Aspinity, Inc.

West Virginia University

Other

Brandon David Rumberg

David W Graham

Michael Fuhrman

Steven Andryzcik

Matthew A Zeleznik

Brandon Michael Kelly

Madhumita Harish

Thomas Doyle

Vinod Kulathumani

Glen Edward Clark

Lorenzo Ponzanelli

Matthew Zeleznik

Nicolas Steven Miller

According to some embodiments, a sound sensor is located in an automotive vehicle cabin. A processor coupled to the sound sensor is configured to receive an acoustic signal sensed by the sound sensor and automatically determine a vehicle event that occurred based on an analysis of the acoustic signal. The determined vehicle event may be, for example, associated with an impact to the vehicle and/or vandalism monitoring while the vehicle is parked. In some embodiments, the processor automatically triggers a vehicle action responsive to the determined vehicle event. The acoustic signal may be analyzed through linear signal processing techniques and/or machine learning performed via analog processing.

Vehicle in-cabin audio detection of vandalism

Provided is an analog-based machine learning apparatus and method that enables low-power sensing and smarter determinations on a vehicle. As an example, the method may include storing a machine learning model and configuration data for an analog processor in a storage device of a digital processor in a vehicle, receiving, via the analog processor, sensor data from one or more hardware sensors that are communicably coupled to the analog processor, extracting features from the sensor data, determining an event that occurred based on the configuration data and execution of a machine learning model on the extracted features of the sensor data, and storing an identifier of the event in the storage device.

Low-power analog vehicle monitoring system

According to some embodiments, re-programmable and/or reconfigurable analog circuitry may be provided. An image interpreter (e.g., a Micro Control Unit ('MCU')) may be configured to receive and store an image, generated for a particular application, to facilitate variation trimming of the re-programmable and/or reconfigurable analog circuitry. The variation trimming may, for example, be performed during production of the re-programmable and/or reconfigurable analog circuitry or post-production of circuitry, in the field, after the circuitry is provided to a customer.

Variation trimming for re-programmable and/or reconfigurable analog circuitry

According to some embodiments, re-programmable and/or reconfigurable analog circuitry monitor an acoustic signal sensed by a sound sensor and selectively generates a tone detection signal in response to an analysis of the acoustic signal and a defined tone detection condition. The tone detection condition may be, for example, associated with presence of at least one pre-determined tone frequency. A digital Microcontroller Unit ('MCU'), coupled to the analog circuitry, may receive the tone detection signal as an interrupt causing the MCU to wake-up, generate a digital timestamp, and/or analyze a series of digital timestamps to detect at least one temporal audio alarm pattern, such as a temporal-three (“T3”) or a temporal-four (“T4”) audio alarm pattern.

Audio tone detection using analog processing

Motion detection in a video signal stream representing a series of rows in one or more image frames includes filtering the video signal stream for one or more features, generating a plurality of masked video signal streams by multiplying the feature video signal stream with a plurality of mask signal streams, which correspond to an image mask region within one or more image frames, determining a value of an intensity-based parameter of the feature in the plurality of mask signal streams, and determining a change in the value of the intensity-based parameter to detect motion over image frames.

Motion detection based on analog video stream

According to some embodiments, re-programmable and/or reconfigurable analog circuitry may be provided. A plurality of reference floating-gate transistors are each programmable to be connectable to a plurality of global reference control lines of the analog circuitry to facilitate temperature compensation. In some embodiments, the plurality of analog nonvolatile memory cells are associated with parameter floating-gate transistors. Moreover, the plurality of analog parameter nonvolatile memory cells may be programmed to several orders of parameter magnitude.

Multi-range temperature compensation for programmable circuit elements

According to some embodiments, a memory controller may be provided. A compute-in-memory array may be connected to a plurality of word lines of the memory controller, with multiple word lines per word being associated with different temperature coefficients, to facilitate temperature compensation of the compute-in-memory array. In some embodiments, the compute-in-memory array may be associated with parameter floating-gate transistors. Moreover, a plurality of compute-in-memory arrays may be individually programmed to several orders of parameter magnitude.

Compute-in-memory array multi-range temperature compensation

According to some embodiments, an analog processing portion may receive an audio signal from a microphone. The analog processing portion may then convert the audio signal into sub-band signals and estimate an energy statistic value, such as a Signal-to-Noise Ratio ('SNR') value, for each sub-band signal. A classification element may classify the estimated energy statistic values with analog processing such that a wakeup signal is generated when voice activity is detected. The wakeup signal may be associated with, for example, a battery-powered, always-listening audio application.

Analog voice activity detection

According to some embodiments, a sensor network may be provided with re-programmable and/or reconfigurable analog circuitry configured to monitor data collected by the sensor network. The re-programmable and/or reconfigurable analog circuitry may also generate a wakeup signal in response to a defined wakeup event detected by the sensor network.

Selective wakeup of digital sensing and processing systems using reconfigurable analog circuits

Aspects of a low power memory buffer are described. In one embodiment, a sampling rate of a signal is adjusted to identify extrema of a signal. An extrema pulse is generated and, in response to the extrema pulse, a time segment and potential value of the signal are stored in a memory. In other aspects, rising and falling slopes of the signal are tracked to identify a local maximum and a local minimum of the signal. In this scenario, an extrema pulse is generated for each of the local maximum and minimum, and time segment and potential values are stored for the local maximum and minimum. Generally, the storage of analog values of the signal at an adjusted sampling rate is achieved with low power, and the signal may be reconstructed at a later time.

Compressed sampling and memory

Aspects of a continuous-time memory cell circuit are described. In various embodiments, the memory cell circuit may comprise a memory cell, a current source coupled to the memory cell, and circuitry for programming the memory cell at an adaptive rate, based on a target voltage for programming, using a feedback loop between a gate terminal of the memory cell and a reference control input. Based on the circuitry for programming, the memory cell may be programmed according to various voltage and/or current references, by linear injection and/or tunneling mechanisms. According to various aspects, the circuitry for programming drives a memory cell to converge to a voltage target for programming within a short period of time and to a suitable level of accuracy.

Growing community of inventors

Morgantown, WV, United States of America

Brandon David Rumberg