123 results about "Accelerometer data" patented technology

The invention discloses a sleep staging detection method and system based on a smart watch, and the method comprises the steps: S1, obtaining the heart rate variability, triaxial accelerometer data and body movement intensity index signals of a wearer through a sensor of the smart watch, and carrying out the multi-source signal fusion and time synchronization; s2, carrying out noise reduction processing on the synchronized multi-source signal, and constructing a feature vector; s3, calculating a time sequence self-correlation feature of the feature vector; s4, based on a bidirectional long and short time memory network structure, performing time sequence modeling on the input feature vector and the time sequence self-correlation feature to obtain fused bidirectional feature representation; and S5, performing multi-classification processing on the fused bidirectional feature representation based on a Softmax classifier to realize accurate classification of sleep stages. According to the method, the heart rate variability signal and the three-axis acceleration signal can be fused, and the sleep state of the human body can be accurately recognized and classified in combination with the bidirectional long-short-term memory network and time sequence self-correlation feature analysis.

The invention provides an oil well load indicator diagram prediction method and system, and the method comprises the steps: synchronously collecting an initial electrical parameter data set, a load data set, an accelerometer data set and a barometer data set of an oil well, the initial electrical parameter data set comprising an active power data unit, and then obtaining an active power data segment and a load data segment; obtaining a time lag based on the two, and further obtaining a final electrical parameter data segment; acquiring a reference displacement sequence through the accelerometer data set and the barometer data set; obtaining a dynamic stroke length based on the reference displacement sequence and the load data segment, and further obtaining a final displacement sequence; and constructing a prediction neural network, and obtaining an oil well load indicator diagram based on the prediction neural network and the real-time electrical parameter data segment. According to the technical scheme, the indicator diagram is obtained through continuous and high-frequency real-time electric parameter data segments, motion period information loss caused by low-frequency data collection is avoided, accumulative errors are avoided, and the accuracy of the indicator diagram is ensured.

Systems and methods for providing assessments of a disease using sensor data for a subject captured during day-to-day living are provided. The sensor data includes accelerometer data and is acquired by a sensor disposed on the subject's wrist while the subject performs both active and sedentary activities. The sensor data is analyzed for one or more bouts of activity; the sensor data is filtered, optionally rotated, and Fourier transformed. Spectral analysis parameters are then calculated from the transformed data to detect disease-relevant movement patterns. Movement distribution parameters for the accelerometer data associated with the disease-relevant movement patterns are calculated and compared to one or more disease scores to evaluate a progression of the disease or an efficacy of a treatment

The invention discloses a real-time multi-mode physiological signal analysis method for myocardial ischemia, and belongs to the technical field of data analys.The technical scheme includes that electrocardiogram, photoelectric volume pulse waves and thoracic impedance signals are synchronously acquired, and phase difference caused by motion displacement is compensated in real time by the aid of a triaxial accelerometer; constructing a multi-dimensional quality evaluation matrix containing an electrocardiogram signal-to-noise ratio, a photoelectric volume pulse wave perfusion index and a chest impedance variance, and jointly judging whether signal reconstruction is triggered or not based on a dynamic threshold value and accelerometer data; a multi-channel signal block which is judged to be low in quality through the quality evaluation matrix and comprises the electrocardiogram and photoelectric volume pulse waves and chest impedance synchronized with the electrocardiogram is input into a generative adversarial network with electrophysiological constraints to be reconstructed, and a reconstructed high-quality electrocardiogram signal is output; and myocardial ischemia key indexes are extracted from the reconstructed signals, and multi-level risk early warning is carried out. The real-time multi-modal physiological signal analysis method for myocardial ischemia has the beneficial effect that the real-time multi-modal physiological signal analysis method for myocardial ischemia is provided.

