Abstract: A tubing assembly for use with electronic catheter guidance systems is provided and includes a catheter and an acoustic sensor. The catheter extends in a longitudinal direction and has a proximal end and a distal end that define a lumen therebetween. Further, the catheter is configured for placement within a patient's digestive tract. The acoustic sensor can be located within the lumen of the catheter or in a sampling chamber connected to the catheter. The acoustic sensor can communicate with a processor to deliver sound data to a display device. The appearance of random spikes on a frequency versus time spectrogram can indicate placement of the catheter in the digestive tract, while a rhythmic/repetitive pattern on a frequency versus time spectrogram can indicate placement of the catheter in the respiratory tract. A catheter guidance system and method for accurately placing a catheter in the digestive tract are also provided.

Abstract: In order to determine a degree of dementia of a user, contents are output through a user terminal, a voice of the user for a content acquired by a microphone of the user terminal is received, a spectrogram image is generated by visualizing the voice, and the degree of dementia of the user is determined by means of a convolutional neural network (CNN) and a deep neural network (DNN) based on the spectrogram image.

Abstract: An earphone includes a loudspeaker, a microphone, a housing supporting the loudspeaker and microphone, and an ear tip surrounding the housing and configured to acoustically couple both the loudspeaker and the microphone to an ear canal of a user, and to acoustically close the entrance to the user's ear canal. A processor receives input audio signals from the microphone, detects peaks having a frequency of around 1 Hz in the input audio signals, based on the detected peaks, computes an instantaneous heart rate, measures a frequency of an oscillation within the instantaneous heart rate, and based on the frequency of the oscillation, computes a rate of respiration.

Abstract: There is provided a recognition system adaptable to a portable device or a wearable device. The recognition system senses a body heat using a thermal sensor, and performs functions such as the living body recognition, image denoising and body temperature prompting according to detected results.

Abstract: A method for detecting cough sounds from a sound wave of a subject includes applying features extracted from the sound wave to at least two electronic pattern classifiers including a first classifier trained to detect an explosive phase of a cough and a second classifier trained to detect one or more post-explosive phases of the cough sound. The features extracted from the sound wave are applied to the second classifier after the first classifier has classified features of the sound wave as an explosive phase of a cough sound.

Abstract: Devices and methods for predicting risk and likelihood of post-operative gastrointestinal impairment based on regression analysis of multiple spectral events related to intestinal sounds, with decreased or eliminated falsely elevated values of those events due to ambient noise.

Abstract: Embodiments herein relate to systems, devices and methods for managing pharmacological therapeutics and aspects of the same. In an embodiment, a hearing assistance device can include a control circuit, an electroacoustic transducer for generating sound in electrical communication with the control circuit, a power supply circuit in electrical communication with the control circuit, and a sensor package in electrical communication with the control circuit. The control circuit can be configured to evaluate a signal from at least one of the sensors of the sensor package to detect administration of a therapy or receive data indicating that administration of a therapy has taken place. The control circuit can also be configured to record an instance of a detected medication administration event along with a timestamp. Other embodiments are also included herein.

Abstract: Described herein are a computer enhanced medical method and device for generating an asthmatic condition indication. The apparatus receives a lung signal from a stethoscope, the lung signal having been converted from an analog signal to a digital signal. Furthermore, circuitry included in the apparatus performs, inter alia, the following: displays a patient recording canvas corresponding to physical locations on a body of the patient, the canvas including an anterior patient orientation and a posterior patient orientation, generates a recording process, the recording process including recording, for a predetermined period of time, the detected lung signal, and associates the recording with a marked location. Furthermore, the circuitry merges the recorded lung signal from each marked location on the patent recording canvas as merged information, and applies processing to the merged information to generate the asthmatic condition indication.

Abstract: An audio-based repetition counter system and method are disclosed. In some embodiments, the audio-based repetition sound counter system includes a computing device connected to a microphone. The computing device includes a processor and one or more memory devices, and a repetition counter module is stored on the memory device and executed by the processor. The repetition counter module processes audio data received from a microphone and provide a number of repetitions for one or more series of one or more activities; for example, jumping rope. Further, an audio-based method of counting repetitions for a physical activity is provided.

