Ball Aerospace & Technologies Corp.

Other

James Michael Shima

Methods and systems for identifying occupied areas of a radio frequency (RF) spectrum, identifying areas within that RF spectrum that are unusable for further transmissions, and identifying areas within that RF spectrum that are occupied but that may nonetheless be available for additional RF transmissions are provided. Implementation of the method then systems can include the use of multiple deep neural networks (DNNs), such as convolutional neural networks (CNN's), that are provided with inputs in the form of RF spectrograms. Embodiments of the present disclosure can be applied to cognitive radios or other configurable communication devices, including but not limited to multiple inputs multiple output (MIMO) devices and 5G communication system devices.

Spectral sensing and allocation using deep machine learning

Systems and method for determining an angle of arrival of a radio frequency (RF) signal are disclosed. A radio frequency receiving system as disclosed herein can include a plurality of antenna or receiving elements formed on a common plane. A spacing between the receiving elements can be arbitrary. In response to receiving a radio frequency signal, a difference in an integer number of wavelengths that have passed and a difference in a phase of the received signal is determined between each of a plurality of pairs of antenna elements. More particularly, a residual error is calculated for each possible difference in the number of integer wavelengths that can occur as the received signal travels to the elements in each pair of elements. A solution with a minimum residual value is taken as the difference in the actual integer number of wavelengths that have been traversed by the received signal. That integer value and the detected phase difference is applied to determine the angle of arrival.

Systems and methods for determining an angle of arrival of a signal at a planar array antenna

Methods and systems for processing a noisy time series input to detect a signal, generate a de-noising mask, and/or output a de-noised time series output are provided. The input is transformed into one or more datagrams, such as real and imaginary time-frequency grams. The datagrams are stacked and provided as first and second channel inputs to a neural network. A neural network is trained to detect signals within the input. Alternatively or in addition, the network is trained to generate a de-noise mask, and/or to output a de-noised time series output. Implementation of the method and systems can include the use of multiple deep neural networks (DNNs), such as convolutional neural networks (CNN's), that are provided with inputs in the form of RF spectrograms. Embodiments of the present disclosure can be applied to various RF devices, such as communication devices, including but not limited to multiple inputs multiple output (MIMO) devices and 5G communication system devices, and RADAR devices.

Weak signal processing systems and methods

Methods and systems for locating a target radio frequency (RF) device within an area are provided. In particular, a signal sent from a known transmitter while that transmitter is at a known location is received by a plurality of receivers located in or around the area. This is repeated multiple times for multiple locations. Representations of the signals received at the receivers for the different locations are provided as inputs to a neural network and are used to train the network. After training, representations of signals received at the receivers as a result of one or more signals emitted from a target transmitter located in or traveling through the area can be provided to the network, which in response provides a location of the target transmitter.

Geolocation determination using deep machine learning

A programmable sound effects device which utilizes a motion-sensitive mechanism for selecting unique sound effects. The device is comprised of an electronic motion-sensitive actuator, a sound effect storage media for storing a plurality of predetermined sound effects, and a playback mechanism for audibly emitting the motion-activated sound effects. This device is designed to be used with amusement and entertainment type products such as toys, games, dolls, and props, with exemplary uses in toy swords, drumsticks, magic wands, and the like. A preferred embodiment is comprised of a unit which is physically incorporated into the handle of a toy sword. As the user moves the toy sword in a predefined manner, the motion-sensitive actuator senses the motion and plays out a plurality of unique sound effects as a function of the user's movements. The motion-detection algorithm which triggers the different sound effects is programmable. In another embodiment, the device is contained within a single housing unit that is worn on the user's body. This embodiment is well suited for many toys, props, games, and the like that do not have any sound effects capability but would benefit from such capability.

Growing community of inventors

Superior, CO, United States of America

James Michael Shima