268 results about "Motion artifacts" patented technology

The invention discloses a multi-mode pet health monitoring and motion artifact elimination method and system based on a millimeter wave radar, and relates to the technical field of pet health monitoring, and the method comprises the following steps: S001, building a unified time baseline and an energy fingerprint auditing surface, constructing an energy distribution model from a chest to a tail, and taking the model as a reference for artifact evolution, identifying a signal spectrum coupling trend in a time-frequency domain; and S002, based on the energy distribution model, performing causal playback on continuous time sequence signals acquired by the millimeter-wave radar, extracting a pseudo-motion energy nucleus caused by tail or limb movement, and calibrating a phase anchor point and a space observation area of a respiratory signal. According to the method, multi-source physiological data are fused, pure respiratory signals are extracted through energy distribution modeling, causal playback, phase anchor point calibration and three-dimensional resampling, risk assessment is achieved based on physiological credibility tensor, and the accuracy and anti-interference capacity of health monitoring are improved by combining phase conjugate traction and a space-time regulation strategy.

The invention discloses a space-time speckle projection three-dimensional imaging method based on multi-frame optical flow alignment. Firstly, a projector based on DLP is used for projecting a space-time speckle pattern to a measured scene, and a binocular camera synchronously collects a three-dimensional space-time speckle image. The calibration parameters of the binocular camera are used to carry out stereo correction on an acquired original speckle image, and a parallax image is generated frame by frame in combination with a coarse-to-fine single-frame speckle matching strategy. And estimating a two-dimensional inter-frame displacement field between continuous disparity maps by using an optical flow method by taking an intermediate frame disparity map as a reference, compensating motion artifacts in a space-time speckle image, and ensuring strict space-time registration of a dynamic target. And based on the speckle image after motion correction, a speckle matching strategy is expanded to a time-space domain, and high-precision multi-frame three-dimensional measurement of a complex dynamic scene is realized. The method is suitable for performing rapid and high-precision three-dimensional modeling on a moving target in an unstructured environment, and can perform accurate three-dimensional measurement on a high-speed dynamic target undergoing any translation or rotation motion.

The invention provides a textile cloth defect real-time detection method and system based on multi-modal feature fusion, and the method comprises the steps: collecting visual image data, infrared thermal imaging data and ultrasonic acoustic data of textile cloth through a multi-sensor array, and forming multi-modal input; performing time sequence alignment and noise filtering preprocessing on the multi-modal data to eliminate motion artifacts and environmental interference; a parallel feature extraction module is used for extracting texture features from the visual data, extracting temperature distribution features from the thermal imaging data and extracting acoustic impedance features from the acoustic data. By deeply fusing complementary information of three modes of vision, thermal imaging and ultrasonic wave, the detection capability is improved, the vision mode captures surface texture details, the thermal imaging mode reveals thermodynamic anomalies related to friction and materials, the ultrasonic wave mode perceives subcutaneous structure defects, hidden flaws which cannot be recognized by a single mode can be found, and the detection efficiency is improved. Therefore, the omission ratio is greatly reduced, and flaw types are distinguished more accurately.

The invention discloses a motion artifact elimination method and system based on PPG signals, and relates to the technical field of electronic digital data processing, in particular to a high-accuracy and high-robustness artifact elimination method oriented to the PPG signals in wearable equipment. Firstly, artifact detection is carried out through a multi-base learner fusion model based on meta-learning, and efficient identification of different individual motion artifacts is realized; afterwards, for the detected artifact signals, the system introduces an AVAE model to carry out artifact removal, through multi-loss function joint optimization, high-quality PPG signals with time sequence details reserved are recovered, an effective solution is provided for high-quality perception and robustness health monitoring of the PPG signals in the wearable device in a complex dynamic environment, and the method has the advantages of being high in accuracy and high in robustness. Good popularization and application prospects are realized.