Abstract: Systems, methods, and computer-readable mediums for operating an electromechanical device are disclosed. The system includes, in one example, the electromechanical device, a patient portal, and a computing device. The computing device is configured to receive user data relating to a user, and receive treatment data relating to treatment plans and outcomes. The computing device is also configured to generate a prehabilitation plan by using a machine learning model to process the user data and the treatment data. The computing device is further configured to select, for the electromechanical device, an electromechanical device configuration that enables exercises of the prehabilitation plan to be performed by the user such that performance improves an area of the user's body. The computing device is also configured to enable the electromechanical device to implement the electromechanical device configuration.

Abstract: A monitoring device has microphones, an ADC; a digital radio; and a processor with firmware. The firmware includes code for digitizing audio from the microphones into time-domain audio, performing FFT to provide frequency-domain audio, running a first neural network on time domain and frequency-domain audio to extract features, executing a classifier on the features to identify candidate events, and using the digital radio to upload candidate events and features. A pressure sensor awakens the processor from a low-power state. In particular embodiments, the first neural network is an embedded Gated Recurrent Unit having weights trained to extract features of use in the classifier; and candidate events include normal inhalation and exhalation breathing sounds, crackles, wheezes, coughs, snoring, gasping, choking, and speech sounds and in some embodiments heart sounds. A method of monitoring breathing during sleep includes attaching the device to, or embedding the device within, a pillow.

Abstract: The disclosure relates and extends to a light source having a strobing or pulsing sequence suitable for use with a CMOS sensor that does not require, have, or use a global shutter. Instead, the CMOS sensor synchronizes the strobing input with the blanking portion of the sensor readout pattern and disables the strobing during sensor readout, or when the strobing would otherwise leave artifacts in the image. The CMOS sensor freezes its readout during the strobing.

Abstract: A swallowing diagnosis apparatus includes a controller which enables a first swallowing determination process of determining whether or not there is an aspiration risk in the swallowing on the basis of respiratory phases before and after a period in which swallowing has been estimated as having occurred; and a second swallowing determination process of extracting reference information including at least one of the sound information and the respiration information in a predetermined period including the period in which swallowing has been estimated as having occurred, obtaining a feature quantity from the extracted reference information, and performing a machine learning process on the obtained feature quantity to determine whether or not there is a possibility of dysphagia in the swallowing; and a display control process of causing a determination result obtained by the first swallowing determination process and a determination result obtained by the second swallowing determination process to be displayed.

Abstract: Aspects of the present disclosure provide methods, apparatuses, and systems for dynamic starting rates for guided breathing. According to an aspect, a user's initial breathing metric is determined. A multiplier is then determined, where the multiplier varies as a function of the initial breathing metric within a range. The level of intensity of the multiplier may vary, and may be a dynamic feature based on the determination of the user's initial breathing metric. Once the multiplier is determined, the multiplier is applied to the user's initial breathing metric to determine a starting breathing metric for guided breathing. The starting breathing metric is slower than or equal to the user's initial breathing metric.

Abstract: A method to measure sound-producing behaviors of a subject with a power- and bandwidth-limited electronic device that includes a processor includes measuring, by a microphone communicatively coupled to the processor, sound in a vicinity of the subject to generate an audio data signal that represents the sound. The method also includes measuring, by at least one second sensor communicatively coupled to the processor, at least one parameter other than sound to generate at least a second data signal that represents the at least one parameter other than sound. The method also includes detecting one or more sound-producing behaviors of the subject based on: both the audio data signal and the second data signal; or information derived from both the audio data signal and the second data signal.

Abstract: Various embodiments of the present technology include a soft, conformal class of device configured specifically for mechano-acoustic recording from the skin, capable of being used on nearly any part of the body, in forms that maximize detectable signals and allow for multimodal operation, such as electrophysiological recording. Some embodiments can be configured for use in cardiovascular diagnostics, implantable device diagnostics, and human-machine interfaces (HMIs). In some embodiments, a conformal sensing device for measuring mechano-acoustic recording from skin of a human subject can include a mechano-acoustic sensor, a wireless transmitter, a flexible housing, and/or one or more electrodes.

