43 results about "Gait speed" patented technology

The invention relates to a control method of an artificial limb knee joint. According to the technical scheme, the control method comprises the steps that a heel pressure sensor signal Ph, a sole pressure sensor signal Pf and an inclination angle theta and an angular velocity omega output by a shank inertial measurement unit are obtained in real time; when it is detected that the Pf decline rate exceeds a preset multiple threshold value of the heel pressure decline rate, dynamically calibrating an inclination angle reference theta base and calculating an offset theta cal; dividing six stages of a gait period based on the theta < cal > and the pressure signal, and calculating period duration T; a step speed-damping mapping knowledge base is constructed, and the damping opening degree in the early stage of swing is optimized through iterative learning; finally, the adjusted U value is applied in the early stage of swinging, and fixed damping is kept in other stages. The method is mainly used for improving the walking naturalness and terrain adaptability of the artificial limb at different speeds.

Training at the proper level of effort is important for athletes whose objective is to achieve the best results in the least time. In running, for example, pace is often monitored. However, pace alone does not reveal specific issues with regard to running form, efficiency, or technique, much less inform how training should be modified to improve performance or fitness. A sensing system and wearable sensor platform described herein provide real-time feedback to a user / wearer of his power expenditure during an activity. In one example, the system includes an inertial measurement unit (IMU) for acquiring multi-axis motion data at a first sampling rate, and an orientation sensor to acquire orientation data at a second sampling rate that is varied based on the multi-axis motion data.

Provided is a cognitive impairment determination method that discloses a model for determining cognitive impairment based on a gait feature value measured by an accelerometer attached to a subject, discloses a configuration for determining cognitive impairment by using a model including a mathematical linear regression equation that includes a gait speed and step time variability as predictors by receiving personal data and gait data, easily and quickly screens for cognitive impairment, such as dementia, regardless of a root cause, and accurately determines even cognitive impairment in an early stage.

The invention belongs to the field of gait prediction, and particularly discloses a personalized gait prediction method fusing a self-attention mechanism and Bayesian regression, and the method comprises the steps: obtaining motion parameters of an artificial limb wearer, and constructing a time sequence feature sequence; dividing the time sequence feature sequence into a plurality of gait sub-stages; respectively outputting a gait speed prediction result of each gait sub-stage through an independent prediction model; wherein the prediction model adopts a space-time convolution attention network to extract features, probability output is performed through a Bayesian linear regression layer, and the prediction model is obtained through online transfer learning training. According to the invention, the problem of poor gait speed prediction precision can be solved, so that the precision and stability of an artificial limb control system are improved.

Embodiments of footwear to optimize propulsion while swimming in the water and walking on land, in particular, amphibious footwear capable of duty on land and in the water as well as versions that are optimized for predominantly use in the water for swimming. The exoskeleton amphibious footwear reduces metabolic demand of walking and swimming while also improving gait speed and swim speed. This is accomplished by assisting plantar flexion during land mode, and assisting dorsiflexion in water mode.

The present invention provides a method and device for planning gait trajectories for a lower-limb exoskeleton based on self-oscillation. The method comprises continuously collecting joint angle information and plantar pressure information from a plurality of walking groups of a wearer, preliminarily dividing the walking process into multiple gait phases based on the plantar pressure information, using the preliminarily acquired gait phases and corresponding joint angle information as a data set, building a convolutional neural network (CNN) model, using the data set as training data, and continuously training the CNN model to accurately acquire the starting point of each gait phase. Each gait phase is accurately acquired from the starting point, establishing an adaptive oscillator model, inputting the data set into the adaptive oscillator model, outputting a tracking phase, and performing gait trajectory planning for the lower-limb exoskeleton based on the gait phases acquired by the CNN convolutional neural network model. The predicted output trajectory is dynamically adjusted in real time online. The present invention can adapt to the requirement of non-constant walking speed and achieve dynamic gait trajectory planning.

The present application relates to a kind of power ankle prosthesis based on adjustable position one-way parallel spring, mainly by support mechanism, power direct drive mechanism, spring mechanism, adjusting mechanism, toe mechanism composition.Support mechanism is connected with human lower extremity stump, power direct drive mechanism, spring mechanism, adjusting mechanism are fixed on support mechanism, and toe mechanism is hinged with support mechanism.The support mechanism of the present application provides the support of ankle prosthesis, power direct drive mechanism and spring mechanism provide the energy output and support torque required in the walking process of power ankle prosthesis, spring mechanism stores passive energy and releases, compensates motor energy consumption, adjusting mechanism realizes the adaptive adjustment to wearer gait speed in the walking process, and elastic toe mechanism simulates the elastic mechanism of normal human toe in the walking process, provides passive elastic grip for ankle.

