A solution for estimating effectiveness of periodic motion during a physical exercise. such as a running exercise, is disclosed. According to an aspect, a computer-implemented method for estimating the effectiveness of the periodic motion includes: measuring, by using at least one motion sensor, periodic motion of a user, and thus acquiring motion measurement data during a time interval of a physical exercise; transforming the motion measurement data into frequency-domain samples; extracting, amongst the frequency-domain samples by using peak detection, a first subset of frequency-domain samples representing periodic motion; computing a metric indicating a ratio between energy on the first subset of frequency domain samples and energy on other frequency domain samples; and mapping the computed ratio to an effectiveness parameter by using a determined mapping rule and outputting the effectiveness parameter via an interface.

Technologies and implementations for a wearable healthcare system, which may be worn by a person. The wearable healthcare systems may include one or more motion sensors. A motion analysis modules may be included in the wearable healthcare system, which may be configured to determine physical activities and intensity of the physical activities of the person.

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 method and system of training a machine learning neural network (MLNN) in anatomical degenerative conditions in accordance with anatomical dynamics. The method comprises receiving, in a first input layer of the MLNN, from a millimeter wave (mmWave) radar sensing device, a first set of mmWave radar point cloud data representing a first gait characteristic of a subject in motion, comprising an arm swing velocity, receiving, in a second layer, a second set of mmWave radar point cloud data representing a second gait characteristic comprising a measure of dynamic postural stability, the input layers being interconnected with an output layer of the MLNN via an intermediate layer, and training a MLNN classifier in accordance with a classification that increases a correlation between a degenerative condition of the subject as generated at the output layer and the sets of mmWave point cloud data.

A processing device, program, method, and processing system are provided which can be more simply used by a user when estimating a condition during exercise or assisting estimation. The processing device comprises: an input/output interface configured to receive an acceleration rate detected, in a wired or wireless manner, from a sensor which is attached to or around the knee of a leg of a person and is for detecting at least the acceleration rate of the person during exercise; a memory configured to store the received acceleration rate in addition to a predetermined instruction command; and a processor configured to perform processing for estimating the condition of the knee joint of the person during exercise on the basis of the acceleration rate by executing the predetermined instruction command stored in the memory.

An apparatus includes a frame, a sensor, and an electric stimulator. The frame is removably couplable to a portion of a limb. The sensor is configured to produce a first signal associated with a gait characteristic at a first time, and a second signal associated with the gait characteristic at a second time, after the first time. The electric stimulator is removably coupled to the frame and is in electrical communication with an electrode assembly and the sensor to receive the first signal substantially at the first time and the second signal substantially at the second time. Based in part on the gait characteristic at the first time, the electric stimulator sends a third signal to the electrode assembly to provide an electric stimulation to a portion of a neuromuscular system of the limb substantially during a time period defined between the first time and the second time.

A mobile music listening device synchronizing in a personalized way music and movement, and dedicated to improving the kinematics of the runner. Thanks to inertial units connected to a smartphone, the runner's steps are detected in real time by the mobile application. A dedicated algorithm adapts the pulsation of the musical excerpts in such a way as to bring the runner to a suitable cadence, capable of preventing injuries. A method for the synchronization of the rhythmic stimulation with the biological variability using a Kuramoto model characterized in that phase oscillator with a coupling term from the movement dynamics with parameters of, coupling strength, maximum and minimum frequencies for a fraction of the unmodified song frequency, maximum difference between the tempo and target frequency, Target the target frequency.

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 method of providing workout training for a user of an activity tracking system includes displaying a plurality of training plan options to the user on a screen of a personal electronic device, and then receiving a selected training plan option from the user. Selected workout day options are received from the user and the system generates a training schedule for the user based on the selected training plan and the selected workout day options. One or more reminders identify the type of workout for the scheduled day and an option to accept or reject the workout. When the user selects the option to accept the workout, the workout goal associated with the scheduled workout is displayed. The method further includes determining progress toward the workout goal based on the received workout data, and displaying an indicator of progress toward the workout goal on the screen during the workout.

A method of detecting gaits of an individual with a sensor worn by the individual. The sensor includes an accelerometer and a processing unit. The method includes obtaining an signal representing one or more sensor acceleration values; sampling the signal to obtain a sampled signal; segmenting the sampled signal into windows to obtain a segmented acceleration signal; extracting a feature set from the segmented acceleration signal; determining a probability value, for a respective window, n, where n is a positive integer greater than zero, the probability value giving an estimated probability value of gait occurrence for the individual during the respective window; modifying the estimated probability value by using a histogram of previously detected gait durations to obtain a modified probability value; and determining, based on the modified probability value, and by using a determination threshold whether or not the respective window represents gait occurrence.