The invention discloses a patch position correction method and system, relates to the technical field of biomedical engineering and digital health, and adopts a hardware-level time synchronization and motion-artifact coupling modeling technology to effectively solve the problems of time delay drift and motion interference of signal acquisition in a dynamic environment and remarkably improve the basic quality of electrocardiosignals. Secondly, by establishing a body surface reference coordinate system and a pose compensation parameter generation algorithm, the micro-displacement state of the patch can be accurately recognized, and visual position adjustment guidance is generated, so that the patch is always kept at the optimal measurement position, and the phenomenon of signal attenuation caused by poor contact is fundamentally reduced; a signal quality multi-dimensional evaluation system adapts to quality discrimination requirements in different motion states through an intelligent weighted fusion mechanism, and combines an adaptive filtering and deep learning enhancement technology, so that the morphological integrity of a QRS waveform is kept, various interference components are effectively inhibited, and the system can still keep excellent electrocardiosignals in a strenuous motion state.

The invention relates to the technical field of health management, in particular to a teenager scoliosis intelligent monitoring system based on multi-modal sensing. Comprising a multi-modal data acquisition unit; the data preprocessing unit is used for performing standardization processing on the multi-source original data output by the multi-modal data acquisition unit, eliminating environmental interference and motion artifacts based on an adaptive Kalman filtering algorithm, and extracting quantifiable physical characteristic parameters; an intelligent analysis unit; and an early warning execution unit. According to the invention, the optical image sensor and the inertial sensor are combined through the multi-modal data acquisition unit, and accurate matching calibration of static morphological parameters and dynamic motion data is realized through a space-time association algorithm of the data association module, so that the problem of insufficient complementarity caused by lack of space-time association of multi-modal data in the prior art is solved; a complementarity data set containing static and dynamic features can be formed.

The invention relates to the technical field of image processing and biological signal detection, discloses a facial physiological detection method and system based on signal quality driven ROI selection, and aims to solve the problem of signal degradation of a traditional fixed geometric ROI in a complex scene. The method comprises the following steps: collecting a user face video stream through a camera and preprocessing the user face video stream; detecting a face bounding box and dividing the face bounding box into a plurality of sub-regions; calculating the signal-to-noise ratio, the periodic intensity and the motion artifact interference degree of each sub-region; screening an optimal sub-region according to a weighted fusion formula to generate a dynamic ROI mask; extracting a pure rPPG signal from the dynamic ROI mask coverage area; detrending and band-pass filtering are carried out on the rPPG signals, and physiological parameters such as the heart rate and the blood oxygen saturation degree are extracted. The system comprises a face video acquisition module, a face region positioning and segmentation module, a signal quality evaluation module, a dynamic ROI selection module, an rPPG signal extraction module and a physiological parameter estimation module. According to the technical scheme, signal degradation caused by local shielding, illumination abrupt change or attitude offset can be effectively avoided, the signal-to-noise ratio and the stability of the rPPG signal are remarkably improved, and the universality and the robustness of the method are enhanced.

The invention relates to the technical field of image recognition, in particular to a medical image intelligent evaluation system based on image recognition. The system comprises an image registration module, an image segmentation module, a preliminary fusion module, an image evaluation module, an optimization feedback module and an image output module. According to the method, the CT image and the MRI image are subjected to image registration, spatial alignment is ensured, then the region of interest is segmented and fused, namely, the skeleton contour in the CT image is superposed on the MRI image, and due to the fact that motion artifacts generated by movement of a patient in the scanning process possibly exist in the original CT image, the skeleton contour in the CT image is fused with the motion artifacts in the MRI image. If the skeleton contour does not exist in the MRI image, the overlapping degree and the blank degree of the skeleton contour and the anatomical structure edge of the MRI image are analyzed, and an optimized registration parameter or segmentation parameter is fed back, so that when the segmentation network is trained, the segmentation precision under the conditions of artifacts and low contrast is improved, spectrum and texture information of the two images is reserved to the maximum extent, and the fusion effect is guaranteed.

The invention provides an intelligent motion evaluation and damage early warning method and system based on multi-source biological signal fusion, and is applied to the technical field of medical data processing. The method comprises the following steps: acquiring a multi-modal biological signal acquired based on a multi-source sensing node; carrying out self-adaptive preprocessing on the multi-modal biological signals, eliminating motion artifacts by adopting an improved spectral subtraction formula, realizing multi-rate synchronization through a Lagrange kernel, triggering node vibration by virtue of signal quality evaluation to prompt electrode reattachment, and generating preprocessed signal features; and constructing cross-modal fusion features by using multi-scale cavity convolution and the like, and outputting results such as a motion mode and the like. A target depth model is trained in combination with signal optimization and data enhancement and the like, a motion pattern classification result, joint load estimation data and a damage risk scoring result are processed based on the target depth model, damage early warning information is generated, and accurate and dynamic motion evaluation and damage early warning are achieved.

