Arris Enterprises LLC

Cogniac, Corp.

Other

Ruckus Wireless, Inc.

Sandip C Patel

Steve A Martin

William S Kish

Huayan Wang

David Sheldon Stephenson

Shailender Potharaju

Doron Givoni

Henry H Tzeng

Ron Mok

Sudhakar Padala

Stuart Kerry

Yui Ming Tsang

Victor Shtrom

Wenge Ren

Ilango Purushothaman

Steve Martin

An electronic device may determine whether a machine-learning model is operating within predefined limits. In particular, the electronic device may receive, from another electronic device, instructions for the machine-learning model, a reference input and a predetermined output of the machine-learning model for the reference input. Note that the instructions may include an architecture of the machine-learning model, weights associated with the machine-learning model and/or a set of pre-processing transformations for use when executing the machine-learning model on images. In response, the electronic device may configure the machine-learning model based on the instructions. Then, the electronic device may calculate an output of the machine-learning model for the reference input. Next, the electronic device may determine whether the machine-learning model is operating within predefined limits based on the output and the predetermined output.

Operating machine-learning models on different platforms

An electronic device that transmits traffic in a wireless network is described. During operation, the electronic device transmits, using a first transceiver, a first type of traffic in a shared frequency band that is unlicensed. Then, the first transceiver reserves time for transmitting a second type of traffic in the shared frequency band. The reserved time may be determined in response to a request to reserve the time from a second transceiver in the electronic device transmitting the second type of traffic in the shared frequency band. Next, the first transceiver permits, in the reserved time, transmission by the second transceiver of the second type of traffic in the shared frequency band. Furthermore, the first transceiver prevents transmission of the first type of traffic during the reserved time, thereby segregating the first type of traffic from the second type of traffic in the shared frequency band.

Transmitting traffic in a shared frequency bandwidth

During a communication technique, an access point provides a message that includes one or more public land mobile network identifiers of one or more cellular-telephone networks that are supported by the access point. Then, an electronic device, which received the message, provides a candidate list specifying one or more access points that support communication with a cellular telephone network to a radio node that is associated with this cellular-telephone network. By communicating with a wireless-local-area-network (WLAN) controller, the radio node validates the one or more access points, and selects a target access point based on performance feedback from the WLAN controller. Next, the radio node instructs the electronic device to associate with the target access point. Moreover, the radio node and the target access point establish a secure-communication pathway, which allows the radio node to communicate data to the electronic device via the access point using an LTE Wi-Fi aggregation protocol.

Discovery and security in LWA communication

During operation, an electronic device may emulate client functionality associated with a virtual client in a wireless network, where emulating the client functionality includes generating a first frame that is compatible with a wireless communication protocol and is associated with fictious wireless communication with the virtual client. Then, the electronic device may provide, to a computer, a second frame that includes at least a portion of the first frame, where the second frame is compatible with a wired communication protocol. Next, the electronic device may receive, from the computer, a response message based at least in part on the first frame, where the response message includes information associated with a service provided by the computer. Moreover, the electronic device may assess the service based at least in part on the information and may selectively perform the remedial action based at least in part on the assessment.

Service validation using emulated virtual clients

A technique for testing wireless-local-area-network (WLAN) infrastructure is described. In particular, a radio-frequency abstraction layer (RFAL) in a physical instance of an electronic device is used to simulate the physical layer communication hardware and radio channels. RFAL allows frames in initial packets that are compatible with a WLAN communication protocol (such as an IEEE 802.11 standard) to be encapsulated in the data-link layer into additional packets that are compatible with a network communication protocol (such as an IEEE 802.3 standard). These additional packets can include information that characterizes transmission of the packet through a simulated radio-frequency environment so that the software stack associated with a physical or virtual instance of an electronic device can be exercised as if the packet had been received over a wireless connection. Then, the additional packets can be communicated via Ethernet (i.e., without radio-frequency communication) among virtual instances of access points, clients and/or WLAN controllers.

WLAN testing using an RF abstraction layer

A computer system may train and use a machine-learning model to quantitatively analyze an image. In particular, the computer system may generate the machine-learning model based on a set of reference images that include content with instances of a quantitative feature attribute and one or more feedback metrics that specify locations of the instances of the quantitative feature attribute in the reference images and numerical values associated with the instances of the quantitative feature attribute. Then, after receiving the image from an electronic device, the computer system may analyze the image using the machine-learning model to perform measurements of one or more additional instances of the quantitative feature attribute in the image. Moreover, the computer system may provide a measurement result for the image, the measurement result including a second numerical value associated with the one or more additional instances of the quantitative feature attribute in the image.

Machine-learning measurements of quantitative feature attributes

An electronic device iteratively determines an optimal transmit antenna radiation pattern and an optimal receive antenna radiation pattern based on a feedback process with a second electronic device. First, the electronic device transmits outgoing messages to the second electronic device using a set of transmit antenna radiation patterns having different transmit spatial orientations. Based on throughput feedback from the second electronic device, the electronic device selects the optimal transmit antenna radiation pattern. Then, based on throughputs for incoming messages from the second electronic device that were received using a set of receive antenna radiation patterns having different receive spatial orientations, the electronic device selects the optimal receive antenna radiation pattern. Note that the transmit antenna radiation pattern and the receive antenna radiation pattern may reduce or eliminate interference between the electronic device and the second electronic device.

Antenna-radiation-pattern selection for reduced interference

In order to determine a sounding interval, an electronic device iteratively revises a set of potential sounding intervals based on transmission statistics associated with communication of some packets with and other packets without transmission beamforming for the set of potential sounding intervals. In particular, the electronic device calculates rank positions for the set of potential sounding intervals based on an estimated throughput and numbers of packets transmitted with transmission beamforming for the set of potential sounding intervals out of a total number of packets transmitted. Then, the electronic device may determine the output sounding interval based on the ranking. When the convergence criterion is achieved, the electronic device may determine a moment based on calculated frequencies of the rank positions over multiple iterations, which is used to revise the set of potential sounding intervals in the next iteration.

Determining a sounding interval based on throughput

An electronic device modifies a schedule of communication frequencies (such as an orthogonal frequency division multiplexing access schedule) by changing the times when subcarriers are used for communication with a set of electronic devices in order to cluster subsets of the set of electronic devices. This clustering may leave the throughput associated with the communication at least approximately unchanged. Then, the electronic device selects, for the subsets, transmit antenna radiation patterns and receive antenna radiation patterns in order to increase the throughputs during transmission and/or receiving.

Growing community of inventors

San Jose, CA, United States of America

Sandip C Patel