The invention relates to the technical field of data calibration, and particularly discloses an attitude calibration method and system for a self-adaptive anti-shake handheld three-dimensional scanner, and the method comprises the steps: reading IMU initial data to initialize an attitude calculation algorithm and an initial gyroscope zero offset estimation value, carrying out the real-time compensation of the original angular velocity data of a gyroscope based on the current zero offset estimation value, and carrying out the calibration of the attitude of the self-adaptive anti-shake handheld three-dimensional scanner. Second attitude data is obtained by resolving accelerometer data; a final attitude is output through complementary filtering fusion; the quasi-static state of a scanner is analyzed and judged through IMU data variance; original data of a gyroscope is collected in the state to solve an average value; and the zero offset estimation value is updated through first-order low-pass filtering and is fed back to the compensation step. According to the method, hardware cost does not need to be increased, whole-process online self-calibration is achieved, attitude drift is reduced, the algorithm is efficiently adaptive to a low-cost processor, and long-time scanning precision and real-time performance are guaranteed.

An exemplary virtual IMU extraction system and method are disclosed for human activity recognition (HAR) or classifier system that can estimate inertial measurement units (IMU) of a person in video data extracted from public repositories of video data having weakly labeled video content. The exemplary virtual IMU extraction system and method of the human activity recognition (HAR) or classifier system employ an automated processing pipeline (also referred to herein as “IMUTube”) that integrates computer vision and signal processing operations to convert video data of human activity into virtual streams of IMU data that represents accelerometer, gyroscope, or other inertial measurement unit estimation that can measure acceleration, inertia, motion, orientation, force, velocity, etc. at a different location on the body. In other embodiments, the automated processing pipeline can be used to generate high-quality virtual accelerometer data from a camera sensor.

A controller for a vehicle, the vehicle comprising an imaging device for generating image data and the imaging device further comprising an imaging accelerometer for generating imaging accelerometer data for determining the orientation of the imaging device relative to the vehicle, the controller comprising: an input for receiving a signal indicative of the imaging accelerometer data and the generated image data; a processor arranged to identify alignment artefacts in the received image data in dependence on the received imaging accelerometer data; and an output for outputting an error signal in dependence on the identified alignment artefacts.

This invention discloses a method and system for detecting the angle between a tractor and trailer based on a dual-antenna combined inertial navigation system, applicable to vehicle systems. The method includes: acquiring the position difference vector between the main and auxiliary antennas using a dual-antenna GNSS system on the tractor; calculating the first coarse heading angle of the tractor; and then fusing IMU data and filtering it to obtain a high-precision first heading angle. The roll and pitch angles are calculated using accelerometer data from the trailer's IMU, and tilt compensation is performed on the magnetometer data to obtain the second heading angle of the trailer. Furthermore, the heading and lane curvature data from the tractor can be combined to dynamically compensate and correct the trailer's heading online. The difference between the first and second heading angles is calculated in real time to obtain the angle between them. This invention can maintain heading output using IMU and wheel speed data even when GNSS signals fail, and ensure trailer heading accuracy through dynamic compensation, thereby achieving stable and high-precision tractor-trailer angle measurement.

The invention relates to an out-of-levelness estimation method, device and equipment of an inclinometer and a medium, and belongs to the technical field of inclinometers. The method comprises the following steps: in a hardware environment without a gyroscope, acquiring initial attitude angle information through accelerometer data sampling and alignment; performing attitude matrix construction, navigation coordinate system projection, Kalman filter modeling, attitude error calculation and error compensation to equivalently realize a gyroscope-free zero-velocity correction effect, and obtaining a final attitude angle; a self-adaptive Kalman filter based on gravity acceleration module value constant constraint is provided, so that the influence of external interference on the measurement precision can be reduced; and finally, performing smooth filtering on the final attitude angles at a plurality of adjacent sampling moments, and outputting high-precision and high-stability unlevelness. According to the method, under the condition that the hardware cost is not increased, the measurement precision and stability of the inclinometer on the out-of-levelness are improved.

