公开(公告)号：US20250134409A1

公开(公告)日：2025-05-01

申请号：US18496728

申请日：2023-10-27

Applicant: STMicroelectronics International N.V.

Inventor： Federico RIZZARDINI ,  Alessandro MAGNANI

IPC: A61B5/08 ,  A61B5/00 ,  A61B5/11

Abstract: The present disclosure is directed to cough detection for electronic devices, such as wireless headphones. The cough detection utilizes inertial sensors to perform both head movement detection and vocal activity detection. The dual identification of head movement and vocal activity allows improved detection accuracy, and minimal false detections caused by environmental noise.

公开(公告)号：US20240401978A1

公开(公告)日：2024-12-05

申请号：US18326880

申请日：2023-05-31

Applicant: STMicroelectronics International N.V.

Inventor： Federico RIZZARDINI ,  Lorenzo BRACCO

IPC: G01C25/00 ,  G01P15/125

Abstract: The present disclosure is directed to accelerometer measurement compensation for a device with first and second accelerometers. The first and second accelerometers are included in first and second components, respectively, of the device that are configured to rotate with respect to a hinge. The device detects a stuck condition of the first accelerometer, and compensates acceleration measurements of the first accelerometer by exploiting redundant information from the second accelerometer and applying a runtime calibration of undesired offsets.

公开(公告)号：US20250076864A1

公开(公告)日：2025-03-06

申请号：US18799307

申请日：2024-08-09

Applicant: STMicroelectronics International N.V.

Inventor： Federico RIZZARDINI ,  Lorenzo BRACCO

IPC: G05B23/02

Abstract: Sensor device with a microcontroller unit and a sensor including a transducer, which is coupleable to a device and generates a signal indicative of a physical quantity, and a processing circuit including: a conversion stage which generates samples of the physical quantity; a data generation stage which generates data vectors as a function of the samples, each data vector being formed by programmable quantity values; and a decision stage. The microcontroller unit programs the decision stage so that it classifies the data vectors by executing a decision tree having a structure and thresholds. In a configuration mode, the microcontroller unit programs the data generation stage; in a calibration mode, the microcontroller unit acquires a corresponding set of data vectors, determines, for each programmable quantity, a corresponding range of admissible values and programs the thresholds as a function of the ranges of admissible values; in a detection mode, the decision stage classifies the data vectors, by executing the decision tree on the basis of the programmed thresholds.

公开(公告)号：US20240255386A1

公开(公告)日：2024-08-01

申请号：US18161674

申请日：2023-01-30

Applicant: STMicroelectronics International N.V.

Inventor： Federico RIZZARDINI ,  Lorenzo BRACCO

IPC: G01M99/00 ,  G06N20/00

CPC classification number: G01M99/005 ,  G06N20/00

Abstract: A sensor unit is coupled to a machine and configured to detect anomalous behavior of the machine. The sensor unit includes a low power microcontroller that learns to recognize a plurality of operations of the machine. The sensor unit generates mean vector and inverse of a Cholesky decomposition matrix for each operation. During a detection mode the sensor unit computes a Mahalanobis distance for each feature vector, mean vector and first matrix. The sensor unit detects anomalous behavior or classifies the operation of the machine based on the Mahalanobis distances.

公开(公告)号：US20250103864A1

公开(公告)日：2025-03-27

申请号：US18472063

申请日：2023-09-21

Applicant: STMicroelectronics International N.V.

Inventor： Federico RIZZARDINI ,  Giacomo TURATI

IPC: G06N3/0464

Abstract: A device includes a sensor and processing circuitry. The sensor, in operation, generates a sequence of data samples. The processing circuitry, in operation, implements a sliding convolutional neural network (SCNN) having a plurality of layers to generate classification results based on the sequence of data samples. The SCNN sequentially processes the sequence of data samples, the sequentially processing the sequence of data samples including, for each received sample of a set of received data samples of the sequence of data samples, iteratively updating partial results of an inference of a first layer of the plurality of layers based on a respective patch of data samples of the sequence of data samples. The respective patch of data samples includes the received data sample. The classification results may be used to generate control signals, such as by the sensing device or a host processor coupled to the sensing device.

公开(公告)号：US20250053246A1

公开(公告)日：2025-02-13

申请号：US18447147

申请日：2023-08-09

Applicant: STMicroelectronics International N.V.

Inventor： Stefano Paolo RIVOLTA ,  Federico RIZZARDINI ,  Lorenzo BRACCO

IPC: G06F3/0346 ,  G06F3/01

Abstract: The present disclosure is directed to lift-up gesture detection for electronic devices. An initial lift-up gesture is detected in response to an orientation change and a lift-up motion of the device being detected. The initial lift-up gesture is validated as a true lift-up gesture in a case where a shaking motion of the device is not being detected when the initial lift-up gesture is detected. If a shaking motion of the device is detected when the initial lift-up gesture is detected, the initial lift-up gesture is rejected.

公开(公告)号：US20240383429A1

公开(公告)日：2024-11-21

申请号：US18317795

申请日：2023-05-15

Applicant: STMicroelectronics International N.V.

Inventor： Stefano Paolo RIVOLTA ,  Federico RIZZARDINI ,  Marco BIANCO

IPC: B60R21/0132

Abstract: A crash detection system includes first and second sensors and a processor. The processor receives first sensor data output by the first sensor, determines whether the first sensor data indicates a first class or a second class, outputs an enable signal to the second sensor if the first sensor data indicates the second class, receives second sensor data output by the second sensor after the enable signal is output, determines whether the second sensor data indicates a high acceleration value, determines whether the first sensor data indicates the first class within a predetermined amount of time after the second sensor data is determined to indicate the high acceleration value, and outputs a signal indicating a crash has occurred in response to determining that the first sensor data indicates the first class within the predetermined amount of time after the second sensor data is determined to indicate the high acceleration value.

公开(公告)号：US20240331522A1

公开(公告)日：2024-10-03

申请号：US18191782

申请日：2023-03-28

Applicant: STMicroelectronics International N.V.

Inventor： Federico RIZZARDINI ,  Lorenzo BRACCO

IPC: G08B21/04 ,  G08B29/18

CPC classification number: G08B21/0446 ,  G08B21/043 ,  G08B29/188

Abstract: The present disclosure is directed to a device and method for human fall detection solution. Fall detection is performed by a low power inertial measurement unit (IMU) that is communicatively coupled between a pressure sensor and an application processor. The IMU includes one or more motions sensors, such as an accelerometer and gyroscope. The application processor is the main processor of the containing device. The IMU receives pressure sensor data from the pressure sensor, and executes the fall detection using both the pressure sensor data and accelerometer data.