16 results about "Functional electrical stimulation" patented technology

Systems and methods for generating a finite element model (FEM) of current flow in an anatomical human forearm are disclosed. The disclosed FEM may assist in determining optimal stimulation parameters in electrical stimulation systems for achieving movement of paralyzed limbs or enhancement of able limbs. This model will allow users to determine which muscle groups are receiving stimulation under different parameters. Systems and methods which leverage electrical impedance tomography (EIT) for autonomous recalibration following garment donning are also disclosed. The method may comprise performing an EIT measurement across an electrode array of an electrode garment and constructing an anatomical model based on the EIT measurement. Next, one or more alignment variations may be estimated based on an alignment variation model. Finally, the electrode array is adjusted, automatically or manually, to accommodate the alignment variations using an alignment adjustment function.

This invention relates to the fields of rehabilitation medicine, brain-computer interfaces, and functional electrical stimulation, and discloses an alternating synergistic stimulation control method suitable for asymmetric gait. The invention collects various baseline data from the patient's healthy and affected sides, calculates the initial asymmetry, and initializes training parameters based on the baseline data. After configuration, the patient undergoes rehabilitation training, and various training data are collected in real time. The training process is controlled in real time, and the phase synchronization rate and cumulative asymmetry are calculated based on the training data, thereby optimizing the training parameters in a closed-loop manner. This invention solves the specific problem of asymmetric gait in hemiplegic patients, significantly improves gait coordination and neural remodeling efficiency, and is applicable to lower limb rehabilitation devices such as brain-computer interface rehabilitation treadmills, possessing extremely high clinical application value.

This invention discloses a wavelet-enhanced co-activation method for multi-target temporal modulation of functional electrical stimulation (FES), relating to the field of biomedical engineering technology. The model constructs a time-frequency energy salient feature matrix by analyzing multi-channel surface electromyography (SEMG) signals using an overlapping sliding window combined with energy proportions. Simultaneously, it constructs an intermuscular co-activation matrix within the multi-channel SEMG sliding window. Each single-channel time-frequency energy salient feature matrix and the multi-channel intermuscular co-activation matrix are then combined to form a multi-channel high-dimensional matrix. This high-dimensional matrix is ​​then dimensionality-reduced to a multi-channel, multi-dimensional time-frequency energy-intermuscular co-activation matrix. An adaptive threshold logic combination rule is used to filter muscle activation temporal vectors, and finally, the activation temporal sequence is applied to FES experiments. This invention, by analyzing multi-channel SEMG signals and multi-target muscle co-activation characteristics, accurately predicts hand movements in the sagittal plane and dynamically adjusts FES parameters, achieving precise control over muscle activity phases.

This invention discloses a closed-loop control method for functional electrical stimulation (fEP) that combines muscle activation and deep learning. It integrates muscle activation analysis with an LSTM model from deep learning to design and develop a closed-loop control method for fEP based on muscle activation and LSTM. This method can automatically learn appropriate fEP parameters based on real-time analysis of electromyographic signals to determine muscle state. This allows the method to automatically adjust the fEP parameters according to changes in muscle activation when the patient clenches their fist on the healthy side, making the grip strength on the affected and healthy sides more consistent. Furthermore, the LSTM model continuously learns and optimizes the output fEP parameters as the input dataset increases. This solves the problems in clinical fEP treatment where parameters cannot be adjusted in real-time according to the user's muscle state, parameter adjustment relies entirely on experience, patient participation is low, and active rehabilitation is not possible.

