Abstract: Various arrangements for performing fall detection are presented. A smart-home device may transmit radar waves. Based on reflected radar waves, raw waveform data may be created. The raw waveform data may be processed to determine that a fall by a person has occurred. Speech may then be output announcing that the fall has been detected via the speaker of the smart home device.

Abstract: A handheld system includes a housing, a motion-generating mechanism disposed within the housing, an attachment arm extending from the housing and having a first end coupled to the motion-generating mechanism and a second end configured to receive a user assistive device, a first sensor mounted to measure a first motion of the handheld system and generate a first signal indicative of the first motion, and a control system coupled to the motion-generating mechanism and the first sensor. The control system is configured to use the first signal to stabilize the user-assistive device and compensate for human tremors imparted to the housing.

Abstract: Various arrangements for performing fall detection are presented. A smart-home device (110, 201), comprising a monolithic radar integrated circuit (205), may transmit radar waves. Based on reflected radar waves, raw waveform data may be created. The raw waveform data may be processed to determine that a fall by a person (101) has occurred. Speech may then be output announcing that the fall has been detected via the speaker (217) of the smart home device (110, 201).

Abstract: Various arrangements are presented for training and using a machine learning model. A first training data set may be created that has more samples but fewer dimensions than a second dataset. A second set of training data, created from the second dataset, has at least one additional dimension of data than the first set of training data. An additional dimension of data can then be simulated for the first set of training data. The simulated additional dimension of data can be incorporated with the first set of training data. A first machine learning model can be trained based on the first set of training data that comprises the simulated additional dimension of data to obtain various weights. A second machine learning model can then be trained based on the second set of training data and the obtained plurality of weights from the first trained machine learning model.

Abstract: A disclosed method includes receiving at least an indication of audio data generated based on sound captured by a microphone of a monitoring device. A set of audio event labels are generated by processing the received audio data with a model that includes audio recognition patterns. Each audio event label is generated by matching an audio pattern in the received audio data with an audio pattern of the audio recognition patterns. The method further includes identifying a hazard event type occurring within a time window of the time period by processing the set of audio event labels with a hazard detection model. In response to detecting the hazard event type, a hazard alert is generated and at least an indication of the hazard alert is communicated to an electronic device other than the monitoring device, which is authorized to receive communications from the monitoring device.

Abstract: Various arrangements for performing fall detection are presented. A smart-home device (110, 201), comprising a monolithic radar integrated circuit (205), may transmit radar waves. Based on reflected radar waves, raw waveform data may be created. The raw waveform data may be processed to determine that a fall by a person (101) has occurred. Speech may then be output announcing that the fall has been detected via the speaker (217) of the smart home device (110, 201).

Abstract: Various arrangements for performing radar-based measurement of vital signs. Waveform data may be received then filtered of data indicative of static objects to obtain motion-indicative waveform data. The motion-indicative waveform data may be analyzed to determine one or more frequencies of movement present within the motion-indicative waveform data. A spectral analysis may be performed on the motion-indicative waveform data to determine a spectral-analysis state of a monitored region. The spectral-analysis state of the monitored region may be determined to match a predefined spectral-analysis state during which vital sign monitoring is permitted. One or more vital signs of a monitored user present within the monitored region may be determined and output based on analyzing the motion-indicative waveform data.

Abstract: Various examples are described for using a movement sensor to detecting an activity of an infant. In an example, an activity classification system includes a sensor configured to measure the activity of an infant and an external monitor. The monitor receives, from a sensor, a time series of data comprising an inertial measurement for each a time period. The monitor determines, from the time series and by using a predictive model, an activity from a list of identified activities. Examples of identified activities are deep sleep, light sleep, sitting, awake, nursing, or bottle feeding.

Abstract: Systems and techniques are provided for light source status detection. Ambient light values generated by an ambient light sensor of a device in an environment over a period of time may be received. A first light source model for the device may be generated using a first subset of the ambient light values. A second light source model for the device may be generated using a second subset of the ambient light values. A current ambient light value generated by the ambient light sensor of the device may be received. The first light source model or the second light source model may be selected based on a time at which the current ambient light value was generated. Whether the current ambient light value indicates that a local artificial light source is on may be determined using the current ambient light value and selected light source model.

Abstract: A method of tremor reduction in a handheld device includes measuring a tremor motion and a tilt motion with a motion tracking module (“MTM”) disposed in a housing of the handheld device. In response to measuring the tremor motion, an attachment arm is moved with at least one motion generating mechanism to reduce the tremor motion in the attachment arm. Additionally, in response to measuring the tilt motion, the attachment arm is moved with the at least one motion generating mechanism to resist the attachment arm hitting a hard stop in the handheld device.

