99 results about "Noise classification" patented technology

The invention discloses a text retrieval enhancement generation method and device, a medium and equipment, and relates to the technical field of retrieval enhancement generation. Comprising the following steps: establishing a database through vectorized corpora, and screening and labeling key information to generate a golden section vector library; extracting an adversarial sample from an external database by using a training problem, and fusing the adversarial sample with related corpora in a golden section vector library to obtain a training set; and adding a noise classification layer to improve the language large model, and training the improved language large model by using the fusion training set. When a user question is processed, relevant corpora are recalled, noise is recognized through the classification layer, context representation is generated through the attention fusion layer, and the output layer dynamically adjusts a decoding strategy and generates an answer. According to the method, a large language model added with a noise classification task is trained through the fusion training set, so that the model can identify and distinguish different types of noise, the adaptability of the model to different types of noise is enhanced, the model is helped to learn how to distinguish related and unrelated information, and thus the method is more robust when an actual problem is processed.

The invention discloses an electrocardiosignal preprocessing system and method based on filtering and deep learning, and relates to the field of electrocardiosignal data processing. The multi-stage adaptive filtering module comprises a baseline drift elimination unit, a power frequency interference suppression unit and a myoelectricity noise removal unit, and all the units are connected in sequence to form pipelined parallel processing; the deep learning fusion module is used for performing deep feature extraction and noise classification on the output signal and feeding back a classification result to the multi-stage adaptive filtering module; the signal quality evaluation module carries out quality evaluation on the electrocardiosignals subjected to multi-stage adaptive filtering and deep learning fusion and judges whether the signal quality is qualified or not; a feature enhancement and standardization module; the technical effects of improving the self-adaptability and robustness, improving the calculation efficiency of heart disease classification, the signal fidelity and the diagnosis reliability, and enhancing the signal quality evaluability and the self-adaptive ability are achieved.

The invention relates to the related field of underwater acoustic signal processing, in particular to an underwater acoustic target radiation noise classification method, which constructs an efficient and accurate underwater acoustic target radiation noise classification model through the technologies of lightweight model selection, feature fusion, transfer learning, hyper-parameter optimization, model pruning, quantification and the like. The model not only can realize real-time processing in an environment with limited resources, but also has good classification performance, low energy consumption and high flexibility, is suitable for various application occasions, and particularly has remarkable advantages in an underwater acoustic target classification and real-time monitoring system.

The invention discloses a motor abnormal sound detection method and system based on contact acquisition and small sample learning, and the method comprises the steps: directly coupling a motor housing through a contact vibration sensor, collecting an original vibration signal, and generating an anti-interference vibration signal; inputting the anti-interference vibration signal into a nonlinear resonance enhancement module to generate an enhanced sound signal; performing wavelet packet decomposition on the enhanced sound signal, extracting a multi-scale frequency band energy entropy, and generating a motor abnormal sound feature matrix by combining singular value decomposition dimension reduction; on the basis of a dynamic weight distribution element learning algorithm, a small number of normal samples and abnormal samples are utilized to construct an abnormal sound classification model; and inputting the motor abnormal sound characteristic matrix into an abnormal sound classification model, detecting transient abnormality through a sliding window time sequence matching algorithm, and outputting an abnormal sound judgment result. According to the embodiment of the invention, high-precision and low-false-alarm motor abnormal sound detection under complex working conditions can be realized.

The invention belongs to the technical field of electromyographic signal classification detection, discloses an electromyographic signal classification detection method combining SNN and HDC, provides an electromyographic signal classification detection framework combining SNN and HDC, and aims to realize ultra-low power consumption operation. In the framework, the SNN executes event-driven feature extraction by using a random untrained weight, so that the calculation overhead is reduced to the greatest extent; and the HDC realizes anti-noise classification through high-dimensional representation. The integration of the two not only realizes real-time detection of energy conservation, but also is particularly suitable for being applied to resource-limited scenes such as wearable equipment and the like. The method provided by the invention realizes 95% of average accuracy (the peak accuracy is 96.44%) in three types of fatigue recognition tasks, and the training speed is 5.7 times faster than that of a one-dimensional convolutional neural network (1D-CNN) and 45 times faster than that of a five-dimensional long-short-term memory network (5D-LSTM). Even under the condition that only 20% of training data is used, the method can still keep the accuracy of 90% or above, and the high efficiency and robustness of the method in actual deployment are fully proved.

