Abstract: An electronic device includes a sensor unit. The sensor unit includes a sensor and low power, low area sensor processing unit. The sensor processing unit performs an unsupervised machine learning processes to learn to recognize an activity or motion of the user or device. The user can request to learn the new activity. The sensor processing unit can request that the user remain stationary for a selected period of time before performing the activity. The sensor processing unit records sensor data while the user performs the activity and generates an activity template from the sensor data. The sensor processing can then infer when the user is performing the activity by comparing sensor signals to the activity template.

Abstract: The present disclosure is directed to kickback detection for devices, such as handheld drills. Kickback is detected using a gyroscope and an accelerometer, and is detected at the end of each of a plurality of time windows. At the end of each time window, kickback is detected based on, for example, a variance of a norm of gyroscope measurements. False kickback detections are then removed based on, for example, a minimum and a mean of accelerometer measurements. Kickback detection is completed before the next time window begins.

Abstract: A method includes receiving, at a master agent, announcements from candidate consumer agents indicating the presence of the candidate consumer agents. Each announcement includes display parameters for a display of the corresponding candidate consumer agent. The method further includes receiving at the master agent content parameters from a producer agent, the content parameters defining characteristics of content to be provided by the consumer agent. A mosaic screen is configured based on the received announcements and the content parameters. This configuring of the mosaic screen includes selecting ones of the consumer agents for which an announcement was received and generating content distribution parameters based on the content parameters and the display parameters of the selected ones of the consumer agents. The generated content distribution parameters are provided to the consumer agent.

Abstract: The present disclosure is directed to a device and method for detection of motion events including towing of the vehicle, jacking of the vehicle, and the vehicle being hit by another object. Processing is split between an MCU and a sensor unit. After the vehicle is turned off and before the MCU enters a sleep mode, the MCU calculates a gravity vector of the vehicle using accelerometer data, calculates threshold values based on the gravity vector, and saves the threshold values. After the MCU enters the sleep mode, the sensor unit subsequently monitors and detects motion events with the saved threshold values.

Abstract: The present disclosure is directed to an air filter sensor system that can monitor a status of a filter and provide information to a remote system regarding the filter's status. The system can receive, by a computing server via one or more computer networks and from each of a plurality of sensor assemblies coupled to a corresponding plurality of air filters, information indicative of filter contamination levels respectively associated with each corresponding air filter of the plurality of air filters. Each of the respective filter contamination levels being provided by one sensor assembly of the plurality of sensor assemblies based at least in part on a difference in detected air pressure between first and second sides of the corresponding air filter.

Abstract: A sensor system includes a plurality of inertial measurement units (IMU) and a control circuit. The control circuit is configured to receive sensor data from each of the inertial measurement units two alignment the timestamps of the sensor data, and to fuse the sensor data from the various IMUs. The control circuit detects whether the sensor data indicates a high degree movement or a low degree of movement and selects a high dynamic fusion process or a low dynamic fusion process based on the detected degree of movement.

Abstract: An electronic device includes a sensor unit. The sensor unit includes a sensor and low power, low area sensor processing unit. The sensor processing unit performs an unsupervised machine learning processes to learn to recognize an activity or motion of the user or device. The user can request to learn the new activity. The sensor processing unit can request that the user remain stationary for a selected period of time before performing the activity. The sensor processing unit records sensor data while the user performs the activity and generates an activity template from the sensor data. The sensor processing can then infer when the user is performing the activity by comparing sensor signals to the activity template.

Abstract: A blood pressure monitoring device includes a patch including two inertial measurement units placed adjacent to the skin of a user. The blood pressure monitoring device includes a control unit coupled to the patch and configured to receive sensor data from the inertial measurement units. The control unit includes an analysis model trained with multiple machine learning processes to generate blood pressure estimations based on the sensor data. A first general machine learning process trains the analysis model with a training set gathered from plurality of other individuals. The second general machine learning process retrains a portion of the analysis model with a second machine learning process utilizing individualized training set gathered from the user.

Abstract: An electronic device includes a magnetometer that outputs magnetometer sensor signals and a gyroscope that outputs gyroscope sensor signals. The electronic device includes a magnetometer calibration module that calibrates the magnetometer utilizing the gyroscope sensor signals. The electronic device generates a first magnetometer calibration parameter based on a Kalman filter process. The electronic device generates a second magnetometer calibration parameter based on a least squares estimation process.

Abstract: An electronic device includes a magnetometer that outputs magnetometer sensor signals and a gyroscope that outputs gyroscope sensor signals. The electronic device includes a magnetometer calibration module that calibrates the magnetometer utilizing the gyroscope sensor signals. The electronic device generates a first magnetometer calibration parameter based on a Kalman filter process. The electronic device generates a second magnetometer calibration parameter based on a least squares estimation process.

Abstract: A device including microelectromechanical systems (MEMS) sensors are used in dead reckoning in conditions where Global Positioning System (GPS) signals or Global Navigation Satellite System (GNSS) signals are lost. The device is capable of tracking the location of the device after the GPS/GNSS signals are lost by using MEMS sensors such as accelerometers and gyroscopes. By calculating a misalignment angle between a forward axis of a sensor frame of the device and a forward axis of a vehicle frame using the data received from the MEMS sensors, the device can accurately calculate the location of a user or the vehicle of the device even without the GPS/GNSS signals. Accordingly, a device capable of tracking the location of the user riding in the vehicle in GPS/GNSS signals absent environment can be provided.

