Abstract: Example implementations relate to mobile virtual private network (mVPN) configuration. For example, a system for mVPN configuration may include a configuration selector to intercept an internet protocol (IP) packet in a mobile virtual private network (mVPN) and select a mVPN configuration for the IP packet using a lookup table. The system may further include a configuration adapter to adapt the IP packet according to the selected mVPN configuration.

Abstract: An example method of operating a network may include determining whether a flow is to be added to the network based on: a flow type of the flow, a link condition of the flow, and for each possible combination of flow type and link condition out of multiple flow types and multiple link conditions, the number of flows currently carried on the network that correspond to the respective combination.

Abstract: Systems and methods are provided for an improved machine learning (ML) model system. The improved ML system can be configured to (1) initially classify the types of images and videos received by the various devices and provide the classified input to different ML models based on the classification (e.g., of the distortion level, etc.), and/or (2) reuse portions (referred to as base components) of each ML model where parameters of the base components are unchanged across the various ML models, while replacing other portions (referred to as adapted components) of the ML model where the parameters of the adapted components may change greatly.

Abstract: A method of adjusting a communication link of a client device of a wireless local area network is described. The method includes monitoring two or more communication links between two or more client devices and a network device in a wireless local area network. The two or more client devices including a first client device and a second client device. The method also includes detecting a degradation in a first communication link between the first client device and the network device. The communication link degradation is not detected in a second communication link between the second client device and the network device. The method further includes determining the degradation in the first communication link is caused at least in part by interference from cellular network communications.

Abstract: An example video analytics device can include a memory, a processor executing instructions stored in the memory, an active region detector to identify a plurality of active regions of a plurality of video streams, wherein the plurality of active regions are sections in the plurality of video streams that change from a first frame to a second frame, and a bin packer communicatively coupled with the processor to combine the plurality of active regions to produce a multi-batch of an individual slice, wherein the multi-batch of the individual slice is a batch including the plurality of active regions that is processed at once.

Abstract: Example method includes receiving, at an access point (AP), a plurality of virtual reality (VR) data from each of a plurality untethered mobile devices associated with a multi-user VR environment, receiving, at the AP, an indication of an atomic data block size for data to be transmitted to one or more of the plurality of untethered mobile devices, reducing, by the AP and based on the indication, a transmission duration of a VR data block to be transmitted to one or more of the plurality of untethered mobile devices.

Abstract: A system described herein provides real-time wireless video delivery using a multi-channel communications link. A method of employing elements of the system includes generating a first set of video data and generating a second set of video data. Further, encoding the first set of video data such that the second set of video data is a higher resolution version of the first set of video data and the encoded first set of video data is to supplement the second set of video data in response to a data drop.

Abstract: Example method includes: transmitting a plurality of probe images from an IoT device at an edge network to a server hosting a target DNN, wherein the plurality of images are injected with a limited amount of noise to probe sensitivities of the target DNN to the red, green, and blue colors; receiving a feedback comprising a plurality of DCT coefficients unique to target DNN from the server hosting the target DNN; computing a plurality of color conversion weights based on the feedback received from the server; converting a set of real-time images from RGB color space to YUV color space using the plurality of color conversion weights unique to the target DNN; compressing the set of real-time images using a quantization table unique to the target DNN by the IoT device; and transmitting the compressed set of real-time images to the server hosting the target DNN for DNN inferences.

Abstract: Embodiments are directed to passive multi-person location tracking utilizing signal polarization. An embodiment of a system includes multiple receivers, including a first receiver at a first location and a second receiver at a second location, each receiver including one or more receiver antennas to receive polarized radio signals; a transmitter located at a third location to transmit polarized radio signals, the transmitter including antennas for a first signal at a first polarization direction and a second signal at a second, different polarization direction; and a processing system to receive channel state information from each receiver, and to track a plurality of individuals utilizing the received channel state information, wherein the tracking of the plurality of individuals is based at least in part on analysis of a polarization parameter and a set of location parameters generated for each of multiple reflection paths based on the channel state information.

Abstract: Embodiments are directed to multi-user virtual reality over wireless networks. An embodiment of a storage medium includes instructions for receiving a request at a network device for a virtual reality (VR) operation, the VR operation to serve VR client devices utilizing a wireless communication network; obtaining statistics regarding the wireless communication network and the VR client devices, the statistics including data transmission rates and data transmission quality; exposing the statistics to a server to assist with optimization of the wireless communication network; and facilitating optimization of the wireless communication network for multi-user VR operation based at least in part on the statistics.

Abstract: This disclosure provides systems through which a wireless access point (AP) can determine the location of a client device with a high degree of accuracy. The AP uses CIR measurements for a plurality of directional beams used to communicate with the client device to determine a respective amplitude of a Line-of-Sight (LOS) path between the AP and the client device for each beam. The AP identifies a high-LOS-amplitude subset of the beams and, based on predefined radiation patterns associated with the beams included in the high-LOS-amplitude subset, determines a direction of the LOS path between the AP and the client device. The AP also determines a Time-of-Flight (ToF) for radio frames exchanged between the AP and the client device via the plurality of directional beams and uses the ToF to determine a distance between the AP and the client device.