The invention relates to a walking aid (1) for an individual comprising a chassis (10), a base (20) that is movable at least vertically with respect to the chassis (10) between a low sitting position and a high walking position and a device (30) for modifying the vertical elevation position of the base (20), characterized in that it is equipped with at least one sensor (60) measuring the displacement of the aid (1) while the individual is walking in order to determine a distance travelled, a sensor (70) measuring a difference in position of at least one moving limb of the individual in order to determine at least one item of data from an amplitude of swinging movement of the limb, a step rate, and an asymmetry of the gait, the sensors (60, 70) being coupled to determine the length of the step, the asymmetry of the length of the steps or the walking speed, and an electronic board executing at least one function from among the retrieval of the data from the set of sensors, the storage of the data, the analysis of the data and the transmission of the data to a processing unit.

According to the outdoor walking auxiliary type portable foot drop correction electrical stimulation device provided by the invention, through innovative design, the correction effect and the user experience are remarkably improved; the device adopts a multi-mode sensor array and an original gait phase prediction algorithm, real-time gait recognition with response delay lower than 50 ms is achieved, the walking rhythm of a patient is accurately matched, and it is ensured that electrical stimulation and a motion period are synchronous; based on a 3D stimulation mode library of terrain recognition and a self-adaptive intensity adjustment algorithm, stimulation parameters can be dynamically adjusted according to different terrains, and the gait stability in a complex environment is effectively improved; the bionic electrode layout and the magnetic type quick wearing system are combined with an invisible design, so that the wearing comfort and convenience are remarkably improved; clinical tests show that the device enables the step speed of a patient to be increased, the number of tumble times to be reduced, the comfort level of a user to be high, technical spanning from clinic to daily life is achieved, and an efficient, safe and easy-to-popularize rehabilitation solution is provided for the foot drop patient.

The present invention discloses a multi-gait adjustment training device, comprising a base, a stepless height adjustment device, a weight reduction device, and a leg-split device; one end of the stepless height adjustment device is connected to the base, and the other end is connected to the weight reduction device, so that the weight reduction device and the stepless height adjustment device are raised and lowered synchronously; the leg-split device is fixedly connected to the base, the leg-split device guides the gait cycle, and the base assists the leg-split device, which can prevent the training device from moving backward and adjust the gait speed. The multi-gait adjustment training device disclosed by the present invention can be used to train people who cannot maintain a normal standing position, cannot maintain the distance between their legs when standing, or kick their legs or adduct their lower limbs during walking.

The present invention relates to an adaptive zero-speed detection algorithm based on interval search under variable speed motion conditions, and belongs to the field of pedestrian navigation technology. It includes: 1) zero-speed interval proportion analysis; 2) gait cycle extraction; 3) preliminary screening of zero-speed intervals; 4) fine determination of zero-speed intervals. The present invention determines the search interval of the gait cycle by performing SWA filtering on the modulus of angular velocity, and preliminarily determines a zero-speed interval based on the statistical characteristics of the zero-speed interval in the gait cycle under different speeds, and sets a new threshold based on the 3σ criterion to achieve adaptive zero-speed detection. The present invention not only provides a new, efficient and accurate positioning solution for wearable devices and location services, but also provides a valuable reference for pedestrian navigation research under complex motion patterns.

The invention provides a personalized step speed self-adaptive control method applied to an ankle-assisted exoskeleton, and the method comprises the steps: installing a feedback device at the bottom of a heel and the bottom of a toe, and detecting the acting force of the sole in real time so as to divide four action stages of single-foot walking; and constructing a conversion relation between a first function characterization action duration and the step speed, and constructing a second function characterization step speed and the driving torque. And during walking, the real-time action duration in the middle stage of the supporting action is obtained, the real-time step speed is calculated through the first function, the real-time driving torque is obtained through the second function, and the ankle exoskeleton assistance is controlled according to the real-time driving torque. The driving torque is dynamically adjusted by sensing the gait and the step speed in real time, so that the assisting power fits the walking state of an individual, and the self-adaptive capacity and the assisting power accuracy under the change of the step speed are remarkably improved; and meanwhile, the method has good individuation and generalization capabilities.