Abstract: The present disclosure is directed to a device and method for detection of motion events including towing of the vehicle, jacking of the vehicle, and the vehicle being hit by another object. Processing is split between an MCU and a sensor unit. After the vehicle is turned off and before the MCU enters a sleep mode, the MCU calculates a gravity vector of the vehicle using accelerometer data, calculates threshold values based on the gravity vector, and saves the threshold values. After the MCU enters the sleep mode, the sensor unit subsequently monitors and detects motion events with the saved threshold values.

Abstract: A device including microelectromechanical systems (MEMS) sensors are used in dead reckoning in conditions where Global Positioning System (GPS) signals or Global Navigation Satellite System (GNSS) signals are lost. The device is capable of tracking the location of the device after the GPS/GNSS signals are lost by using MEMS sensors such as accelerometers and gyroscopes. By calculating a misalignment angle between a forward axis of a sensor frame of the device and a forward axis of a vehicle frame using the data received from the MEMS sensors, the device can accurately calculate the location of a user or the vehicle of the device even without the GPS/GNSS signals. Accordingly, a device capable of tracking the location of the user riding in the vehicle in GPS/GNSS signals absent environment can be provided.

Abstract: A method includes receiving, at a master agent, announcements from candidate consumer agents indicating the presence of the candidate consumer agents. Each announcement includes display parameters for a display of the corresponding candidate consumer agent. The method further includes receiving at the master agent content parameters from a producer agent, the content parameters defining characteristics of content to be provided by the consumer agent. A mosaic screen is configured based on the received announcements and the content parameters. This configuring of the mosaic screen includes selecting ones of the consumer agents for which an announcement was received and generating content distribution parameters based on the content parameters and the display parameters of the selected ones of the consumer agents. The generated content distribution parameters are provided to the consumer agent.

Abstract: A method includes receiving, at a master agent, announcements from candidate consumer agents indicating the presence of the candidate consumer agents. Each announcement includes display parameters for a display of the corresponding candidate consumer agent. The method further includes receiving at the master agent content parameters from a producer agent, the content parameters defining characteristics of content to be provided by the consumer agent. A mosaic screen is configured based on the received announcements and the content parameters. This configuring of the mosaic screen includes selecting ones of the consumer agents for which an announcement was received and generating content distribution parameters based on the content parameters and the display parameters of the selected ones of the consumer agents. The generated content distribution parameters are provided to the consumer agent.

Abstract: A distributed computing system for artificial intelligence in autonomously appreciating a circumstance context of a smart device. Raw context data is detected by sensors associated with the smart device. The raw context data is pre-processed by the smart device and then provided to a cloud based server for further processing. At the cloud based server, various sets of feature data are obtained from the pre-processed context data. The various sets of feature data are compared with corresponding classification parameters to determine a classification of a continuous event and/or a classification of transient event, if any, which occur in the context. The determined classification of the continuous event and the transient event will be used to autonomously configure the smart device or another related smart device to fit the context.

Abstract: A device for generating a control signal based on the linear movement of a linear member is provided. The device includes a linear member, a rotatable member, a first inertial measurement unit (IMU) coupled to the rotatable member and a second IMU having a fixed position. The device also includes a processing circuit which uses sensing signals from the IMUS to determine an attitude of the first IMU referenced to the second IMU and generate a control signal based on the attitude.

Abstract: An electronic device includes a magnetometer that outputs magnetometer sensor signals and a gyroscope that outputs gyroscope sensor signals. The electronic device includes a magnetometer calibration module that calibrates the magnetometer utilizing the gyroscope sensor signals. The electronic device generates a first magnetometer calibration parameter based on a Kalman filter process. The electronic device generates a second magnetometer calibration parameter based on a least squares estimation process.

Abstract: The disclosure describes methods and apparatus for quickly prototyping of a solution developed using one or more sensing devices (e.g., sensors), functional blocks, algorithm libraries, and customized logic. The methods produce firmware executable by a processor (e.g., a microcontroller) on an embedded device such as a development board, expansion board, or the like. By performing these methods on the apparatus described, a user is able to create a function prototype without having deep knowledge of the particular sensing device or any particular programming language. Prototypes developed as described herein enable the user to rapidly test ideas and develop sensing device proofs-of-concept. The solutions produced by the methods and apparatus improve the functioning of the sensor being prototyped and the operation of the embedded device where the sensor is integrated.

Abstract: Technological advancements are disclosed that utilize inertial sensor data for multiple classes to select a combination of filters to extract information though features to train a machine learning core decision tree. A determination is made whether the data for a class includes a frequency peak or dominating frequency that contains significant information about the class. In response to the data for the class including a frequency peak, a peak-based frequency range is determined. An entropy value is calculated for multiple frequency ranges in the data for the class. An entropy-based frequency range is selected from the multiple frequency ranges having a minimum entropy value. A frequency of interest is selected from the peak-based frequency range and the entropy-based frequency range for the class. A combination of filters is selected for each frequency of interest for each class and a decision tree is trained based on selected filter combination.