The invention discloses a millimeter wave radar health monitoring method and system based on wearable equipment, and relates to the technical field of non-contact physiological signal monitoring, the specific steps are as follows: low-frequency life signals of a monitored object are collected based on frequency modulation continuous waves emitted by a radar system, and the low-frequency life signals are time sequence signals of multiple channels; performing wavelet packet decomposition and adaptive filtering on the low-frequency life signal to obtain a filtered signal; and inputting the filtered signal into a trained feature extraction and separation model, carrying out feature extraction and evaluation, and outputting a heartbeat signal and a respiration signal. According to the method, a strong anti-interference preprocessing process is constructed by fusing wavelet packet dynamic decomposition and a sub-band energy entropy threshold method and combining an NLMS adaptive filtering technology, motion artifacts and environmental noise can be effectively stripped, the signal-to-noise ratio of original millimeter wave radar signals is increased, and the anti-interference performance of the millimeter wave radar signals is improved. And a solid foundation is laid for subsequent accurate extraction of weak vital sign signals (respiration and heart rate).

The invention discloses a medical CT (Computed Tomography) communication method for high-precision synchronization of multi-source data and a CT system. Wherein the rotary control unit and the fixed control unit are connected with each other through a private wireless link, take an FPGA / MCU platform as a core, and realize microsecond-level synchronization by utilizing a unified clock source, a hardware timestamp and round-trip delay correction; during scanning, the fixing unit returns multi-source data such as bed codes, electrocardio and high-voltage parameters in real time, and the rotating unit fits and triggers instantaneous bed information based on cached data and sends the instantaneous bed information to the image reconstruction unit after the instantaneous bed information is strictly aligned with detector data. According to the scheme, traditional high-voltage cables and drag chains are replaced, hidden dangers of insulation aging, mechanical abrasion and data interruption are eliminated, and the fault rate is remarkably reduced; meanwhile, motion artifacts are inhibited, and the image definition and real-time performance are improved. Protocol multiplexing and dynamic bandwidth allocation further reduce delay and bit error rate, and support seamless expansion of subsequent modules.

The invention discloses a measuring electrode and wearable equipment. The measuring electrode includes a bottom layer, an electrode layer, and a pad. The bottom layer and the electrode layer are stacked. The liner is arranged between the bottom layer and the electrode layer, the area of the electrode layer and the bottom layer is larger than that of the liner, and the liner is wrapped by the bottom layer and the electrode layer. By means of the mode, the measuring electrode can be better attached to the skin, and the problem of motion artifacts is solved.

The invention discloses a wearable electrocardiogram monitoring method based on composite lead and intelligent reconstruction. Belongs to the technical field of medical signal processing and wearable medical instruments, and solves the technical problems of insufficient multi-lead information amount, poor lead stability, motion artifact interference, unreliable missing lead complementation and the like of the existing wearable electrocardio equipment. According to the technical scheme, the method comprises the steps that a plurality of non-inductive electrodes are arranged on a trunk to achieve multi-channel collection of composite leads; the front end uses an analog front end (AFE); multi-stage denoising is carried out cooperatively at the equipment end and the edge end; when the lead is missing or poor in quality, complementing the lead by using a deep reconstruction network of cross-lead attention and fuzzy gating; and finally, inputting the purified or reconstructed electrocardiosignal into a multi-label deep learning classifier. According to the method, the wearing comfort, the information integrity, the transmission efficiency and the real-time diagnosis capability are considered, and the method is suitable for multi-scene long-time electrocardiogram monitoring and early warning in families, hospitals, exercise rehabilitation and the like.