Disclosed is a gait analysis device using artificial intelligence (AI) technology, according to some embodiments of the present invention. The gait analysis device may comprise: a camera unit for capturing an image of the gait of a target user in response to a user interaction through a display unit; a gait analysis unit for generating a gait analysis result obtained by analyzing the gait of the target user on the basis of the captured gait image, wherein the gait analysis result includes at least one of a stride length, a gait speed, a swing angle of both arms, an upper body angle, a hip joint angle of both legs, or a knee angle of the target user; and the display unit for outputting the gait analysis result.

A system and method for collecting and analyzing real-time walking and balance data from mobile device users through an opt-in mechanism integrated with smartphone operating systems (iOS and Android). Users voluntarily share their mobility data, including gait speed, stride length, and balance stability, which is anonymized and analyzed using machine learning algorithms. The system provides personalized health insights, such as real-time warnings about fall risks, and generates population-level health trend reports. Aggregated, anonymized data helps public health organizations and healthcare providers identify emerging trends, such as regional increases in fall risks or correlations between medication use and mobility issues. This dual-purpose system bridges individual health monitoring and population-level public health analysis, offering proactive interventions to improve well-being. The system ensures privacy compliance while enabling early detection and prevention of health risks for both individuals and broader communities.

The invention provides a human body posture data set construction method based on a large model. A large language model is combined with a fine-grained attribute database to generate motion description, then the motion description is converted into 3D human skeleton motion data through a MoMask model, and quality control is carried out. And then view control and gait speed control are performed on the motion data to increase data diversity. And then radar data simulation is carried out, including human body modeling, RCS estimation, radar signal generation and processing, and micro-Doppler spectrogram generation. Meanwhile, a VQ-VAE model is adopted to generate background noise and add the background noise, shielding is simulated, and the data trueness is enhanced. And finally, constructing a data set containing a plurality of activities. The data set generated by the method has semantic and physical diversity, a real scene can be simulated with high fidelity, the performance of a human body posture recognition model is effectively improved, and powerful support is provided for application of related technologies in multiple fields.

Disclosed herein is a frailty diagnosis apparatus. The frailty diagnosis apparatus includes a physical performance meter and a processor for determining a frailty index of a target person based on physical performance of the target person obtained by the physical performance meter. The physical performance meter includes at least one among a gait speed meter for measuring a gait speed of the target person, a body balance meter for measuring a body balance maintenance time of the target person, and a muscle strength meter for measuring a muscle exercise time.

A system and method for managing medication titration using real-time walking and balance data collected from mobile electronic devices are disclosed. Smartphone sensors, including accelerometers and gyroscopes, capture mobility metrics such as gait speed, stride characteristics, postural stability, and fall risk. The mobility data is integrated with additional physiological metrics and a patient's electronic medical records. Analytical algorithms, including machine-learning models, evaluate changes in mobility to identify correlations between medication usage and functional performance. Based on detected changes, the system generates alerts and recommendations to assist healthcare providers in adjusting medication dosages. The invention supports proactive and personalized medication management, particularly for medications that affect balance or fall risk, and improves patient safety by enabling data-driven clinical decision-making using real-world mobility insights.

Embodiments of footwear, in particular, a shoe, sandal or boot, that have the unexpected benefit of reducing the pressure on the plantar surface of the foot while also reducing metabolic demand of walking while also gait speed and improving walking, running, hiking, as well as jumping, hopping, and other motion involving the ankle, lower leg and Achilles tendon, through integration of force-carrying mechanisms within footwear that manage the forces and energy associated with such motion by productively harvesting and storing energy during dorsiflexion motion and releasing and returning energy during plantar flexion and limiting range of motion that conduce towards ankle inversion and eversion. Such footwear may comprise a yoke connected to footwear at a pivot region in parallel to the axis of rotation of the ankle and a tension spring region suspended between the yoke and the posterior portion of the footwear sidewalls or sole.

The invention discloses a control method based on a weight loss gait rehabilitation device and the weight loss gait rehabilitation device, and relates to the technical field of medical rehabilitation. A first deviation in the length direction of the running belt and a second deviation in the width direction of the running belt are respectively determined by combining a target footprint center point coordinate of the guide footprint image and an actual footprint center point coordinate of the actual footprint image, and the first deviation in the length direction of the target running belt reflects the pace speed of the patient; the speed of the target running belt is dynamically adjusted to be matched with the step speed of the patient, so that the patient is effectively prevented from falling down; the second deviation in the width direction of the target running belt reflects whether the step width is appropriate or not, and the step width adjustment information of the target foot corresponding to the target running belt is generated according to the second deviation, so that the patient is helped to form the standard and stable step width to improve the effectiveness and scientificity of training.

