公开(公告)号：US20180218275A1

公开(公告)日：2018-08-02

申请号：US15877138

申请日：2018-01-22

Applicant: STMICROELECTRONICS S.r.l.

Inventor： Valentina ARRIGONI ,  Giuseppe DESOLI ,  Beatrice ROSSI ,  Pasqualina FRAGNETO

IPC: G06N5/04 ,  G06F17/16 ,  G06N7/00

CPC classification number: G06N5/046 ,  G06F7/729 ,  G06F17/16 ,  G06N3/0454 ,  G06N7/005 ,  G06N7/023

Abstract: A method of operating neural networks such as convolutional neural networks including, e.g., an input layer, an output layer and at least one intermediate layer between the input layer and the output layer, with the network layers including operating circuits performing arithmetic operations on input data to provide output data. The method includes: selecting a set of operating circuits in the network layers, performing arithmetic operations in operating circuits in the selected set of operating circuits by performing Residue Number System or RNS operations on RNS-converted input data by obtaining RNS output data in the Residue Number System, backward converting from the Residue Number System the RNS output data resulting from the RNS operations.

公开(公告)号：US20170340292A1

公开(公告)日：2017-11-30

申请号：US15169184

申请日：2016-05-31

Applicant: STMicroelectronics S.r.l. ,  Politecnico Di Milano

Inventor： Beatrice ROSSI ,  Pasqualina FRAGNETO ,  Daniele ZAMBON ,  Diego CARRERA ,  Giacomo BORACCHI

IPC: A61B5/00 ,  A61B5/04 ,  A61B5/0245 ,  A61B5/0402 ,  A61B5/024

CPC classification number: A61B5/7267 ,  A61B5/0022 ,  A61B5/02438 ,  A61B5/0245 ,  A61B5/04012 ,  A61B5/04017 ,  A61B5/0402 ,  A61B5/04525 ,  A61B5/0456 ,  A61B5/0468 ,  A61B5/0472 ,  A61B5/1118 ,  A61B5/7207 ,  A61B5/7221 ,  A61B5/7232 ,  A61B5/7253 ,  A61B5/7278 ,  A61B2505/07 ,  A61B2562/0219

Abstract: A heartrate monitor detects heartbeats in a test signal. A local heartrate and an energy of acceleration are associated with the detected heartbeats. Detected heartbeats are included or excluded from a test set of heartbeats based on the local heartrate and energy of acceleration associated with the respective heartbeats. Anomalous heartbeats in the test set of heartbeats are detected using a sparse approximation model. The heartrate monitor may detect heartbeats in a training heartbeat signal. A reference heart rate and an energy of acceleration are associated with detected beats of the training heartbeat signal and selectively included in a set of training data based on the heart rate and energy of acceleration associated with the detected beat in the training heartbeat signal. A dictionary of the sparse representation model may be generated using the set of training data.

公开(公告)号：US20230221422A1

公开(公告)日：2023-07-13

申请号：US18150534

申请日：2023-01-05

Applicant: STMICROELECTRONICS S.r.l.

Inventor： Francesca CARMINATI ,  Marco PASSONI ,  Beatrice ROSSI ,  Diego CARRERA ,  Pasqualina FRAGNETO

IPC: G01S7/526 ,  H04R29/00 ,  H04R3/04 ,  H04R17/10 ,  G01S15/06

CPC classification number: G01S7/526 ,  H04R29/001 ,  H04R3/04 ,  H04R17/10 ,  G01S15/06 ,  H04R2201/003

Abstract: A method of operating a PMUT electro-acoustical transducer, the method comprising: applying over an excitation interval to the transducer an excitation signal which is configured to emit corresponding ultrasound pulses towards a surrounding space, acquiring at a receiver reflected ultrasound pulses as reflected in said surrounding space, generating a reference echo signal, performing a cross-correlation of said acquired received ultrasound pulses with said reference echo signal, performing a measurement based on the cross-correlation results, in particular a measurement of the time of flight of the ultrasound pulses, wherein said reference echo is obtained by finding an oscillation frequency of the transmitter on the basis of a transmitter ringdown signal, finding an oscillation frequency of the receiver on the basis of a receiver ringdown signal, performing a frequency tuning respectively on the transmitter and the receiver on the basis of said respective oscillation frequencies, then sweeping an input frequency of the transmitter to find a frequency of the maximum displacement in the ringdown signal, performing a frequency tuning of the receiver at said frequency of the maximum displacement in the ringdown signal of the transmitter.

公开(公告)号：US20220366105A1

公开(公告)日：2022-11-17

申请号：US17244313

申请日：2021-04-29

Applicant: STMicroelectronics S.r.l.

