197 results about "EMG - Electromyography" patented technology

Methods and systems are disclosed for collecting EMG speech signals using a speech signal detection device. The methods and systems collect a combination of signals comprising electromyograph (EMG) data signals and one or more non-EMG data signals. The methods and systems process the combination of signals by a machine learning (ML) model to detect inner speech of the user, the ML model trained to establish a relationship between training signals comprising training EMG data signals and training non-EMG data signals and ground-truth inner speech data and, in response, performing one or more operations associated with the speech signal detection device.

The invention relates to the technical field of signal processing, and provides an electromyogram data-based muscle movement analysis method, device and equipment and a storage medium, the electromyogram data-based muscle movement analysis method comprises the following steps: using an adaptive filter to pre-process original electromyogram signals, and dynamically filtering noise signals; segmenting the electromyographic signal after the noise signal is filtered by using a sliding window, calculating the energy of the signal in each window, and detecting the zero-crossing rate of the signal in each window; performing wavelet threshold denoising on the original electromyographic signals to obtain wavelet domain features; fusing the signal energy, the zero-crossing rate and the wavelet domain features to form a feature vector; and inputting the feature vector into a pre-trained classification model for analysis to obtain a muscle motion state. The signal energy, the zero-crossing rate and the wavelet are fused with the features for analysis, real-time effective analysis of the muscle motion state is achieved, and the accuracy of muscle motion state analysis under the dynamic condition is improved.

An electromyographic gesture detection system for wearable devices, useful for entering text, selecting, controlling and manipulating virtual objects and smart applications on a display using gestures of the user. A wearable band is adapted to allow electromyographic detection and classification of specific gestures. The wearable device in some embodiments may also be adapted to recognize certain characteristics of the gestures, such as duration or amplitude, to allow enhanced navigation of a computer interface.

A system of fibers, filaments, and / or other electrically conductive materials forms an electrically conductive-to-semi-conductive yarn that can be assembled into a textile for measurement of voltage, current, resistance, capacitance, inductance, RF, and / or EM signals. Textiles are formed through weaving, knitting, lacing, and / or non-woven mechanical methods of yarn-making into 2D / 3D structures. Textile-based electrodes can be formed via folding, cutting, layering, sewing, and / or embroidering patterns to control signal transmission within / through the electrode. Multiple electrodes are positioned on a surface (e.g., a body) to sequentially or simultaneously perform multiple diagnostic modalities (e.g., electrocardiography, electromyography, electrooculography, electroencephalogram, bioelectrical impedance analysis, skin impedance analysis, and / or electrodermal activity). These modalities are multiplexed using an optimized electrode set through amplitude and frequency deconvolution and filtering algorithms to minimize the quantity of electrodes and connections on the surface while maximizing signal-to-noise ratio, differential and common mode noise rejection, and elimination of external signals (e.g., RF and EM noise).

The present invention discloses a stretchable wristband high-density electromyography system for thumb micro-gesture recognition, including a high-density electromyography array and a micro wireless acquisition module; the high-density electromyography array includes three layers of flexible materials, the middle layer of flexible material is printed with flexible electrodes and interconnects, the uppermost and lowermost layers of flexible materials can be removed when in use, and the high-density electromyography array is formed with three parts: a soft skin sensing component, a flexible interconnection, and a rigid pluggable contact pad, wherein the soft skin sensing component is used to closely conformally adhere to the wrist skin, and a flexible electrode is arranged on it, which is electrically connected to the rigid pluggable contact pad through a flexible interconnection, and the rigid pluggable contact pad is a plug-and-play FPC interface for connecting to the micro wireless acquisition module. The system can be directly fitted with the wrist, capture high-fidelity surface electromyography of dynamic and fine gestures centered on the thumb, and apply it to human-computer interaction control.

Systems, methods, and computer programs for eye tracking. In one embodiment, an eye tracking system includes a head-mounted device that takes measurements indicative of a position of the eye of a user. A head-mounted camera captures an image of the eye. A computer calculates the position of the eye based on the measurements, utilizes the position of the eye to crop the image around the pupil, and provides a cropped image to a video-based eye tracker. Optionally, the size of the cropped image is less than a third of the size of its respective uncropped image. Optionally, the head-mounted device includes one or more of the following: a photosensor-oculography device (PSOG), an electrooculography device (EOG), an electromyography device (EMG), an optical flow sensor, and a range sensor. Optionally, the image-based eye tracker calculates, based on the cropped image, at least one of pupil diameter and pupillary response.