The invention relates to the field of GNSS (Global Navigation Satellite System) positioning, and discloses a sensor-assisted GNSS walking positioning method, which comprises the following steps of: judging whether a user state is in a walking mode or not through sensor information; dividing the GNSS environment into open, slight shielding, medium shielding and serious shielding according to CN0 and sky map distribution information of the GNSS in a tracking satellite; and if the GNSS environment is judged to be in a walking mode and the GNSS environment is in a medium-shielding or severe-shielding environment, calculating a horizontal speed through a step length and a step speed, and calibrating the GNSS speed by taking the horizontal speed as an observed quantity of a Kalman filter. According to the method, 1, the step speed is obtained through the step length and the step number in a complex environment, and the step speed is used for updating and calibrating the GNSS speed in the GNSS, so that the positioning effect of the GNSS is improved;

Disclosed is a portable muscle quality assessment system (100) for screening of sarcopenia, comprising: a memory (110), storing personal information data of a user; an ultrasonic sensing apparatus (130), measuring muscle parameters and transmitting ultrasonic sensing data to the memory (110); a force sensing apparatus (140), measuring muscle strength and transmitting force sensing data to the memory (110); a motion sensing apparatus (150), measuring a pace and / or a gait of the user during motion and transmitting motion sensing data to the memory (110); and a processor (120), generating, on the basis of the personal information data, the ultrasonic sensing data, the force sensing data, and the motion sensing data on the memory (110), an assessment report on whether the user suffers from sarcopenia and the severity thereof.

The embodiment of the application provides a health assessment system and a health assessment method, and belongs to the technical field of health assessment. The health assessment system comprises an assessment chair assembly, a gait guiding assembly and a footpath. The assessment chair assembly is configured to measure the grip strength, heart rate, leg lifting frequency and sit-to-stand state of a subject. The gait guiding assembly is configured to guide the subject to present a preset gait. The footpath is configured to measure the walking speed of the subject. The health assessment system and the health assessment method of the embodiment of the application have corresponding devices for each test, and do not need to paste test marks, thereby improving the assessment environment, almost not needing the participation of assessment personnel in the normal test process, reducing the labor intensity of the assessment personnel, reducing the human consumption, and the test result is relatively objective.

This invention relates to a control method for a prosthetic knee joint, the key technical points of which include: real-time acquisition of heel pressure sensor signals. P h Foot pressure sensor signal P f and the tilt angle output by the lower leg inertial measurement unit i and angular velocity ω; when detected P f When the descent rate exceeds a preset multiple threshold of the heel pressure descent rate, the tilt angle reference is dynamically calibrated. i base And calculate the offset. i cal ;based on i cal The gait cycle is divided into six stages based on the pressure signal, and the cycle duration is calculated. T This invention constructs a gait-damping mapping knowledge base and optimizes the damping opening in the early stage of the swing through iterative learning. Finally, the adjusted U-value is applied in the early stage of the swing, while the damping remains fixed for the remaining stages. This invention primarily aims to improve the naturalness of walking and terrain adaptability of prostheses at different gait speeds.

The application discloses a kind of digital twinborn auxiliary crocodile-imitating robot gait control deep reinforcement learning method, which is divided into pre-training and real-time training two stages.The specific steps include: step 1, utilize simulation and modeling technology to construct crocodile-imitating robot twinborn system model, and store it in edge device;Step 2, construct the state space and action space of crocodile-imitating robot gait control;Step 3, design reward function considering forward motion gait speed, stability and low energy consumption;Step 4, pre-training is carried out by using multi-process parallel data collection, and the twinborn decision model is obtained;Step 5, deploy the twinborn decision model in edge device, and use communication module to transmit information with twinborn physical entity, and real-time training is carried out on crocodile-imitating robot.The application improves the training efficiency of crocodile-imitating robot gait control by establishing digital twinborn model for pre-training and using the powerful computing power and storage resources of edge device.