The invention relates to the technical field of medical monitoring, and provides a high-precision sleep electrocardio continuous monitoring system and method.The high-precision sleep electrocardio continuous monitoring system and method.A modular closed-loop framework is adopted, and synchronous acquisition of electrocardio, movement and respiration signals is achieved through a multi-modal sensing and high-precision synchronous acquisition module; the signal quality multi-dimensional traceability diagnosis module performs feature extraction and noise classification on the input signal; the dynamic traceability filtering processing module intelligently calls a corresponding filtering algorithm to perform signal purification according to the noise type; and the intelligent output and self-adaptive resource management module outputs high-quality electrocardiosignals and realizes dynamic optimization of system power consumption. By establishing a complete signal quality evaluation system and an intelligent processing mechanism, the whole process optimization of the sleep electrocardiosignals from collection to output is realized, and the accuracy of monitoring data and the cruising ability of the system are remarkably improved.

The invention discloses a multi-granularity financial text noise open classification method based on a large model, and belongs to the technical field of text noise classification. Performing clustering processing on the semantic features to obtain a plurality of balls with different labels, and calculating attributes of the plurality of balls with different labels; according to the positions of the samples in the pellets and the attributes of the pellets, the samples in the pellets are classified into clean samples, internal noise is distributed, and external noise is distributed. A plurality of pellets with different labels are obtained through clustering processing, the attribute of each pellet is calculated, at the moment, each category is finally represented by a plurality of pellets with the same label but different attributes, the multi-granularity prototype and the distribution range of the category can be effectively reflected, and the representation learning effect is improved. Meanwhile, classification processing is carried out according to the positions of the samples in the pellets and the attributes of the pellets, and the method can be suitable for data environments of various distribution types.

The invention relates to a magnetotelluric dead band data correction method and system based on deep learning, and the method comprises the steps: carrying out the segmentation processing of actually-measured magnetotelluric data, obtaining a plurality of original segments, carrying out the processing of each original segment through a DnCNN-GRU network, extracting a low-frequency effective signal, and separating a high-frequency noise-containing signal; performing identification and classification processing on the high-frequency noisy signal through an IncepTCN network model to identify a first high-quality fragment and a noisy fragment, and performing denoising processing on the noisy fragment through an IVIT network model to obtain a second high-quality fragment; and splicing the first high-quality segment and the second high-quality segment to obtain a spliced segment, and carrying out combination reconstruction on the spliced segment and the low-frequency effective signal to obtain a reconstructed signal. According to the invention, the method can achieve the automation of the whole process from low-frequency protection, noise classification to denoising, can avoid the manual parameter adjustment, and remarkably improves the recognition and suppression precision of complex noise.

The invention provides an environmental noise monitoring method based on multi-modal data, and relates to the technical field of environmental monitoring, and the method comprises the following steps: S1, synchronously collecting multi-modal data in an environment, the multi-modal data comprising original acoustic signals, meteorological data and video image data; s2, data processing and feature extraction; s3, dynamically adjusting the number of heads and a weight calculation mode of a self-attention mechanism based on the signal-to-noise ratio and the time domain variance of the spectrogram, and extracting voiceprint feature vectors based on the adjusted self-attention mechanism; s4, splicing the voiceprint feature vector, the meteorological feature vector and the visual feature vector into a multi-modal feature matrix along the feature dimension, and performing weighted fusion on the multi-modal feature matrix to generate a fused feature vector; s5, noise classification and early warning; according to the method, three kinds of heterogeneous modal information of acoustic signals, meteorological data and video images are fused, feature weighted fusion is realized in combination with a cross-modal self-attention mechanism, and the problem of data limitation of a single sensor is solved.

The invention discloses a noise platform analysis method based on feature extraction, and the method comprises the following steps: obtaining target noise data information, carrying out the preprocessing of the noise information, carrying out the feature extraction of the processed noise information, cleaning the extracted features, constructing a noise classification and recognition model according to the feature data, constructing a sample set, and training the model. And optimizing the model. Compared with the prior art, the noise platform analysis method based on feature extraction has the advantages that targeted feature extraction analysis can be conveniently carried out, so that noise analysis is completed, and the noise category can be output.