Abstract: Systems, devices, methods for providing a speech pattern as a metric of well-being system for remotely monitoring the well-being of a patient are disclosed. In one exemplary embodiment, a system can include at least one wearable device that is configured to collect body sensor data and speech pattern data associated with a patient wearing the device and analyze the data to determine if the patient's emotional well-being is compromised. In some exemplary embodiments, the wearable device can be configured to send an alert to at least one caregiver device that indicates the patient's emotional well-being is compromised. The wearable device can also be configured to send recommendations on courses of action to alleviate the condition.

Abstract: A pressure sensor that includes a piezoelectric film having a flat part and a curved part and having opposed first and second main surfaces, a first electrode on the first main surface of the piezoelectric film, and a second electrode on the second main surfaces of the piezoelectric film. When the flat part of the piezoelectric film receives a pressing operation a first output is generated, and when the curved part of the piezoelectric film receives a pressing operation a second output different from the first output is generated.

Abstract: A controller and associated sensor system for augmenting the automatic delivery of drugs is provided. The controller and associated sensor system is based on the detection and determination of particular physical lifestyle events. As a specific example, a pump augmentation system includes a six-axis accelerometer sensor, a gyroscopic pitch sensor and a controller. The controller is configured to receive motion data from the six-axis accelerometer sensor and orientation data from the gyroscopic pitch sensor. The controller provides a pump instruction signal for changing a delivery rate of a drug to a user based on the motion data and the orientation data. When the pump is an insulin pump, the pump augmentation system is an insulin pump augmentation system and provides accurate insulin control for controlling blood glucose levels of a user.

Abstract: According to various embodiments, there is provided a method for detecting a sleep disorder, the method including: processing an audio signal, the audio signal including breathing sounds made by a subject when the subject is asleep; identifying intervals of the audio signal where breathing sounds are absent; and detecting the sleep disorder based on the identified intervals.

Abstract: Various examples of methods, systems, and apparatus are provided for monitoring using an improved mouth guard apparatus. In one example, a battery-free diagnostic mouth guard includes a biting force-voltage transducer comprising a piezoelectric film; a compact resonance tank comprising a wireless sensor; and a transmitting antenna for transmitting sensing data. A piezo-voltage from the biting force-voltage transducer can bias a varactor diode loaded on the wireless sensor whose response frequency is tuned due to a capacitance change of the varactor diode. In some implementations, an external processing equipment can wirelessly detect a frequency shift of the varactor diode integrated resonator. In another example, a method includes detecting a biting force via a biting force-voltage transducer; biasing a varactor diode with a voltage from the transducer; tuning a response frequency of a split ring resonator using a capacitance change of the varactor diode; and emitting sensing data at the response frequency.

Abstract: A method of classifying a swallow of a subject includes obtaining vibration data that is based on and indicative of a number of vibrations resulting from the swallow, and using a computer implemented deep learning classifier to classify the swallow based on the vibration data. Also, a system for classifying a swallow of a subject includes a computing device implementing a deep learning classifier. The computing device includes a processor apparatus structured and configured to receive vibration data that is based on and indicative of a number of vibrations resulting from the swallow, and use the deep learning classifier to classify the swallow based on the vibration data. The deep learning classifier may comprise a single layer or a multi-layer Deep Belief network.

Abstract: A method of monitoring body sounds using a sensor including an array of microphones, the method includes acquiring a first sound produced by certain physiology using the array of microphones of the sensor, identifying a source of the first sound, performing an automatic auscultation of the source using the first sound, wherein the automatic auscultation including matching the first sound to an acoustic model stored in a memory, wherein the acoustic model corresponds to a physiology, generating an image representing the physiology using an image library, and determining a health condition using the physiology and the image.

Abstract: Wearable devices and methods of using the same for inputting ambient conditions and the movement and bio-signals of a user to an external device are provided. The wearable device can include a finger sensor and a wrist sensor, wherein each includes an accelerometer, a gyroscope, and a compass. The compass can be a magnetometer. The wrist sensor can also include a power source, a computer, and a touchscreen.

Abstract: An apparatus to measure isometric muscle strength has a table section having a top surface adapted to allow a person to sit thereon. An upright frame section is movably attached to the table section and spans the top surface and includes an open area sized to allow the person's legs and thighs to extend therethrough when the person is seated on the top surface. A cradle is attached to the frame section and holds a force-measuring device that is acted upon by the person's body segment when the person is seated on the top surface. Movement-impeding devices allow or prevent movement of the frame section. Belts and/or straps are attached to the table section and adapted to be secured to various parts of the person's body to stabilize the person on the top surface and to isolate muscle groups that are to be tested for isometric muscle strength.

