Devices, including robotic devices, operating in viscous fluid flow can use passive sensor data collected to represent fluid parameters at an instant in time to derive information about the flow, the motion and position of the device, and parameters of the physical system constraining the flow. Using quasi-static analysis techniques, and appropriate feature selection for machine learning, very accurate determinations can be made, generally in real time, with very modest computational requirements. These determinations can then be used to map systems, navigate devices through a system, or otherwise control the actions of, e.g., robotic devices for clean-up, leak detection, or other functions.

Embodiments are disclosed for sleep staging using machine learning. In an embodiment, a method comprises: receiving, with at least one processor, sensor signals from a sensor, the sensor signals including at least motion signals and respiratory signals of a user; extracting, with the at least one processor, features from the sensor signals; predicting, with a machine learning classifier, that the user is asleep or awake based on the features; and computing, with the at least one processor, a sleep or wake metric based on whether the user is predicted to be asleep or awake.

A method of deriving depth EEG data from non-invasive 2D EEG data is described. The method receives several EEG scalp signals, each of which is produced by a contact of an EEG recording device. The method converts each EEG scalp signal into multiple frequency band signals. The method identifies a set of contacts that have similar signal fragments in frequency band signals for a particular frequency band. The method determines relative time delay in frequency band signal arrival at the set of contacts. The method determines relative radius of sphere for the set of contacts based on the relative time delay in frequency band signal arrival at the set of contacts. The method then determines a signal source location by performing trilateration on the set of contacts using locations of the set of contacts and the relative radius of sphere for the set of contacts.

The present invention relates to a method of effectively removing various vibration noises using microwave Doppler radar, and an apparatus therefor. The method comprises the steps of: (a) generating and transmitting an oscillation frequency to a dynamic target, and receiving a signal reflected from the dynamic target and various signals generated around the dynamic target; (b) generating a Doppler IF signal from each of n received signals; (c) converting each Doppler IF signal into digital data; (d) configuring digital signals into a data set, and converting the data set into a frequency component symbol set; (e) calculating a value by adding index symbols and dividing by n reception antennas; and (f) classifying deviation between spectrum components of a commonly-generated periodic signal and an uncommon aperiodic signal, and obtaining only a periodic signal through filtering. The present invention can improve accuracy of sensing a biometric signal.

In some examples, a medical device system includes an electrode. The medical device system may include impedance measurement circuitry coupled to the electrode, the impedance measurement circuitry may be configured to generate an impedance signal indicating impedance proximate to the electrode. The medical device system may include processing circuitry that may be configured to identify a first component of the impedance signal. The first component of the impedance signal may be correlated to a cardiac event. The processing circuitry may be configured to determine that the cardiac event occurred based on the identification of the first component of the impedance signal.

The present invention is directed to a method for determining a paroxysmal slow waves event (PSWE) so as to determine blood-brain barrier dysfunction (BBBD) or increased risk of developing a neurological disease or disorder in a subject.

Systems and methods for minimizing or eliminating transient non-glucose related signal noise due to non-glucose rate limiting phenomenon such as ischemia, pH changes, temperatures changes, and the like. The system monitors a data stream from a glucose sensor and detects signal artifacts that have higher amplitude than electronic or diffusion-related system noise. The system replaces some or the entire data stream continually or intermittently including signal estimation methods that particularly address transient signal artifacts. The system is also capable of detecting the severity of the signal artifacts and selectively applying one or more signal estimation algorithm factors responsive to the severity of the signal artifacts, which includes selectively applying distinct sets of parameters to a signal estimation algorithm or selectively applying distinct signal estimation algorithms.

In one embodiment, a method for detecting tremors includes generating electromagnetic fields proximate to an individual's body part with a circuit to generate an eddy current density on a surface of the body part, receiving magnetic fields generated by the eddy current with the circuit that change a resonant frequency of the circuit, sensing the resonant frequency as it changes over time, and determining a movement frequency of the body part from the resonant frequency to quantify tremors in the body part.

The present invention relates to a method and system for calculating eating bites of a user. The method comprises: (a) continuously measuring the electrical properties data of mastication of a user for a predetermined period of time; (b) periodically determining single eating bites according to the data obtained in step (a) through a time interval; (c) periodically storing the bites determined throughout the predetermined period of time, through a time interval.

A method implemented on a computing device having at least one processor, storage, and a communication platform connected to a network for determining blood pressure may include: receiving a request to determine blood pressure of a first subject from a terminal, obtaining data related to heart activity of the first subject, determining a personalized model for predicting blood pressure with respect to the first subject, determining the blood pressure of the first subject using the personalized model based on the data related to heart activity of the first subject, and sending the blood pressure of the first subject to the terminal in response to the request.