The invention relates to the technical field of voice communication, in particular to a voice signal processing method and device, equipment, a storage medium and a computer program product. The method comprises the following steps: performing real-time noise classification on a received original voice signal based on a preset deep neural network noise recognition model; according to the noise classification result, selecting a corresponding combined noise reduction model to perform multi-stage noise reduction processing on the original voice signal to obtain a noise-reduced voice signal, the combined noise reduction model comprising one or more of a deep neural network-based noise reduction module, a Wiener filtering module and a spectral subtraction module; and on the basis of time domain feature extraction and frequency domain feature extraction, voice feature enhancement processing is performed on the noise-reduced voice signal to obtain the target voice signal, so that the transmission quality of the voice signal is improved.

The invention provides a factory boundary noise online monitoring traceability system and method, and belongs to the technical field of noise monitoring. The system comprises a data acquisition module; the data processing module is used for judging whether factory boundary noise processing is carried out or not; when the boundary noise processing is determined to be carried out, determining a direction corresponding to the directional microphone with the maximum sound level as a noise source direction; based on the noise source direction, a data acquisition instruction is generated and sent to the data acquisition module, and audio frequency information and video information, collected in real time and fed back by the data acquisition module, in the noise source direction are recycled; and taking the audio frequency information and the video information in the noise source direction as input parameters, and based on a pre-established abnormal sound source positioning model and a pre-established sound feature recognition model, obtaining a noise source visual sound field cloud picture and a noise classification recognition result. The purposes of noise comprehensive response, noise orientation definition and noise accurate traceability are achieved, evidence is provided for factory boundary noise source definition, and disputes are effectively avoided.

The invention particularly relates to a voice noise reduction method suitable for different noise environments, and relates to the technical field of voice signal processing. Analyzing a noise environment and characteristics; adaptive selection of a noise reduction algorithm; adaptive noise reduction processing is executed; and noise reduction effect evaluation and iterative optimization are carried out. According to the invention, refined noise classification is matched with the algorithm, so that the limitation of a traditional single algorithm in a complex environment is solved; the steady-state noise is dynamically counteracted by adopting an adaptive filter, the frequency domain gain of the unsteady-state noise is adjusted in real time through Wiener filtering, and the pulse noise is subjected to dynamic threshold processing by combining median filtering and wavelet transform; especially, the design of cooperation factors in wavelet transform can accurately distinguish signal details and noise: intensively suppress pulse noise, loosely retain details such as voices and consonants, and realize dynamic balance of noise reduction intensity and signal distortion.

The invention relates to the technical field of voice processing, in particular to an edge AI-based interphone audio processing method, system and device and a medium, and the method comprises the steps: collecting and analyzing an original audio through an audio collection assembly, and obtaining an audio feature set containing noise and scene features; inputting the image into an edge side audio analysis model to obtain a noise classification and scene recognition result; dynamically adjusting filter parameters, and generating a filtering parameter group adaptive to the current environment; extracting user voiceprint features to construct an exclusive voiceprint library, and optimizing the audio in combination with the filtering parameter group to generate a personalized processing audio; and training the model locally based on the personalized processing audio and the audio feature set, generating update parameters, and updating the audio analysis model for subsequent re-analysis. The technical problem that dynamic adaptation, personalized optimization and low-power-consumption and high-performance balance cannot be achieved at the same time in the prior art can be solved.

The invention discloses an underwater target radiation noise classification method and system, and a related device. The method comprises the following steps: obtaining radiation noise signals of the same underwater target under different working conditions and radiation noise signals of different underwater targets under the same working condition; carrying out normalization and sampling processing on the obtained radiation noise signal, and carrying out enhanced image conversion on the radiation noise signal of the underwater target after normalization and sampling processing; taking the converted image data set as the input of the convolutional neural network, and classifying the radiation noise of the underwater target; specifically, on the basis of different enhanced images and a convolutional neural network, loss of effective information is effectively reduced without a noise processing link, frequency domain transformation is not carried out, limitation of frequency domain resolution is avoided, signals in different frequency ranges can be represented more robustly, a nonlinear relation is better captured, and the method is suitable for being popularized and applied. And the method is more sensitive to some nonlinear modes.

