Patents by Inventor Andrea Fasoli

Andrea Fasoli 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: 12261619
    Abstract: An apparatus includes multiple analog to digital converters. Individual analog to digital converters are configured to produce a digital output from an analog input and configured to compute a least significant bit of the digital output by comparing an internal residual voltage for determination of the least significant bit and a residual voltage from another analog to digital converter.
    Type: Grant
    Filed: December 20, 2022
    Date of Patent: March 25, 2025
    Assignee: International Business Machines Corporation
    Inventors: Chia-Yu Chen, Ankur Agrawal, Andrea Fasoli, Kyu-hyoun Kim
  • Publication number: 20250077804
    Abstract: A first circuit is configured to split a first integer value into a first coarse value and a first fine value, and split a second integer value into a second coarse value and a second fine value. A second circuit performs an analog multiply and accumulate (MAC) operation on the first and second coarse values to produce a first analog output, perform an analog MAC operation on the first coarse value and the second fine value to produce a second analog output, perform an analog MAC operation on the first fine value and the second coarse value to produce a third analog output, and perform an analog MAC operation on the first and second fine values together to produce a fourth analog output. A third circuit is configured to perform analog-to-digital (A/D) conversion on and combine the analog output signals to produce a reconstructed digital output signal.
    Type: Application
    Filed: August 29, 2023
    Publication date: March 6, 2025
    Inventors: Ankur Agrawal, Andrea Fasoli, Monodeep Kar, Kyu-hyoun Kim, Sergey Rylov, Chia-Yu Chen, Xiao Sun
  • Patent number: 12099043
    Abstract: A small-sized, portable enclosure protects a gas sensor against degradation due to environmental exposure and changes in atmospheric conditions. The protective enclosure includes an inlet for introduction of a gas into the enclosure, an outlet for release of the gas upon completion of a sensing run, and at least one retractable filter that removes from the inflowing gas deleterious compounds that can compromise the integrity of the sensor or cause the sensor to degrade over time. The enclosure does not include any filters during the measurement phase of the sensing run in order to allow the gas sensor to accurately measure an unmodified gas mixture and/or analyte.
    Type: Grant
    Filed: December 15, 2022
    Date of Patent: September 24, 2024
    Assignees: International Business Machines Corporation, The University of Melbourne, Technische Universiteit Eindhoven
    Inventors: Thomas Geoffrey Pattison, Tom Van der Pol, Linda Karin Sundberg, Krystelle Lionti, Andrea Fasoli, Luisa Dominica Bozano
  • Publication number: 20240204792
    Abstract: An apparatus includes multiple analog to digital converters. Individual analog to digital converters are configured to produce a digital output from an analog input and configured to compute a least significant bit of the digital output by comparing an internal residual voltage for determination of the least significant bit and a residual voltage from another analog to digital converter.
    Type: Application
    Filed: December 20, 2022
    Publication date: June 20, 2024
    Inventors: Chia-Yu CHEN, Ankur Agrawal, Andrea Fasoli, Kyu-hyoun Kim
  • Publication number: 20240201950
    Abstract: A scale factor can be determined and applied to input values of an analog neural network implemented by a crossbar array of non-volatile memory devices. An inverse of the scale factor can be applied to synaptic weight values stored by the crossbar array of non-volatile memory devices. Operations by the crossbar array can be performed using the scaled input values and the synaptic weight values. The scale factor can be determined for each row of the crossbar array. The scale factor can be determined using a combination of the input values and the synaptic weight values.
