69results about How to "Remove noise" patented technology

The invention relates to the field of environment monitoring, and discloses an efficient and accurate pollution source monitoring quality control system and method, and the system comprises a multi-modal data collection module, a high-dimensional data modeling module, a time-space correlation analysis module, a time sequence prediction module, a multi-task learning module and an anomaly detection feedback module. The method comprises the following steps: collecting data of pollutants such as air, water quality and noise, performing high-dimensional modeling and optimization on the data, and capturing space-time propagation paths of the pollutants among different sensor nodes; the system predicts the short-term change and the long-term trend of the pollutant concentration in real time; the multi-task learning model is used for predicting concentration changes of multiple pollutants at the same time, multi-scale decomposition is carried out on a time sequence through wavelet transform, abnormal changes in data are detected, and a feedback control strategy is generated. According to the invention, the precision and real-time performance of pollution source monitoring are improved, the dynamic change of multiple pollutants can be effectively handled, and the high efficiency and reliability of environment quality monitoring are ensured.

The invention relates to the technical field of data processing and optimization, in particular to a liquid crystal display screen display optimization method and system. The method comprises the following steps: acquiring display data of a liquid crystal display screen by using a sensor to obtain the display data of the liquid crystal display screen; preprocessing the display data of the liquid crystal display screen to obtain standard display data of the liquid crystal display screen; performing multi-dimensional feature recognition on the display data of the standard liquid crystal display screen to obtain multi-dimensional display feature data; performing key display information extraction on the multi-dimensional display feature data to obtain key display information; according to the invention, through a data processing technology, an image identification technology and an intelligent regulation and control technology, a specific environment condition is analyzed so as to obtain an abnormal display condition of the liquid crystal display screen caused by environmental influence; and dynamic display optimization adjustment is carried out on abnormal display conditions of the liquid crystal display screen, so that the display effect of the liquid crystal display screen is improved.

The invention provides a distributed photovoltaic output power estimation method, and the method comprises the steps: installing a load sensor and a photovoltaic output sensor at an access point, and collecting original data including load data and photovoltaic output data in real time; processing the collected original data; carrying out time synchronization on the load data and the photovoltaic output data; key features are extracted from the cleaned original data, and photovoltaic output is predicted through a time sequence analysis model; inputting load data and photovoltaic output data which are acquired in real time into the trained time sequence analysis model; the time sequence analysis model performs real-time operation according to the load data and the photovoltaic output data, and estimates the photovoltaic output power at the current moment; and based on the estimated photovoltaic output power and the real-time load data, the intelligent coordination controller performs dynamic adjustment, so that the photovoltaic output is matched with the load power. According to the invention, efficient estimation and optimal control of photovoltaic output are realized.

The invention discloses a soil organic matter content inversion method based on a near infrared spectrum, and relates to the technical field of soil detection. Compared with a previous soil organic matter content measurement technology, the problems that in the aspect of soil organic matter content measurement, an existing near infrared spectrum technology is complex in data preprocessing, difficult in feature selection and insufficient in model generalization ability are solved; the near infrared spectrum range is optimally selected, key characteristic wave bands related to soil organic matter changes are effectively focused, and the accuracy and reliability of measurement are improved; a differential transformation preprocessing technology is used, and the data quality is effectively improved; efficient feature selection is carried out by adopting a stable competitive self-adaptive reweighted sampling method, a feature wave band which can reflect the soil organic matter content is extracted, and the prediction capability of the model is enhanced. And a plurality of machine learning algorithms and parameter optimization technologies are combined to optimize the model structure and parameters so as to adapt to soil samples of different areas and different types, and the prediction precision and stability are improved.

The invention relates to an intelligent behavior analysis and anomaly detection system for Internet of Things security, which is applied to the technical field of Internet of Things security, and comprises a data acquisition module, a data preprocessing module, a behavior modeling module and an anomaly detection module, the data preprocessing module cleans the data, the behavior modeling module generates a vector sequence of equipment behaviors through feature embedding and position coding, and the anomaly detection module analyzes time sequence association of the equipment behaviors by utilizing a self-attention mechanism and a multi-head attention mechanism and judges whether the equipment has abnormal behaviors or not. The cooperative defense module realizes cross-device cooperative defense through an edge detection unit and a cloud analysis unit, and the threat intelligence sharing module realizes sharing and updating of threat intelligence through a local intelligence database and an external intelligence interface. And the response module carries out automatic defense and notifies a system administrator through the automatic defense unit and the alarm unit when an abnormity is detected.