Abstract: An example system comprising: a processing resource; and a memory resource storing machine readable instructions executable to cause the processing resource to: receive a Bluetooth Low Energy (BLE) signal transmitted from a user device; generate, from the BLE signal, a BLE moving pattern of the user device, wherein the BLE moving pattern is generated at a different entity than an entity that transmits the BLE signal; track an object carrying the user device via visual information of the object such that a visual moving pattern of the object is generated from the tracking; determine the visual moving pattern matches the BLE moving pattern; and assign, responsive to the determination, an identity obtained from the user device to the object being tracked via the visual information.

Abstract: Example method includes: transmit a plurality of probe images from an Internet of Things (IoT) device at an edge network to a server hosting a target deep neural network (DNN), wherein the plurality of images are injected with a limited amount of noise; receive a feedback comprising a plurality of discrete cosine transform (DCT) coefficients from the server hosting the target DNN, wherein the plurality of DCT coefficients are unique to the target DNN; generate a quantization table based on the feedback received from the server hosting the target DNN; compress a set of real-time images using the generated quantization table by the IoT device at the edge network; and transmit the compressed set of real-time images to the server hosting the target DNN for DNN inferences.

Abstract: Examples include classifying high frequency radio signals. Some examples include receiving a fast Fourier transform (FFT) of a high frequency radio signal, determining a first signal strength at a first guard frequency bin, determining a second signal strength at a second guard frequency bin, and determining a third signal strength at a direct current carrier frequency bin. Examples also include classifying the high frequency radio signal based on the first signal strength, the second signal strength, and the third signal strength.

Abstract: The present invention relates to an air purifier in which vertical rotation and horizontal rotation are performed simultaneously and independently and which has a stable structure.

Abstract: Embodiments are directed to multi-user virtual reality over wireless networks. An embodiment of a storage medium includes instructions for receiving a request at a network device for a virtual reality (VR) operation, the VR operation to serve VR client devices utilizing a wireless communication network; obtaining statistics regarding the wireless communication network and the VR client devices, the statistics including data transmission rates and data transmission quality; exposing the statistics to a server to assist with optimization of the wireless communication network; and facilitating optimization of the wireless communication network for multi-user VR operation based at least in part on the statistics.

Abstract: Example method includes: transmit a plurality of probe images from an Internet of Things (IoT) device at an edge network to a server hosting a target deep neural network (DNN), wherein the plurality of images are injected with a limited amount of noise; receive a feedback comprising a plurality of discrete cosine transform (DCT) coefficients from the server hosting the target DNN, wherein the plurality of DCT coefficients are unique to the target DNN; generate a quantization table based on the feedback received from the server hosting the target DNN; compress a set of real-time images using the generated quantization table by the IoT device at the edge network; and transmit the compressed set of real-time images to the server hosting the target DNN for DNN inferences.

Abstract: Example method includes: transmitting a plurality of probe images from an IoT device at an edge network to a server hosting a target DNN, wherein the plurality of images are injected with a limited amount of noise to probe sensitivities of the target DNN to the red, green, and blue colors; receiving a feedback comprising a plurality of DCT coefficients unique to target DNN from the server hosting the target DNN; computing a plurality of color conversion weights based on the feedback received from the server; converting a set of real-time images from RGB color space to YUV color space using the plurality of color conversion weights unique to the target DNN; compressing the set of real-time images using a quantization table unique to the target DNN by the IoT device; and transmitting the compressed set of real-time images to the server hosting the target DNN for DNN inferences.

Abstract: A computer implemented method for decreasing latency in a billing cycle, the method comprising receiving a first charging data report (CDR) including a sent data volume from a vendor and comparing the first CDR to an operator received data volume and when the first CDR does not match the operator received data volume, rejecting the first charging report. The method further comprising providing a second CDR having the operator received data volume to the vendor, receiving a charging data acceptance including a negotiated data volume from the vendor, constructing a publicly verifiable proof of charging based on the charging data acceptance, and sending the publicly verifiable proof of charging to the vendor.

Abstract: Embodiments are directed to interference-aware link-rate adaptation for wireless communication. An embodiment of a storage medium includes instructions to operations including receiving data regarding wireless signals received by an access point, the access point to provide Wi-Fi communication, the wireless signals being communicated in an unlicensed radio spectrum; performing spectral analysis of the received wireless signals to identify a channel of an LTE (Long-Term Evolution) signal; and upon determining that energy level of the LTE signal is below an energy detection (ED) level and that the channel is a primary Wi-Fi channel for the access point, adapting a link rate for the access point based on channel state information for the channel.