公开(公告)号：US20220414496A1

公开(公告)日：2022-12-29

申请号：US17360977

申请日：2021-06-28

Applicant: STMICROELECTRONICS S.r.l.

Inventor： Luca GANDOLFI ,  Marco CASTELLANO ,  Marco LEO

IPC: G06N5/04 ,  G06N20/00 ,  G01P1/00 ,  G01C19/5712 ,  G01P15/08

Abstract: System, method, and circuitry for utilizing sequential input inertial sensor data to calculate recursive features for training a machine learning algorithm or for classifying the data as a known class. The recursive feature values of a current data sample are calculating based on comparisons between the current data sample value and previous recursive feature values. The recursive features include a recursive maximum, recursive minimum, recursive peak to peak, recursive average, recursive root mean square, and recursive variance.

公开(公告)号：US20230048422A1

公开(公告)日：2023-02-16

申请号：US17870172

申请日：2022-07-21

Applicant: STMicroelectronics S.r.l.

Inventor： Enrico Rosario ALESSI ,  Marco LEO ,  Luca GANDOLFI ,  Fabio PASSANITI ,  Marco CASTELLANO

IPC: A61B5/308 ,  A61B5/024 ,  A61B5/366 ,  A61B5/11 ,  A61B5/0205 ,  A61B5/352

Abstract: A device for monitoring the health state is made in a chip including a semiconductor die integrating an electric potential sensor and a cardiac parameter determination unit. The potential sensor is configured to detect potential variations on the body of a living being and associated with a heart rhythm and to generate a cardiac signal. The cardiac parameter determination unit is configured to receive the cardiac signal and determine cardiac parameters indicative of a health state. In particular, the cardiac parameter determination unit is configured to detect triggering events and to determine features of the cardiac signal in time windows defined by the triggering events. The die also integrates a decision unit, configured to receive the cardiac parameters and generate a health signal based on a comparison with threshold values. The cardiac parameters include heart rate and QRS-complex.

公开(公告)号：US20240086152A1

公开(公告)日：2024-03-14

申请号：US18453158

申请日：2023-08-21

Applicant: STMICROELECTRONICS S.r.l.

Inventor： Luca GANDOLFI ,  Ugo GAROZZO

IPC: G06F7/544

CPC classification number: G06F7/5443

Abstract: A device includes a multiplier, an accumulator and a floating point adder. The multiplier generates a product of a first factor having a sign bit and exponent bits and a second factor having a sign bit and exponent bits. The multiplier includes a sign multiplier and a subtractor. The sign multiplier generates a product of the sign bit of the first factor and the sign bit of the second factor. The subtractor subtracts the exponent bits of the first factor from the exponent bits of the second factor. The accumulator stores a current accumulation value. The floating-point adder is coupled to the multiplier and to the accumulator, and, in operation, the adder generates an updated accumulation value based a sum of the product and the current accumulation value, and stores the updated accumulation value in the accumulator. The first factor may be a weight of a neural network.