Abstract: This disclosure describes methods, systems, and devices configured to determine a timing of a future bladder related event of a patient. For example, a system includes processing circuitry configured to identify a timing of a plurality of bladder related events of a patient, determine, based on the timing of the plurality of bladder related events of the patient, a probability to experience a bladder related event function for the patient, the probability to experience a bladder related event function indicating a probability that the patient will experience a bladder related event at an elapsed time after a previous bladder related event, predict, based on the probability to experience a bladder related event function, a timing of a future bladder related event, and control delivery of a therapy to the patient based on the predicted timing of the future bladder related event.

Abstract: Disclosed is a device and method for monitoring an earphone wearing state. A device and method for monitoring an earphone wearing state according to the present invention comprises: an internal microphone for receiving an internal voice generated inside an ear and generating an internal voice signal; an external microphone for receiving an external sound selectively including external noise and an external voice transferred from a vocal cords to the outside of an oral cavity and generating an external sound signal; a control unit for determining the volume of external noise though a comparison between an internal voice signal and an external sound signal and determining whether to generate an alarm signal; and an alarm unit for performing alarming in response to an alarm signal.

Abstract: In various embodiments methods and devices are provided for regulating bladder function in a subject after a spinal cord and/or brain injury. In certain embodiments the methods comprise applying a pattern of electrical stimulation to the Lumbosacral spinal cord at a frequency and intensity sufficient to initiate micturition and/or to improve the amount of bladder emptying. In certain embodiments the electrical stimulation is at a frequency and intensity sufficient to improve the amount of bladder emptying (e.g., to provide at least 30% emptying or at least 40% emptying, or at least 50% emptying, or at least 60% emptying, or at least 70% emptying, or at least 80% emptying, or at least 90% emptying, or at least 95% emptying.

Abstract: The present disclosure describes a system and method for determining cardiac parameters and physiological conditions of a user by analysing speech samples of said user. A user device of the user may record specifics of speech and use these specifics of speech as a speech sample of user's utterance. The user device may transmit the speech samples to a backend system. The system may isolate phonation segments from the speech samples. The system may filter one or more phonation segments. The system may isolate uttered speech segments from one or more phonation segments. The system may perform an acoustic-phonetic analysis of the uttered speech segments. The acoustic-phonetic analysis may use plurality of features for the analysis. The IPA phonemes may be used to derive speech markers that correspond to specific cardiac parameters and physiological conditions. The system may generate a resulting report after analysis which is transmitted to the user.

Abstract: This application relates to a portable electronic device including a first sensing module and a second sensing module that are both in communication with a processor. The portable electronic device can include access ports that are formed in the housing, where the first and second sensing modules are capable of receiving an external stimulus by way of the access ports. A plate is positioned in the housing between a wall of the housing and the sensing modules. The plate and the wall define non-linear flow paths between the access ports to the first and second sensing modules. The non-linear flow paths can transmit the external stimulus to cause at least one of the first or second sensing modules to provide a detection signal to the processor that causes a display unit to present a notification that corresponds to the external stimulus.

Abstract: A three-dimensional, head mounted microphone array is employed to isolate and analyze intracranial sound sources such as may provide for objective tinnitus. The microphone array allows a region of interest within the patient's head to be isolated for the detection of sounds and allows episodic sounds to be automatically identified as to location. An interactive display allows a better understanding of sound locations and the extracted sounds can be analyzed with respect to a library of sounds linked to particular locations and diagnoses.

Abstract: A new non-invasive tool for cartilage assessment, exercise and sports management, and prevention of osteoarthritis is provided. In various embodiments, cartilage condition is assessed using audible signals from joints. Assessment test results are used to provide feedback regarding joint stress and friction that is related to physiological or pathological loads. Data obtained from audible signals are processed to provide an index that can be interpreted by a user or third parties. The index is useful as a baseline for exercise practices, training routines, wellness programs, or rehabilitation protocols.

