time delay signal; extracting a periodic term of the initial Rowland time delay signal, and inputting the periodic term to a constructed multi-periodic term and trend term model; calculating a residual signal between the observed value of the initial Rowland time delay signal and the output of the multicycle term and trend term model; wavelet decomposition and threshold denoising are carried out on the residual signals; fusing the output of the multi-cycle term and trend term model and the denoised residual signal through an adaptive weight mechanism to obtain a predicted Rowland time delay signal; the deterministic periodic term and the long-term trend drift of the Rowland time delay signal are captured through a multi-periodic term and trend term model, and non-stationary disturbance is processed by using wavelet denoising, so that the Rowland time delay prediction precision is remarkably improved, and the method is particularly suitable for a high-precision timing scene in a complex electromagnetic environment.

The invention discloses a water level prediction method and device based on multi-modal fusion and a double-flow space-time network PredFormer, and the method comprises the steps: firstly, building a double-flow space-time network PredFormer model frame in a dynamic manner from a time sequence signal prediction problem as an entry point and considering that the water level and meteorological data have high nonlinearity and dynamic space-time dependence, and carrying out the prediction of a time sequence signal; obtaining spatio-temporal characteristics of rainfall data and water level data of a plurality of meteorological stations; thirdly, performing feature-level fusion on the obtained water level data time sequence features and multi-site rainfall data spatial-temporal features by using an efficient low-rank tensor fusion method; and finally, a multi-layer perceptron is used as an output prediction result. According to the method, the nonlinear time sequence relation problem of water level prediction is considered, time-space dynamic association of water level data and rainfall data can be fused, and meanwhile, the cross-site prediction problem of personality and generality of the water level data of the hydrometric station and the rainfall data of different meteorological stations is considered. Therefore, the method has strong generalization ability in water level prediction across multiple meteorological stations.

The invention discloses a multi-GNSS satellite signal power abnormity real-time monitoring method. The method comprises the following steps: acquiring real-time observation data of an observation station network which is uniformly distributed globally; when the linear relation between the carrier-to-noise ratios of different frequency signals of each satellite in each observation station and the dynamic monitoring threshold value related to the elevation angle of each satellite are determined, one signal is used for predicting another signal by using the linear coefficient, and the deviation between an actual value and a predicted value is calculated; calculating a satellite elevation angle of the real-time observation data, and determining a monitoring threshold value of the current satellite at the current moment according to the satellite elevation angle; and counting an average value of the deviations of all satellites monitored by all observation stations at the current moment, and marking that the power of the current satellite at the current moment is abnormal when the absolute deviation of the current satellite is greater than a monitoring threshold value. According to the invention, on the basis of the carrier-to-noise ratio linear relation of different frequency signals and the dynamic monitoring threshold, real-time monitoring of various power abnormal scenes including natural interference, man-made interference, satellite active power adjustment and the like is realized.

The invention discloses a respiratory signal estimation method based on ECG and PPG signal time-frequency fusion analysis, and belongs to the technical field of biological signal extraction. The method mainly comprises the steps that a respiratory signal prediction model used for predicting corresponding respiratory signals according to ECG signals and PPG signals is constructed, and the respiratory signal prediction model comprises a time sequence feature extraction module and a frequency domain feature extraction module; the time sequence feature extraction module and the frequency domain feature extraction module separately process the ECG signal and the PPG signal which are subjected to coding mapping, and outputs of the time sequence feature extraction module and the frequency domain feature extraction module are added to obtain a predicted respiration signal; training a respiratory signal prediction model based on the model training data set; and acquiring an ECG signal and a PPG signal to be estimated, performing coding mapping, and inputting the signals into the trained respiratory signal prediction model, thereby acquiring a predicted respiratory signal. According to the invention, the TF-RR network is provided, the ECG and PPG signals are subjected to fusion analysis from two angles of time domain and frequency domain, and accurate estimation of respiratory signals is realized.

The invention provides an audio processing method and system for wearable acoustic equipment, and belongs to the technical field of audio processing, and the method comprises the steps: calculating the equipment wearing fitting degree of the acoustic equipment based on a contact pressure data sequence of the acoustic equipment and the auricle of a target user, a device offset angle of the acoustic device relative to the auricle of the user is calculated based on the spatial attitude data of the acoustic device. And determining a dynamic leakage transfer function based on the equipment wearing fit degree and the equipment deviation angle. And calculating an environment compensation coefficient based on the environment parameters. And predicting a leakage signal mixed in the initial acoustic signal based on the dynamic leakage transfer function and the environmental compensation coefficient. Extracting pure environment noise from the initial acoustic signal based on the leakage signal, generating a noise reduction parameter based on the pure environment noise, and performing audio noise reduction processing on the acoustic equipment based on the noise reduction parameter. According to the audio processing method and system of the wearable acoustic equipment, the audio leakage signal prediction accuracy can be improved, and the audio noise reduction effect of the open type wearable acoustic equipment is improved.