The invention discloses a grinding workpiece edge shape detection method and system based on machine learning, and the method comprises the steps: obtaining an original image of a grinding workpiece, and carrying out the preliminary image preprocessing; denoising the image and enhancing edge information by combining image filtering and mathematical morphology image processing; based on a second-order differential operator, edge detection is carried out in combination with the morphological gradient, and a workpiece edge contour is obtained; performing feature extraction on the image by using a convolutional neural network, automatically learning workpiece edge features, and constructing and training an edge detection model; acquiring a workpiece image in real time, inputting the workpiece image into the edge detection model for detection, and dynamically correcting the model; and S6, outputting a final edge detection result. According to the invention, by combining image preprocessing, composite image filtering, second-order differential operator and morphological gradient edge detection and feature extraction and model construction of the convolutional neural network, high-precision and robust detection of the edge of the grinding workpiece is realized.

The invention belongs to the technical field of ultrasonic positioning diagnosis, and discloses an ultrasonic phased array positioning diagnosis method for a dry-type bushing capacitor core with a microcrack defect, and the ultrasonic detection technology is a nondestructive detection method, and cannot damage a detected insulating material, so that the ultrasonic phased array positioning diagnosis method is suitable for long-term monitoring and preventive maintenance. As the ultrasonic wave has very high frequency and energy, the ultrasonic wave can penetrate through a thicker layer of the insulating material, so that tiny defects and changes can be found. The ultrasonic detection technology can find out the defects of aging, bubbles, impurities, cracks and the like in the insulating material, and can also be applied to other types of electrical equipment, such as cables, transformers and the like, so as to evaluate the insulating properties of the electrical equipment. And taking the discharge signal starting time measured by an electric detection method as a reference to obtain time delay data of all the sensors, and then carrying out next positioning calculation.

The invention discloses a single-face array low-altitude radar target recognition system based on deep learning, and the system comprises a data collection module which obtains the radar echo data of different targets in various environments, a receiver has a specific sampling frequency and a dynamic range, the collection time is set according to the characteristics of the targets, and the data is compressed and stored; the data preprocessing module is used for denoising, clutter suppression and normalization; the feature extraction module extracts features by using CNN; the target recognition module classifies and recognizes a target; the model training and optimizing module is used for training a model and optimizing parameters; and the visual display module displays the result. According to the invention, data can be accurately collected and efficiently preprocessed, target features are accurately extracted and recognized by using deep learning, the model is optimized to improve the accuracy, the result can be visually displayed, the accuracy, real-time performance and reliability of low-altitude radar target recognition are effectively improved, and the monitoring requirements are met.

A transparent visual power grid operation and maintenance system comprises a data acquisition and preprocessing module which is composed of a sensor network and SCADA system docking unit and a data preprocessing unit; the data processing and analysis module is composed of a fault prediction and diagnosis unit, an operation and maintenance strategy optimization unit and a three-dimensional modeling and dynamic simulation unit; the visual display and user interaction module is composed of an AR / VR interface development unit and a user-defined interface and report generation unit; and the system integration and communication module is composed of a standardized API interface and cloud platform unit and a remote access and cooperation unit, and the scheme of the invention solves the problem that the complexity of power grid operation and maintenance system data causes that detection information is difficult to provide visually, thereby affecting the operation and maintenance work quality and efficiency.

The invention provides a deep learning-based turbid underwater image restoration method, which comprises the following steps: establishing a CycleGAN cyclic consistency network model, respectively adding attention modules in an encoder and a decoder to optimize the model so as to enhance the detail extraction ability of the model, the attention modules comprising simAM and MLCA, and training the CycleGAN cyclic consistency network model by using the data set, adjusting the model configuration, adding a loss function and an optimizer, and performing image quality and visual effect evaluation on the processed image of the CycleGAN cyclic consistency network model. By means of the mode, the problems of blurring, distortion and noise in the underwater image can be better solved, the restored image is clearer and more accurate, the underwater image processing efficiency and quality can be improved, and development of the fields of underwater exploration, underwater archaeology, underwater robots and the like can be promoted.

