A physiological signal sensing system and a physiological signal sensing method are provided. The physiological signal sensing system includes a signal processing device and a physiological signal sensing device having a plurality of sensing electrodes. The sensing electrodes are used to contact the skin of an organism to sense a plurality of physiological signals. The signal processing device is coupled to the physiological signal sensing device to receive the physiological signals, compares these physiological signals with the reference physiological signal pattern to obtain a comparison result, selects a selected electrode pair from the sensing electrodes based on the comparison result, and uses the selected electrode pair to perform physiological signal measurement on the organism during a normal operation period.

A technology is described for determining an intended movement from neuromuscular signals. An example method (800) includes receiving electromyography (EMG) data corresponding to single-ended channels of an electrode array (810), where EMG signals are detected by electrodes comprising the single-ended channels of the electrode array and the EMG signals are converted to the EMG data. Determining differential channel pairs for the single-ended channels of the electrode array (820) and extracting feature data from the EMG data of the differential channel pairs (830). Thereafter a feature data set is selected from the feature data of the differential channel pairs (840) and the feature data set is input to a decode model configured to correlate the feature data set to an intended movement (850). Decode output is received from the decode model indicating the intended movement (860) and the decode output is provided to a device (870).

A technology is described for determining an intended movement from neuromuscular signals. An example method (800) includes receiving electromyography (EMG) data corresponding to single-ended channels of an electrode array (810), where EMG signals are detected by electrodes comprising the single-ended channels of the electrode array and the EMG signals are converted to the EMG data. Determining differential channel pairs for the single-ended channels of the electrode array (820) and extracting feature data from the EMG data of the differential channel pairs (830). Thereafter a feature data set is selected from the feature data of the differential channel pairs (840) and the feature data set is input to a decode model configured to correlate the feature data set to an intended movement (850). Decode output is received from the decode model indicating the intended movement (860) and the decode output is provided to a device (870).

Automatic electromyography (EMG) electrode selection for robotic devices is disclosed. A plurality of signals from a corresponding plurality of sensors coupled to a skin of a user is received. For each pair of at least some pairs of the plurality of sensors, a sensor pair signature is generated based on differences in signals that are generated by the respective pair of sensors. Each of the sensor pair signatures is compared to a predetermined sensor pair signature to identify a particular pair of sensors. A signal difference between two signals generated by the particular pair of sensors is subsequently utilized to generate a command to drive a motor.

An active orthotic device, e.g. a hand orthosis, is attached to one or more limbs of a human subject and comprises a respective set of actuators (21) for moving a respective limb (1A) among the one or more limbs. A method for controlling the orthotic device comprises obtaining one or more bioelectric signals, [S(t)], from one or more bioelectric sensors (10) attached to or implanted in the human subject; processing the one or more bioelectric signals, [5(t)], for prediction of an intended application force, FA(t), of the respective limb (1A) onto an object; obtaining a force signal, PA(t), from a force sensing device (22) associated with the respective set of actuators (21) and/or the respective limb (1A); and generating, as a function of a momentary difference, e(t), between the intended application force, FA(t), and the force signal, PA(t), a respective set of control signals, it(t), for the respective set of actuators (21).

Devices, systems, and techniques for analyzing video information to objectively identify patient behavior are disclosed. A system may analyze obtained video information of patient motion during a period of time to track one or more anatomical regions through a plurality of frames of the video information and calculate one or more movement parameters of the one or more anatomical regions. The system may also compare the one or more movement parameters to respective criteria for each of a plurality of predetermined patient behaviors and identify the patient behaviors that occurred during the period of time. In some examples, a device may control therapy delivery according to the identified patient behaviors and/or sensed parameters previously calibrated based on the identified patient behaviors.

Devices, systems, and techniques for analyzing video information to objectively identify patient behavior are disclosed. A system may analyze obtained video information of patient motion during a period of time to track one or more anatomical regions through a plurality of frames of the video information and calculate one or more movement parameters of the one or more anatomical regions. The system may also compare the one or more movement parameters to respective criteria for each of a plurality of predetermined patient behaviors and identify the patient behaviors that occurred during the period of time. In some examples, a device may control therapy delivery according to the identified patient behaviors and/or sensed parameters previously calibrated based on the identified patient behaviors.

The present disclosure relates to method and system for signal processing rehabilitation exercise signals. The method comprises the step of receiving a first and a second motion signals associated with movements of a body part, wherein the motion signals comprise temporal data of the movements. The method further comprises the step of segmenting each of the first and second motion signals into a plurality of segmented signals based on gradients of the motion signals, wherein each segmented signal has consistent gradient. The method further comprises the step of automatically modifying the segmented signals to form multiple combinations of matching signals with similar gradients between the first and second motion signals, such that the first and second motion signals are in one-to-one correspondence. The method further comprises the step of extracting corresponding time intervals of the matching signals in the correspondences.

A patient-specific arthroplasty system comprising a database comprising preoperative data, ligament balancing tool data, and postoperative data associated with a plurality of patients, a preoperative evaluation module that receives preoperative data for a given patient, an analysis engine that analyzes the database, receives the preoperative data, and generates a surgical recommendation based on the preoperative data of the given patient and the analysis of the database, and a pin positioning block module that receives the surgical recommendation and determines a pin positioning block based on the surgical recommendation.

A patient-specific arthroplasty system comprising a database comprising preoperative data, ligament balancing tool data, and postoperative data associated with a plurality of patients, a preoperative evaluation module that receives preoperative data for a given patient, an analysis engine that analyzes the database, receives the preoperative data, and generates a surgical recommendation based on the preoperative data of the given patient and the analysis of the database, and a pin positioning block module that receives the surgical recommendation and determines a pin positioning block based on the surgical recommendation.