The invention provides an optical fiber transmission receiving signal prediction model training method, a prediction method and equipment, and relates to the technical field of transmission, and the training method comprises the steps: generating a training sample corresponding to a transmitting signal according to the transmitting signal generated by a transmitting end in a continuous spectrum nonlinear frequency division multiplexing system in advance, and training a neural network model based on the training sample to perform mixed domain feature extraction, multi-scale processing and attention feature extraction based on a peak perception attention mechanism on the training sample to obtain received signal prediction result data and optimize the neural network model so as to train the neural network model as an optical fiber transmission received signal prediction model. According to the method and the device, the received signal in the continuous spectrum nonlinear frequency division multiplexing system can be predicted, the accuracy of performing received signal prediction by adopting the trained optical fiber transmission received signal prediction model can be improved, and further the research and development period of the modeling process of the optical fiber communication system and the computing resource consumption of research and development equipment can be reduced.

The invention discloses a VLF propagation signal prediction method based on a three-dimensional finite element and a neural network, and belongs to the technical field of electronic communication. The method comprises the following steps: firstly, constructing a geosphere-ionosphere waveguide model based on a three-dimensional frequency domain finite element method, and solving by using a multi-grid method to improve the operation efficiency; secondly, constructing a VLF signal propagation data set of a plurality of known paths at one time based on a three-dimensional frequency domain finite element method; then, constructing a neural network model reflecting a mapping relation between an ionized layer electron density parameter and a VLF wave characteristic based on the data set; then, obtaining electron density distribution on a plurality of known paths based on neural network inversion; and finally, carrying out inversion by adopting an inverse square weight formula to obtain electron density distribution on the to-be-solved path. According to the method, the VLF signal transmission characteristics on multiple paths can be simulated at a time, the workload of modeling simulation is effectively reduced, and the method is suitable for the fields of inversion of a multi-path electron density parameter model, prediction of very low frequency wave propagation and the like.

The invention belongs to the related technical field of time series prediction, and particularly relates to a multi-scale autoregression time series prediction model construction method based on a Next-Scale prediction normal form, which comprises the following steps: in a training reasoning process, introducing a coarse-to-fine scale-by-scale prediction mechanism, firstly, constructing a token sequence of a preset scale through a residual signal, and then, constructing a multi-scale autoregression time series prediction model; preset-scale residual signal prediction depends on a prefix sequence, the loss of scale-by-scale weighting is calculated based on prediction and a target, advancing is carried out in sequence, the prefix sequence is kept visible when all scales are predicted, and stable global context and consistency constraints are provided for all decoding layers. According to the method, a Next-Scale Prediction normal form is introduced, multi-scale representation based on residual errors is put forward, in training, it is ensured that prediction of all scales is mutually conditional, and global and local prediction performance is improved at the same time through multi-scale loss weighted optimization.

Provided are a reinforcement learning (RL)-based traffic signal control (TSC) method and apparatus, a device, a medium, and a product. The TSC method includes: obtaining traffic state data of a target intersection at a current time point and a road network graph, where the traffic state data includes a quantity of lanes at the target intersection and a traffic flow of each of the lanes; inputting the traffic state data and the road network graph into a preset traffic signal prediction model, and obtaining a target phase action output by the traffic signal prediction model, where the traffic signal prediction model includes a spatiotemporal encoder and a return-based action decoder, and the traffic signal prediction model is obtained through training based on return-based contrastive learning; and controlling, based on the target phase action, a traffic light at the target intersection to execute the target phase action.

The invention belongs to the field of network fault analysis, and particularly relates to a network fault intelligent prediction system based on dial testing, which comprises a dial testing module, a network testing module, a data acquisition and storage module, a signal prediction module, a fault analysis module and a monitoring and early warning module, according to the method, the principle of a graph neural network is creatively utilized, dynamic spatial-temporal feature extraction is performed on the dial test data, fusion features including overall network features and local features of network nodes are obtained, and rapid fault analysis is realized; according to the method, a bidirectional gating dynamic space-time signal prediction method based on a Pearson's correlation coefficient is creatively adopted, VMD decomposition is utilized, data proximity, periodicity and tendency characteristics are enhanced, Pearson characteristics are fused into a GAT model, a hidden space relation and potential characteristics between network nodes are highlighted, bidirectional gating characteristics are fused into a TCN model, and the prediction precision of the bidirectional gating dynamic space-time signal is improved. The problem of long-time dependence is solved, global features and dynamic changes are effectively extracted, and finally accurate processing of complex fault conditions is improved.

A detector system for molecular imaging of a radionuclide comprises a 3D semiconductor detector comprising a plurality of sensor stacks of sensors made of a semiconductor material having an average atomic number Z below 40. A read-out circuitry connected to the pixels is configured to output, for each interaction induced by an incident gamma ray in the detector, a signal representative of a time, a position and an energy of the interaction in the detector. The interactions in the detector belonging to a same event induced by the incident gamma ray are predicted based on the output signals and used to estimate a direction of the incident gamma ray and reconstruct an image based on the estimated directions of incident gamma rays.