Abstract: An ionic transistor including a first source, a first drain spaced apart from the first source, and a first storage layer electrically connected to the first source and the first drain. The ionic transistor also includes a second source spaced apart from the first source, a second drain spaced apart from the second source, and a second storage layer electrically connected to the second source and the second drain. The ionic transistor further includes an electrolyte layer situated between and electrically connected to the first and second storage layers. The ionic transistor may be implemented as non-volatile memory in a machine learning (ML) application.

Abstract: A mold sensor is configured with an enclosed chamber in which a nutrient-treated substrate is positioned. The mold sensor includes an optical sensor that is configured to measure optical properties in the enclosed chamber. A controller operates the optical sensor and is programmed to detect a presence of mold growing in the chamber based on the optical properties measured by the optical sensor.

Abstract: In one embodiment, a temperature sensor system includes a sensor assembly with a temperature sensing portion configured to generate a first signal based upon a temperature of body proximate a surface portion of the temperature sensing portion, and a thermoelectric generator portion configured to receive heat flow from the body through the temperature sensing portion and to generate a second signal based upon the heat flow. A control unit is operably connected to the sensor assembly and a memory and configured to execute program instructions stored in the memory to calculate and output a corrected temperature based upon the first signal, the second signal, and at least one correction factor stored in the memory. The at least one correcting factor is determined based upon at least one of a thermal conductivity of the sensor assembly, a size of the sensor assembly, and an aspect ratio of the sensor assembly.

Abstract: A mold sensor include a housing that defines an enclosed chamber in which a nutrient-treated substrate is positioned. The mold sensor includes a substrate advancement mechanism that is configured to selectively move the substrate to expose a surface of the substrate within the chamber. The mold sensor includes a sensor configured to detect mold growth on the substrate within the chamber.

Abstract: In one embodiment a temperature sensor system includes two sensor assemblies with different thermal resistances, each sensor assembly including a temperature sensing portion and a thermoelectric generator portion configured to receive heat flow from a body through the associated temperature sensing portion. A control unit is operably connected to the sensor assemblies and the memory. The control unit is configured to execute program instructions stored in the memory to obtain signals from the temperature sensor portions and the thermoelectric generator portions and to calculate and output a body core temperature (TB) based upon the obtained signals.

Abstract: A system for detecting blood velocity within a blood vessel includes a piezoelectric transducer supported on a ceramic substrate. The ceramic substrate supports the piezoelectric transducer at a fixed angle of incidence that is greater than 0° and less than 90°. The ceramic substrate is formed of steatite ceramic and is configured to couple an ultrasonic signal emitted by the transducer to skin underlying the substrate.

Abstract: A vital signs monitoring system includes a peak pattern detection module configured to output a peak prediction signal from sensor signals based on a peak prediction algorithm; a vital sign estimating module configured to estimate a vital sign based on the peak prediction signal; an activity and context detector module configured to output a context signal based on at least one environmental condition and/or activity level of the person; and a concept drift detection module configured to output a drift signal based on drift detected in the estimated vital sign. The peak pattern prediction module is configured to update the peak prediction algorithm based on the context signal and the drift signal.

Abstract: A cascaded machine learning inference system and method is disclosed. The cascaded system and method may be designed to be employed in resource restricted environments. The cascaded system and method may be applicable for applications that operate with limited power (e.g., a wearable smart watch). The cascaded system and method may employ two or more subsystems that are operable to classify an input signal provided by any number or types of sensors suitable for a given application. For instance, the sensors used may include gyroscopes, accelerometers, magnetometers, or barometric altimeters. The system and method may also be further split functionality across additional or new subsystems. By splitting operations and functionality across additional subsystems, the overall power consumption may further be reduced.

Abstract: A system and method for generating and using fixed-point operations for neural networks includes converting floating-point weighting factors into fixed-point weighting factors using a scaling factor. The scaling factor is defined to minimize a cost function and the scaling factor is derived from a set of multiples of a predetermined base. The set of possible scaling function is defined to reduce the computational effort for evaluating the cost function for each of a number of possible scaling factors. The system and method may be implemented in one or more controllers that are programmed to execute the logic.

Abstract: A thickness analyzer unit for determining a thickness of a layer includes a temperature change device, a temperature sensor, a memory, and a controller. The temperature change device is configured to induce a temperature change of the layer from a first temperature value to a second temperature value. The temperature sensor is configured to generate first temperature data corresponding to the first temperature value and second temperature data corresponding to the second temperature value. The memory is configured to store the first and second temperature values, a thermal conductivity value, a specific thermal capacity value, and a density value. The controller is configured (i) to determine a time constant value of the layer based on the first and second temperature values, and (ii) to determine the thickness of the layer based on the time constant value, the thermal conductivity value, the specific thermal capacity value, and the density value.

