Patents by Inventor Francesco RUNDO
Francesco RUNDO has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11954922Abstract: A time series of face images of a human during a human activity are captured. A first artificial neural network (ANN) processing pipeline processes the captured time series of face images to provide a first attention level indicator signal. An electrophysiological signal indicative of the level of attention of the human during the activity is also captured. A second ANN processing pipeline processes the sensed electrophysiological signal to providing a second attention level indicator signal. A risk indicator signal is then generated based on at least one of the first attention level indicator and second attention level indicator. A user circuit is then triggered as a result of the risk indicator reaching or failing to reach at least one attention level threshold.Type: GrantFiled: April 7, 2022Date of Patent: April 9, 2024Assignee: STMicroelectronics S.r.l.Inventors: Francesco Rundo, Giancarlo Asnaghi, Sabrina Conoci
-
Patent number: 11950911Abstract: 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.Type: GrantFiled: September 1, 2020Date of Patent: April 9, 2024Assignee: STMicroelectronics S.r.l.Inventors: Francesco Rundo, Sabrina Conoci, Concetto Spampinato
-
Patent number: 11793406Abstract: A method includes receiving a video signal that comprises a time series of images of a face of a human, wherein the images in the time series of images comprise a set of landmark points in the face, applying tracking processing to the video signal to reveal variations over time of at least one image parameter at the set of landmark points in the human face, generating a set of variation signals indicative of variations revealed at respective landmark points in the set of landmark points, applying processing to the set of variation signals, the processing comprising artificial neural network processing to produce a reconstructed PhotoPletysmoGraphy (PPG) signal, and estimating a heart rate variability of a variable heart rate of the human as a function of the reconstructed PPG signal.Type: GrantFiled: September 20, 2022Date of Patent: October 24, 2023Assignee: STMicroelectronics S.r.l.Inventors: Francesco Rundo, Francesca Trenta, Sabrina Conoci, Sebastiano Battiato
-
Publication number: 20230009282Abstract: A method includes receiving a video signal that comprises a time series of images of a face of a human, wherein the images in the time series of images comprise a set of landmark points in the face, applying tracking processing to the video signal to reveal variations over time of at least one image parameter at the set of landmark points in the human face, generating a set of variation signals indicative of variations revealed at respective landmark points in the set of landmark points, applying processing to the set of variation signals, the processing comprising artificial neural network processing to produce a reconstructed PhotoPletysmoGraphy (PPG) signal, and estimating a heart rate variability of a variable heart rate of the human as a function of the reconstructed PPG signal.Type: ApplicationFiled: September 20, 2022Publication date: January 12, 2023Inventors: Francesco Rundo, Francesca Trenta, Sabrina Conoci, Sebastiano Battiato
-
Patent number: 11471084Abstract: A method includes receiving a video signal that comprises a time series of images of a face of a human, wherein the images in the time series of images comprise a set of landmark points in the face, applying tracking processing to the video signal to reveal variations over time of at least one image parameter at the set of landmark points in the human face, generating a set of variation signals indicative of variations revealed at respective landmark points in the set of landmark points, applying processing to the set of variation signals, the processing comprising artificial neural network processing to produce a reconstructed PhotoPletysmoGraphy (PPG) signal, and estimating a heart rate variability of a variable heart rate of the human as a function of the reconstructed PPG signal.Type: GrantFiled: December 30, 2019Date of Patent: October 18, 2022Assignee: STMicroelectronics S.R.L.Inventors: Francesco Rundo, Francesca Trenta, Sabrina Conoci, Sebastiano Battiato
-
Publication number: 20220327845Abstract: A time series of face images of a human during a human activity are captured. A first artificial neural network (ANN) processing pipeline processes the captured time series of face images to provide a first attention level indicator signal. An electrophysiological signal indicative of the level of attention of the human during the activity is also captured. A second ANN processing pipeline processes the sensed electrophysiological signal to providing a second attention level indicator signal. A risk indicator signal is then generated based on at least one of the first attention level indicator and second attention level indicator. A user circuit is then triggered as a result of the risk indicator reaching or failing to reach at least one attention level threshold.Type: ApplicationFiled: April 7, 2022Publication date: October 13, 2022Applicant: STMicroelectronics S.r.l.Inventors: Francesco RUNDO, Giancarlo ASNAGHI, Sabrina CONOCI
-
Publication number: 20220273183Abstract: In an embodiment, PhotoPlethysmoGraphy (PPG) signals are processed by detecting peaks and valleys in the PPG signal, segmenting the PPG signal to provide a time series of PPG waveforms located between two subsequent valleys in the PPG signal, applying to the waveforms in the time series pattern recognition with respect to a reference PPG waveform pattern produced based on a mathematical model of the PPG signal by assigning to the waveforms in the time series a recognition score. A resulting PPG signal is produced by retaining the waveforms in the time series having an assigned recognition score reaching a recognition threshold, and discarding the waveforms in the time series having an assigned recognition score failing to reach the recognition threshold.Type: ApplicationFiled: May 17, 2022Publication date: September 1, 2022Inventors: Francesco Rundo, Piero Fallica, Sabrina Conoci, Salvatore Petralia, Massimo Cataldo Mazzillo