The invention relates to a reconfigurable smart surface (RIS). Provided is an RIS capable of fitting a non-planar surface, the RIS comprising: a plurality of RIS unit cells; a plurality of accelerometers, each configured to detect accelerometer data of at least one of the RIS unit cells; and a controller configured to determine an operating condition of the RIS based on the detected accelerometer data of the RIS unit cell, and adjust one or more operating parameters based on the operating condition. A method of operating such an RIS is also provided in which each RIS unit cell includes a dedicated accelerometer configured to detect accelerometer data of the RIS unit cell.

The present invention pertains to an advanced method for automatically detecting and recognizing wellness activities and kinetic movements using accelerometer data from wearable devices. This method involves creating a user profile, linking the user to their wearable device via specific identifiers (make, type, and unique device ID), and processing accelerometer data to develop and continuously update a supervised machine learning model. This model accurately identifies and classifies various physical activities by utilizing detailed device information and user preferences. Designed for scalability, the system integrates new wearable devices and models as they emerge. It is particularly effective in tracking activities across diverse environments, including homes and fitness centers. Moreover, it identifies and associates ICD-10 activity codes with the performed activities and integrates with Electronic Medical Records (EMR) systems. This method offers valuable applications for fitness centers, healthcare providers, government agencies, and payers interested in monitoring or promoting physical wellness through reliable activity tracking.

The invention belongs to the technical field of positioning navigation, and discloses an initial course alignment method and device based on geometric constraint type filtering, and the method comprises the steps: calculating a magnetic course angle and estimating the GNSS driving distance and orientation according to received GNSS original observation data, earth magnetic field information, and accelerometer data and gyroscope data obtained based on an IMU array; based on an unscented Kalman filtering algorithm under a Gaussian progressive framework, correcting accelerometer data in combination with geometric constraints, and identifying an IMU with a fault in the IMU array for isolation to obtain filtered accelerometer data and gyroscope data; calculating to obtain a GNSS-IMU course angle by combining the filtered accelerometer data and gyroscope data and the GNSS driving distance and direction; and according to the loss duration of the GNSS original observation data, synthesizing the magnetic course angle and the GNSS-IMU course angle to obtain a final initial course angle. The initial alignment time of the integrated navigation system is effectively shortened, and the robustness of the system is enhanced.

Implantable medical devices and methods that utilize a sensing circuit to sense cardiac activity (CA) signals and an accelerometer to obtain accelerometer data. Memory stores program instructions and device parameters associated with a collection of ventricular arrhythmia (VA) therapies. A processor analyzes the CA signals over one or more cardiac beats, determines a VA episode based on the analysis of the CA signals, determines the VA episode to be hemodynamically stable or unstable based on at least one of the accelerometer data or the CA signals, selects a first VA therapy from the collection of VA therapies based on whether the VA episode is hemodynamically stable or unstable, and apply the first VA therapy using at least one of the at least two coils.

The invention belongs to the technical field of atmospheric density prediction, and discloses a cross-source data fusion thermal layer atmospheric density hierarchical progressive full-scale prediction system and method, which utilize respective advantages of different gradient data sources to construct a reference density field-corrected density field-instantaneous refined density field three-level hierarchical fusion refinement architecture. Cross-source data calibration and physical constraint modeling are combined to realize month-year scale long-term prediction, day-week scale medium-short-term prediction and short-term prediction of the thermal layer atmospheric density. According to the method, through a three-level layered refinement architecture, the long-term coverage advantage of TLE data, the mesoscale variable rate description advantage of precise orbit data and the high-frequency and high-precision advantages of accelerometer data are fully mined, the defect of a single data source is avoided, full-scale and full-area density precise description is achieved, the thermal layer atmospheric density refinement precision and prediction suitability can be improved, and the method is suitable for large-scale and large-scale measurement. And data cost is reduced.