The invention discloses a blood vessel inner diameter correction method and device based on an X-ray total attenuation conservation principle and a storage medium, and belongs to the technical field of medical image processing. The core of the method is to discover and utilize the total net attenuation of a blood vessel filled with a contrast agent in an actual motion state and the total net attenuation of the blood vessel in an ideal static state to be kept in conservation. The method comprises the steps that an angiography image is acquired, and a target area and an initial inner diameter measuring line are determined; calculating the gray scale decline amount and the maximum value of each pixel of the line; on the basis of the conservation principle, the inner diameter of the blood vessel in an ideal state is inversely calculated through the formula that the inner diameter is corrected to be equal to sigma [(delta Ii / delta Imax) * Li]. Furthermore, based on the same principle, the method can be expanded and applied to correction of the two-dimensional contour of the target blood vessel. According to the method, errors caused by motion artifacts and resolution limitation are fundamentally compensated through a volume measurement method based on integration and distribution, and the method is particularly suitable for accurate measurement of severe stenosis blood vessels.

The invention discloses a small animal in-vivo multi-parameter dynamic monitoring method based on photoacoustic imaging, and relates to the technical field of biomedical imaging, and the method comprises the steps: obtaining a photoacoustic signal generated by a small animal under the excitation of pulse laser output by an optical excitation module through an acoustic detection module; reconstructing a photoacoustic image of the photoacoustic signal through a filtering back projection algorithm; calculating the similarity between adjacent images in the photoacoustic image, identifying the image of which the similarity is lower than a set frame threshold value as a cross section slice polluted by respiratory motion artifacts and removing the cross section slice, and replacing the removed image frame by using the interpolation of an adjacent artifact-free image so as to obtain an updated photoacoustic image; selecting a region of interest in the photoacoustic image, and carrying out oxygenation kinetics monitoring, pharmacokinetics monitoring, perfusion kinetics monitoring or nanoparticle in-vivo kinetics monitoring; according to the monitoring method, motion artifacts caused by breathing of the small animals are effectively inhibited, and in-vivo multi-parameter dynamics monitoring of the small animals is achieved.

Systems and methods are provided for performing Doppler (phase-sensitive) optical coherence tomographic vibrometry measurements involving the vibrometric response of a rigid structure to an acoustic stimulus, such that the impact of speckle noise on a calculated vibrometric measure is reduced. Detected signals are processed to determine a depth range associated with the rigid structure, and to provide sampled time-dependent phase data encoded with the vibratory response of the rigid structure during application of the acoustic stimulus. The sampled time-dependent phase profile is processed to generate a vibrometric measure characterizing the rigid structure, based on non-uniformly-weighted contributions from one or more subregions within the depth region associated with the rigid structure (and optionally one or more time windows). The contribution from each subregion may be dependent on a depth-domain intensity measure associated with the subregion, where each subregion may be sufficiently small to encompass speckle-induced spatially-dependent changes.

The invention discloses a self-reference three-phase polarization imaging system and method based on an integrated photon neural network, and the method comprises the steps: setting a fixed phase difference in a silicon-based photon chip to achieve three-phase projection and single-port reading, outputting a three-phase interference signal at the same time, obtaining all phase and polarization information in one-time imaging to achieve full-polarization measurement, and carrying out the single-port reading of the silicon-based photon chip; according to the invention, the effective resolution ratio is consistent with that of an original detection array, power and temperature drift is eliminated, single-frame acquisition has no time sequence error and motion artifact, a stable and compact single-port self-reference reading mode is realized through a three-phase interference measurement architecture constructed on a chip in combination with channel normalization and rotation correction, and complete Stokes parameters and polarization information can be measured. According to the system provided by the invention, the MZI is adopted, so that the phase bias can be flexibly adjusted, and different bandwidth requirements can be met by adjusting an interference path. The silicon-based photon platform has a broadband response characteristic and can cover a visible wave band, so that the device can keep stable interference performance in a communication wave band.

