12 results about "Nonlinear noise" patented technology

The invention discloses a swimming skeleton point coordinate data denoising method and device based on spatio-temporal topological structure learning, and belongs to the field of data processing. The method comprises the following steps: acquiring and splicing a swimming video of a target object; detecting a target object in the video, and obtaining skeleton point coordinates and corresponding confidence scores of the target object by adopting a posture estimation model; preprocessing the coordinates to obtain feature vectors; adjacency information of each skeleton point is obtained based on the human body skeleton topology, the feature vectors of all the skeleton points are input into a spatial domain noise removal network, the adjacency information of the skeleton points is aggregated, multi-scale pooling is carried out, and denoised spatial domain features are obtained; sampling the high-dimensional spatial-temporal characteristics by adopting a deformable time convolutional network; and carrying out deformable convolution operation and decoding operation on the sampling features to obtain skeleton point coordinates after time-space domain denoising. Linear and nonlinear noise in data is processed in a time-space domain in a cooperative manner, so that the limitation of a traditional low-pass filter method and an existing ST-GCN method is effectively overcome.

The invention relates to the technical field of communication transmission, and provides an equivalent simulation method and device for transmission performance evaluation of an optical fiber communication system, and the method comprises the steps: generating a signal power density spectrum of each span according to a link parameter; calculating a nonlinear noise power density spectrum according to the link parameters and the signal power density spectrum of each span; and taking the signal power density spectrum as an input parameter of the equivalent simulation model, and calculating a nonlinear damage index at the tail end of the optical transmission system to obtain transmission performance evaluation. A simulated signal power density spectrum is used for replacing a tested signal power density spectrum, the nonlinear damage simulation precision is still kept under the condition that model parameter dependence is reduced, and a nonlinear model is more flexibly applied to various scenes. According to the calculation method, the algorithm is optimized and upgraded from the two aspects of operation efficiency and input parameter dependency, the problems that a non-linear noise algorithm is low in operation speed and input parameters are difficult to obtain are solved, and the algorithm implementation complexity is reduced while the algorithm simulation precision is guaranteed.

This invention relates to the field of sensor measurement technology and discloses a multimodal sensor orientation measurement fusion system, aiming to solve the problems of insufficient time synchronization accuracy, limited sensor anomaly detection and compensation capabilities, and degraded fusion performance under nonlinear noise environments in multimodal sensor orientation measurement. The system includes a sensor array module, a spatiotemporal alignment preprocessing module, a multimodal feature extraction and encoding module, an adaptive weighted fusion decision module, and a system output and feedback control module. Through hardware synchronous sampling, phase-locked loop clock compensation, extrinsic parameter calibration, adaptive feature extraction, sensor health assessment, and improved capacitive Kalman filter fusion, combined with a closed-loop correction mechanism, it achieves high-precision, robust, and adaptive orientation measurement, effectively improving state estimation accuracy and system stability.

The invention provides a signal processing method based on a Brillouin optical time domain reflectometer system, which comprises the following steps: filtering an input signal to obtain an output signal, comparing an expected signal with the output signal to obtain an error signal, iteratively updating a weight coefficient of an adaptive filter, and repeatedly executing filtering operation by using the iteratively updated weight coefficient. Enabling an error signal to approach 0; and performing square operation on the filtered and denoised signal to obtain a square filtered and denoised signal, and performing envelope demodulation processing on the square filtered and denoised signal to obtain a root-mean-square envelope demodulation signal to determine a mutational sensing optical fiber signal. And according to the suddenly changed sensing optical fiber signal, determining a suddenly changed sensing optical fiber detection point. According to the method, the carried sensing information can be effectively extracted from a Brillouin optical time domain reflectometer signal containing a large amount of nonlinear noise, and demodulation and extraction of event points by a Brillouin optical time domain reflectometer system under a low signal-to-noise ratio are realized.

The application discloses an optical OFDM modulation method combining a probability shaping technology and a subcarrier grouping transmission technology, and belongs to the technical field of optical communication, and comprises the following steps: optimizing a QAM constellation diagram based on a probability shaping method, acquiring optimal probability distribution of constellation points, mapping the optimal probability distribution of the constellation points based on a constant distribution matcher, and obtaining OFDM symbols; performing frequency domain symbol transformation on the OFDM symbols, generating transformed frequency domain signals; converting the transformed frequency domain signals into LED group signals based on a filtering block; and processing the LED group signals based on a DCO modulation mode, and completing OFDM modulation. Different subcarriers are modulated on multiple LEDs, so that the peak-to-average power ratio of the OFDM signals modulated on each LED is reduced, and the nonlinear noise interference of the system is further resisted.

This invention discloses an active noise reduction algorithm based on a convolutional-fuzzy neural network without secondary path sensors. The algorithm establishes a correlation model between noise sources at different locations within a vehicle and the noise in the target noise reduction area using a convolutional-fuzzy neural network. It calculates and fits a virtual error noise signal for the target noise reduction area, replacing the error signal obtained through secondary path sensors in traditional methods. This reduces the dependence of active noise reduction in large vehicle interior spaces on multiple secondary path sensors. Furthermore, the invention uses the virtual error noise signal as input to the fuzzy layer, iteratively calculating and identifying secondary paths, and outputting the optimal noise cancellation signal in real time, improving computational efficiency and enhancing the ability to handle nonlinear noise.