Inventor： Nicolo FOLLONI ,  Mattia MONETTI ,  Diego CARRERA ,  Beatrice ROSSI ,  Giancarlo ZINCO ,  Alberto BALZAROTTI ,  Pasqualina FRAGNETO

IPC: G06F30/23

Abstract: A method of performing an electro-thermo simulation includes defining a non-linear heat diffusion problem for at least a portion of a semiconductor device to be modeled, performing a finite volume discretization of the non-linear heat diffusion problem, reformulating a non-linear term of the discretized non-linear heat diffusion problem to decrease dimensions thereof, performing a hyper reduction of the reformulated non-linear term, and recovering the non-linear heat diffusion problem for the portion of the semiconductor device, and manufacturing the modeled semiconductor device.

公开(公告)号：US20220027715A1

公开(公告)日：2022-01-27

申请号：US17383132

申请日：2021-07-22

Applicant: STMICROELECTRONICS S.r.l.

Inventor： Diego CARRERA ,  Matteo COLELLA ,  Giuseppe DESOLI ,  Giacomo BORACCHI ,  Beatrice ROSSI ,  Pasqualina FRAGNETO ,  Luca FRITTOLI

IPC: G06N3/063 ,  G06N3/04 ,  G06K9/62

Abstract: A method, comprising: providing an ANN processing stage having a plurality of processing layers with respective parameters including at least one set of weight parameters, at least one input, resp. output, activation parameter and at least one activation function parameter; setting to an integer value a dimensional parameter of a lattice having a plurality of lattice points and identified by a set of basis vectors; selecting a set of weight parameters of a respective processing layer; vectorizing the selected set of weight parameters producing a set of weight vectors arranged as items of a matrix of weight vectors; normalizing the matrix of weight vectors; applying lattice vector quantization, LVQ, processing to the matrix of normalized weight vectors, producing a codebook of codewords; indexing by encoding codewords of the codebook as a function of the lattice, producing respective tuples of indices. The normalization comprises solving an optimization problem having a first term configured to provide normalized weight values approximating at least output, as a function of at least one input, activation parameter, and a regularization term ΩL, configured to amplify weight values having a short distance from the lattice points of the lattice L.

公开(公告)号：US20170360377A1

公开(公告)日：2017-12-21

申请号：US15696051

申请日：2017-09-05

Applicant: STMicroelectronics S.r.l. ,  POLITECNICO DI MILANO

Inventor： Beatrice ROSSI ,  Pasqualina FRAGNETO ,  Diego CARRERA ,  Giacomo BORACCHI ,  Daniele ZAMBON

IPC: A61B5/00 ,  A61B5/0245 ,  A61B5/0456 ,  A61B5/0432

CPC classification number: A61B5/7267 ,  A61B5/0006 ,  A61B5/0022 ,  A61B5/02438 ,  A61B5/0245 ,  A61B5/04012 ,  A61B5/04017 ,  A61B5/04325 ,  A61B5/04525 ,  A61B5/0456 ,  A61B5/0468 ,  A61B5/0472 ,  A61B5/1118 ,  A61B5/6802 ,  A61B5/7207 ,  A61B5/7221 ,  A61B5/7232 ,  A61B5/7253 ,  A61B5/7278 ,  A61B2505/07 ,  A61B2562/0219

Abstract: A heart-rate associated with a heartbeat signal is determined. A transform is selected based on the determined heart-rate associated with the heartbeat signal and a reference heart-rate associated with a dictionary of a sparse approximation model. The transform is selected independent of other factors associated with generation of the heartbeat signal. The selected transform is applied to the dictionary of the sparse approximation model, generating an adjusted dictionary of the sparse approximation model. Anomalous heartbeats in the heartbeat signal are detected using the adjusted dictionary of the sparse approximation model.

公开(公告)号：US20140161359A1

公开(公告)日：2014-06-12

申请号：US14068437

申请日：2013-10-31

Applicant: STMICROELECTRONICS INTERNATIONAL N.V. ,  STMICROELECTRONICS S.R.L

Inventor： Luca MAGRI ,  Beatrice ROSSI ,  Subarna TRIPATHI ,  Pasqualina FRAGNETO ,  Emiliano Mario PICCINELLI

IPC: G06K9/46

CPC classification number: G06K9/4604 ,  G06T7/13 ,  G06T2207/20061

Abstract: An embodiment is a computer-implemented method for detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected edge, generating a second straight line which passes through a second pixel of the detected edge, which is different from the first pixel, determining at least two intersections with a boundary of the digital image for each generated straight line, determining a set of two parameter values for each generated straight line based on the respective determined at least two intersections, wherein the set of two parameter values uniquely determines the respective generated straight line, and detecting the straight line in the digital image based on the determined sets of two parameter values.

Abstract translation: 一个实施例是用于检测包括多个像素的数字图像中的直线的计算机实现的方法，包括以下步骤：检测数字图像中的边缘，生成穿过检测到的边缘的第一像素的第一直线， 产生穿过所检测的边缘的不同于第一像素的第二像素的第二直线，为每个生成的直线确定与数字图像的边界的至少两个交点，确定一组两个参数值，以供 每个生成的直线基于相应确定的至少两个交点，其中所述两个参数值的集合唯一地确定相应生成的直线，并且基于所确定的两个参数值的集合来检测数字图像中的直线。