Methods and systems are disclosed for collecting EMG speech signals. The methods and systems present a target word for electromyograph (EMG) data collection on a graphical user interface (GUI) and receive input to initiate recording of EMG data. The methods and systems, in response to receiving the input, collect, by an EMG communication device, a set of EMG signals generated based on an individual user of the EMG communication device over a threshold period of time. The methods and systems determine whether the set of EMG signals collected over the threshold period of time corresponds to the target word and present feedback in the GUI based on whether the set of EMG signals collected over the threshold period of time corresponds to the target word.

Methods and systems are disclosed for synthetically generating inner speech training data. The methods and systems access a collection of overt speech signals representing phonemes, phoneme sounds, words or phrases spoken at least partially using overt speech. The methods and systems transform the collection of overt speech signals into inner speech training data comprising electromyograph (EMG) data representing inner speech corresponding to the phonemes, phoneme sounds, words or phrases spoken at least partially using the overt speech. The methods and systems train a machine learning model to decode inner speech signals into a set of corresponding phonemes, phoneme sounds, words or phrases based on the inner speech training data.

The invention relates to a multi-mode human body respiration prediction method and system. The method comprises the steps that a difference value time sequence T is obtained through a visible light video and a thermal infrared video, and then the respiration frequency f1 of a target human body is obtained; collecting an electrophysiological signal containing a surface diaphragm electromyogram from the thoracic skin surface by means of an electromyographic signal collection system, and processing the electrophysiological signal to obtain a separated diaphragm electromyographic signal E; the heart rate f2 of the target human body is obtained through an electrocardiosignal collecting system; acquiring an environmental parameter Y of the target human body by using an environmental parameter acquisition system; the parameters obtained in the step S1-4 are processed, and a breathing state evaluation model is built; and S4, optimizing and constructing a BP neural network, and predicting the respiratory movement state of the human body by matching the sample data obtained in the step S5 with the BP neural network.

Methods and systems are disclosed for collecting electromyograph (EMG) speech signals using a speech signal detection device and calibrating the speech signal detection device using online learning. The system accesses a machine learning (ML) model that has been trained based on a collection of training data to detect presence of inner speech (silent speech or any other form of speech) and collects, by a speech signal detection device, a combination of signals comprising EMG data signals and one or more non-EMG data signals. The system processes the combination of signals by the ML model to predict presence of inner speech and updates the collection of training data based on the combination of signals and prediction made by the ML model. The system retrains the ML model in an online learning approach using the updated collection of training data.

A closed-loop neuromodulation system includes at least one implantable neurostimulator configured to deliver electrical stimulation to a target nerve innervating a muscle; at least one biosignal sensor configured to detect a physiological signal associated with the target muscle, wherein the physiological signal may include an electromyographic (EMG) or electroneurographic (ENG) signal; and a controller operatively coupled to the neurostimulator and the sensor. The controller is configured to receive the physiological signal from the sensor, determine whether the signal satisfies a predefined condition indicative of weakness, strength, fatigue, muscle underactivity, or overstimulation, and, in response to detecting that the condition is satisfied, automatically adjust one or more stimulation parameters selected from amplitude, frequency, pulse width, train duration, or train count.

An exemplary system and method are disclosed that employs (i) a forearm-based soft wearable hand-gesture recognition system that may detect a user's hand gestures as sensed from electromyographic signals acquired at a user's forearm and (ii) an AI-based classifier to continuously determine in real-time hand gestures as HMI inputs from the sensed EMG signal. The forearm-based soft wearable electronic system may be integrated into a soft, all-in-one wearable device having a scalable electrode array and integrated wireless system that may can measure electromyograms for real-time continuous recognition of hand gestures.

A computer-implemented method, system, and computer program product for predicting fatigue and injury risk for users, such as workers performing material handling operations, in real-time. Motions performed by a user, such as lifting, carrying, and manipulating objects, are captured in real-time, such as via camera-based optical devices, electromyography sensors, and inertia measurement units. Upon capturing motions performed by the user, such captured motions are utilized by a trained machine learning model to predict fatigue and injury risk to users. Such a prediction is made by the trained machine learning model by comparing the captured motions to predefined thresholds of range of motion constraints based on the biomechanical parameters of the user from a digital twin model of the user. Feedback may then be provided based on the predicted fatigue and injury risk of the user, such as in the form of video, audio, and / or haptic alerts.

An electromyography (EMG) measurement device includes a garment configured to be worn on an anatomical region of an associated wearer, a plurality of electrodes arranged on the garment to contact skin of the anatomical region when the garment is worn on the anatomical region of the associated wearer, electronics operatively connected with the plurality of electrodes and configured to measure EMG data emanating from the anatomical region, and an electronic processor programmed to derive a contribution of spatial muscle activity of a target muscle or muscle group to the measured EMG data.