    Type: Application
    Filed: December 15, 2022
    Publication date: June 20, 2024
    Inventors: Stefano Ambrogio, Andrea Fasoli
  • Publication number: 20240176584
    Abstract: An apparatus comprising: a first plurality of inputs representing an activation input vector; a second plurality of inputs representing a weight input vector; an analog multiplier-and-accumulator to generate a first analog voltage representing a first multiply-and-accumulate result for the said first inputs and the second inputs; a voltage multiplier that takes the said first analog voltage and produces a second analog voltage representing, a second multiply-and-accumulate result by multiplying at least one scaling factor to the first analog voltage; an analog to digital converter configured to convert the said second analog voltage multiply-and-accumulate result into a digital signal using a limited-precision operation during a neural network inference operation; and a hardware controller configured to determine the at least one scaling factor based on the first multiply-and-accumulate result, or a software controller configured to determine the at least one scaling factor based on the first multiply-and-acc
    Type: Application
    Filed: November 29, 2022
    Publication date: May 30, 2024
    Inventors: Chia-Yu Chen, Andrea Fasoli, Ankur Agrawal, Kyu-hyoun Kim, Chi-Chun LIU, Mauricio J. Serrano, Monodeep Kar, Naigang Wang, Leland Chang
  • Publication number: 20240152574
    Abstract: A computer-implemented method to generate weights and inputs in a multiply-and-accumulate (MAC) operation that are resilient to reduced precision. The method includes providing a matrix M and its pseudoinverse M?1. Weights W are multiplied with M?1 and an input vector value x is multiplied with M. Two new matrices W2 and x2 are defined based on the multiplying of W with M?1 and x with M. The matrices W2 and x2 are encoded with increased resilience to reduce precision in place of the weights W and input vector value x.
    Type: Application
    Filed: November 4, 2022
    Publication date: May 9, 2024
    Inventors: Stefano Ambrogio, Andrea Fasoli
  • Patent number: 11694770
    Abstract: Volatile organic compounds classification by receiving test data associated with detecting volatile organic compounds (VOCs), analyzing the test data according to a set of data features associated with known VOCs, determining a match between each feature of the test data and a corresponding feature of the set of data features, yielding a set of matches, defining a first degree of anomaly for the test data according to the set of matches, and classifying the test data according to the first degree of anomaly.
    Type: Grant
    Filed: October 26, 2020
    Date of Patent: July 4, 2023
    Assignee: International Business Machines Corporation
    Inventors: Vito Paolo Pastore, Simone Bianco, Nimrod Megiddo, Andrea Fasoli, Aminat Adebiyi, Mohammed Abdi, Alberto Mannari, Luisa Dominica Bozano
  • Patent number: 11686697
    Abstract: A method of identifying a gas is provided. The method includes providing a gas sensor device comprising at least two stacked metal oxide layers, wherein a change in conductance of the gas sensor device in a presence of a gas varies with a temperature of the stacked metal oxide layers. The method includes bringing the gas into proximity with the stacked metal oxide layers. The method also includes measuring the conductance of the gas sensor device when the gas is in proximity with the stacked layers at multiple temperatures to generate a temperature-conductance profile. The method also includes identifying a gas of interest based on the temperature-conductance profile.
    Type: Grant
    Filed: September 24, 2020
    Date of Patent: June 27, 2023
    Assignee: International Business Machines Corporation
    Inventor: Andrea Fasoli
  • Publication number: 20230122407
    Abstract: A small-sized, portable enclosure protects a gas sensor against degradation due to environmental exposure and changes in atmospheric conditions. The protective enclosure includes an inlet for introduction of a gas into the enclosure, an outlet for release of the gas upon completion of a sensing run, and a number of in-line filters that remove from the inflowing gas sample analytes, contaminants, and other materials that can compromise the integrity of the sensor or cause the sensor to degrade over time. The enclosure does not include any filters during the measurement phase of the sensing run in order to allow the gas sensor to accurately measure an unmodified gas mixture and/or analyte.
    Type: Application
    Filed: December 15, 2022
    Publication date: April 20, 2023
    Inventors: Thomas Geoffrey Pattison, Tom Van der Pol, Linda Karin Sundberg, Krystelle Lionti, Andrea Fasoli, Luisa Dominica Bozano
  • Patent number: 11624740
    Abstract: A small-sized, portable enclosure protects a gas sensor against degradation due to environmental exposure and changes in atmospheric conditions. The protective enclosure includes an inlet for introduction of a gas into the enclosure, an outlet for release of the gas upon completion of a sensing run, and a number of in-line filters that remove from the inflowing gas sample analytes, contaminants, and other materials that can compromise the integrity of the sensor or cause the sensor to degrade over time. The enclosure does not include any filters during the measurement phase of the sensing run in order to allow the gas sensor to accurately measure an unmodified gas mixture and/or analyte.