The invention discloses an image processing system based on the Internet of Things, which relates to the field of image processing technology and comprises a multispectral sensor integration module, an image feature extraction module, an edge computing module, a cloud computing guidance module, a dynamic task scheduling module and an edge-cloud feedback closed-loop module; the multispectral sensor integration module collects image data through the collaborative work of visible light and infrared light sensors; the image feature extraction module is used to extract valuable features from the image data; the edge computing module is used to realize adaptive compression; the cloud computing guidance module classifies the noise type in the image through a noise classification network; the dynamic task scheduling module comprises a high-performance mode, a basic mode and an emergency power-saving mode; the edge-cloud feedback closed-loop module regularly uploads the image quality index after noise reduction to the cloud; the invention effectively solves the problems of image noise and image quality degradation in a low-light environment while maintaining high computing efficiency and real-time performance.

To provide an information processing device, an information processing method, and an information processing program that can identify noise contained in point cloud information.SOLUTION: An information processing device includes, for example, an acquisition unit that acquires point group information and an estimation unit that classifies noise into a plurality of types on the basis of cause of noise occurring in a point group and a shape of the noise, and estimates noise included in the point group information on the basis of a trained model trained for each type and the point group information acquired by the acquisition unit. As an example, the noise may be moving object noise, pulling noise, aerial, reflected mirror noise, and other noise.SELECTED DRAWING: Figure 1

The invention discloses a character extraction method for a power transmission and transformation project document. The method comprises the following steps: acquiring data information of a target power transmission and transformation project document and preprocessing the data information to obtain a binary image of the target power transmission and transformation project document; noise detection, noise classification and noise reduction processing are carried out; carrying out character region positioning on the target power transmission and transformation project document; segmenting and extracting characters; character recognition is carried out based on a local binary pattern; and carrying out association and replacement of characters and completing character extraction of the target power transmission and transformation project document. The invention also discloses a system for realizing the character extraction method for the power transmission and transformation project document. According to the method, the image of the target power transmission and transformation project document is processed and extracted, and particularly the characters of the table part in the document are positioned, segmented, identified and replaced, so that the character extraction of the power transmission and transformation project document is realized, the reliability is higher, and the accuracy is better.

The invention relates to the technical field of power equipment fault diagnosis, in particular to a switch cabinet discharge fault dynamic diagnosis method. The environment humidity, the electric field signal and the vibration signal of the switch cabinet are acquired in real time, the compensation parameter is dynamically generated based on the environment humidity change, and nonlinear compensation is performed on the electric field signal; frequency domain features of the compensated signals are extracted, a noise classification result is output, a discharge density threshold value is adjusted in a self-adaptive mode by combining environment state quantities and the noise classification result, and the environment state quantities comprise a real-time humidity value, an equipment load rate and a historical misjudgment rate; and calculating a mutual information value of a high-frequency energy ratio and an impact strength factor through hardware acceleration, triggering fault judgment when the mutual information value exceeds a dynamically adjusted discharge density threshold, and updating diagnosis model parameters according to a judgment result.

The invention relates to the technical field of computers, and discloses an object classification method and device based on deep reinforcement learning under a complex noise condition. The method comprises: acquiring to-be-classified data; performing noise classification on the to-be-classified data based on a noise classification model obtained by deep reinforcement learning to obtain noise classification corresponding to the to-be-classified data; a noise reduction algorithm corresponding to the noise classification is called to carry out noise reduction processing on the to-be-classified data, and the denoised data is obtained; performing object classification on the denoised data based on an object classification model obtained by deep reinforcement learning to obtain an object classification result; the problem that a traditional denoising algorithm is poor in noise removal effect can be solved. According to the method, the noise reduction algorithm can be adaptively switched to perform noise reduction processing under the condition of more noise types, so that the noise reduction effect of the to-be-classified data in a complex noise scene is improved.