Disclosed herein are methods for determining a location of a hearing aid, performed by an electronic device having a processor, a memory, and interface circuitry. The method includes obtaining first accelerometer data from a hearing aid. The method includes obtaining second accelerometer data from the electronic device. The method includes determining, based on the first accelerometer data and the second accelerometer data, an acceleration parameter indicative of a difference between the first accelerometer data and the second accelerometer data. In accordance with the acceleration parameter meeting a safety criterion, the method includes generating lost control data and outputting the lost control data to the hearing aid.

Activity level and fall detection using accelerometer data is described. In one or more implementations, measurements of a user generated by a wearable monitoring device during an observation period are obtained, the measurements including accelerometer data. Physical steps taken by the user are detected based on peaks in the accelerometer data above a threshold, and a step count is generated based on the detected physical steps within predetermined time epochs. Activity level classifications of the user for the predetermined time epochs are generated based on the step count. The step count and the activity level classification for the predetermined time epochs may then be output, such as a notification or in a user interface. Fall predictions may be generated and output by processing the accelerometer data using machine learning models trained to correlate patterns in accelerometer data to fall events.

The invention belongs to the technical field of sleep detection, and particularly discloses a sleep detection method and system based on time sequence continuity optimization, and the method comprises the following steps: collecting original wrist strap accelerometer data through a triaxial accelerometer, and carrying out the preprocessing, thereby obtaining an input tensor; inputting the input tensor into a feature extraction module, and extracting local features and global features of the input tensor to obtain an advanced feature tensor; inputting the high-level feature tensor into a feature reconstruction module, and performing up-sampling and feature jump connection on the high-level feature tensor by adopting a linear interpolation reconstruction strategy to obtain a final data tensor; and carrying out secondary fine adjustment and time sequence smooth correction on the data tensor output by the feature reconstruction module to form complete sleep state prediction of one day per minute and corresponding confidence score output. By adopting the technical scheme, the residual unit is improved by utilizing the multi-scale cavity convolution, and the prediction result of the sleep event is more accurate through a bidirectional time sequence information processing mechanism.

The invention relates to a gyro accelerometer data fusion method, and belongs to the technical field of high-precision acceleration measurement inertia, the gyro accelerometer data fusion method is based on an optical fiber gyro inertial navigation system with a three-axis rotating mechanism, a table body can be controlled to keep stable relative to an inertial space, and three orthogonally placed quartz accelerometers are configured on the table body; the method comprises the following steps of: configuring a pendulum-type integral gyro accelerometer in an X direction, normalizing measured values of the quartz accelerometer and the gyro accelerometer by utilizing measurement redundancy of the quartz accelerometer on acceleration information, and compensating output pulses at non-whole circle points of the gyro accelerometer, under the condition of low overload, the advantage of high-precision acceleration measurement of the gyro accelerometer at the whole precession circle point can be brought into full play; according to the invention, the problem that the measurement error of the gyro accelerometer is large under the condition of low overload in the use process of the existing fiber-optic gyro inertial navigation is solved, and the use precision of the gyro accelerometer on an inertial navigation system is improved.

The invention relates to a system (1) for detecting the presence of life inside a motor vehicle (V) by means of a radar (10) and an accelerometer (40), the system being configured to implement the following steps: - processing, in particular by means of a presence-detection algorithm, data from the radar (10) in order to deliver a result regarding a presence of life in the vehicle, - processing data from the accelerometer (40) in order to deliver a result regarding a movement of the vehicle, - processing, in particular by means of a correlation algorithm, the data from the radar (10) and the data from the accelerometer (40) in order to establish a presence of correlation or an absence of correlation between at least one feature derived from the data from the radar (10) and at least one feature derived from the data from the accelerometer (40), the presence of correlation being representative of a state of actual movement of the radar (10), - in the event of presence of correlation, ignoring the result regarding a presence of life in the vehicle obtained by processing the data from the radar (10).