Abstract: Systems and related methods for controlling an ear stimulation device with a personal computing device are described. Multiple factors, including a mood of the user, a user control input, and a secondary factor input are used in controlling the ear stimulation device. Secondary factors include, a variety of factors relating to or influencing the state of the user, including but not limited to, environmental conditions, sleep, diet, or various activities of the user. User inputs can be open-ended or selected from a menu, for example. In an aspect, a correlation module correlates mood of the user to other factors, and control of stimulation is based thereon. In various aspects, the system is also responsive to inputs from sensors or computing networks. In an aspect, the earpiece delivers an audio output such as music from an audio player.

Abstract: A system (100) for monitoring and diagnosing heart conditions includes a sensor array (102) with accelerometers, an electrocardiogram sensor, and a system to synchronously capture and process (103, 105, or 106) composite heart signals. The system performs separation, identification and marking (201-205 or 501-509) of the signals, to extract information in cardiac vibrations. Machine learning, auditory scene analysis, or spare coding approaches can be used to resolve source separation problems. Analysis of the composite signals separates different vibration signals (302, 303, 304, 305), identifies streams for particular valve signal, and marks them with event time information with respect to a synchronous electrocardiogram signal (306). The psychoacoustic analysis mimics human auditory processing to enhance hearing of heart valve sounds by separating valve vibrations from the composite signal, and providing extraction, identification, marking and display of individual valve signals.

Abstract: A wearable breathing sensor, such as a piezoelectric chest belt system, generates a breathing signal that is analyzed by a classifier to identify apnea patterns indicating that the subject has swallowed during breathing. These breathing signals are computer-analyzed to extract inferences regarding the subject's eating and drinking patterns and thereby provide useful data for monitoring food or beverage intake for remote health monitoring.

Abstract: Described herein is an apparatus and method of detecting bruxism. The method includes the steps of: capturing a video of a subject, performing by circuitry included in the apparatus, spatial filtering of each image frame included in the captured video. Further, the method includes generating by circuitry, a filtered image by temporally filtering the spatially filtered image frames, the temporally filtered image including data belonging in a first frequency range, and wherein a subset of data is associated with a predetermined color variation to indicate presence of bruxism in the subject.

Abstract: A method of controlling an anti-snoring device is disclosed. The method includes the steps of capturing sound data within a period of time, sampling the sound data continuously, extracting multiple sound characteristic sections arising periodically from the sound data, and activating the anti-snoring device to stop snoring when the repeated occurrence count of the sound characteristic sections reach a threshold value.

Abstract: The disclosure relates and extends to a light source having a strobing or pulsing sequence suitable for use with a CMOS sensor that does not require, have, or use a global shutter. Instead, the CMOS sensor synchronizes the strobing input with the blanking portion of the sensor readout pattern and disables the strobing during sensor readout, or when the strobing would otherwise leave artifacts in the image. The CMOS sensor freezes its readout during the strobing.

Abstract: A removable oral device is disclosed. The removable oral device comprises a mounting retainer configured to align with a set of teeth. An electrical stimulator is coupled to the mounting retainer. A single lead is employed that has a first and a second end and lacking a mechanical connection to the mounting retainer. A first and a second electrode are positioned along the single lead. The lead is disposed perpendicular to a longitudinal axis of a patient's tongue such that the first electrode is proximate a first hypoglossal nerve and the second electrode is proximate a second hypoglossal nerve.

Abstract: There is provided a sound and vibration information collecting mechanism, which collects low-frequency sound and vibration information with a predetermined frequency or lower from a detection target, the mechanism including a resonance layer, which includes a natural oscillator having a natural frequency within a frequency band of the sound and vibration information being a collection target, and generates a resonance carrier by the natural oscillator emphasizing the sound and vibration information; and a sensor, which detects the resonance carrier. The mechanism detects a bioacoustic signal and a biosignal more accurately than conventionally.

Abstract: A physiological signal processing method for filtering noise generated by a physiological signal processing system is performed by a physiological signal processing system having a sensing device and a filtering device in connection with the sensing device. The method comprises steps of synchronously receiving a physiological signal and a vibrational signal detected by the sensing device, performing a noise determination algorithm to acquire information in multiple time periods with noises occurring in corresponding time periods according to the vibrational signal, performing a physiological signal filtering algorithm to filter the noises in corresponding time periods of the physiological signal and compensate the filtered physiological signal, and estimating a physiological parameter according to a result of the signal compensation to generate the physiological parameter with accuracy.