-
Patent number: 11337617Abstract: In an embodiment, PhotoPlethysmoGraphy (PPG) signals are processed by detecting peaks and valleys in the PPG signal, segmenting the PPG signal to provide a time series of PPG waveforms located between two subsequent valleys in the PPG signal, applying to the waveforms in the time series pattern recognition with respect to a reference PPG waveform pattern produced based on a mathematical model of the PPG signal by assigning to the waveforms in the time series a recognition score. A resulting PPG signal is produced by retaining the waveforms in the time series having an assigned recognition score reaching a recognition threshold, and discarding the waveforms in the time series having an assigned recognition score failing to reach the recognition threshold.Type: GrantFiled: July 17, 2018Date of Patent: May 24, 2022Assignee: STMICROELECTRONICS S.R.L.Inventors: Francesco Rundo, Piero Fallica, Sabrina Conoci, Salvatore Petralia, Massimo Cataldo Mazzillo
-
Publication number: 20220104775Abstract: Blood pressure signals are reconstructed from PhotoPlethysmoGraphy (PPG) signals by: receiving PPG signals including systolic, diastolic and dicrotic phases; and determining first and second derivatives of the PPG signals and: a first set of values indicative of lengths of the signal paths of the PPG signal, the first derivative and the second derivative thereof in the systolic, diastolic and dicrotic phases; a second set of values indicative of relative durations of the PPG signal and the first and second derivatives thereof in the systolic, diastolic and dicrotic phases; and a third set of values indicative of the time separation of peaks and/or valleys in subsequent waveforms of the PPG signal. Reconstruction also includes applying artificial neural network processing to the first, second and third set of values. The artificial neural network processing includes artificial neural network training as a function of blood pressure signals to produce reconstructed blood pressure signals.Type: ApplicationFiled: December 16, 2021Publication date: April 7, 2022Inventors: Francesco Rundo, Sabrina Conoci, Piero Fallica, Rosalba Parenti, Vincenzo Perciavalle
-
Patent number: 11229404Abstract: Blood pressure signals are reconstructed from PhotoPlethysmoGraphy (PPG) signals by: receiving PPG signals including systolic, diastolic and dicrotic phases; and determining first and second derivatives of the PPG signals and: a first set of values indicative of lengths of the signal paths of the PPG signal, the first derivative and the second derivative thereof in the systolic, diastolic and dicrotic phases; a second set of values indicative of relative durations of the PPG signal and the first and second derivatives thereof in the systolic, diastolic and dicrotic phases; and a third set of values indicative of the time separation of peaks and/or valleys in subsequent waveforms of the PPG signal. Reconstruction also includes applying artificial neural network processing to the first, second and third set of values. The artificial neural network processing includes artificial neural network training as a function of blood pressure signals to produce reconstructed blood pressure signals.Type: GrantFiled: November 19, 2018Date of Patent: January 25, 2022Assignee: STMICROELECTRONICS S.R.L.Inventors: Francesco Rundo, Sabrina Conoci, Piero Fallica, Rosalba Parenti, Vincenzo Perciavalle
-
Patent number: 11164315Abstract: A method includes receiving a time series of slice images of medical imaging. The images have a region of interest located at a lung lesion. The method also includes tracking over at least one subset of slice images in a time series of slice images variations over time of at least one image parameter at the set of points in the region of interest. Classifier processing is applied to set of signals indicative of tracked time variations of the at least one image parameter at respective points in the set of points. A classification signal is indicative of the tracked time variations of the at least one image parameter reaching or failing to reach at least one classification threshold.Type: GrantFiled: November 18, 2019Date of Patent: November 2, 2021Assignee: STMICROELECTRONICS S.R.L.Inventors: Francesco Rundo, Sabrina Conoci, Giuseppe Luigi Banna
-
Publication number: 20210232901Abstract: 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.Type: ApplicationFiled: January 22, 2021Publication date: July 29, 2021Inventors: Francesco Rundo, Sabrina Conoci, Concetto Spampinato
-
Patent number: 10987007Abstract: A method of processing electrophysiological signals includes: receiving, over a limited time duration, sample electrocardiography (ECG) signals indicative of heart pulsatile activity occurring with a variable heart rate, wherein receiving the sample ECG signals is discontinued at an expiry of the limited time duration; receiving photoplethysmography (PPG) signals indicative of the heart pulsatile activity; determining a correlation between the sample ECG signals and the PPG signals; determining reconstructed ECG signals from the PPG signals as a function of the correlation between the sample ECG signals and the PPG signals; and estimating a heart rate variability of the variable heart rate as a function of the reconstructed ECG signals.Type: GrantFiled: October 23, 2018Date of Patent: April 27, 2021Assignee: STMicroelectronics S.R.L.Inventors: Francesco Rundo, Sabrina Conoci, Piero Fallica
-
Publication number: 20210068739Abstract: 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.Type: ApplicationFiled: September 1, 2020Publication date: March 11, 2021Inventors: Francesco Rundo, Sabrina Conoci, Concetto Spampinato
-