The invention relates to an adaptive weighted bilateral filtering deconvolution OCT image processing method and system, and the method comprises the steps: carrying out the preprocessing of an original OCT signal, including background noise removal, wave number calibration, spectrum shaping and dispersion compensation, so as to obtain an OCT reconstructed image; enhancing the contrast ratio through histogram stretching, adjusting the space weight and the intensity weight of the OCT stretching image, and performing adaptive denoising on the image; and further optimizing the image by using a blind deconvolution algorithm, and iteratively updating the estimated image and a point spread function (PSF) to obtain a high-definition OCT reconstructed image. According to the method, efficient denoising and detail reservation of the OCT image are realized through adaptive weighted bilateral filtering and blind deconvolution technologies, so that a high-definition reconstructed image is obtained.

The invention relates to the technical field of medical health, in particular to a cardiac muscle tissue electrophysiology unmarked optical detection method based on deep learning. The method comprises the following steps: acquiring optical detection image data and electrophysiological signal data of myocardial tissue; the optical detection image data and the electrophysiological signal data are subjected to image preprocessing, so that optical-physiological signal mapping data are obtained, and image preprocessing comprises image registration, image cutting, periodic enhancement, time difference enhancement, spatial filtering, intensity normalization and data smoothing; and according to the optical-physiological signal mapping data, carrying out feature signal extraction based on a mechanical contraction curve and an electrophysiological curve so as to obtain mechanical contraction curve data and electrophysiological curve data. According to the method, unmarked optical detection is adopted, so that direct interference on myocardial tissues is avoided, and the physiological state of the tissues is better maintained.

The invention provides a target identification method and system based on multi-source information fusion, and relates to the technical field of low-altitude target detection. The method comprises the following steps: acquiring target radar track data, interception equipment track data and position area information data; based on target radar track data, extracting a first feature in an RCS form dimension, and extracting a second feature in a motion dimension; based on the target radar track data and the track data of the monitoring equipment, determining a frequency spectrum monitoring correlation factor and regional position information features; performing feature fusion on the first feature, the second feature, the spectrum interception correlation factor and the regional position information feature to obtain a target feature, and identifying a target type; and identifying a target threat level based on the target type and the target radar track data. The method and the device are used in a target identification process based on multi-source information fusion, and the technical problem that the target threat degree cannot be accurately identified in a complex environment in the prior art is solved.

The invention relates to a satellite short-term clock error forecasting method fusing time sequence decomposition and deep learning, and belongs to the technical field of satellite clock error forecasting. The method comprises the steps of performing primary difference processing on a satellite historical clock error sequence, screening out abnormal values existing in data according to a Raida criterion, performing time sequence decomposition on clock error primary difference data, firstly, decomposing the clock error primary difference sequence by adopting an adaptive noise complete set empirical mode decomposition algorithm to obtain a plurality of mode components, and performing time sequence decomposition on the plurality of mode components; a permutation entropy algorithm is introduced to sort modal components, and a t check algorithm is used to classify random items and periodic items of the components and reconstruct the components into trend items, periodic items and random items. And inputting the reconstruction item into a Transform model in a channel independent mode for training, and obtaining the clock error required to be forecasted after inverse primary difference processing and superposition of component prediction results. According to the method, the precision and the stability of satellite short-term clock correction forecasting are improved, and meanwhile, the interpretability of a forecasting result is also improved.

The invention relates to the technical field of analysis by measuring material properties, in particular to an intelligent detection method for mycotoxin and a workstation. The method comprises the following steps: analyzing spectrum curves of an original chromatographic signal and an IMF component signal to obtain a noise possibility and an abnormal interference factor of each frequency; clustering all frequencies according to the abnormal interference factor of each frequency to obtain a frequency cluster; high-noise component signals are screened out according to distribution characteristics of frequencies in different frequency clusters; obtaining the interference influence degree of the high-noise component signal according to the noise possibility distribution of different frequencies in the frequency spectrum curve; obtaining a frequency abnormal factor of the high-noise component signal by combining the confusion degree of the difference between adjacent extreme values in the high-noise component signal, and obtaining an abnormal cut-off frequency; and filtering the original chromatographic signal to obtain a filtered chromatographic signal. According to the invention, the accuracy of mycotoxin detection is improved by obtaining accurate signal expression during mycotoxin detection.

