Anurag M Ganguli

20190377870, Dec 12, 2019

Jun 11, 2018

16/004571

- Palo Alto CA, US
Alexander Feldman - Santa Cruz CA, US
Bhaskar Saha - Redwood City CA, US
Anurag Ganguli - Milpitas CA, US
Bernard D. Casse - Saratoga CA, US
Johan de Kleer - Los Altos CA, US
Shantanu Rane - Mountain View CA, US
Ion Matei - Sunnyvale CA, US

Palo Alto Research Center Incorporated - Palo Alto CA

G06F 21/55
G06N 99/00

The following relates generally to defense mechanisms and security systems. Broadly, systems and methods are disclosed that detect an anomaly in an Embedded Mission Specific Device (EMSD). Disclosed approaches include a meta-material antenna configured to receive a radio frequency signal from the EMSD, and a central reader configured to receive a signal from the meta-material antenna. The central reader may be configured to: build a finite state machine model of the EMSD based on the signal received from the meta-material antenna; and detect if an anomaly exists in the EMSD based on the built finite state machine model.

20190196892, Jun 27, 2019

Dec 27, 2017

15/855560

- Palo Alto CA, US
Rajinderjeet S. Minhas - Palo Alto CA, US
Johan de Kleer - Los Altos CA, US
Anurag Ganguli - Milpitas CA, US

Palo Alto Research Center Incorporated - Palo Alto CA

G06F 11/07
G06N 99/00
G06N 5/04

Embodiments described herein provide a system for facilitating a training system for a device. During operation, the system determines a system model for the device that can be based on empirical data of the device. The empirical data is obtained based on experiments performed on the device. The system then generates, from the system model, synthetic data that represents behavior of the device under a failure. The system determines uncertainty associated with the synthetic data and, from the uncertainty, determines a set of prediction parameters using an uncertainty quantification model. The system generates training data from the synthetic data based on the set of prediction parameters and learns a set of learned parameters associated with the device by using a machine-learning-based classifier on the training data.

20190146469, May 16, 2019

Nov 16, 2017

15/815528

- Palo Alto CA, US
Rajinderjeet S. Minhas - Palo Alto CA, US
Johan de Kleer - Los Altos CA, US
Anurag Ganguli - Milpitas CA, US

Palo Alto Research Center Incorporated - Palo Alto CA

G05B 23/02
G06F 15/18
G05B 17/02
G06F 11/30
G06F 17/50

Embodiments described herein provide a system for facilitating comprehensive control data for a device. During operation, the system determines one or more properties of the device that can be applied to empirical data of the device. The empirical data can be obtained based on experiments performed on the device. The system applies the one or more properties to the empirical data to obtain derived data and learns an efficient policy for the device based on both empirical and derived data. The efficient policy indicates one or more operations of the device that can reach a target state from an initial state of the device. The system then determines an operation for the device based on the efficient policy.

20190025376, Jan 24, 2019

Jul 18, 2017

15/652973

- Palo Alto CA, US
Anurag Ganguli - Milpitas CA, US
Ajay Raghavan - Mountain View CA, US
Peter Kiesel - Palo Alto CA, US
Kyle Arakaki - Mountain View CA, US
Julian Schwartz - Oakland CA, US

G01R 31/36
H01M 10/0525
H01M 10/42
H01M 10/44
H01G 11/08
H01G 11/06
G01R 15/24

A system detects and/or predicts metal ion plating events of a metal ion energy storage device. The system includes an optical sensor disposed internally within or externally on a metal ion energy storage device wherein the optical sensor has an optical output that changes in response to strain within a metal ion energy storage device. A current sensor senses current through the metal ion energy storage device. Plating detection circuitry measures a wavelength shift in the optical output of the optical sensor and estimates a state of charge (SOC) of the metal ion energy storage device based on the current. An expected wavelength shift is determined from the estimated SOC. A plating event can be detected and/or predicted based on the difference between the expected wavelength shift and the measured wavelength shift.