According to the logistics robot self-balance adjusting system based on the reaction wheel principle, data of the tilt angle sensor, the gyroscope and the accelerometer are integrated through the data acquisition module, multi-dimensional attitude data are obtained, a comprehensive and accurate data basis is provided for accurate determination of the real-time balance state of a logistics robot, and the real-time balance state of the logistics robot is accurately determined. Based on sensor data, the real-time balance state of the logistics robot is determined, state obtaining of the logistics robot is achieved, based on the real-time balance state of the logistics robot, a control algorithm is combined, a rotating speed adjusting instruction of a reaction wheel of the logistics robot is determined, and quick response to the real-time balance state of the robot is achieved. The control precision is guaranteed, self-balancing of the logistics robot is achieved, finally, energy use of the rotating speed under the rotating speed adjusting instruction is optimized, and the endurance time of the logistics robot is prolonged.

An apparatus and method for position determination in a 3D model of an environment and a computer-executed iterative method for position determination in a 3D model of an environment. The method includes the steps of: a) acquisition of camera, gyroscope and accelerometer data, b) determination of visual features from the acquired camera sensor data, c) creation of a current key image of the pose (PK) from the visual features and the gyroscope and accelerometer sensor data, d) addition of the key image of the pose (PK) to a database, and e) position determination by comparing the current key image of the posture (PK) with those of the database.

The invention discloses a remote island reference-free control network autonomous construction and transmission method, which belongs to the technical field of geodetic survey and surveying and mapping engineering, and comprises the following steps: receiving sea surface laser ranging, land gravity, mobile platform images and accelerometer data; performing statistics on peak values of the laser ranging histograms to extract local average sea surface elevation; a relative geometric point cloud is generated based on image texture tracking in combination with an accelerometer calculation scale; calculating a vertical line inclination angle by using a difference value between the gravity data and an earth normal gravity field; and correcting a point cloud vertical component by using a difference value between a water line and a sea surface elevation, correcting a plane component by using an inclination angle, and outputting a control point. According to the invention, a mode of fusing sea surface laser ranging, mobile platform images, inertial data and land gravity data is adopted, and a local three-dimensional control network with unified scale, elevation reference and vertical line direction can be autonomously constructed under the condition of no external reference dependence.

A system may obtain one or more engagement measurements including at least one engagement measurement of a surface in a wellbore from an engagement sensor, wherein the engagement sensor is housed in an electronics housing positioned within a body of a downhole tool. A system may obtain accelerometer data from an accelerometer that is concurrent with the one or more engagement measurements. A system may correlate data variations in the one or more engagement measurements and in the accelerometer data, wherein the data variations are values outside of a threshold value. A system may identify at least one drilling dysfunction based on correlated accelerometer data and engagement measurements. A system may change at least one wellbore parameter based on the correlated accelerometer data and engagement measurements.

This invention provides a six-position temperature-compensated calibration method for accelerometers in a strapdown inertial navigation system (SINS), belonging to the field of inertial navigation technology. The specific steps are as follows: The SINS is calibrated for a short time at different temperatures on a dual-axis temperature-controlled turntable without a mounting reference. The accelerometer zero bias, scale coefficient, and installation error at different temperatures are estimated using the least squares method. A cubic polynomial model is established relating the accelerometer zero bias, scale coefficient, and installation error to the actual temperature. The initial temperature scale coefficient is obtained by fitting the curve. Then, six-position calibration is performed on a turntable with a mounting reference to obtain a transformation matrix. The final temperature compensation coefficient is obtained from the transformation matrix and applied to the SINS to reduce the impact of temperature on the accelerometer output. This invention features short accelerometer data acquisition time, high reliability, and ease of operation. It is a method for improving accelerometer output accuracy through accelerometer compensation calibration.