Functional electrical stimulation devices and methods of operating the same are described. For example, a device includes a high-efficiency power boost circuit configured to step a low battery voltage to a boosted output voltage, an open-loop charge pump circuit coupled to the power boost circuit to further increase the boosted voltage, and a switched capacitor output stage to generate high-slew-rate, charge-balanced stimulation pulses. The switched capacitor stage may produce symmetric or asymmetric bi-phasic pulses with adjustable amplitudes, widths, and frequencies over an operating range. The boost and charge pump stages may operate in discontinuous conduction and discontinuous voltage modes to achieve soft switching and improved efficiency at high conversion ratios. The devices may be incorporated into wearable electrical stimulators using textile electrodes. Methods are also provided for operating the power boost circuit, the charge pump circuit, and the switched capacitor stage to deliver controlled stimulation to electrically excitable tissue.

A brain-computer interface (BCI) includes a multichannel stimulator and a decoder. The multichannel stimulator is operatively connected to deliver stimulation pulses to a functional electrical stimulation (FES) device to control delivery of FES to an anatomical region. The decoder is operatively connected to receive at least one neural signal from at least one electrode operatively connected with a motor cortex. The decoder controls the multichannel stimulator based on the received at least one neural signal. The decoder comprises a computer programmed to process the received at least one neural signal using a deep neural network. The decoder may include a long short-term memory (LSTM) layer outputting to a convolutional layer in turn outputting to at least one fully connected neural network layer. The decoder may be updated by unsupervised updating. The decoder may be extended to include additional functions by transfer learning.

This invention discloses a functional electrical stimulation rehabilitation aid for stroke, belonging to the field of medical rehabilitation aid technology. It includes an electrical stimulation component, a walking component, a height adjustment component, a body support adjustment component, and a rehabilitation component. This device integrates the electrical stimulation component, the body support adjustment component, and the lower limb rehabilitation training component into one unit, overcoming the limitations of traditional devices that separate head electrical stimulation from limb training. It transmits precise electrical signals to the head's nerve function areas through flexible electrode pads within the helmet, directly promoting the repair and regeneration of damaged nerves. Furthermore, the servo motor-driven linkage mechanism in the rehabilitation component simulates human gait, achieving passive training of lower limb joints and muscles. This eliminates the need for patients to transfer between multiple devices, reducing physical exertion and avoiding safety risks during transfers, making it particularly suitable for acute-phase patients with weak limb mobility.

The application provides a functional electrical stimulation upper limb tremor suppression method based on residual reinforcement learning, comprising the following steps: acquiring joint angle signals and affected side active muscle surface electromyogram signals; acquiring joint angle error signals based on the joint angle signals and inputting the joint angle error signals into a HORC controller to obtain a compensation signal; superimposing the compensation signal and the joint angle error signal and then inputting the superimposed signal into an ADRC controller to obtain a basic stimulation current; performing [4, 12] Hz band-pass filtering on the joint angle signals to obtain a tremor amplitude; calculating electromyogram energy of the affected side active muscle surface electromyogram signals in a [0, 2] Hz frequency band; taking the tremor amplitude, the electromyogram energy, a compensation error of a high-order internal model in the HORC controller and a total disturbance estimation value output by an ESO in the ADRC controller as a four-dimensional state vector and inputting the four-dimensional state vector into a constructed reinforcement learning intelligent agent to obtain a residual correction signal; and performing weighted synthesis on the residual correction signal and the basic stimulation current to obtain a total stimulation current as a driving signal of the FES.

The present application relates to medical rehabilitation training and power-assisted equipment, in particular to a shoulder joint exoskeleton device based on human-like movement mechanism. The device comprises a back plate, a shoulder joint mechanism and a functional electrical stimulation system. The shoulder joint mechanism is arranged on one side or both sides of the back plate. The shoulder joint mechanism comprises a fixed shoulder joint, a driving wheel, a scissor-type scapula following mechanism and a shoulder support. The fixed shoulder joint is arranged on the back plate. The driving wheel is installed on the fixed shoulder joint through a center of symmetry shaft. One end of the scissor-type scapula following mechanism is connected with the center of symmetry shaft, and the other end is connected with the shoulder support. The scissor-type scapula following mechanism is used for passively following the protraction and retraction movement of the human scapula. By rotating the driving wheel, the abduction and adduction movement of the shoulder joint is realized. The functional electrical stimulation system is used for assisting the activation of target muscles. The present application has simple structure, is easy to wear and portable, can realize active movement and electrical stimulation collaborative rehabilitation, and effectively improves the rehabilitation efficiency.