The invention discloses a non-woven fabric quality detection method, and belongs to the technical field of quality detection, and the method comprises the following steps: S1, collecting a production image of a non-woven fabric, and carrying out the preprocessing of the production image through a homomorphic filtering method, so as to obtain a stable production image; s2, extracting characteristic elements of other pixel points except the first row and the last row in the stable production image by using a gray-level co-occurrence matrix, and generating texture characteristics; and S3, taking the pixel points of which the gray values are smaller than the texture characteristics as quality defect positions of the non-woven fabric. According to the invention, flaws and defects on the surface of the non-woven fabric can be accurately identified; labor cost can be saved for enterprises, and the quality of the non-woven fabric is strictly controlled.

The invention discloses an electric vehicle charging load prediction method and system considering data cleaning, and the method comprises the steps: collecting historical electric vehicle load related data and historical electric vehicle load data, and extracting electric vehicle load related features; performing normalization processing on the collected data, cleaning the normalized electric vehicle load data, and forming a training data set by using the normalized electric vehicle load related characteristics and the cleaned data; establishing a load prediction model based on a CNN-GRU convolutional neural network-gating cycle unit; training a load prediction model by using the training data set; and acquiring related characteristics of the electric vehicle load in real time, inputting the related characteristics into the trained load prediction model, and predicting the short-term charging load of the electric vehicle in real time. The electric vehicle charging load prediction method has the outstanding advantages that the electric vehicle charging load prediction result is good, the model practicability is high, and complex factors influencing electric vehicle charging load prediction are fully considered.

The invention provides a lung cancer image recognition method and system, and the method comprises the steps: obtaining a lung image of a patient, and carrying out the image correction processing of the lung image, so as to obtain a corrected lung image; performing iterative denoising processing on the corrected lung image to obtain a denoised lung image; performing feature image segmentation on the denoised lung image to obtain a lung feature image; the method comprises the following steps: acquiring a historical template lung cancer image set, inputting the historical template lung cancer image set into a preset recognition model for training, inputting a lung feature image into the trained preset recognition model for recognition, and outputting a recognition result. Noise and artifacts existing in the image are effectively removed, interference information existing in the image can be eliminated at the same time, and then the recognition accuracy is improved.

The invention is suitable for the technical field of motor control, and provides a method for obtaining the running position of a motor through a resistor, and the high-precision detection of the position of the motor is realized through a high-precision current source and an MCP3561 single-path low-noise 24-bit delta-sigma ADC (Analog to Digital Converter). And high-frequency interference signals sensed during operation of the motor are filtered, so that the anti-interference capability of the system during operation of the motor is improved, and the accuracy of measured data is ensured. According to the invention, the reading speed is improved to 1.2 KHz, and the real-time monitoring of the displacement of the motor is realized in cooperation with the real-time 50Hz power frequency and high-frequency FIT filtering algorithm, so that the 50Hz periodic noise and burst noise are effectively removed, and the response speed of the system is improved to accurately obtain the running position of the motor.

The application discloses an infrared image enhancement method, system, device and storage medium based on a wavelet threshold, which comprises the following steps: performing multi-scale discrete wavelet transform on an input original infrared image to separate low-frequency components and high-frequency components; the low-frequency components bear overall outlines and illumination distribution information of the image, and the high-frequency components contain edge, texture details and noise information of the image; performing improved adaptive wavelet threshold denoising processing on the high-frequency components to obtain denoised high-frequency components; performing layered enhancement processing based on weighted guided filtering and multi-scale Retinex on the low-frequency components to obtain enhanced low-frequency components; performing wavelet inverse transform reconstruction on the enhanced low-frequency components and the denoised high-frequency components to obtain a preliminary enhanced image; performing size upsampling on the preliminary enhanced image, and applying adaptive contrast restriction histogram equalization processing to output a final enhanced infrared image. The method can effectively suppress noise, retain details, adaptively enhance low-resolution infrared images, and is computationally efficient.

