9results about How to "Effective noise" patented technology

Disclosed herein is a system for removing the noise of electrocardiogram data based on deep learning, the system including: an electrocardiogram measurement unit (110) configured to measure electrocardiogram data for each lead from the body of an examinee; and a style-based electrocardiogram generation unit (120) configured to extract a corresponding unique style from the electrocardiogram data measured by the electrocardiogram measurement unit (110) and convert the electrocardiogram data into and generate electrocardiogram data of a specific lead style not containing noise through the extracted unique style while reflecting the characteristics of the examinee and the characteristics of a measurement method therein through an electrocardiogram generation deep learning algorithm (121) that is constructed by being previously trained on training datasets of electrocardiogram data for each lead having less noise and the unique style of the electrocardiogram data for each lead based on a large number of pieces of electrocardiogram data.

Provided are an optical image processing method, a machine learning method, a trained model, a machine learning pre-processing method, an optical image processing module, an optical image processing program, and an optical image processing system that make it possible to effectively remove noise in an optical image. An optical image processing module 3 includes an image acquisition unit 32 that acquires an optical image obtained by capturing an image of light L from a target object F, a selection unit 33 that selects a trained model 36 from a plurality of trained models 36 each of which is built in advance through machine learning using condition information including photodetector information indicating a type of photodetector 21, and a processing unit 34 that inputs the optical image to the selected trained model 36 and executes image processing of removing noise from the optical image.

The utility model discloses a low noise automobile wheel hub relates to automobile parts technical field, including wheel hub, is fixedly arranged with the spoke on the wheel hub, is fixedly arranged with the rim on the spoke, is provided with a plurality of connecting holes on the wheel hub, is provided with the slot on the spoke, the plug -in block is inserted in the slot, is fixedly arranged with the wind -resistant noise reduction board on the plug -in block, and the wind -resistant noise reduction board cooperation round block constitutes the complete disc and covers wheel hub and spoke, effectively reduces the influence of air to wheel hub and spoke in the process of car driving to the effect of noise reduction, second sound absorption board cooperation arc convex effectively breaks open air, reduces the wind resistance, effectively reduces the generation of noise, simultaneously through the cooperation of first sound absorption board and second sound absorption board effectively absorbs and eliminates the noise generated to reduce the noise, and the practicality is strong, when first sound absorption board and second sound absorption board appear damage, it is convenient through the cooperation of front clamping strip and rear clamping strip and quickly disassembles and maintains, and the flexibility is high.

This invention discloses an image enhancement method and system for use in severe weather, belonging to the field of image processing technology. The image enhancement method for severe weather includes the following steps: S1. Receiving image data affected by severe weather from a camera device; the input image is I_in, with a size of H x W x 3; S2. Dividing the input image I_in into 64x64 blocks to obtain image blocks I_in_block, where each block contains local image information. The image enhancement method in this invention can automatically generate adaptive processing strategies based on different weather conditions and noise types, and dynamically adjust the image processing process through a denoising diffusion model. Furthermore, the denoising diffusion model not only effectively removes noise but also preserves image details and textures through a detail enhancement module, avoiding the "over-smoothing" problem in traditional denoising methods.

The invention belongs to the technical field of optical precision measurement, and discloses a vacuum ultraviolet spectrophotometric measurement method based on a photon counting method, which comprises the following steps: in a sample-free state, setting a polarization state of incident light according to a measurement task, and aiming at each wavelength point in a preset measurement wave band, calculating the polarization state of the incident light; collecting an initial dark count and an initial baseline count corresponding to the wavelength point; on the basis of the initial dark count and the initial baseline count, through signal-to-noise ratio optimization, respectively calibrating the optimal working voltage of the photon counting detector under each wavelength point and a double-discrimination threshold value for separating noise; under the same polarization state, dark counts and reference counts corresponding to the wavelength points are collected based on the optimal working voltages and the double discrimination thresholds corresponding to the wavelength points; the problems that in vacuum ultraviolet band measurement in the prior art, due to the fact that detection parameters cannot be dynamically optimized in the whole spectrum band, the signal-to-noise ratio of a system is low, and the measurement precision is insufficient are effectively solved.

The invention belongs to the technical field of geological exploration, and relates to a longitudinal wave data seismic elastic parameter full-waveform inversion method, system and device and a medium. According to the method, longitudinal wave data is used, and a classic least square objective function is utilized to establish an adaptive filtering objective function of a pure longitudinal wave analog signal and a received signal error; obtaining longitudinal wave and transverse wave velocity gradient corrections according to the adaptive filtering objective function and a pseudo scalar wave equation under an elastic medium assumption condition; the longitudinal wave and transverse wave velocity gradient correction is utilized to invert and update the longitudinal wave and transverse wave velocity model, when the error reaches a preset threshold value or the number of iterations reaches a preset upper limit, the inversion process is ended, and an adaptive filtering objective function with the minimum error difference is obtained; and recovering the longitudinal wave velocity, the transverse wave velocity and the density model in the elastic medium according to the adaptive filtering target function with the minimum error difference. The longitudinal wave velocity, the transverse wave velocity and the density model in the elastic medium can be accurately recovered according to the longitudinal wave data.

The invention provides an operation identification method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring an initial capacitance signal of each pixel in a current frame; counting the initial capacitance signal of each pixel, and determining a target moisture level of the current frame; and filtering the initial capacitance signal of each pixel according to the target moisture level, determining a target capacitance signal of each pixel, and identifying user operation according to the target capacitance signal of each pixel. By means of the method, accurate recognition of user operation can be ensured, and therefore the effect of improving the overall user experience and the system reliability is achieved.

Provided are an optical image processing method, a machine learning method, a trained model, a machine learning preprocessing method, an optical image processing module, an optical image processing program, and an optical image processing system that make it possible to effectively remove noise in an optical image. An optical image processing module 3 includes an image acquisition unit 32 that acquires an optical image obtained by capturing an image of light L from a target object F, a noise map generation unit 33 that derives a standard deviation of noise values from a pixel value of each pixel in the optical image on the basis of relationship data indicating a relationship between the pixel value and the standard deviation of noise values obtained by evaluating spread of the noise value and generates a noise map that is data in which the derived standard deviation of noise values is associated with each pixel in the optical image, and a processing unit 34 that inputs the optical image and the noise map to a trained model 36 built in advance through machine learning and executes image processing of removing noise from the optical image.

The application belongs to the technical field of power load prediction and the field of network flow prediction, discloses a power flow prediction method based on neural network and boosting, combines a GRU-Xgboost module, a residual adjustment module and a missing value reconstruction, carries out decomposition reconstruction and adjustment on a complex network flow time sequence, proposes a new network flow time sequence prediction model, considers time correlation of time sequence data, and improves prediction accuracy.For the difference of the power network, according to the service characteristics of the power, the characteristic factors influencing the flow model and the effective processing of the nonlinear complex characteristics and unknown noise of the flow sequence are found, so that the flow prediction model for the power network is established, and the prediction information is provided for the relevant departments to make decisions.