The invention discloses a video pulse wave extraction method and system based on automatic noise recognition. The method comprises the steps that a face area is divided into a plurality of sub-areas; calculating the signal-to-noise ratio of each sub-region in the pulse frequency band, and performing weighted fusion on the original pulse signals of each sub-region according to the signal-to-noise ratio; performing ensemble empirical mode decomposition on the fusion signal; according to the peak-to-peak interval variation coefficient, the amplitude stability index and the spectrum purity, determining a noise component dominated by the motion artifact; performing adaptive filtering processing on the fused signal by using an adaptive filter and taking a reference noise signal as input; carrying out distortion detection on the filtered fusion signal, and carrying out signal restoration processing on a detected distortion region to obtain an extracted pulse signal; in order to solve the problem that in the prior art, when video pulse signals are extracted, motion artifacts and physiological signal frequency spectrums are overlapped, and consequently signal separation of a traditional frequency domain filtering method fails, effective signal separation and accurate pulse signal extraction are achieved.

The invention discloses an rPPG physiological signal reconstruction recognition system based on generative adversarial optimization, and relates to the technical field of data processing. The system comprises a signal preprocessing module used for extracting an initial rPPG signal from an input video sequence; and the signal reconstruction module comprises a generator and is used for receiving the initial rPPG signal and outputting a reconstructed rPPG signal. According to the method, by introducing a multi-dimensional discriminator set and physiological prior loss collaborative optimization mechanism, the precision and robustness of rPPG signal reconstruction are remarkably improved. The system can restrain signal quality from multiple angles of time domain, frequency domain and time-frequency domain, and restrain irrational fluctuation in combination with physiological laws, thereby effectively overcoming motion artifacts and illumination interference. Meanwhile, the dynamic region-of-interest selection module adaptively focuses an optimal signal region through a learnable attention mechanism, the input quality is improved from the source, and finally high-reliability estimation of the physiological parameters such as the heart rate and the respiration rate in a complex scene is achieved.

The invention relates to the technical field of early screening of child autism, in particular to a child autism recognition method and system based on fNIRS signals and wearable equipment, and the method comprises the steps: collecting forehead multi-band cerebral blood flow signals and head movement data of a child through an fNIRS intelligent helmet; the method comprises the following steps: eliminating motion artifacts by using an edge computing chip, obtaining a noise-reduced fNIRS signal through adaptive filtering, extracting a time-domain signal slope, a frequency-domain wavelet energy entropy and an inter-channel function connection matrix, and processing time-frequency features and topological features by using a 1D convolution branch and a graph convolution branch by means of a double-current neural network, thereby obtaining a noise-reduced fNIRS signal. After features are fused, an autism risk probability value is output through channel attention weighting, a screening grade report is generated and transmitted to a mobile terminal, the system comprises a signal acquisition unit, an edge processing unit, an intelligent analysis unit and an interactive output unit, the system is adaptive to daily scenes of children, and the screening precision is improved.

The invention relates to the technical field of brain-computer interfaces, in particular to a wearable helmet brain-computer control system and a wearable helmet brain-computer control method. The wearable helmet brain-computer control system comprises a multi-mode sensor assembly, an inertial measurement unit, an inertial measurement unit, an inertial measurement unit and a brain-computer interface control module, and the multi-mode sensor assembly is used for synchronously collecting electroencephalogram, electrocardiogram and electromyogram physiological signals and head movement data of the inertial measurement unit; the motion artifact removing module is used for predicting motion artifacts through a Hammerstein-Wiener model on the basis of IMU (Inertial Measurement Unit) data, separating artifact components in mixed electroencephalogram signals by combining an independent component analysis model, and reconstructing pure electroencephalogram signals; the central processor is used for carrying out feature extraction and decoding on the pure electroencephalogram signal and generating a control instruction; the control instruction interface is used for outputting the control instruction to external equipment; the storage module is used for storing an original signal and a processing result; the wireless transmission module is used for realizing data interaction with a terminal; the core problems that a traditional device is poor in signal quality and unstable in control in a dynamic environment are effectively solved.

