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.

A method for generating PPG signals may include photographing a skin surface to generate fragment video data; extracting fragment frame images from the fragment video data; performing image quality detection on the fragment frame images to generate an image quality detection result; when the image quality detection result indicates an up-to-standard image, performing one-dimensional red and green light signal extraction on the fragment frame images to generate first red and green signals; performing signal band-pass filtering preprocessing on the first red and green signals to generate second red and green signals; performing maximum frequency difference determination on the second red and green signals to generate a first determination result; when the first determination result indicates an up-to-standard signal, performing signal-to-noise ratio determination on the second red and green signals to generate a second determination result; and when the second determination result indicates an up-to-standard signal, generating a first PPG signal.

A system and a method include an implantable medical device (IMD) having one or more inputs configured to receive one or more sensed signals from one or more electrodes. A plurality of filters are configured to filter the one or more sensed signals and output a plurality of filtered signals. Memory is configured to store program instructions. A processor, when executing the program instructions, is configured to receive the plurality of filtered signals, and analyze the plurality of filtered signals to determine a desired one of the plurality of filters.

In some embodiments, an electric field generator generates an electric field at a nominal frequency. A detector measures, at multiple time points during a measuring period, one or more properties of the generated electric field. In various embodiments, the one or more properties of the electric field change over time due to interactions with a human body in a reactive near-field region of the electric field. From the measured one or more properties, a computation unit determines one or more periodic behaviors (such as a respiration or heartbeat) and one or more non-periodic behaviors (such as movement of a limb). The computation unit also computes, from at least one of the periodic and non-periodic behaviors, one or more physiological parameters of the human body. From the one or more physiological parameters, the computation unit detects one or more symptoms of a condition of the human body.

A method for predicting sleep apnea from neural networks that mainly includes the following steps: a) retrieving an original signal; b) retrieving at least one snoring signal from the original signal by a snoring signal segmentation algorithm and converting the snoring signal into one with one-dimensional vector; c) applying a feature extraction algorithm to process the snoring signal with one-dimensional vector and transform the snoring signal into a feature matrix of two-dimensional vectors; and d) classifying the feature matrix by a neural network algorithm to obtain the number of times of sleep apnea and sleep hypopnea from the snoring signal. The method thereby is able to decide whether the snoring signal has revealed indications of sleep apnea or sleep hypopnea or not.

The present disclosure is related to methods, systems and apparatus for performing electrophysiological measurements utilizing three or more electrodes attached to a patient. The system in various embodiments may include three or more electrodes attached to the patient and at least one analog-to-digital converter with external circuitry electrically coupled to the electrodes. The system may further include a microprocessor for driving the analog-to-digital conversion process, various inputs and variable frequency current outputs electrically coupled to the microprocessor for receiving signals from the electrodes and sending driven current signals to the electrodes.

A sensor on an earpiece is used to attempt to detect a signal corresponding to a heartbeat. If a heartbeat is detected, it can be determined that the earpiece is being worn by a user. The sensor may be an acoustic transducer on a surface of the earpiece that is located within the wearer's ear canal, while the earpiece is being worn normally.

In an example, a method includes collecting biodata of a subject. The method includes generating or updating a personalized ML model of the subject from the biodata of the subject. The method includes detecting anomalies in the biodata based on the personalized ML model. The method includes filtering the detected anomalies to determine whether the detected anomalies indicate that the subject has a clinical condition or is at risk of having the clinical condition.

A method for detecting wheeze from an audio respiratory signal comprises capturing the audio respiratory signal from a subject using a microphone. Further, the method comprises recognizing a plurality of breath cycles and a plurality of breath phases from the audio respiratory signal and detecting wheezing from the plurality of breath cycles and the plurality of breath phases. The detecting comprises analyzing a block of interest in the audio respiratory signal, wherein the block of interest comprises a plurality of frames. The detecting further comprises calculating an auto-correlation function (ACF) for each frame in the block and determining a maximum value of the ACF calculated for each frame in the block. Finally, the detecting comprises analyzing the maximum value to detect if wheezing is present in the block.

The differential voltage measuring system has a number of signal measuring circuits, each having a capacitive sensor element for capturing a measurement signal relating to the patient. The differential voltage measuring system further has a signal processing apparatus for determining at least one bioelectrical signal from the measurement signals and a computer unit which is configured to ascertain, on the basis of the at least one bioelectrical signal, and to provide, an item of breathing information, said breathing information indicating a breathing activity of the patient.