A portable and wearable hand-grasp neuro-orthosis is configured for use in a home environment to restore volitionally controlled grasp functions for a subject with a cervical spinal cord injury (SCI). The neuro-orthosis may include: a wearable sleeve with electrodes; electronics for operating the wearable sleeve to perform functional electrical stimulation (FES) and electromyography (EMG), the electronics configured for mounting on a wheelchair; and a controller configured for mounting on a wheelchair. The controller controls the electronics to read EMG via the sleeve, decode the read EMG to determine an intent of the user, and operate the electronics to apply FES via the sleeve to implement the intent of the user. The neuro-orthosis may restore hand function. The controller may include a display arranged to be viewed by the subject, for example mounted on an articulated arm attached to the wheelchair.

Devices, systems, and methods herein relate to electromyography (EMG) that may be used in diagnostic and/or therapeutic applications, including but not limited to electrophysiological study of muscles in the body relating to neuromuscular function and/or disorders. Sensor assemblies and methods are described herein for non-invasively generating an EMG signal corresponding to muscle tissue where the sensor may be positioned directly on a surface of the muscle tissue including any associated membrane (e.g., mucosal, endothelial, synovial) overlying the muscle tissue. A sensor assembly may include one or more pairs of closely spaced, atraumatic electrodes in a bipolar or multipolar configuration. The first and second electrodes may be applied against a surface of muscle tissue (that may include a membrane overlying the muscle) and receive electrical activity signal data corresponding to an electrical potential difference of the portion of muscle between the electrodes.

Devices, systems, and methods herein relate to electromyography (EMG) that may be used in diagnostic and/or therapeutic applications, including but not limited to electrophysiological study of muscles in the body relating to neuromuscular function and/or disorders. Sensor assemblies and methods are described herein for non-invasively generating an EMG signal corresponding to muscle tissue where the sensor may be positioned directly on a surface of the muscle tissue including any associated membrane (e.g., mucosal, endothelial, synovial) overlying the muscle tissue. A sensor assembly may include one or more pairs of closely spaced, atraumatic electrodes in a bipolar or multipolar configuration. The first and second electrodes may be applied against a surface of muscle tissue (that may include a membrane overlying the muscle) and receive electrical activity signal data corresponding to an electrical potential difference of the portion of muscle between the electrodes.

In a system for measuring biopotential signals generated by the physiological activity of a subject, it is necessary to monitor the measured biopotentials against a reliable reference. An apparatus and method of deriving a reference suitable for use in referencing and grounding of the subject are described.

The electronics arrangement comprising a processor (201); and a memory (203), the at least one memory (203) storing instructions, the instructions, when executed by the processor (201), cause the processor (201) to perform operations comprising: obtaining a current version of a machine-learned model; obtaining first data from at least one sensor (211) of the wearable article (20); and employing the current version of the machine-learned model to generate an inference using the first data. The processor (201) may determine whether to update the machine-learned model based on the generated inference. The processor (201) may comprise a hardware accelerator. The processor (201) may cause data to be transmitted to a base station for updating the machine-learned model.

The electronics arrangement comprising a processor (201); and a memory (203), the at least one memory (203) storing instructions, the instructions, when executed by the processor (201), cause the processor (201) to perform operations comprising: obtaining a current version of a machine-learned model; obtaining first data from at least one sensor (211) of the wearable article (20); and employing the current version of the machine-learned model to generate an inference using the first data. The processor (201) may determine whether to update the machine-learned model based on the generated inference. The processor (201) may comprise a hardware accelerator. The processor (201) may cause data to be transmitted to a base station for updating the machine-learned model.

The electronics arrangement comprising a processor (201); and a memory (203), the at least one memory (203) storing instructions, the instructions, when executed by the processor (201), cause the processor (201) to perform operations comprising: obtaining a current version of a machine-learned model; obtaining first data from at least one sensor (211) of the wearable article (20); and employing the current version of the machine-learned model to generate an inference using the first data. The processor (201) may determine whether to update the machine-learned model based on the generated inference. The processor (201) may comprise a hardware accelerator. The processor (201) may cause data to be transmitted to a base station for updating the machine-learned model.

The electronics arrangement comprising a processor (201); and a memory (203), the at least one memory (203) storing instructions, the instructions, when executed by the processor (201), cause the processor (201) to perform operations comprising: obtaining a current version of a machine-learned model; obtaining first data from at least one sensor (211) of the wearable article (20); and employing the current version of the machine-learned model to generate an inference using the first data. The processor (201) may determine whether to update the machine-learned model based on the generated inference. The processor (201) may comprise a hardware accelerator. The processor (201) may cause data to be transmitted to a base station for updating the machine-learned model.

The technology disclosed can be implemented to construct devices with an array of optical elements to provide power to stimulate a biological process in a nerve system in living objects, and to provide patterned light outputs from the array of optical elements to indicate a corresponding electrical pattern monitored from the biological process in the nerve system. In one aspect a nerve stimulator apparatus is disclosed including a plurality of optical to electrical transducers arranged in a two-dimensional array, wherein each of the plurality of optical to electrical transducers is configured to convert light to an electrical signal; a plurality of electrodes, each electrode associated with one or more associated optical to electrical transducers; and a plurality of electrical interconnects to connect each of the plurality of electrodes to the one or more associated optical transducers. In another aspect nerve sensor apparatus is disclosed including a plurality of optical to electrical transducers; a plurality of optical sources; a plurality of electrodes, each electrode associated with one or more optical to electrical transducers, each optical source configured to modulate light output according to a voltage at one of the plurality of electrodes; and a plurality of electrical interconnects.

Aspects of the subject disclosure may include, for example, a device, including: a sensor affixed to an article of clothing; a transducer affixed to the article of clothing; a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of: receiving sensor data from the sensor; processing the sensor data; sending the sensor data to a trained machine learning (ML) model having as inputs the sensor data, and providing as output, control data to control the transducer; receiving the control data from the trained ML model; and sending the control data to the transducer to provide therapy to a patient. Other embodiments are disclosed.