This application discloses a noise joint processing method, apparatus, electronic device, and readable storage medium. The noise joint processing method includes: extracting a first sub-band feature signal and a first speech signal from a nonlinear noise residual signal, and extracting a second sub-band feature signal and a second speech signal from a far-end signal; fusing the first sub-band feature signal and the second sub-band feature signal to obtain a first input feature signal, and fusing the first speech signal and the second speech signal to obtain a second input feature signal; fusing the first input feature signal and the second input feature signal to obtain a fused feature signal; determining a target sub-band gain and target speech filter coefficients based on the fused feature signal, the first input feature signal, and the second input feature signal; and obtaining a sound signal based on the target speech filter coefficients and the target sub-band gain. This application solves the technical problem of difficulty in jointly processing echo, noise, and reverberation while achieving good noise reduction effect.

The application discloses a transmitting power optimization method and system of an improved simulated annealing algorithm, and the method comprises the following steps: modeling self-emission noise of an amplifier of an ultra-wideband wavelength division multiplexing system, obtaining linear noise of the ultra-wideband wavelength division multiplexing system, and obtaining nonlinear noise of the ultra-wideband wavelength division multiplexing system according to an ISRS GN model; determining the relationship between the throughput of the ultra-wideband wavelength division multiplexing system and the channel transmitting power through a Shannon formula and the linear noise and the nonlinear noise; and optimizing the transmitting power of the ultra-wideband wavelength division multiplexing system through the improved simulated annealing algorithm based on the relationship between the throughput of the ultra-wideband wavelength division multiplexing system and the channel transmitting power. The application can improve the convergence speed of the algorithm while searching for the optimal transmitting power distribution.

The invention discloses a pod rapid self-alignment method based on multi-sensor joint estimation, and relates to the technical field of safety management, and the method comprises the following steps: I, initializing a multi-source sensor and collecting environment information; iI, constructing an adaptive filtering structure and estimating the initial attitude of the pod; iII, analyzing the causal relationship of the multi-source observation data and evaluating the credibility of the multi-source observation data; iV, correcting the postures of the pods and eliminating redundant information in the multi-source observation data; the method can significantly shorten the overall alignment time, improve the system starting efficiency, avoid the influence of single sensor failure or noise increase on the system, improve the data fusion effect, dynamically adjust the filtering structure according to the actual operation condition, improve the adaptability to the complex environment, and improve the reliability of the system. A non-linear noise mode which is difficult to find by a traditional statistical method can be identified, abnormal data are stripped through a noise index positioning and data reconstruction mode, and the observation data quality is improved.

The application discloses an enhanced model day-ahead electricity price prediction method based on dynamic feature selection, which extracts features from the original data set through a multi-head attention mechanism for multidimensional correlation analysis, generates a feature weight vector in real time to realize dynamic screening of the optimal feature subset, thereby suppressing redundant information and nonlinear noise features at the source; then, an enhanced XGBoost model is used to deeply mine the structured relationship of power market data, simultaneously combined with a Transformer model to capture the long-range time series dependence characteristics of the electricity price sequence, and through a gating mechanism to perform dynamic weighted fusion, to realize the complementary integration of spatial features and time series features; finally, a multi-objective Bayesian optimization algorithm is introduced to obtain a trained enhanced model through multi-objective collaborative optimization, and then prediction is performed. The application significantly improves the prediction accuracy and robustness, effectively solves the deployment problem of the model in a resource-limited environment, and has high engineering application value and power market prediction practicality.

The invention discloses an EBAPS-oriented low-light image denoising method and system and a data set construction method, which are used for solving the problem of nonlinear noise of an electron bombardment active pixel sensor (EBAPS) under an extremely low-light condition. According to the data set construction method, clear-noisy image pairs of pixel-level alignment are obtained by adjusting the aperture of a light source instead of changing exposure at a fixed geometric position. The denoising method adopts a two-stage neural network, and the core of the denoising method is a frequency domain-based noise estimation module (FANS). The FANS module generates a noise priori parameter accurately corresponding to illumination by calculating an under-curve area (AUC) of a normalized radial power spectrum of an input image. According to the network, by using the parameter, through low-rank guided decomposition (LROD), two-way adaptive spatial fusion (DASF) and other modules, denoising is carried out on a noisy image. According to the method, EBAPS noise under 10 <-5 > lx limit illumination can be effectively removed, and image details are reserved.

The application relates to the technical field of image processing, and discloses a noise model calibration method, an image denoising method, a device, equipment and a medium. The method comprises the following steps: acquiring multiple RAW domain images; performing nonlinear noise denoising processing based on the multiple RAW domain images to generate a target image; and calibrating a preset RAW domain noise model based on the target image to generate a target RAW domain noise model. Through the technical scheme, the denoising precision of the target RAW domain noise model is improved, and thus the image definition and the image quality of the RAW domain image are improved.