The invention discloses a time-frequency fusion power line noise classification modeling method, system and device based on deep learning, and a medium, and belongs to the technical field of power line noise classification modeling, and the method comprises the steps: constructing a data set containing multiple types of typical power line noise signals; performing short-time Fourier transform on the noise signal to obtain a spectrogram, and extracting local texture features in the spectrogram; extracting global time sequence characteristics of the original time domain waveform of the noise signal; splicing the local texture features and the global time sequence features to form a fusion feature vector, inputting the fusion feature vector into a full-connection neural network, and outputting a multi-label noise prediction result; and training the full-connection neural network, and updating network parameters by optimizing a binary cross entropy loss function. According to the method, different characteristics and generation mechanisms of each type of noise are considered, through fusion of time domain information and frequency domain information, the characteristics can be extracted more comprehensively, the space relation and mode of the time domain and the frequency domain are effectively captured, and the adaptability and accuracy of the model to a noise classification task are improved.

The invention discloses an environmental noise classification method based on adaptive joint parameter space optimization, and the method comprises the steps: collecting a plurality of noise signals, enabling each type of signals to correspond to a specific environmental noise type, and constructing a data set; defining a joint parameter space comprising a plurality of optimization variables, wherein the joint parameter space comprises a data enhancement parameter subspace, a model network parameter subspace and a model training hyper-parameter subspace; according to training data characteristics, environmental noise classification task complexity and model deployment constraint, adaptively calculating each parameter range space; and constructing an objective function, and searching a multi-parameter optimal collaborative combination by using Bayesian optimization. According to the method, a joint parameter space is constructed, and Bayesian optimization is utilized to adaptively search a multi-parameter optimal collaborative combination of a data enhancement parameter, a model network parameter and a training hyper-parameter in a multi-model training process, so that synchronous dynamic optimization of data enhancement, a model structure and model training is realized; and finally, the performance of the neural network model in environmental noise classification is improved.

The invention discloses an AI-driven vehicle-mounted sound field real-time modeling and voice separation method, and relates to the technical field of voice signal processing. A main control unit comprising a time sequence synchronizer, a resource scheduler and a health monitor is constructed. 3D sound field modeling is carried out by adopting a lightweight STCN + bidirectional LSTM network, adaptive updating of the model is realized through EWC incremental learning, and a CNN-LSTM noise classification network and targeted suppression algorithms such as ANF / spectral subtraction are developed. The voice separation module adopts an improved Conv-TasNet architecture, 3D spatial constraint and a multi-task loss function are fused, and low delay is realized under INT8 quantization and pipeline processing. The system dynamically optimizes parameters through a real-time regulation and control unit, supports scene self-adaption, finally achieves a separation effect in a mixed noise scene, reduces the delay of the whole system, and effectively improves the definition and stability of vehicle-mounted voice interaction.

The invention provides an image denoising method and device based on a generative artificial intelligence technology, and the method comprises the steps: inputting a to-be-denoised medical image into a noise type recognition model, and obtaining a noise classification result corresponding to the to-be-denoised medical image; inputting the to-be-denoised medical image and the noise classification result corresponding to the to-be-denoised medical image into an image denoising model to obtain a denoised medical image corresponding to the to-be-denoised medical image; the image denoising model is a conditional generative adversarial network; the noise type identification model is obtained after training based on a to-be-denoised medical image sample and a predetermined noise classification label, and the to-be-denoised medical image sample is obtained by performing noise addition based on different types of clear medical image samples; the image denoising model is obtained based on training of different types of clear medical image samples, a to-be-denoised medical image sample and a predetermined noise classification label, and can meet the denoising efficiency and precision requirements of different types of medical images at the same time.

The invention discloses a Tibetan language Andole speech enhancement method suitable for specific noise and general noise, and relates to the technical field of low-resource language speech processing. The method specifically comprises the following steps: acquiring noisy voice information; preprocessing the noisy voice information, and dividing the processed data into a training set and a test set; a noise spectrum feature input by the noise classification module is optimized based on a weighted average method of a logarithmic power spectrum domain hard threshold; constructing a noise classification task and noise suppression task fused multi-target Tibetan speech enhancement model; training and testing the built speech enhancement model by using the training set and the test set to obtain a trained speech enhancement model; and inputting the actually collected noisy speech into the trained speech enhancement model to obtain an enhanced logarithmic power spectrum. Through effective fusion of the noise classification task and the suppression task, the quality and the intelligibility of the Tibetan language Andor dialect enhancement voice are improved, the human-computer interaction of the Tibetan language Andor dialect is more perfect, and the method has a positive effect on popularization of Tibetan language informatization.