The present invention relates to a gait stability detection method and application for personnel working in special environments, constructs a stop-and-brake difficulty coefficient model, quantifies the influence of various factors on the balance of walking in special environments, and accurately determines the imbalance risk of personnel working in special environments during walking in special environments. During the training process, the present invention can select the optimal gait, pace, and step length of personnel working in special environments during their movement, thereby improving the stability of personnel working in special environments during their movement. The present invention evaluates various gait recoveries, provides an optimal recovery method, and uses the optimal recovery method to train personnel working in special environments, thereby improving the ability of personnel working in special environments to restore stability; in the case where personnel working in special environments need multiple steps of braking, the optimal recovery method prompt is output, ensuring that personnel working in special environments restore their gait as soon as possible.

An AI-assisted, data driven, real time posture detection system for physiotherapy, fall prevention, and / or frailty assessments. The system uses a pre-trained pose detection model and video images from multiple angles captured by multiple cameras to determine the three-dimensional locations of user joints in real time. In embodiments, the system calculates qualitative metrics (e.g., range of motion, ankle dorsiflexion, Q-angle, hip-knee-ankle alignment, gait speed, etc.) to determine whether the user has suffered or is at risk of an injury (e.g., ACL tear, patellar tendonitis, hip fracture, etc.) and / or whether a physiological condition has worsened or improved over time (e.g., after surgery or physical therapy). In some embodiments, the system constructs a digital twin of the user and displays a visual representation of the digital twin performing idealized movements (e.g., proper form for exercise or physical therapy) to provide real-time instruction and feedback to improve the physiological condition of the user.

Systems and methods for monitoring heart failure (HF) status in a patient are discussed. An exemplary system includes a gait analyzer circuit than can receive gait or balance information, and generate a gait feature such as gait speed or a gait pattern. The system includes a HF detector circuit that can detect patient HF status, or to predict patient risk of a future worsening heart failure (WHF) event, using the gait feature. In some examples, the system may trigger sensing physiologic information according to the detected gait, and detect patient HF status using the sensed physiologic information. The system can initiate or adjust a heart failure therapy according to the HF status or the WHF risk.

The present invention relates to the field of intelligent detection technology, and specifically to a Parkinson intelligent detection method and system based on data recognition, which includes the following steps: collecting the user's physiological and motion data through a smart watch, a wristband, and a mobile gait detector, recording the gait speed, stride length, and hand tremor frequency, analyzing the smoothness of hand movements, recording the timestamp of each data point, and organizing the data in chronological order to obtain a time series data set. In the present invention, the physiological and motion data collected by intelligent devices are processed through time serialization, carefully tracking every tiny change in Parkinson's disease, using a neural network to analyze the time segment data, effectively distinguishing normal and abnormal patterns, and accurately extracting key behavioral features, which not only enhances the ability to judge Parkinson's disease in the early stage, but also helps doctors adjust treatment plans in a timely manner through continuous monitoring, significantly improving the quality of life of patients and providing continuous medical decision-making support.

The invention relates to a lower limb exoskeleton real-time gait recognition method fusing spatio-temporal characteristics, which comprises the following steps: step 1, a subject wears an exoskeleton gait recognition device, and motion data under a variable speed condition is acquired; step 2, preprocessing the collected data; 3, performing real-time gait phase division based on multi-sensor fusion; 4, detecting a zero-speed interval based on an adaptive threshold method, and extracting spatio-temporal characteristic parameters such as step length, gait cycle and step speed; 5, constructing a training set and a test set, performing feature importance analysis by using an SVM, and screening key features; step 6, constructing a hybrid model fusing a GNN module, an improved TCN module and a BiLSTM module to perform gait phase classification on new data; and step 7, comparing and analyzing a classification result with an identification result of a traditional model. The method aims at achieving the gait recognition purposes of high precision, low cost, stability, comfort, convenience and good real-time performance.

The invention discloses an abnormal gait detection method based on a smart phone camera and image convolution, and belongs to the technical field of mobile health. According to the technical scheme, video data of walking of a subject is collected through a camera of a smart phone; preprocessing the video data, and extracting human body key point coordinates; calculating gait parameters based on the key point coordinates, wherein the gait parameters comprise step length, step speed, support phase time, swing phase time and gait symmetry; constructing a multi-dimensional data set containing static space features and dynamic time sequence features; and training the data set by using a deep learning model to identify an abnormal gait type and evaluate the severity of the abnormal gait type. The method has the beneficial effects that the compliance of a patient and the monitoring universality are greatly improved, noise interference in a video acquisition process can be effectively removed, and the generalization ability of a subsequent model is effectively improved; the model can synchronously complete classification of multiple types of abnormal gaits and grading evaluation of severity; the method has superiority, robustness and clinical application potential in a real scene.