A computer-implemented method for detecting onset of a spontaneous breath by a patient coupled to a ventilation system includes receiving, at a processor, an electromyography (EMG) signal from an EMG sensor disposed on the patient. The method also includes pre-conditioning, via the processor, the EMG signal to separate the EMG signal into a plurality of components having EMG information utilizing a set of bandpass filters. The method further includes individually analyzing, via the processor, each component of the plurality of components to detect an onset of the spontaneous breath by the patient. The method still further includes determining, via the processor, the onset of the spontaneous breath by the patient is occurring when at least two components of the plurality of components indicate the onset of the spontaneous breath by the patient.

Methods and systems are disclosed for training a machine learning (ML) model to detect inner speech. The system collects, by an electromyograph (EMG) communication device used by a user, a first set of EMG signals over a first time interval. The system generates a first plurality of features based on the first set of EMG signals and generates a first probability associated with presence of inner speech by processing the first plurality of features with a machine learning (ML) model. The system compares the first probability generated by the ML model to a specified threshold and detects presence of the inner speech of the user in response to determining that the first probability generated by the ML model transgresses the specified threshold.

A tremor suppression device includes a garment wearable on an anatomical region and including electrodes contacting the anatomical region when the garment is worn on the anatomical region, and an electronic controller configured to: detect electromyography (EMG) signals as a function of anatomical location and time using the electrodes; identify tremors as a function of anatomical location and time based on the EMG signals; and apply neuromuscular electrical stimulation (NMES) at one or more anatomical locations as a function of time using the electrodes to suppress the identified tremors.

Methods and systems are disclosed for training a user-specific machine learning (ML) model to detect inner speech. The system accesses the ML model trained to detect inner speech based on a general population dataset. The system collects, by an electromyograph (EMG) communication device, a set of EMG signals generated based on an individual user of the EMG communication device. The system updates parameters of the ML model based on the set of EMG signals associated with the individual user. The system detects inner speech of the individual user by applying the ML model with the updated parameters to a new set of EMG signals received from the EMG communication device.

The invention discloses a gesture recognition system and method based on multi-channel mixing of EMG, FMG and IMU. The system comprises a multi-channel signal acquisition module, a signal conditioning and synchronous acquisition circuit, a data preprocessing module, a deep neural network fusion recognition module and an output interface module. By integrating a surface electromyogram, a muscle force diagram and an inertial measurement unit, synchronous acquisition of multi-modal physiological signals of the forearm of a human body is realized; a double-flow convolution-time sequence attention fusion network (DCTANet) is adopted for feature extraction and classification decision making, and neuromuscular activity, muscle mechanical response and limb movement information are effectively fused. The accuracy, robustness and real-time performance of gesture recognition are improved, and the method is suitable for the fields of intelligent prostheses, wearable interaction, rehabilitation training and the like. The system is compact in structure, supports embedded deployment, and has a good practical prospect.

Systems, processes and device configurations are provided for electronic game control with electromyography (EMG) sensing. Embodiments include processes for receiving EMG sensor output and detection of EMG user controls, such as user electrical activity in connection with movement of fingers and hands, and output of user EMG control signals for control of electronic game content. EMG signals may be detected by a one or more sensors on a wrist strap to detect user signals and secure user controllers. Embodiments include game controller configurations and systems for electronic game content presentation. Game controller configurations may include at least one of an interface for receiving EMG data and for powering EMG sensors. System configurations may include processing EMG signals and user activation signals of a game controller to reduce latency of generated game content. Machine learning models are described for training and use to identify user control signals from the EMG signal.

An intelligent interactive neuromodulation system by intravesical and pelvic floor stimulation is provided, including: an electromyography (EMG) acquisition module, an intelligent diagnostic module, a display interaction module, and an electrical stimulation module. The intelligent diagnostic module is configured to receive an original EMG signal acquired by the EMG acquisition module and obtain feature information, generate a first treatment protocol by using the feature information and a preconfigured intelligent fitting model, and generate a classification result of an abnormal bladder activity based on the feature information and a preconfigured intelligent classification model; in response to identifying that a detrusor activity of a patient changes, automatically complete dynamic switching between a first treatment mode and a second treatment mode. The display interaction module is configured to receive a first treatment protocol and a second treatment protocol, and send the first treatment protocol to the electrical stimulation module to apply electrical stimulation pulses.

An electromyography (EMG) measurement system includes a garment configured to be worn on an anatomical region, electrodes arranged on the garment to contact skin of the anatomical region when the garment is worn on the anatomical region, electronics connected with the electrodes to measure EMG data emanating from the anatomical region, and an electronic processor programmed to filter the EMG data to suppress or remove artifacts using filters computed using approximate joint diagonalization of covariance (AJDC) matrices or by transforming the EMG data to source signals using iteratively adjusted forward filters.