This method discloses a phase-adaptive FES modulation system based on multimodal signal fusion. It integrates brainwave motor imagery (BCI) signals, treadmill mechanical sensing signals (pedal angle, rotation speed, resistance), and electromyography (EMG) signals to construct a dynamic FES modulation model based on the lower limb pedaling motion phase (initiation / force exertion / retraction). Through AI algorithms, it decodes the intensity of motor intention and muscle activation state in real time, adaptively adjusting FES stimulation parameters (intensity, frequency, pulse width) to achieve precise closed-loop stimulation with a triple match of "intention-phase-muscle strength." This system ensures that stimulation is applied only during physiologically appropriate phases, avoiding motor interference and significantly improving the effectiveness and safety of lower limb rehabilitation training after stroke.

The application discloses a kind of based on motor imagination and collaborative stimulation brain-computer interface rehabilitation training system and method.The system includes signal acquisition module, data processing module and collaborative stimulation module.Data processing module is based on affine invariant riemannian metric and Transform model according to the multi-channel electroencephalogram signal of acquisition, generates movement intention decoding result and trigger signal;Collaborative stimulation module responds to trigger signal, drives functional electrical stimulation and vagus nerve stimulation unit to execute synchronous stimulation, constitutes closed-loop rehabilitation training.The core lies in that decoding unit is reduced by dimension to electroencephalogram signal by based on affine invariant riemannian distance unsupervised clustering, then input Transform model classification, in combination with the double verification mechanism of trigger control unit, realize high-precision intention decoding and reliable trigger.The present application accurately synchronizes central nervous regulation and peripheral muscle feedback, effectively improves the neural remodeling efficiency and system generalization ability of motor function rehabilitation.

The application provides a fatigue adjustment method based on brain-computer interface and functional electrical stimulation closed-loop regulation, and relates to the technical field of fatigue adjustment. The method comprises the following steps: collecting electroencephalogram signals and behavioral information of a target user; preprocessing the electroencephalogram signals and the behavioral information to obtain electroencephalogram and behavioral data corresponding to a plurality of electroencephalogram analysis windows; extracting a multi-dimensional feature vector corresponding to a pre-selected representative feature dimension sequence from the electroencephalogram and behavioral data in the electroencephalogram analysis windows; inputting the multi-dimensional feature vector into a pre-constructed fatigue model to obtain a fatigue score; and generating an FES control instruction according to the fatigue scores corresponding to the plurality of electroencephalogram analysis windows, wherein the FES control instruction is used to control stimulation parameters, stimulation modes and / or stimulation durations of an FES device to perform fatigue relief stimulation on the target user, thereby achieving low-cost and good-migration fatigue adjustment.

The present invention relates to a movement recovery system, and a method of improving the functional motor recovery of a subject with a movement disorder. The present invention provides for a system and method, which in some embodiments can accurately quantify therapy parameters including compliance, task time spent, muscle coordination and functional improvement by utilizing kinetic, gyroscopic or other movement related information, and / or electromyography (EMG) data. In other embodiments, the system and method provide for functional electrical stimulation (FES) to help control the exercise therapy. The present invention further includes the methods of controlling or utilizing the movement related information, EMG and / or FES to detect, monitor, and control the exercise therapy.

A functional electrical stimulation device (10) includes: four or more conductive wires (12); four or more electrode portions (13) each provided to each of the four or more conductive wires (12) for stimulating four or more upper limb-related nerves constituting a brachial plexus or stimulating four or more lower limb-related nerves located in a cauda equina; and a main body portion (11) for supplying electric current to the four or more electrode portions (13) via the four or more conductive wires (12).