Abstract: A technology for obtaining a respiratory rate from a photoplethysmogram (PPG) signal. In one example, an artificial neural network model can be trained to predict a respiratory rate using a training dataset containing PPG data. The artificial neural network model can include a first series of convolutional layers to remove artifacts from a PPG signal, a fast Fourier transform (FFT) layer to convert the PPG signal to PPG frequency representations, and a dense layer to decode the PPG frequency representations to respiratory rate predictions. After training the artificial neural network model, PPG data generated by a pulse oximeter monitor can be obtained, and the PPG data can be input to the artificial neural network model. The artificial neural network model outputs a respiratory rate prediction, wherein the respiratory rate prediction represents the respiratory rate obtained from the PPG signal.

Abstract: An infant monitoring device is disclosed having a band or sock configured to wrap around the foot or other portion of an infant. The sock houses a removable sensing module configured to couple to the sock and measure health parameters of the infant. The sensing module is removably couplable with a base station that charges the sensing module. The sensing module transmits and receives information from the base station. Both the base station and the sensing module can transmit and receive information from a remote location.

Abstract: A technology for obtaining a heart rate from a photoplethysmogram (PPG) signal. In one example, an artificial neural network model can be trained to predict a heart rate using a training dataset containing PPG data. The artificial neural network model can include a series of convolutional layers to remove artifacts from a PPG signal, a fast Fourier transform (FFT) layer to convert the PPG signal to PPG frequency representations, and a dense layer to decode the PPG frequency representations to heart rate predictions. After training the artificial neural network model, PPG data generated by a pulse oximeter monitor can be obtained, and the PPG data can be input to the artificial neural network model. The artificial neural network model outputs a heart rate prediction, wherein the heart rate prediction represents the heart rate obtained from the PPG signal.

Abstract: Devices, systems, and methods for multi-channel common-mode coupled alternating current (AC) gain amplifiers (MC-CM-AC Amp) are disclosed. The MC-CM-AC Amp can comprise a first operational amplifier including: a first non-inverting input port configured to be coupled to a first input signal, and a first inverting input port configured to be coupled to a first capacitor. The MC-CM-AC Amp can comprise a second operational amplifier including a second non-inverting input port configured to be coupled to a second input signal, and a second inverting input port configured to be coupled to a second capacitor. The MC-CM-AC Amp can comprise one or more gain-setting resistors configured to be coupled between the first capacitor and the second capacitor.

Abstract: A multi-purpose biometric sensor includes both a transmissive topology and reflective topology for measuring biometric information. The multi-purpose biometric sensor is configured to allow for dynamically switching between the transmissive topology and the reflective topology based on user input or a current measuring scenario. The multi-purpose biometric sensor includes multiple types of light emitting sources and is further configured to dynamically switch between different types of light emitting sources based on user input or a current measuring scenario. The multi-purpose biometric sensor is further configured to measure multiple biometric signals from a single sensor.

Abstract: A system for monitoring fetal health data and mother health data comprises a belly-covering garment that is configured to at least partially cover a belly and to hold one or more sensor modules directly adjacent to the belly. One or more sensor modules disposed within the belly-covering garment. The one or more sensor modules comprise a pulse-oximeter sensor that gathers pulse oximetry data from the mother through contact with the belly. The one or more sensor modules also comprise an accelerometer sensor that gathers movement data from the mother. Additionally, the one or more sensor modules comprise a fetal sensor that gathers health data from a fetus within the belly.

Abstract: A computer system for simultaneously sampling multiple light channels is configured to emit a first pulse-oximetry light signal from a first light source and to emit a second pulse-oximetry light signal from a second light source. The computer system then captures a combined pulse-oximetry signal from both the first pulse-oximetry light signal and the second pulse-oximetry light signal simultaneously at a photoreceptor sensor. The computer system identifies information within the combined pulse-oximetry signal, wherein the first light source and the second light source capture different attributes of the information.

Abstract: An abdominal electrocardiogram processing system for determining a fetal heart rate of a fetus in a pregnant woman obtains a combined electrocardiogram measurement of a maternal heart rate and a fetal heart rate. The system then transforms the combined electrocardiogram measurement into a wavelet domain to create a combined electrocardiogram measurement wavelet transform. The system can then remove the maternal heart rate from the combined electrocardiogram measurement wavelet transform. The system then identifies a fetal heart rate from the compensated combined electrocardiogram measurement wavelet transform.

Abstract: Embodiments are directed to methods and systems for adaptive heart rate monitoring. In one scenario, a method for adaptive heart rate monitoring includes receiving, from a pulse-oximeter, a sensor signal, where the sensor signal is photoplethysmogram waveform. The method next includes generating a frequency-domain photoplethysmogram waveform by applying a transform algorithm to the sensor signal, and dividing the resulting frequency-domain photoplethysmogram waveform into discrete frequency regions. The method further includes identifying a fundamental heart rate harmonic within one of the discrete frequency regions by analyzing each discrete frequency region according to a specified analytic algorithm, and triggering a user interface to display a biometric measurement corresponding to the identification of the fundamental heart rate harmonic.

Abstract: Biometric sensor systems are provided for identifying fundamental heart rate harmonics within noisy sensor signals. The system calculates a local signal-to-noise ratio for one or more identified frequency bands received in a biometric signal. The identified frequency bands are ranked based upon the calculated local signal-to-noise ratio. The fundamental heart rate is identified based upon the ranking of the identified frequency bands.

Abstract: A system for wirelessly monitoring the health of an infant comprising a sensing module removably disposed within a wearable article. At least a portion of the sensing module can be in contact with an infant's foot. The sensing module can include a processing unit configured to receive and process health readings received by the sensing module. A wireless transmitter can also be in communication with the processing unit. The wireless transmitter can be configured to transmit the processed health readings to a receiving station. The receiving station can indicate an alarm if the processed health readings indicate a health trend that falls outside of a particular threshold.

Abstract: A system for wirelessly monitoring the health of an infant comprising a sensing module removably disposed within a wearable article. At least a portion of the sensing module can be in contact with an infant's foot. The sensing module can include a processing unit configured to receive and process health readings received by the sensing module. A wireless transmitter can also be in communication with the processing unit. The wireless transmitter can be configured to transmit the processed health readings to a receiving station. The receiving station can indicate an alarm if the processed health readings indicate a health trend that falls outside of a particular threshold.