The invention belongs to the technical field of electrocardiosignal classification, and discloses an electrocardiosignal quality automatic identification and classification method, which comprises the following steps: carrying out discrete wavelet decomposition on an electrocardiosignal to obtain a low-frequency sub-band, a reconstructed sub-band and a high-frequency sub-band, and carrying out time domain feature extraction on the low-frequency sub-band, the reconstructed sub-band and the high-frequency sub-band; according to the method, wavelet analysis, time domain feature extraction and a fault diagnosis technology are organically combined, and automatic identification and classification of electrocardiogram signal quality are achieved on the premise of not depending on event features such as QRS complex waves and RR intervals.

The invention discloses a medical data intelligent identification method and apparatus. The method comprises the steps of obtaining to-be-identified target data; inputting the target data into a pre-trained intelligent recognition model to obtain a recognition result output by the intelligent recognition model, the recognition result at least comprising all sample categories of the target data and statistics of the number of the categories; wherein the intelligent identification model is obtained by training and optimizing a pre-constructed neural network by using a training data set, the training data set trains the neural network to obtain an initial network, and the initial model is optimized by using a preset optimization target to obtain the intelligent identification model. According to the intelligent recognition model based on feature distribution robustness optimization, by optimizing feature distribution, automatically exploring and constructing an optimal and most robust feature space and introducing anti-noise classification loss, the problems of medical data imbalance, annotation noise and generalization in the prior art are solved.

The invention provides a method and a system for identifying fault data of a power transformer. The method comprises the following steps: acquiring online monitoring data of multi-dimensional operating parameters of the power transformer from a data input interface; effective monitoring data generated after the online monitoring data are preprocessed are input into a dynamic threshold value model for self-adaptive threshold value calculation, a threshold value calculation result is obtained, and the effective monitoring data with the threshold value calculation result not in a set dynamic threshold value range are marked as first-level abnormal data; performing physical constraint dual verification on the first-level abnormal data, and marking the first-level abnormal data which does not pass at least one verification as second-level abnormal data; and inputting a feature vector generated by feature extraction of the secondary abnormal data into a constructed noise classification model for noise type identification, and outputting a final identification result according to a confidence value and a noise type output by a noise classification module. According to the method and the system, redundant alarms are greatly reduced, and the fault positioning accuracy is improved.

This invention discloses a multi-source electromagnetic noise suppression method based on noise classification and deep learning, belonging to the field of geophysical electromagnetic exploration technology. The method includes: segmenting and preprocessing the original electromagnetic observation sequence; using an improved U-Net network with an encoder embedded in a Mamba time-series modeling module for low-frequency noise suppression; identifying strong noise types in the data segments using a ROCKET classifier; based on the classification results, calling a second improved U-Net network trained for the corresponding noise type for class-based targeted denoising; and finally, splicing the data segments to obtain complete, high-quality data. This invention, through a phased processing framework of "low-frequency pre-suppression—noise classification—class-based denoising," combined with the strong time-series modeling capabilities of the Mamba module and the efficient classification performance of ROCKET, significantly improves the suppression accuracy and signal fidelity for complex, multi-source electromagnetic noise, and is particularly suitable for processing ground and airborne electromagnetic exploration data.

The invention relates to the technical field of voice analysis, in particular to a remote voice control method and system of a numerical control system, the system comprises a feature extraction module, a noise classification and detection module and a time window scale determination module, the feature extraction module obtains noise signals and extracts spectrum features and time features of the noise signals; the noise classification and detection module classifies the noise signals according to the spectrum features and the time features of the noise signals to generate different types of noise signals; the time window scale determining module is used for selecting different time window scales according to different types of noise signals and carrying out noise detection on the noise signals, and the time window scale determining module is used for calculating the sizes of the different time window scales according to frequency spectrum characteristics and time characteristics of the noise signals; wherein the different time window scales comprise a long time window scale and a short time window scale.