DETECTING ANOMALOUS EVENTS IN A DISCRIMINATOR OF AN EMBEDDED DEVICE

    公开(公告)号:US20220138506A1

    公开(公告)日:2022-05-05

    申请号:US17089193

    申请日:2020-11-04

    Abstract: In an embodiment, an apparatus includes: a sensor to sense real world information; a digitizer coupled to the sensor to digitize the real world information into digitized information; a signal processor coupled to the digitizer to process the digitized information into an image; a discriminator coupled to the signal processor to determine, based at least in part on the image, whether the real world information comprises an anomaly, where the discriminator is trained via a generative adversarial network; and a controller coupled to the discriminator.

    Angle of arrival using machine learning

    公开(公告)号:US11415657B2

    公开(公告)日:2022-08-16

    申请号:US16587221

    申请日:2019-09-30

    Abstract: A system and method of determining the angle of arrival or departure using a neural network is disclosed. The system collects a plurality of I and Q samples as a packet containing a constant tone extension is being received. The I and Q samples are used to form I and Q arrays, which are used as the input to the neural network. The neural network produces a first output representative of the azimuth angle and a second output representative of the elevation angle. In certain embodiments, the neural network is capable of detecting a plurality of angles, where, for each angle, there are three outputs, a first output representative of the azimuth angle, a second output representative of the elevation angle and a third output representative of the relative amplitude. In some embodiments, the neural network is configured to determine the carrier frequency offset of an incoming signal as well.

    End node spectrogram compression for machine learning speech recognition

    公开(公告)号:US11227614B2

    公开(公告)日:2022-01-18

    申请号:US16898806

    申请日:2020-06-11

    Abstract: A system and method of recording and transmitting compressed audio signals over a network is disclosed. The end node device first converts the audio signal to a spectrogram, which is commonly used by machine learning algorithms to perform speech recognition. The end node device then compresses the spectrogram prior to transmission. In certain embodiments, the compression is performed using Discrete Cosine Transforms (DCT). Furthermore, in some embodiments, the DCT is performed on the difference between two columns of the spectrogram. Further, in some embodiments, a function that replaces values below a predetermined threshold with zeroes in the Encoded Spectrogram is utilized. These functions may be performed in hardware or software.

    System, apparatus and method for performing antenna diversity selection based on multi-symbol correlations

    公开(公告)号:US10911129B1

    公开(公告)日:2021-02-02

    申请号:US16711824

    申请日:2019-12-12

    Abstract: In one embodiment, an apparatus includes: an antenna switch to receive a first radio frequency (RF) signal from a first antenna and a second RF signal from a second antenna and controllable to output a selected one of the first and second RF signals; an RF circuit to receive and process the first and second RF signals; at least one mixer to downconvert the first and second RF signals to first and second baseband signals; and an antenna diversity control circuit to receive sub-symbol portions of a first plurality of symbols of the first baseband signal and sub-symbol portions of a second plurality of symbols of the second baseband signal, and control the antenna switch to output one of the first and second RF signals, based at least in part on one or more of the sub-symbol portions of the first and second pluralities of symbols.

    Optimization For Angle Of Arrival And Angle Of Departure Detection

    公开(公告)号:US20200309891A1

    公开(公告)日:2020-10-01

    申请号:US16364482

    申请日:2019-03-26

    Abstract: An optimized system and method for determining an angle of arrival or angle of departure is disclosed. A coarse pre-search is performed to identify the general location of the incoming signal. Based on this information, a high-resolution search is performed at the general location identified in the coarse pre-search. This multi-stage approach significantly reduces the number of computations that must be performed by the device, and also reduces the amount of memory that is required to store the results of the computations. For example, a full scan may require the computations to be performed over 32,000 times. Through use of this approach, the number of computations may be reduced by over 97%. This is a similar reduction in computation time and in the amount of memory consumed by this method.

    Angle of arrival carrier frequency offset correction

    公开(公告)号:US10700901B1

    公开(公告)日:2020-06-30

    申请号:US16587248

    申请日:2019-09-30

    Abstract: A system and method for detecting and compensating for carrier frequency offset is disclosed. This system compensates for CFO and calculates a corrected phase. This corrected phase may be used by, for example, an AoX algorithm, such as MUSIC, to more accurately determine the angle of arrival or angle of departure of a signal. In certain embodiments, the system oversamples the incoming signal to create a plurality of samples. The system then determines the phase of each of the plurality of samples and calculates the carrier frequency based on the time derivative of the phase. In certain embodiments, a particular portion of an incoming packet is used to determine the carrier frequency offset. In other embodiments, the system calculates the carrier frequency offset throughout an entirety of the incoming packet. Once the carrier frequency offset is determined, it can be used to adjust the received signals. These adjusted signals are then used to determine the angle of arrival or angle of departure.

Patent Agency Ranking