Conventionally, a neuronal controller located inside the central nervous system governing the maintenance of the upright posture of the human body is designed from a control system perspective using proportional-integral-derivative (PID) controllers, wherein human postural sway is modeled either along a sagittal plan or along a frontal plane separately resulting in limited insights on intricacies of a governing neuronal controller. Also, existing neuronal controllers using a reinforcement learning (RL) paradigm are based on complex actor-critic on-policy algorithms. Analyzing human postural sway is critical to detect markers for progression of balance impairments. The present disclosure facilitates modelling the neuronal controller using a simplified RL algorithm, capable of producing postural sway characteristics in both sagittal and frontal plane together. The Q-learning technique of the RL paradigm is employed for learning an optimal state-action value (Q-value) function for a tuneable Markov Decision Process (MDP) model.

Embodiments of the present disclosure relate to heart sound measurements using mobile devices. In an embodiment, a medical system for monitoring heart sounds of a subject comprises a medical device configured to obtain, during a first sampling interval, a first physiological signal. The medical system further comprises a mobile device comprising an accelerator, wherein the accelerator is configured to obtain, during a second sampling interval, a second physiological signal. And, the medical system comprises an analysis component configured to extract heart sounds data from the second physiological signal.

A method for monitoring health of a subject based on a physiological response to physical exertion, by processing circuitry of a medical device system, is described that includes detecting a plurality of exertion events of the subject based on a first sensed signal that varies as a function of movement of the subject. The method further includes determining a response of a physiological parameter of the subject to the exertion event for each of the detected exertion events based on second sensed signal that varies as a function of the physiological parameter. The method further includes determining that a change in the responses over time crosses threshold and generating an alert to a user based on the determination that the change crosses the threshold.

The head-position sway measuring device (D) includes a touch panel (1a) that gives the instruction to open or close eyes, an acceleration sensor (2a) that measures a displacement of a head position, and a sway recognition unit (1b) that recognizes a head-position sway value based on the displacement of the head position. The acceleration sensor (2a) measures a first measurement value, which is a measurement value obtained in the eye-open state, and then measures a second measurement value, which is a measurement value obtained in the eye-closed state. The sway recognition unit (1b) recognizes the head-position sway value based on the first measurement value and the second measurement value.

The invention relates to a wearable device for determining a nature of motion and/or a physiological state of a wearer. The wearable device comprises a body portion configured to be worn by the wearer and at least one sensor mounted to the body portion configured to, while the wearable device is being worn, detect a motion parameter of the wearer and/or a physiological parameter of the wearer and generate input data indicative of the motion parameter and/or the physiological parameter. The wearable device further comprises a processor configured to receive the input data from the at least one sensor and process the input data by executing an algorithm to determine the nature of motion and/or the physiological state of the wearer while the wearable device is being worn. The invention further relates to a system for determining a nature of motion and/or a physiological state of a wearer.

A human body sensing mat for sensing the movement of a human body, comprises: a substrate; a sensor array including a plurality of fiber sensors for generating signals according to a distance to a specific object, and disposed on the substrate; and a driving unit for applying a voltage to the sensor array, wherein the sensor array includes a plurality of sensing lines arranged in parallel in a first direction, and regarding the plurality of sensing lines, a first distance between neighboring sensing lines connected to different electrodes is greater than a second distance between neighboring sensing lines connected to the same electrode. The human body sensing mat can analyze user's movements and biometric signals regardless of the user's posture.

Systems and methods for monitoring patients with a chronic disease are described. A patient management system may sense physiological signals from a patient using one or more implantable or other ambulatory sensors, and generate from the physiological signals a chronobiological rhythm indicator (CRI) such as indicating a circadian rhythm. A reference CRI associated with a prior hospital admission event of the patient may be provided to the patient management system, which compares the CRI to the reference CRI and generates a readmission risk score indicating the patient's risk of subsequent hospital readmission due to a worsened condition of the chronic disease. The readmission risk score may be provided to a user or a process, or used to initiate or adjust a therapy delivered to the patient.

A sensor includes: an electrostatic-capacity-type sensor electrode layer having a plurality of sensing units; a reference electrode layer opposed to one main face of the sensor electrode layer; and a deformable layer disposed between the reference electrode layer and the sensor electrode layer, the deformable layer being to deform elastically due to application of pressure. The deformable layer is recessed between the sensing units or discontinuous between the sensing units. The reference electrode layer has a shaped portion between the sensing units.

Neural stimulation is provided according to a closed loop algorithm to treat sleep disordered breathing (SOB), including obstructive sleep apnea (OSA). The closed loop algorithm is executed by a system comprising a processor (which can be within the neural stimulator). The closed loop algorithm includes monitoring physiological data (e.g., EMG data) recorded by a sensor implanted adjacent to an anterior lingual muscle; identifying a trigger within the physiological data, wherein the trigger is identified as a biomarker for a condition related to sleep (e.g., inspiration); and applying a rule-based classification (which can learn) to the trigger to determine whether one or more parameters of a stimulation should be altered based on the biomarker.

A detecting method and a positioning analysis method of human functional joint rotation center are provided. The detecting method of human functional joint rotation center includes: step 11: in a continuous motion, a human functional joint rotation center FCR is abstracted as a center of a flexible ball; step 12: at any moment during a test, position coordinates of the center of the ball (i.e. FCR) at the moment are determined according to position coordinates of M1, M2 and M3, and then the motion trajectory of the FCR is obtained in the continuous motion; the positioning analysis method performs positioning analysis of joint positions based on morphological parameters collected by 3D scanning. The detecting method is based on an idea of flexible ball, its operation is simple within a certain error range, and the method performs very well in the continuity of trajectory of joint.