    Type: Grant
    Filed: July 17, 2020
    Date of Patent: April 11, 2023
    Assignees: International Business Machines Corporation, The University of Melbourne, Technische Universiteit Eindhoven
    Inventors: Thomas Geoffrey Pattison, Tom Van der Pol, Linda Karin Sundberg, Krystelle Lionti, Andrea Fasoli, Luisa Dominica Bozano
  • Patent number: 11619618
    Abstract: Provided is a system and method for tuning an array of sensors to enable selection of the most suitable sensors for a target application. After extracting features from sensor raw data, the extracted features are ranked with gradient boosting decision trees to assign an importance value to each extracted feature. A threshold value for the entire set of extracted features is calculated and an importance score is calculated for the individual sensors of the array. Individual sensors with an importance score on or above the threshold value are selected for the target application.
    Type: Grant
    Filed: December 9, 2019
    Date of Patent: April 4, 2023
    Assignee: International Business Machines Corporation
    Inventors: Mohammed Abdi, Aminat Adebiyi, Alberto Mannari, Andrea Fasoli, Ronald Robert Labby, Luisa Bozano, Pawan Chowdhary, Abubeker Abdullahi
  • Patent number: 11614432
    Abstract: Provided is a gas sensor system with a gas sensor, and a microprocessor programmed to control the gas sensor with at least two operational modes. The first operational mode controls the gas sensor from a baseline level through analyte detection. Upon initiation of the recovery phase after analyte withdrawal, the gas sensor system switches to the second operational mode, which changes conditions of the gas sensor to (i) accelerate removal of the analyte from the gas sensor and (ii) accelerate recovery of the gas sensor output towards the baseline level. When no further analyte is detected, the gas sensor switches back to the first operational mode or to an additional operational mode to complete recovery.
    Type: Grant
    Filed: August 26, 2019
    Date of Patent: March 28, 2023
    Assignee: International Business Machines Corporation
    Inventors: Alberto Mannari, Andrea Fasoli, Aminat Adebiyi, Mohammed Abdi, Ronald Robert Labby
  • Publication number: 20220390401
    Abstract: A method of preparing electronically conductive polyaniline that forms a self-supporting dispersion in water is described. The binder-free dispersion was coated on a pair of interdigitated metal electrodes to form a gas sensing layer of a chemical sensor. The chemical sensor utilizes electrochemical impedance spectroscopy (EIS) to detect and characterize a chemical compound in a gaseous state in contact with the sensing layer. Impedance of the sensing layer is measured over a range of alternating current frequencies. The impedance data allows identification and concentration of the chemical compound to be determined when compared to reference impedance data. The analysis of the impedance measurements is adaptable to machine learning.
    Type: Application
    Filed: May 11, 2021
    Publication date: December 8, 2022
    Inventors: Tim Erdmann, Angelo Milone, Linda Karin Sundberg, Siddhartha Das, Ronald R. Labby, Giuseppe Maruccio, Krystelle Lionti, Andrea Fasoli, Luisa Dominica Bozano, Maria S. Chiriacò
  • Patent number: 11499953
    Abstract: Provided is a method and system for extracting features from raw data for machine learning processing. Using an array of gas sensors, raw data for at least one compound of interest are extracted based upon the type of output signals. Where the output signals are amplitude-variant, mean features are extracted by chunking the raw data into slices and calculating the mean area under the curve. Where the output signals are amplitude-and-time-variant, mean-plus-slope features are extracted by taking logarithmic values of the raw data and calculating the mean area under the curve.