Publication number: 20200330020Abstract: In an embodiment, a method of processing an electrophysiological signal includes collecting the electrophysiological signal that is indicative of a level of attention of a human; filtering the electrophysiological signal via joint low-pass and high-pass filtering using a set of filtering parameters including low-pass filters parameters and high-pass filters parameters having a set of low-pass cut-off frequencies and a set of high-pass cut-off frequencies respectively. The method further includes applying artificial neural network processing to the filtered electrophysiological signal to extract therefrom a set of features of the electrophysiological signal. The method further includes applying classifier processing to the set of features extracted from the filtered electrophysiological signal and producing a classification signal indicative of the level of attention of the human. The method further includes generating a trigger signal to trigger a user circuit based on the classification signal.Type: ApplicationFiled: March 16, 2020Publication date: October 22, 2020Inventors: Francesco Rundo, Sabrina Conoci
-
Publication number: 20200214614Abstract: A method includes receiving a video signal that comprises a time series of images of a face of a human, wherein the images in the time series of images comprise a set of landmark points in the face, applying tracking processing to the video signal to reveal variations over time of at least one image parameter at the set of landmark points in the human face, generating a set of variation signals indicative of variations revealed at respective landmark points in the set of landmark points, applying processing to the set of variation signals, the processing comprising artificial neural network processing to produce a reconstructed PhotoPletysmoGraphy (PPG) signal, and estimating a heart rate variability of a variable heart rate of the human as a function of the reconstructed PPG signal.Type: ApplicationFiled: December 30, 2019Publication date: July 9, 2020Inventors: Francesco Rundo, Francesca Trenta, Sabrina Conoci, Sebastiano Battiato
-
Publication number: 20200184648Abstract: A method includes receiving a time series of slice images of medical imaging. The images have a region of interest located at a lung lesion. The method also includes tracking over at least one subset of slice images in a time series of slice images variations over time of at least one image parameter at the set of points in the region of interest. Classifier processing is applied to set of signals indicative of tracked time variations of the at least one image parameter at respective points in the set of points. A classification signal is indicative of the tracked time variations of the at least one image parameter reaching or failing to reach at least one classification threshold.Type: ApplicationFiled: November 18, 2019Publication date: June 11, 2020Inventors: Francesco Rundo, Sabrina Conoci, Giuseppe Luigi Banna
-
Patent number: 10602975Abstract: A method can be used for analyzing digital images of skin lesions. The images include pixels distributed over a lesion area. Sets of values including a first discrimination value indicative of a weighted average of the image pixels with weighing at the border of the lesion, a second discrimination value indicative of skewness and kurtosis of the distribution of the image pixels, a third discrimination value indicative of the ratio of symmetry and gray-level power of the distribution of the image pixels and calculated. A total additive score of the values in the sets of values is provided and compared with a total score threshold. The first, second and third discrimination values are compared with respective first, second and third discrimination threshold values. An output classification for the image analyzed is provided as a function of the results of the comparing.Type: GrantFiled: June 12, 2019Date of Patent: March 31, 2020Assignee: STMicroelectronics S.r.l.Inventors: Francesco Rundo, Giuseppe Luigi Banna
-
Publication number: 20190290188Abstract: A method can be used for analyzing digital images of skin lesions. The images include pixels distributed over a lesion area. Sets of values including a first discrimination value indicative of a weighted average of the image pixels with weighing at the border of the lesion, a second discrimination value indicative of skewness and kurtosis of the distribution of the image pixels, a third discrimination value indicative of the ratio of symmetry and gray-level power of the distribution of the image pixels and calculated. A total additive score of the values in the sets of values is provided and compared with a total score threshold. The first, second and third discrimination values are compared with respective first, second and third discrimination threshold values. An output classification for the image analyzed is provided as a function of the results of the comparing.Type: ApplicationFiled: June 12, 2019Publication date: September 26, 2019Inventors: Francesco Rundo, Giuseppe Luigi Banna
-
Patent number: 10362985Abstract: A method can be used for analyzing digital images of skin lesions. The images include pixels distributed over a lesion area. Sets of values including a first discrimination value indicative of a weighted average of the image pixels with weighing at the border of the lesion, a second discrimination value indicative of skewness and kurtosis of the distribution of the image pixels, a third discrimination value indicative of the ratio of symmetry and gray-level power of the distribution of the image pixels and calculated. A total additive score of the values in the sets of values is provided and compared with a total score threshold. The first, second and third discrimination values are compared with respective first, second and third discrimination threshold values. An output classification for the image analyzed is provided as a function of the results of the comparing.Type: GrantFiled: May 26, 2017Date of Patent: July 30, 2019Assignee: STMicroelectronics S.r.l.Inventors: Francesco Rundo, Giuseppe Luigi Banna