Aspects of the disclosed technology include machine-learning systems and methods for enhancing speech signals. A machine-learned speech enhancement model can be trained using audio data and synthetic accelerometer data that is generated using a synthetic accelerometer data generation model. The accelerometer data can include synthetic noise data that can be used to train the speech enhancement model to learn a transfer function that models environmental noise to an accelerometer of a wearable device. By simulating data from multiple sensors, the disclosed technology provides a cost-effective solution for training robust large-scale models for speech enhancement.

The invention provides an EKF attitude resolving method and system based on a rotation matrix and gravitational acceleration, and the method comprises the steps: reading data of an inertial measurement element, calculating an initial Euler angle, and converting the initial Euler angle into a quaternion; performing prediction updating through a quaternion differential equation according to gyroscope data and the latest quaternion, calculating and assigning a priori state vector through a quaternion gravitational acceleration extraction formula based on the predicted and updated quaternion, and assigning accelerometer data to a measurement matrix; jacobian matrixes A and W of a state transition equation are calculated according to gyroscope data and a gravitational acceleration differential equation derived based on a differential equation of a rotation matrix, Jacobian matrixes H and V are calculated according to a measurement equation, and then a posterior state vector and a posterior covariance matrix are calculated; and calculating a roll angle and a pitch angle according to the posterior state vector, and calculating a course angle according to the predicted and updated quaternion. According to the invention, EKF divergence can be avoided, and the anti-interference capability is high, so that the attitude calculation precision is ensured.

An agricultural implement includes a main frame having a support bar oriented in a direction generally transverse to a direction of travel when the implement is used to work a field, a plurality of rotating ground-engaging elements aligned along a length of the support bar, and a plugging detection system configured to alert an operator if one or more of the ground-engaging elements have an acceleration different from an acceleration of remaining ground-engaging elements by at least a threshold amount. The plugging detection system has an accelerometer for each of the plurality of ground-engaging elements and a control module that compares accelerometer data of each ground-engaging element to accelerometer data of the remaining ground-engaging elements. Related methods are also disclosed.

The application provides an oil well load work graph prediction method and system, the method comprising: synchronously collecting initial electric parameter data set, load data set, accelerometer data set and barometer data set of the oil well, the initial electric parameter data set comprising active power data unit, and then obtaining active power data segment and load data segment; obtaining time lag amount based on the two, and then obtaining final electric parameter data segment; obtaining reference displacement sequence through the accelerometer data set and the barometer data set; obtaining dynamic stroke length based on the reference displacement sequence and the load data segment, and then obtaining final displacement sequence; constructing a prediction neural network, and obtaining the oil well load work graph based on the prediction neural network and real-time electric parameter data segment. The work graph is obtained by using continuous and high-frequency real-time electric parameter data segment, so that the motion cycle information loss caused by low-frequency data collection is avoided, and then the cumulative error is avoided, and the accuracy of the work graph is ensured.

A system for monitoring a physiologic condition of a patient includes an implantable medical device (IMD) comprising: an accelerometer configured to output an accelerometer signal; sensing circuitry configured to sense a cardiac activity (CA) signal; and a memory configured to store program instructions. One or more processors that, when executing the program instructions, are configured to: determine a heart rate (HR) at a point in time based on the CA signal; determine an activity level (AL) at the point in time based on accelerometer data that is based on the accelerometer signal, the HR and AL forming an HR-AL event; compare the HR-AL event to a heart condition (HC) metric that defines combinations of HRs and ALs representing a physiologically normal heart condition and a physiologically abnormal heart condition; and transmit the HR-AL event or a result of the comparison to a second device for use in diagnosing and / or treating a heart condition.

The invention relates to transforming microphone data into accelerometer data. In a method for transforming microphone data into accelerometer data, microphone data is received. A device-specific filter is applied to the microphone data to generate first data, the device-specific filter for transforming the microphone first data according to characteristics of the device. The first data is expanded by adding sensor noise to the first data to generate second data, the sensor noise characterizing noise inherent to the device. The second intermediate data is expanded by adding ambient vibration noise defining an environment in which use of the device is simulated to generate accelerometer data.