The invention discloses an intelligent monitoring system for motion data of a gravitational rod, and the system comprises the following modules: a motion data collection module which is used for deploying multiple types of sensor arrays in the gravitational rod and at a holding part, so as to collect a corresponding multi-source sensing data set in the motion process of the gravitational rod in real time; the motion data processing and resolving module is used for carrying out layered preprocessing on the multi-source sensing data set to generate a standardized motion-physiological data set; performing motion positioning calculation and noise modeling based on the de-noised time domain vibration waveform, and performing motion artifact calibration and motion and generation calculation at the same time to generate a gravity rod motion monitoring result; the communication interaction module is used for encrypting and compressing the gravity rod motion monitoring result, transmitting the gravity rod motion monitoring result to an external terminal device, displaying a corresponding visual display result in real time, and feeding back and adjusting at the same time; and the power supply module supplies power to the modules and dynamically adjusts the power supply power according to the working state of each module. The method can improve the monitoring efficiency of the motion data of the gravitational rod.

The invention relates to the technical field of electroencephalogram signals, in particular to a method, a device and equipment for removing motion artifacts of electroencephalogram signals, and the method can obtain to-be-processed electroencephalogram signals, decompose the electroencephalogram signals into a plurality of mutually orthogonal intrinsic mode components by utilizing multivariable empirical mode decomposition, and obtain motion artifacts of the electroencephalogram signals. The real electroencephalogram signal and the artifact signal are decomposed into different components; standard mutual information between each intrinsic mode component and a preset class label is calculated; multiplying the standardized mutual information by a corresponding intrinsic mode component to obtain an optimized signal component, so that a component related to a real signal is enhanced, and an artifact signal is weakened; all the optimized signal components are accumulated, and the electroencephalogram signals with the motion artifacts removed are obtained. It can be understood that according to the technical scheme shown by the invention, through multi-level and multi-dimensional signal decomposition and artifact removal processing, the motion artifacts can be accurately recognized and removed, and the quality of the electroencephalogram signals is greatly improved.

The near-infrared wearable subcutaneous fat metabolism monitoring device comprises a flexible substrate, a multi-wavelength NIR light source array, a photoelectric detector, a motion artifact suppression module, a wireless transmission unit, a fixing band and a photonic crystal enhanced detector, and the flexible substrate comprises a biocompatible layer, an optical window array and a pressure sensing layer. The wavelength of the multi-wavelength NIR light source array is 760nm / 850nm / 930nm / 980nm, the photoelectric detector is high-sensitivity InGaAs, the motion artifact suppression module is provided with an embedded signal processing module, the embedded signal processing module contains a motion artifact elimination algorithm, the wireless transmission unit is BLE5.0, the fixing band is connected with the flexible substrate, and the flexible substrate is connected with the fixed band. A first subcutaneous fat oxidation characteristic database based on time-frequency analysis is established by installing a fat oxidation dynamic fingerprint spectrum technology, FODS = summa 850980d [mu] a (lambda, t) dt.e-j2pif0tdt (f0 = 0.05 Hz) FODS = summa 850980dtd [mu] a (lambda, t). E-j2pif0tdt (f0 = 0.05 Hz), metabolic oscillation characteristics are extracted through wavelet-Hilbert transform, and a metabolic activity quantitative evaluation core algorithm WO2023 / 123456 is realized.

The invention relates to the technical field of radiotherapy, and discloses a multi-modal image fusion guided chest tumor adaptive radiotherapy system. The system comprises an asynchronous bimodal sensing module, a spectrum preprocessing module, a parameter inversion module, a boundary construction module and a biomechanical calculation module. According to the method, the feedback voxel-level velocity field is utilized to execute Lagrange reverse warping on the high-energy projection with physical time delay, and motion artifacts are eliminated; and dynamically updating the Young modulus of the lung tissue mechanical model based on the inverted real-time electron density, and solving a full-field three-dimensional displacement field in combination with double boundary conditions of body surface flexibility and internal skeleton rigidity so as to reconstruct a tumor target region and generate a beam control instruction. According to the method, through closed-loop interaction of image physics and biomechanics, the problems of dual-energy imaging motion artifact interference and insufficient lung tissue fixed parameter modeling precision are solved, and accurate self-adaptive tracking of a tumor target region is realized.