Abstract: A mold sensor is configured with an enclosed chamber in which a nutrient-treated substrate is positioned. The mold sensor includes a sensing system that is configured to measure a property of the substrate that corresponds to a pH value of the substrate. A controller operates the sensing system and is programmed to detect a presence of mold growing in the chamber by estimating the pH value from the measured property.

Abstract: A system for detecting mold includes a housing defining a chamber and an opening through a surface. The system includes a movable grate for selectively covering the opening. The system includes a substrate treated to promote mold growth. The system includes a mechanism for moving the substrate to move previously unexposed portions into the chamber. The system includes a thermal control system to maintain predetermined environmental conditions in the chamber. The system includes a sensor configured to detect mold growth in the chamber. The system includes a mold suppressor to kill mold in the chamber when activated. The system includes a controller to coordinate operation of the components to detect mold growth in an environment.

Abstract: A mold sensor is configured with an enclosed chamber in which a nutrient-treated substrate is positioned. The mold sensor includes a sensor for measuring electrical properties of the substrate. The substrate includes conductive elements to interface with a controller to measure the electrical properties. The controller operates the sensor and is programmed to detect a presence of mold growing in the chamber based on the electrical properties.

Abstract: A mold sensor is configured with an enclosed chamber in which a nutrient-treated substrate is positioned. The mold sensor includes a sensing system that is configured to measure properties of pressure waves within the enclosed chamber. A controller operates the sensing system and is programmed to detect a presence of mold growing in the chamber based on the characteristics of the pressure wave response within the chamber.

Abstract: A method of calibrating a monitoring device to generate calibrated vital sign data using a calibration device includes positioning the monitoring device in a first position on a patient, generating vital sign data with a sensing assembly of the positioned monitoring device, and processing the vital sign data with the calibration device to determine if the vital sign data is calibrated vital sign data or uncalibrated vital sign data. The method also includes generating a calibrated data signal if the vital sign data is calibrated vital sign data, generating a reposition signal if the vital sign data is uncalibrated vital sign data, and repositioning the monitoring device on the patient until the calibrated data signal is generated.

Abstract: A transducer includes one or more actuator components configured to be encompassed by a cavity of a frame, wherein the one or more actuator components are configured to allow in-plane and out-of-plane movement with respect to the frame and configured to create haptic feedback in the in-plane or out-of-plane movement to the frame. The transducer also includes one or more sensing layers configured to detect changes of displacement in the frame, wherein the sensing layer is connected to the one or more actuator components.

Abstract: An ionic transistor including a first source, a first drain spaced apart from the first source, and a first storage layer electrically connected to the first source and the first drain. The ionic transistor also includes a second source spaced apart from the first source, a second drain spaced apart from the second source, and a second storage layer electrically connected to the second source and the second drain. The ionic transistor further includes an electrolyte layer situated between and electrically connected to the first and second storage layers. The ionic transistor may be implemented as non-volatile memory in a machine learning (ML) application.

Abstract: A portable electronic communication device including a display, a pressure sensor array including a plurality of pressure sensors, and an electronic processor communicatively coupled to the pressure sensor array. The electronic processor is configured to receive, from the pressure sensor array, a plurality of stress tensor measurements corresponding to a user interaction with the display, perform an interpolation of the plurality of pressure measurements, and determine, based on the interpolation, a faulty sensor of the plurality of sensors.

Abstract: A method for calibrating a blood pressure monitoring system includes activating a reference monitor to perform a reference measurement of the blood pressure of a user as part of a calibration process. A wearable sensing device is activated to detect a parameter of user that is correlatable to the user's blood pressure. A processor of the user interface device processes the at least one parameter detected by the wearable blood pressure sensing device with reference to the reference measurement to determine a correlation factor that correlates the at least one parameter detected by the wearable blood pressure sensing device to the blood pressure of the user. The reference measurement includes an inflation phase, a measurement phase and a deflation phase. The processor is configured to only use the at least one parameter detected by the wearable blood pressure sensing device during the measurement phase in determining the correlation factor.

Abstract: A cascaded machine learning inference system and method is disclosed. The cascaded system and method may be designed to be employed in resource restricted environments. The cascaded system and method may be applicable for applications that operate with limited power (e.g., a wearable smart watch). The cascaded system and method may employ two or more subsystems that are operable to classify an input signal provided by any number or types of sensors suitable for a given application. For instance, the sensors used may include gyroscopes, accelerometers, magnetometers, or barometric altimeters. The system and method may also be further split functionality across additional or new subsystems. By splitting operations and functionality across additional subsystems, the overall power consumption may further be reduced.