A method for human action recognition in a human-machine interactive assembly scene is disclosed in this application, joint coordinate streams of skeleton joints are obtained under a human action from motion sensing devices; a starting position and an ending position of the action are positioned according to data change based on a threshold value to obtain information of joints; resampling of angle change is made on the information of joints to obtain coordinates of joints; the coordinates of joints are normalized, to obtain a sequence of skeletons forming an action; obtaining a vector direction of the upper limb, and the scene is classified to be a left-hand scene or a right-hand scene; training is made for human action recognition in the left-hand scene and the right-hand scene respectively; human action outputs of the left-hand scene and the right-hand scene are fused to realize action recognition in a human-machine interaction scene.

Exemplary embodiments of wearable stretch sensors and applications of using the same are disclosed. In embodiments, the sensors and the applications disclosed herein can be used to capture spinal motion and posture information.

A wearable device and a method of operating the same are provided. The wearable device includes a shoe assembly, a plurality of pressure sensors, a processing circuit and an alarm module. The plurality of pressure sensors are disposed on the shoe assembly and configured to generate a plurality of pressure sensing values. The processing circuit is configured to calculate a center of gravity coordinate according to the plurality of pressure sensing values and coordinates of the plurality of pressure sensors, and generate a determination result according to the center of gravity coordinate. The alarm module is configured to output an alarm signal to perform an alarm function.

An electronic device for gesture recognition, includes a processor operably connected to a transceiver. The transceiver is configured to transmit and receive signals for measuring range and speed. The processor is configured to transmit the signals, via the transceiver. in response to a determination that a triggering event occurred, the processor is configured to track movement of an object relative to the electronic device within a region of interest based on reflections of the signals received by the transceiver to identify range measurements and speed measurements associated with the object. The processor is also configured to identify features from the reflected signals, based on at least one of the range measurements and the speed measurements. The processor is further configured to identify a gesture based in part on the features from the reflected signals. Additionally, the processor is configured to perform an action indicated by the gesture.

An apparatus for monitoring a person, including while sleeping, the apparatus including: a. a garment for a person to wear while sleeping; b. a rigid sensor device configured to detect a temperature and/or a motion of the rigid sensor device while the person is wearing the garment; and c. an elastic pocket configured to hold the rigid sensor device tightly inside the garment during the detection of the temperature and/or the motion.

Systems and methods for assessing, monitoring, or theranosing a condition or disorder based on a comparison of limb stability for one or more limbs of a subject from a baseline. The method includes placing two or more inertial measurement sensors on the limbs of the subject, acquiring baseline limb excursion data from the inertial measurement sensors while a patient is performing at least one of a static balance activity and a dynamic balance activity by tracking the relative displacement of the respective two or more inertial measurement sensors; acquiring post-injury limb excursion data after an injury from the inertial measurement sensors while a patient is performing at least one of a static balance activity and a dynamic balance activity; and determining the activity clearance index as a function of a comparison of the baseline limb excursion data compared to the post-injury limb excursion data.

A single-lower-limb rehabilitation exoskeleton apparatus and control methods includes a controller, an intact lower-limb component and a paretic lower-limb component connecting communicatively with the controller. The controller is used to determine the current state of the intact lower-limb through the intact lower-limb component and the current state of the paretic lower-limb through the paretic lower-limb component. When the intact lower-limb component is in the lifting state, the movement data of the intact lower-limb is collected and sent to the controller. The controller is used to determine the corresponding gait data for the paretic lower-limb component according to the movement data of the intact lower-limb and send the gait data to the paretic lower-limb component. The paretic lower-limb component is used to drive the paretic lower-limb to move or walk according to the gait data while the intact lower-limb is in the supporting state.

A gait evaluation apparatus that evaluates a training gait of a paralyzed patient suffering from paralysis in a leg includes an acquisition unit configured to acquire a plurality of motion amounts of a paralyzed body portion according to a gait motion and an evaluation unit configured to evaluate that the gait motion is an abnormal gait in a case where at least one of the motion amounts acquired by the acquisition unit meets any one of a plurality of abnormal gait criteria set in advance. The abnormal gait criteria include at least two or more first criteria, which are criteria relevant to motion amounts of different parts of the paralyzed body portion, or at least two or more second criteria, which are criteria relevant to motion amounts of the same part of the paralyzed body portion in different directions.

A processing device receives, from a three-dimensional (3D) motion capture system, initial data representing an initial orientation of a subject user's body in an initial position. The processing device further receives x-ray data representing at least the portion of the subject user's body in the initial position. The processing device determines an actual orientation of at least one bone or joint from the portion of the subject user's body in the initial position as represented in the x-ray data and calibrates the initial orientation of the 3D motion capture system to reflect the actual orientation of the at least one bone or joint in the initial position.

Method for detecting biomechanical and functional parameters of the knee in a situation of performance stress, which comprises: a step for the set up of video recording means (1); a step for the set up of multiple optical markers (4) at specific landmark anatomic points (PA) of the foot and of the knee of a person; a step for the set up, at the plantar surface of the foot, of baropodometric means (5); a step for the acquisition, by means of the video recording means (1), of images of at least one reference action, and a step for the detection, by means of the baropodometric means (5), of baropodometric parameters; a step for calculating, from the baropodometric parameters, the coordinates of the center of pressure (COP) of the foot and of the constraining reaction force (FV) acting on the foot; a step for calculating a force arm (BF) given by the distance between the center of pressure (COP) and a reference point (PR) of the knee; a step for calculating a biomechanical parameter indicative of the valgus moment, derived from the vector product (PV) of the force arm (BF) and the constraining reaction force (FV).