The invention relates to a machine learning-based power grid operation data cleaning method and system. The method comprises the following steps of obtaining real-time operation data of a power grid structure; sequentially performing low-dimensional representation and data reconstruction on the real-time operation data by adopting a pre-trained auto-encoder model, and performing screening based on the reconstructed data to obtain abnormal data and normal data; based on the abnormal data, adopting an Apriori algorithm to classify the abnormal data into abnormal state data and dirty data, and removing the dirty data; and adopting a pre-trained GRU recurrent neural network model to complement the abnormal data from which the dirty data is removed to obtain the complemented abnormal data, and completing the data cleaning process. Compared with the prior art, the method has the advantages of realizing efficient and low-threshold power grid operation data cleaning and the like.

This application provides a method, device, equipment, and medium for detecting vascular stenosis. The method includes: acquiring a binary image of a blood vessel diameter curve; determining a convex hull and multiple initial straight lines forming the convex hull in the binary image; determining multiple target straight lines from the initial straight lines, and performing line fitting on each target straight line to obtain multiple fitted straight lines and a fitted line equation corresponding to each fitted line; determining reference diameter information for each target center point in the binary image based on the fitted line equation corresponding to each fitted line; and determining at least one stenotic segment in the blood vessel and the stenosis rate corresponding to each stenotic segment using the equivalent diameter information of each target center point and the reference diameter information of each target center point. The detection method and device improve the accuracy and robustness of detecting vascular stenosis segments and stenosis rates.

The invention discloses a method and system for testing the capacitance value of an integrated capacitor, and relates to the field of electrical measurement, and the method comprises the steps: obtaining the rated information of a to-be-tested integrated capacitor, and generating a control parameter based on the rated information; iteratively calculating the capacitance value of each phase of the to-be-tested integrated capacitor based on a preset adaptive optimization algorithm and the control parameters; and obtaining a target capacitance value of each phase until a preset convergence condition is met, and completing the test. In each iteration process, acquiring a three-phase voltage signal and a three-phase current signal of the to-be-tested integrated capacitor based on the current control parameter; performing feature extraction on the three-phase voltage signal and the three-phase current signal to obtain spectrum feature information; constructing a coupling matrix of the to-be-tested integrated capacitor based on the spectrum feature information, and separately calculating an independent capacitance value of each phase based on the coupling matrix and a coupling residual error to obtain a first calculation result; and optimizing the control parameters based on the first calculation result to obtain the control parameters of the next iteration process.

The invention provides an intelligent control system and method for a rapping hammer, and the system comprises a detection module which is used for detecting the working state of the rapping hammer to generate an analog electric signal; the analog-to-digital converter is used for converting the analog electric signal into a digital signal; the intelligent control module is deployed on the background server and is used for executing the following steps to remotely and intelligently control the rapping hammer: preprocessing the digital signal to obtain a to-be-analyzed signal, the preprocessing at least comprising filtering and denoising; performing statistical analysis on the to-be-analyzed signal to obtain a statistical analysis result; judging the working state of the rapping hammer according to the statistical analysis result; and according to the working state, generating an intelligent instruction for controlling the rapping hammer so as to control the working state of the rapping hammer. Therefore, the real-time performance and the continuity of monitoring are at least improved, and when a fault or an abnormal condition is found, the system can also trigger an alarm or maintenance process in time, so that the normal operation of equipment is further guaranteed.

A method and system for EEG emotion recognition based on multi-task and attention mechanisms is disclosed. The method comprises: S1. Acquiring corresponding EEG signal data according to the locations of emotion-related EEG channels in the international standard 10-20 electrode placement system; S2. Preprocessing the acquired EEG signals using bandpass filtering, power frequency notch filtering, downsampling, baseline correction, artifact removal, and signal segmentation, dividing the signal into windows with a duration of 0.5 seconds; S3. Extracting power spectral density and differential entropy features from the EEG data of each time slice, representing the feature vectors using a two-dimensional brain map to preserve spatial information, and stacking brain maps of all bands and features in three-dimensional space, with each map serving as input to the model; S4. Integrating a convolutional module, a long short-term memory network variant module, and an attention module, employing a multi-task learning strategy to obtain an optimal model capable of accurately identifying both arousal and valence of emotions in EEG signals simultaneously. This invention solves the problem of previous models focusing only on a single feature and a single recognition task, constructing a highly accurate multi-task model in the field of emotion recognition.