Abstract: A method of tremor reduction in a handheld device includes measuring a tremor motion and a tilt motion with a motion tracking module (“MTM”) disposed in a housing of the handheld device. In response to measuring the tremor motion, an attachment arm is moved with at least one motion generating mechanism to reduce the tremor motion in the attachment arm. Additionally, in response to measuring the tilt motion, the attachment arm is moved with the at least one motion generating mechanism to resist the attachment arm hitting a hard stop in the handheld device.

Abstract: A method of conducting a structured test with a user. The structured test includes presenting an instruction to the user to perform at least one action for a test duration to test a current state of the user. Sensor data is received from one or more sensors worn by the user or placed near the user that indicate at least a motion or a posture of the user. The motion or the posture of the user during the structured test is measured with the sensor data. At least one of a timing of providing an instruction to perform at least one action and a test duration of a subsequent structured test is adjusted based on the measured motion or posture of the user, and the subsequent structured test is conducted with the user based on the adjusted at least one of the timing and the test duration.

Abstract: Ophthalmic devices and systems for treating dry eye are described. An ophthalmic device includes a housing having a convex anterior surface and a concave posterior surface and a thermal regulator disposed therein. In an example, the thermal regulator includes a heating element positioned to heat the convex anterior surface. In an example, the thermal regulator includes a cooling element positioned to cool the concave posterior surface. The convex anterior surface is shaped to contact a portion of conjunctiva of an eye adjacent to Meibomian glands of the eye, such as the palpebral conjunctiva, when the ophthalmic device is mounted to the eye. The concave posterior surface is shaped to contact a portion of the conjunctiva adjacent to scleral nerves of the eye, such as the bulbar conjunctiva, when the ophthalmic device is mounted to the eye.

Abstract: A method predicts the fall risk of a user based on a machine learning model. The model is trained using data about the user, which may be from wearable sensors and depth sensors, manually input by the user, and received from other types of sources. Data about a population of users and data from structured tests completed by the user can also be used to train the model. The model uses features and motifs discovered based on the data that correlate to fall risk events to update fall risk scores and predictions. The user is provided a recommendation describing how the user can reduce a predicted fall risk for the user.

Abstract: A method of tremor reduction in a handheld device includes measuring a tremor motion and a tilt motion with a motion tracking module (“MTM”) disposed in a housing of the handheld device. In response to measuring the tremor motion, an attachment arm is moved with at least one motion generating mechanism to reduce the tremor motion in the attachment arm. Additionally, in response to measuring the tilt motion, the attachment arm is moved with the at least one motion generating mechanism to resist the attachment arm hitting a hard stop in the handheld device.

Abstract: A method of tremor reduction in a handheld device includes measuring a tremor motion and a tilt motion with a motion tracking module (“MTM”) disposed in a housing of the handheld device. In response to measuring the tremor motion, an attachment arm is moved with at least one motion generating mechanism to reduce the tremor motion in the attachment arm. Additionally, in response to measuring the tilt motion, the attachment arm is moved with the at least one motion generating mechanism to resist the attachment arm hitting a hard stop in the handheld device.

Abstract: A handheld system includes a housing, a motion-generating mechanism disposed within the housing, an attachment arm extending from the housing and having a first end coupled to the motion-generating mechanism and a second end configured to receive a user assistive device, a first sensor mounted to measure a first motion of the handheld system and generate a first signal indicative of the first motion, and a control system coupled to the motion-generating mechanism and the first sensor. The control system is configured to use the first signal to stabilize the user-assistive device and compensate for human tremors imparted to the housing.

Abstract: Embodiments regard nutrition assessment using a handheld device. An embodiment of an apparatus includes a handle with a controller within the handle, an attachment arm extending from the handle, and a user-assistive device coupled with an end of the attachment arm, wherein the apparatus is to determine a mass held by the user-assistive device, the determination being made during a task by a user of the handheld tool including manipulation of the handheld tool.

Abstract: Various examples are described for using a movement sensor to detecting an activity of an infant. In an example, an activity classification system includes a sensor configured to measure the activity of an infant and an external monitor. The monitor receives, from a sensor, a time series of data comprising an inertial measurement for each a time period. The monitor determines, from the time series and by using a predictive model, an activity from a list of identified activities. Examples of identified activities are deep sleep, light sleep, sitting, awake, nursing, or bottle feeding.

Abstract: A handheld system includes a motion-generating mechanism having a first motor mounted to a housing to generate a first rotary motion and a second motor coupled to a first output of the first motor such that the first rotary motion imparts to the second motor and rotates the second motor within the housing. The second motor generates a second rotary motion. An attachment arm extends out of the housing and has a first end coupled to a second output of the second motor and a second end configured to attach a user assistive device. A motion sensor senses a motion of the handheld system and generates a signal in response. A control system is coupled to receive the signal and to control the first and second rotary motions with commands generated based at least in part upon the signal. The commands direct the motion-generating mechanism to stabilize unintentional muscle movements.