This invention discloses a preprocessing method for highly polluted pediatric EEG data, belonging to the field of EEG signal processing technology. The invention proposes a robust motion artifact detection method based on a multi-channel voting mechanism. This method overcomes the sensitivity of single-channel detection to transient noise through multi-channel joint decision-making, automatically identifying time periods requiring restoration. A comprehensive preprocessing workflow integrating PCHIP interpolation restoration, adaptive Bayesian wavelet denoising, bandpass filtering, and independent component analysis is designed. This workflow is validated using real pediatric continuous task EEG data. This invention demonstrates excellent performance in preserving frequency band information and improving the weighted signal-to-noise ratio, achieving an average accuracy of 96.4% (205 test cases) and a maximum of 100% based on permutation entropy feature classification. This invention effectively solves the preprocessing challenge of pediatric EEG data in high-noise environments, significantly improving the accuracy and reliability of subsequent classification tasks.

The present invention relates to a method for detecting and removing a motion artifact of a functional near-infrared spectroscopy signal. Disclosed are a method and a device for detecting and removing a motion artifact of a near-infrared spectroscopy signal in real time on the basis of an artificial neural network model, the method comprising: a conversion step of converting time series data of functional near-infrared spectroscopy signals measured through a plurality of channels from a target into image data; a detection step of detecting whether noise is present in the converted image data using a pretrained detection model; and a removal step of removing noise from image data where noise has been detected using a pretrained noise removal model.

This invention discloses a high-precision phase recovery method for tooth surface fringe images during gear rotation. The method first establishes an N-step static phase-shift image dataset of the gear at subdivided rotational positions. When constructing network training data pairs, three image combinations with different position indices and phases satisfying the standard three-step phase shift are selected to generate an input sequence simulating unidirectional rotation and motion errors. The high-precision sine and cosine terms calculated using the N-step static images are used as labels. Secondly, an encoder-decoder deep neural network with a bottleneck layer dual attention mechanism and global residual connections is constructed and trained using an adaptive loss function. Finally, the dynamic image to be tested is input into the network to directly predict the sine and cosine terms, calculating the wrap-around phase without motion artifacts. This invention effectively suppresses motion errors caused by gear rotation, contributing to the high-precision reconstruction of the three-dimensional morphology of the tooth surface.

The invention discloses a micro-lens array non-scanning type laser interference three-dimensional imaging method and device for a dynamic sample, and relates to the technical field of optical three-dimensional measurement and imaging, and the method comprises the steps: dividing laser into object light and reference light; irradiating a dynamic sample arranged at the focal plane of the micro-lens array with the object light after beam expansion, modulating the object light carrying sample information by the micro-lens array, and combining the modulated object light with the reference light in space to generate a composite interference field containing a plurality of sub-region interference patterns; recording a single-frame composite interferogram by an area array detector; and finally, reconstructing the three-dimensional morphology of the sample at the measurement moment through a phase extraction and unwrapping algorithm. By means of the mode, full-view-field three-dimensional information can be obtained through single exposure by means of the microlens array, mechanical scanning or multi-frame phase shifting is not needed, the problem of motion artifacts generated when a dynamic sample is measured through a traditional interference method is effectively solved, and high-speed and high-resolution three-dimensional imaging of the surface appearance of the dynamically-changed sample is achieved.

An ear-associated assistive system is disclosed that integrates acoustic sensing and inertial sensing to generate motion-compensated spatial parameters for hearing assistance and, in certain embodiments, to control stimulation for implantable auditory and / or vestibular interfaces. The system maintains temporal alignment between inertial samples and audio samples by maintaining a deterministic mapping between inertial sample times and audio sample indices, including across power-state transitions, thereby enabling reliable sensor fusion and consistent outputs. In certain implementations, an ear-frame coordinate system is established based on fixed mechanical placement of an inertial sensing subsystem relative to one or more microphones, and calibration parameters are stored to align sensor axes, microphone geometry and latency. A processor computes a head-motion state from inertial data and transforms an ear-frame direction estimate derived from acoustic data into a stabilized direction parameter expressed in a stabilized coordinate frame, optionally outputting a quality metric indicative of validity. The stabilized direction parameter and / or quality metric may be used for beamforming, binaural rendering and routing. The system may further detect motion events and apply safety gating rules to mitigate motion artifacts and constrain acoustic output and / or stimulation, subject to safety constraints and, in certain embodiments, clinician-defined bounds. Interoperability with an external directional accessory is also described, wherein inertial-acoustic fusion is used to stabilize directional operation and maintain consistent routing.