A method and an apparatus for classifying an electroencephalogram signal, a device and a computer-readable storage medium. The method includes: obtaining an electroencephalogram signal; performing feature extraction on the electroencephalogram signal to obtain a signal feature corresponding to the electroencephalogram signal; obtaining a difference distribution ratio, the difference distribution ratio being used for representing impacts of difference distributions of different types on distributions of the signal feature and a source domain feature in a feature domain, the source domain feature being a feature corresponding to a source domain electroencephalogram signal; aligning the signal feature with the source domain feature according to the difference distribution ratio to obtain an aligned signal feature; and classifying the aligned signal feature to obtain a motor imagery type corresponding to the electroencephalogram signal.

A method is provided that includes determining a quality of a data portion of an input sensor data stream based, at least in part, on data of a first data type and determining between, at least, generation of two or more streams of a second, different data type including at least one synthesised data stream of the second data type. Determining between generation of two or more streams of a second, different data type is based, at least in part, on the determined quality. The synthesis is based, at least in part, on the data of the first data type. The method further includes causing generation of at least one stream of the second, different data type based, at least in part, on the determination between generation of two or more streams of the second, different data type.

Disclosed is a method for determining an unworn state of a sensor system comprising a pair of sensors configured for mounting on first and second body parts either side of a joint. The method comprises: obtaining one or more measurements from each sensor; calculating a relative angle between the two sensors using one or more of the obtained one or more measurements; calculating, using one or more of the obtained one or more measurements, a joint angle between the first and second body parts, where the joint angle is defined in a plane of normal bending of the joint; and determining, based on the calculated angles, whether either of the sensors is not mounted and if so, determining that the system is in an unworn state. Also disclosed is a system for providing information about a joint.

The invention relates to a system and a method for learning a gesture by a human learner (5), comprising the following steps: equipping said learner (5) with a plurality of motion sensors (6, 7) on a plurality of members that are predetermined in accordance with said gesture to be learned; acquiring biomechanical data provided by said plurality of sensors during a gesture performed by the learner; analyzing said acquired biomechanical data and determining a theoretical correction of the gesture by comparing said biomechanical data of the learner with biomechanical data corresponding to a target gesture; customizing the theoretical correction into a specific correction on the basis of behavior models of the learner derived from a history of biomechanical data acquired for the learner; transmitting said specific correction to the learner; updating said specific correction on the basis of information representing the sensation perceived by the learner when performing the corrected gesture.

Systems and methods for providing a customized exercise protocol to a computing device of a user. As the user performs the exercise protocol, one or more cameras of the computing device can track the user's movements. The user's movement are assessed to determine if proper form and technique is being used.

The motion data monitoring method includes: collecting, by an electronic device, an angular velocity signal and an acceleration signal of a user; obtaining, by the electronic device, a waveform feature of the angular velocity signal based on the angular velocity signal, and obtaining a waveform feature of the acceleration signal based on the acceleration signal; determining, by the electronic device, a gait feature of the user according to the waveform feature of the angular velocity signal and the waveform feature of the acceleration signal, where the gait feature includes a duration of flight from off-ground of a foot of the user to touching of the ground; and determining, by the electronic device, motion data according to the gait feature, where the motion data includes a jump height.

A training pad system for house training of a pet or toilet training of a juvenile human, includes a training pad with one or more diagnostic zones, each comprising one or more diagnostic test areas, optionally a pad cutout that matches a shape of a lower portion of a toilet, a urine indicator composition for visually indicating exposure to urine with a signal color, a liquid absorbing material, an antimicrobial agent, and adhesive surfaces; and a diagnostic decoding chart to interpret diagnostic results by lookup of corresponding test decoding areas.

A cognitive level evaluation system includes a detector and a cognitive level evaluator. The detector is configured to detect a behavior of a subject in a toilet space. The cognitive level evaluator is configured to evaluate a cognitive level of the subject based on a detection result of the detector.

A method for optimizing at least one exercise for a first user. The method includes receiving first user data including attribute data associated with the first user and outcome data associated with the exercise. The method includes generating, based on the first user data, initial target data. The initial target data is associated with at least one of the first user, the exercise apparatus, and the exercise. The method includes receiving measurement data associated with at least one of the first user, the exercise apparatus, and the exercise. The measurement data is associated with one or more sensors. The method includes determining differential data based on one or more differences between the initial target data and the measurement data. The method includes generating, via an artificial intelligence engine and based on the differential data, a machine learning model trained to generate optimized target data.

A chest tube insertion test device for performing a chest tube insertion training procedure at least partially encloses an insertion tool and includes a microcontroller communicatively coupled to one or more force-sensing resistors. The one or more force-sensing resistors convert an insertion force into a voltage signal sent to the microcontroller. A feedback generator compares the chest tube insertion force to one or more predetermined threshold values and provides feedback to a trainee. The feedback can include an instruction to increase, decrease, or maintain the chest tube insertion force. The feedback is one or more audio cues and/or one or more visual cues (e.g., represented by audio files and/or visual data files stored at the chest tube insertion test device). The chest tube insertion test device detects an insertion force rate of change indicating that the insertion tool has passed through an inner pad of the training model.