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses a vehicle damage detection method, device and equipment and a storage medium, and the method comprises the steps: obtaining a to-be-predicted vehicle damage image, and carrying out the image enhancement of the to-be-predicted vehicle damage image, and obtaining a standard vehicle damage image; extracting an initial image feature of the standard vehicle damage image, and performing multilayer deformable convolution on the initial image feature to obtain a layered convolution feature; performing feature fusion on the layered convolution features to obtain target features of the standard vehicle damage image; and calculating the vehicle damage degree corresponding to the standard vehicle damage image by using the target feature. According to the invention, the accuracy and efficiency of vehicle damage detection can be effectively improved.

The invention discloses a fruit tree branch sample disease detection image identification and detection method and system, and the method comprises the steps: synchronously collecting a high-resolution RGB image, a near-infrared image and a depth image of the surface of a target fruit tree branch, and carrying out the preprocessing of the high-resolution RGB image, and obtaining a to-be-detected image; carrying out graying filtering on pixel points of the to-be-detected image to obtain a grayscale image; selecting a local window for the grayscale image to carry out window sliding to calculate a curvature characteristic value of a central pixel point; extracting a fusion coding vector by using the three-dimensional initial feature vector set, the near-infrared image and the depth image; and constructing a historical fusion coding vector database, and matching the fusion coding vector with the historical fusion coding vector database to obtain a fruit tree branch and trunk disease detection result. Different image analyses are performed by combining a high-resolution RGB image, a near-infrared image and a depth image, and fused features are extracted to understand different disease detection results.

The invention discloses a respiratory nerve muscle stimulation control method and system, and relates to the technical field of medical treatment, and the method comprises the steps: collecting the body parameter information of a user; determining stimulation parameters of the user according to the body parameter information and parameters stored in a database; before electrical stimulation is carried out on the body of a user, an initial muscle contraction signal obtained from a treatment terminal is processed through a signal processing module, and an initial muscle contraction filtering signal is obtained; wherein the initial muscle contraction signal is sensed by a treatment terminal attached to the body of the user; according to the stimulation parameters of the user, the initial muscle contraction filtering signal, the real-time muscle contraction filtering signal and the real-time breathing condition, the current of electrical stimulation generated by a treatment terminal arranged on the body of the user is controlled in real time through a self-adaptive current adjustment model which is trained and optimized. According to the invention, the efficiency of electrical stimulation is improved.

The application discloses an infrared image non-uniformity prediction and correction method based on wavelet transform, which comprises the following steps: adopting double-density dual-tree complex wavelet transform to perform multi-scale decomposition on an input infrared image; in a high-frequency subband, detecting a blind element position based on a local variance statistical method; in a low-frequency subband, constructing an autoregressive model, predicting non-uniformity of a background region, and performing accurate processing on a prediction result; combining the prediction results of the high-frequency subband and the low-frequency subband to generate a pre-correction coefficient; and adopting the pre-correction coefficient to perform correction processing on an original infrared image to obtain a corrected image. Through the combination of an adaptive fusion strategy, space-time consistency constraint and dynamic gain and bias updating technology, the problems of non-uniformity noise, balance between details and background, device drift compensation and consistency in a dynamic scene in infrared image processing are solved, and the accuracy and stability of infrared image processing are significantly improved.

The invention relates to a self-adaptive quantum random number generation method based on real-time entropy estimation, and belongs to the technical field of quantum random number generation. According to an existing integrated quantum random number generator, due to the non-stationary characteristic of a physical entropy source, the entropy rate dynamically drifts, and after-processing parameters are fixed, randomness safety and generation efficiency are difficult to guarantee at the same time. According to the method, the state transition probability of the original random bit stream is counted in real time, the confidence interval correction is introduced to calculate the minimum entropy, the input bit width is dynamically adjusted accordingly, the Toeplitz matrix is reconstructed for random extraction, and self-adaptive adjustment of the compression ratio is achieved. According to the method, the compression ratio is increased to ensure the security of the output random number when the entropy source quality is reduced, and the compression ratio is reduced to improve the generation efficiency when the entropy source quality is improved, so that the dynamic balance between the randomness security and the generation efficiency is realized on the premise of keeping integration and low cost.