20180342090, Nov 29, 2018

May 25, 2017

15/605618

- Palo Alto CA, US
Anurag Ganguli - Milpitas CA, US

Palo Alto Research Center Incorporated - Palo Alto CA

G06T 11/20
G06N 99/00
G06K 9/00

One embodiment provides a system for facilitating visualization of input data classifications. The system obtains, from a remote computer system, output data which includes a classification and a score that a corresponding set of input data belongs to one or more classifications. The system computes an objective function based on the score and the input data, and computes a gradient of the objective function based on the input data. In response to determining that the computed gradient is not greater than a predetermined threshold, the system perturbs the input data in a direction of or opposite to the computed gradient, and transmits the perturbed input data to the remote computer system to obtain new output data. The system displays on a device a visualization of whether the input data belongs more or less strongly to a classification.

20180299301, Oct 18, 2018

Apr 14, 2017

15/488021

- Palo Alto CA, US
Kyle Arakaki - Mountain View CA, US
Andreas Schuh - San Francisco CA, US
Alex Hegyi - San Francisco CA, US
Peter Kiesel - Palo Alto CA, US
Anurag Ganguli - Milpitas CA, US

G01D 5/353
G01P 3/36

A monitoring system includes optical sensors disposed on one or more fiber optic waveguides. Each optical sensor is spaced apart from other optical sensors and is disposed at a location along a route defined by a transportation structure that supports a moveable conveyance. The plurality of optical sensors are mechanically coupled to one or both of the transportation structure and the moveable conveyance. Each optical sensor provides an optical output signal responsive to vibrational emissions of one or both of the transportation structure and the conveyance. The monitoring system includes a detector unit configured to convert optical output signals from the optical sensors to electrical signals. A data acquisition controller synchronizes recordation of the electrical signals with movement of the conveyance.

20170026722, Jan 26, 2017

Jul 23, 2015

14/806983

- Palo Alto CA, US
Tse Nga Ng - Palo Alto CA, US
Gregory Whiting - Menlo Park CA, US
Anurag Ganguli - Milpitas CA, US
George Daniel - Palo Alto CA, US

H04Q 9/00
G01M 3/40
H04W 4/00

A sensor network system that includes a sensor array having a plurality of sensor units that include a plurality of sensor elements, each sensor element configured to generate an electrical signal in response to a chemical environment in the vicinity of the sensor unit. The set of electrical signals generated by the sensor elements of the sensor unit represents a measured signature of the environment in the vicinity of the sensor unit. An analyzer is configured to extract the measured signatures of each sensor unit from sensor unit information signals and to detect a presence and concentration of one or more of the gases of interest based on the measured signatures.

20150280290, Oct 1, 2015

Apr 1, 2014

14/242850

- Palo Alto CA, US
Ajay Raghavan - Mountain View CA, US
Peter Kiesel - Palo Alto CA, US
Lars Wilko Sommer - Bretten, DE
Alexander Lochbaum - Landau, DE
Tobias Staudt - Nuernberg, DE
Saroj Kumar Sahu - Fremont CA, US
Anurag Ganguli - Milpitas CA, US

Palo Alto Research Center Incorporated - Palo Alto CA

H01M 10/48
G01R 31/36

A method for determining an operating state (e.g., state-of-charge or state-of-health) and/or generating management (charge/discharge) control information in a system including an electrochemical energy device (EED, e.g., a rechargeable Li-ion battery, supercapacitor or fuel cell) that uses optical sensors to detect the intercalation stage change events occurring in the EED. The externally or internally mounted optical sensors measure operating parameter (e.g., strain and/or temperature) changes of the EED during charge/recharge cycling, and transmit measured parameter data using light signals sent over optical fibers to a detector/converter. A processor then analyzes the measured parameter data, e.g., using a model-based estimation process, to detect intercalation stage changes (i.e., crystalline structure changes caused by migration of guest species, such as Li-ions, between the EED's anode and cathode), and generates the operating state and charge/discharge control information based the analysis.