Abstract: A method and system for speech to speech translation using a plurality of computational cores of a natural liquid architecture are provided. The method includes receiving an audio input to be translated into a target language; identifying, based on the received audio input, a cluster of signatures; identifying, based on the cluster of signatures, a first concept, wherein the first concept is common to all signatures within the signature cluster; and determining a match between the first concept and at least a second concept, wherein the second concept is associated with the target language.

Abstract: The description relates to surgical computer systems, including computer program products, and methods for implant planning using captured joint motion information. Data is captured representative of a range of motion of a joint associated with a particular individual, where the joint includes a first bone and a second bone. The first bone of the joint is represented and a first implant model is associated with the representation of the first bone. Based on the captured data, a relationship is determined between the first implant model and a representation of the second bone or a second implant model through at least a portion of the range of motion of the joint. Information is displayed representative of the determined relationship.

Abstract: The description relates to surgical computer systems, including computer program products, and methods for implant planning using captured joint motion information. Data is captured representative of a range of motion of a joint associated with a particular individual, where the joint includes a first bone and a second bone. The first bone of the joint is represented and a first implant model is associated with the representation of the first bone. Based on the captured data, a relationship is determined between the first implant model and a representation of the second bone through at least a portion of the range of motion of the joint. Information is displayed representative of the determined relationship.

Abstract: In accordance with embodiments of the present disclosure, an apparatus for providing an output signal to an audio transducer may include a signal path and a control circuit. The signal path may include an analog signal path portion having an audio input for receiving an analog signal, an audio output for providing an output signal, and a selectable analog gain, and configured to generate the output signal based on the analog signal and in conformity with the selectable analog gain and a digital path portion having a selectable digital gain and configured to receive a digital input signal and convert the digital input signal into the analog signal in conformity with the selectable digital gain. The control circuit may be configured to determine a spectral content of a signal indicative of the output signal and change the selectable digital gain and the selectable analog gain based on the spectral content.

Abstract: In some embodiments, a method of creating an automatic language characteristic recognition system. The method can include receiving a plurality of audio recordings. The method also can include segmenting each of the plurality of audio recordings to create a plurality of audio segments for each audio recording. The method additionally can include clustering each audio segment of the plurality of audio segments according to audio characteristics of each audio segment to form a plurality of audio segment clusters. Other embodiments are provided.

Abstract: Disclosed is a drinking water reminding system and the reminding method thereof. The water intake of user is measured by the operation of a reminder of the drinking water reminding system, and a collector of the drinking water reminding system is provided for adjusting the daily drinking water demand of user according to environmental parameters or the physiological parameters of user. The drinking water reminding system reminds the user to drink water if the drinking water reminding system determines that the user has taken insufficient water according to predetermined conditions and measurement results, drinking water reminding system.

Abstract: A method for assessing suicide risk for a human subject including receiving recorded voice data of the subject; and classifying the subject as suicidal or non-suicidal based upon a computerized analysis of one or more nonverbal characteristics of the speech data, especially features associated with a breathy phonation type. The analysis of the nonverbal characteristics of the voice data can include an analysis of acoustic characteristics of speech, and/or an analysis of prosodic and voice quality-related features of the voice data. Related apparatus, systems, techniques and articles are also described.

Abstract: The description relates to surgical computer systems, including computer program products, and methods for implant planning using corrected captured joint motion information. Data representative of a corrected limb pose at a plurality of poses within a range of motion of a joint associated with a particular individual is captured, the joint comprising a first bone and a second bone, while the first bone, the second bone, or both are subject to a corrective force aligning the first and second bones in a desired alignment. The first bone of the joint is represented. The second bone of the joint is represented. A first implant model is associated with the representation of the first bone. A second implant model is associated with the representation of the second bone. Based on the captured data, a relationship is determined between the first implant model and the second implant model at one or more poses of the plurality of poses within the range of motion of the joint.

Abstract: Disclosed herein are power detectors and methods for detecting the average power level of an RF input signal and the voltage envelope of the RF input signal. Also disclosed herein are linear envelope detectors and methods for detecting the voltage envelope of an RF input signal.