公开(公告)号：US20210232901A1

公开(公告)日：2021-07-29

申请号：US17156052

申请日：2021-01-22

Applicant: STMicroelectronics S.r.l.

Inventor： Francesco Rundo ,  Sabrina Conoci ,  Concetto Spampinato

IPC: G06N3/063 ,  G06N3/04

Abstract: An embodiment method includes segmenting at least one electrophysiological signal and producing a set of sampled waveforms, applying artificial neural network processing to the set of sampled waveforms and a set of randomly generated noise samples and producing at least one altered data pattern, the altered data pattern comprising the set of filtered waveforms altered as a function of the randomly generated noise samples, providing calibration data comprising expected waveforms for filtered waveforms in the set of filtered waveforms, applying classifier processing to the produced at least one altered data pattern to detect a degree of resemblance between the produced at least one altered data pattern and the calibration data patterns, the classifier processing producing classification signals having values above or below at least one threshold value as a function of the detected degree of resemblance, and triggering a user circuit as a function of the classification signal.

公开(公告)号：US11950911B2

公开(公告)日：2024-04-09

申请号：US17009503

申请日：2020-09-01

Applicant: STMicroelectronics S.r.l.

Inventor： Francesco Rundo ,  Sabrina Conoci ,  Concetto Spampinato

IPC: G06F21/32 ,  A61B5/00 ,  A61B5/024 ,  A61B5/117 ,  A61B5/18 ,  G06N3/045

CPC classification number: A61B5/18 ,  A61B5/02416 ,  A61B5/117 ,  A61B5/7225 ,  A61B5/7246 ,  A61B5/7264 ,  G06F21/32 ,  G06N3/045

Abstract: An embodiment method comprises collecting at least one electrophysiological signal of a human over a limited time duration, and computing a set of electrophysiological signal features. The computing comprises at least one of: providing at least one reference electrophysiological signal and applying dynamic time warping processing to the at least one collected and at least one reference electrophysiological signals, applying stacked-auto-encoder artificial neural network processing to the collected electrophysiological signal, or filtering the electrophysiological signal collected via joint low-pass and high-pass filtering. The method further comprises applying pattern recognition processing to the computed set of features, producing a virtual key signal indicative of an identity of the human, and applying the virtual key signal to a user circuit to switch it between a first state and a second state as a result of the virtual key signal matching an authorized key signal stored in the user circuit.

公开(公告)号：US20210068739A1

公开(公告)日：2021-03-11

申请号：US17009503

申请日：2020-09-01

Applicant: STMicroelectronics S.r.l.

Inventor： Francesco Rundo ,  Sabrina Conoci ,  Concetto Spampinato

IPC: A61B5/18 ,  A61B5/00 ,  A61B5/117 ,  A61B5/024 ,  G06N3/04 ,  G06F21/32

Abstract: An embodiment method comprises collecting at least one electrophysiological signal of a human over a limited time duration, and computing a set of electrophysiological signal features. The computing comprises at least one of: providing at least one reference electrophysiological signal and applying dynamic time warping processing to the at least one collected and at least one reference electrophysiological signals, applying stacked-auto-encoder artificial neural network processing to the collected electrophysiological signal, or filtering the electrophysiological signal collected via joint low-pass and high-pass filtering. The method further comprises applying pattern recognition processing to the computed set of features, producing a virtual key signal indicative of an identity of the human, and applying the virtual key signal to a user circuit to switch it between a first state and a second state as a result of the virtual key signal matching an authorized key signal stored in the user circuit.