    Type: Grant
    Filed: December 9, 2019
    Date of Patent: November 15, 2022
    Assignee: International Business Machines Corporation
    Inventors: Aminat Adebiyi, Mohammed Abdi, Andrea Fasoli, Alberto Mannari, Luisa Bozano
  • Publication number: 20220130491
    Abstract: Volatile organic compounds classification by receiving test data associated with detecting volatile organic compounds (VOCs), analyzing the test data according to a set of data features associated with known VOCs, determining a match between each feature of the test data and a corresponding feature of the set of data features, yielding a set of matches, defining a first degree of anomaly for the test data according to the set of matches, and classifying the test data according to the first degree of anomaly.
    Type: Application
    Filed: October 26, 2020
    Publication date: April 28, 2022
    Inventors: Vito Paolo Pastore, Simone Bianco, Nimrod Megiddo, Andrea Fasoli, Aminat Adebiyi, Mohammed Abdi, Alberto Mannari, Luisa Dominica Bozano
  • Publication number: 20220091060
    Abstract: A method of identifying a gas is provided. The method includes providing a gas sensor device comprising at least two stacked metal oxide layers, wherein a change in conductance of the gas sensor device in a presence of a gas varies with a temperature of the stacked metal oxide layers. The method includes bringing the gas into proximity with the stacked metal oxide layers. The method also includes measuring the conductance of the gas sensor device when the gas is in proximity with the stacked layers at multiple temperatures to generate a temperature-conductance profile. The method also includes identifying a gas of interest based on the temperature-conductance profile.
    Type: Application
    Filed: September 24, 2020
    Publication date: March 24, 2022
    Inventor: Andrea Fasoli
  • Publication number: 20220018822
    Abstract: A small-sized, portable enclosure protects a gas sensor against degradation due to environmental exposure and changes in atmospheric conditions. The protective enclosure includes an inlet for introduction of a gas into the enclosure, an outlet for release of the gas upon completion of a sensing run, and a number of in-line filters that remove from the inflowing gas sample analytes, contaminants, and other materials that can compromise the integrity of the sensor or cause the sensor to degrade over time. The enclosure does not include any filters during the measurement phase of the sensing run in order to allow the gas sensor to accurately measure an unmodified gas mixture and/or analyte.
    Type: Application
    Filed: July 17, 2020
    Publication date: January 20, 2022
    Inventors: Thomas Geoffrey Pattison, Tom Van der Pol, Linda Karin Sundberg, Krystelle Lionti, Andrea Fasoli, Luisa Dominica Bozano
  • Patent number: 11221318
    Abstract: Provided is a system for detection and discrimination of gases, such as volatile organic compounds (VOCs), in a sample comprising two chambers, a first chamber equipped with a crystalline microporous material (CMM) and a second chamber equipped with a gas detector. A gas sample is introduced first into the second chamber for detection by the gas detector and is then re-routed to the first chamber for adsorption/desorption on the CMM. The gas detector in the second chamber produces electronic signals that correspond to the adsorption/desorption profile for the gas, which allows for discrimination of the gas in the sample from other possible gas samples.
    Type: Grant
    Filed: July 24, 2019
    Date of Patent: January 11, 2022
    Assignee: International Business Machines Corporation
    Inventors: Siddhartha Das, Andrea Fasoli, Luisa Dominica Bozano
  • Publication number: 20210172919
    Abstract: Provided is a method and system for extracting features from raw data for machine learning processing. Using an array of gas sensors, raw data for at least one compound of interest are extracted based upon the type of output signals. Where the output signals are amplitude-variant, mean features are extracted by chunking the raw data into slices and calculating the mean area under the curve. Where the output signals are amplitude-and-time-variant, mean-plus-slope features are extracted by taking logarithmic values of the raw data and calculating the mean area under the curve.
    Type: Application
    Filed: December 9, 2019
    Publication date: June 10, 2021
    Inventors: Aminat Adebiyi, Mohammed Abdi, Andrea Fasoli, Alberto Mannari, Luisa Bozano