Methods and systems are disclosed for collecting EMG speech signals using a speech signal detection device. The methods and systems collect, by a speech signal detection device worn by a first person, a combination of signals comprising electromyograph (EMG) data signals and one or more non-EMG data signals. The methods and systems process the combination of signals by a machine learning (ML) model to detect presence of a second person, the ML model trained to establish a relationship between training signals comprising training EMG data signals and training non-EMG data signals and ground-truth presence of people data. The methods and systems control operation of the speech signal detection device being worn by the first person in response to detecting the presence of the second person.

A user interface system enables communication through inaudible speech by detecting physiological signals associated with inner voice communication. The system includes a wearable device positioned in, on, or around a user's ear, housing one or more sensor modalities such as electromyography (EMG) sensors for detecting muscle movements, functional near-infrared spectroscopy (fNIR) sensors for brain activity, and / or detection-and-ranging systems using sonar or radar for micro-deformations. Pre-processing modules condition the sensor data, which is then analyzed by one or more machine learning models to reconstruct the content of the user's inaudible communication and produce output representations. The system enables high-bandwidth natural language interaction without audible vocalization, maintaining privacy while supporting applications including AI assistant interaction, real-time translation, secure authentication, and inter-party communication.

The embodiment of the present application discloses a speech processing method, device, electronic device and computer-readable storage medium, and the method is applied to an extended reality device. The method includes: when a first speech acquisition device acquires a first speech, acquiring the current facial electromyogram of the wearer; acquiring a pre-acquired target facial electromyogram when the wearer is speaking; determining whether the wearer is speaking based on the current facial electromyogram and the target facial electromyogram; when the wearer is speaking, acquiring a second speech acquisition device to directionally acquire a second speech; distinguishing the speech of the non-wearer based on the first speech and the second speech; converting the speech of the non-wearer into text, and displaying the text on a virtual screen. In this way, the present solution can determine whether the wearer is speaking through the facial electromyogram of the wearer, thereby accurately distinguishing the speech of the wearer and the non-wearer, and then accurately displaying the text converted from the speech of the non-wearer on the virtual screen.

Disclosed is a signal measuring device including: at least one electrode configured to contact with a human body to collect an electromyographic (EMG) signal of the human body in a target frequency range; an alternating current (AC) excitation source electrically connected to the at least one electrode, the AC excitation source being configured to provide an excitation signal at a first frequency to generate a detection signal reflecting a contact impedance between the at least one electrode and the human body; and a gain circuit configured to provide a gain for the EMG signal and the detection signal. In the present disclosure, by providing the gain circuit, gains are provided for the EMG signal and the detection signal collected so as to improve strengths and qualities of the EMG signal and the detection signal, and enable an accurate monitoring of the signal measuring device.

Systems, apparatuses, and methods described herein facilitate the placement of spinal cord stimulator (SCS) electrode in relationship to neural tissue of the spinal cord based on electromyography (EMG) data. The systems, apparatuses, and methods are designed to assist physicians and surgeons target specific neurophysiological locations through stimulation and subsequent visualization of EMG activity in response to stimulation to more precisely identify the location of the SCS electrodes that will maximize the intended therapeutics effects of SCS.

An electromyography (EMG) measurement system includes a garment configured to be worn on an anatomical region, electrodes arranged on the garment to contact skin of the anatomical region when the garment is worn on the anatomical region, electronics connected with the electrodes to measure EMG data emanating from the anatomical region, and an electronic processor programmed to filter the EMG data to suppress or remove artifacts using filters computed using approximate joint diagonalization of covariance (AJDC) matrices or by transforming the EMG data to source signals using iteratively adjusted forward filters.

Methods and systems are disclosed for training a machine learning (ML) model to detect inner speech. The system collects, by an electromyograph (EMG) communication device used by a user, a first set of EMG signals over a first time interval. The system generates a first plurality of features based on the first set of EMG signals and generates a first probability associated with presence of inner speech by processing the first plurality of features with a machine learning (ML) model. The system compares the first probability generated by the ML model to a specified threshold and detects presence of the inner speech of the user in response to determining that the first probability generated by the ML model transgresses the specified threshold.

Systems, apparatuses, and methods described herein facilitate the placement of spinal cord stimulator (SCS) electrode in relationship to neural tissue of the spinal cord based on electromyography (EMG) data. The systems, apparatuses, and methods are designed to assist physicians and surgeons target specific neurophysiological locations through stimulation and subsequent visualization of EMG activity in response to stimulation to more precisely identify the location of the SCS electrodes that will maximize the intended therapeutics effects of SCS.