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: A method of detecting occupancy in an area includes obtaining, with a processor, an audio sample from an audio sensor and determining, with the processor, feature functional values of a set of selected feature functionals from the audio sample. The determining of the feature functional values includes extracting features in the set of selected feature functionals from the audio sample, and determining the feature functional values of the set of selected features from the extracted features. The method further includes determining, with the processor, occupancy in the area using a classifier based on the determined feature functional values.

Abstract: A system and method is disclosed for classifying time-series data provided to a machine-learning model from a continuous sensor signal. The data may be “windowed” or “divided” into a smaller data segment using a first stage classifier where an “event of interest” may be identified. The first stage classifier may employ an algorithm that prohibits false negative identifications. The data segment detected as including an event of interest may then be transmitted to a second stage classifier operable to performs a full classification on the data segment. The multi-stage network may require less power and a less complex structure.

Abstract: A method of detecting occupancy in an area includes obtaining, with a processor, an audio sample from an audio sensor and determining, with the processor, feature functional values of a set of selected feature functionals from the audio sample. The determining of the feature functional values includes extracting features in the set of selected feature functionals from the audio sample, and determining the feature functional values of the set of selected features from the extracted features. The method further includes determining, with the processor, occupancy in the area using a classifier based on the determined feature functional values.

Abstract: A wearable health device system includes a housing configured to be worn by a subject, and a sensor assembly with at least two accelerometers which sense acceleration along non-parallel axes. A processor operably connected to the sensor assembly and a memory executes program instructions in the memory to obtain SCG template data from the accelerometers and divide the obtained SCG template data into at least one cardiac cycle segment by converting the SCG template data into polar coordinate SCG template data or spherical coordinate SCG template data. At least one reference cardiac event is identified in the SCG template data using the converted SCG template data, and the SCG template data is divided into at least one cardiac cycle segment based upon the referenced cardiac event.

Abstract: A wearable health device system includes a housing configured to be worn by a subject, and a sensor assembly with at least two accelerometers which sense acceleration along non-parallel axes. A processor operably connected to the sensor assembly and a memory executes program instructions in the memory to obtain SCG template data from the accelerometers and divide the obtained SCG template data into at least one cardiac cycle segment. The cardiac cycle segment is used to generate an SCG acceleration template which is in turn used to generate an SCG rotation matrix. SCG acceleration data is then obtained from the accelerometers and normalized by applying the generated SCG rotation matrix to the obtained SCG acceleration.

Abstract: To efficiently execute deep convolutional neural networks (CNN) on edge devices (e.g., wearable device like an Apple Watch or FitBit) it may be necessary to split the output tasks across different entities. For edge devices with multiple sensors that are connected to multiple hubs, simple activity spotting may then be executed on a sensor while the hub resides in a sleep-like state. The hub may then be activated when an activity is detected by a sensor and further activity classification may then be performed. It is also contemplated that the edge device may include multiple hubs for simultaneous processing of multiple classification tasks.

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: To efficiently execute deep convolutional neural networks (CNN) on edge devices (e.g., wearable device like an Apple Watch or FitBit) it may be necessary to reduce the bit width of the network parameters down to 1-bit. Binarization at the first layer of a CNN has typically not been performed because it may lead to an increase in the output validation error of the input data. The method and systems provided include a binary input layer (BIL) which accepts binary input data by learning bit specific binary weights. By executing the CNN using binary input data, the present method and system may result in a reduction in the chip area consumed and the energy used in contrast to CNN models executed using floating point input data.