Abstract: In one embodiment, a service in a network samples application traffic throughputs for a set of applications present in a network. The service generates a throughput model based on the sampled application throughputs for the set of applications. The service performs anomaly detection on wireless throughput measurements from the network by comparing the wireless throughput measurements to the generated throughput model. The service sends an anomaly detection notification based on a determination that the wireless throughput measurements from the network are anomalous.

Abstract: Embodiments herein describe segmenting a Wi-Fi network into different groups. The embodiments herein assign a user, a client device, or a traffic flow originating from a client device to a group. For example, all the client devices for a particular user can be assigned to the same group tag, or each traffic flow in the client device may be assigned to different groups. Each group corresponds to a group key which can be transmitted to the client device when the device associates to an access point (AP). As such, within the same service set identifier (SSID), there can be multiple groups, and thus, client devices can use different group keys to communicate with other client devices associated to the same SSID. Put differently, rather than all devices connected the same SSID being assigned to the same group, the client devices can be assigned in different groups.

Abstract: In one embodiment, a method includes identifying a face, of a meeting attendee pointing to a display screen, in a first two-dimensional image from a two-dimensional video, determining at least one dimension of the face in the first two-dimensional image, defining a rectangle in the first two-dimensional image, at least one first dimension of the rectangle being a function of the at least one dimension of the face, searching for an image of a pointing indicator in the rectangle resulting in finding the pointing indicator at a first position in the rectangle, and calculating a cursor position of a cursor on the display screen based on the first position. Related apparatus and methods are also described.

Abstract: Modulated radio frequency (RF) packets are received from a wireless device, and converted to modulated baseband packets. Baseband parameters are derived from the modulated baseband packets. A baseband profile including the baseband parameters is created for the wireless device. A database including baseband profiles of wireless devices is accessed. The baseband profiles are classified under known device types based on baseband parameters included in the baseband profiles. The baseband parameters of the baseband profile are compared to corresponding baseband parameters of the baseband profiles in the database. If the comparing indicates a match between the baseband profile and one of the baseband profiles, the wireless device is classified under the known device type of the one of the baseband profiles, and the baseband profile is stored in the database under the known device type.

Abstract: Various implementations disclosed herein provide a search engine that receives a search request from a sensor gateway, and provides search results in return. In various implementations, the search request includes a first set of measurements captured by a first sensor, a first measurement from the first set of measurements is outside a defined range. In various implementations, the search engine determines a first feature vector based on the first set of measurements, and identifies a second feature vector that indicates a second set of measurements within a degree of similarity to the first set of measurements. In some implementations, the second set of measurements are captured by a second sensor. In various implementations, the search engine determines a search result based on the second feature vector, and transmits the search result. In some implementations, the search result indicates one or more instructions executable by the first sensor.

Abstract: In one embodiment, a method generally includes a first edge (E) node in a network receiving an encapsulated data packet, wherein the encapsulated data packet comprises an outer header and a data packet, wherein the outer header comprises a first router locator (RLOC) corresponding to the first E node, wherein the data packet comprises an internet protocol (IP) header, and wherein the IP header comprises a destination endpoint identification (EID) corresponding to a host H. The first E node determines whether the host H is attached to the first E node. And in response to the first E node determining the host is attached to the first E node, the first E node forwards the data packet to the host H. The first E node receives a message from another node after the host H detaches from the first E node and reattaches to another E node, wherein the message comprises the destination EID.

Abstract: In one embodiment, a parent device in an unaligned wireless network may determine a superframe comprising a header timeslot followed by a plurality of sub timeslots. The parent device may transmit, to a plurality of child devices in the unaligned wireless network, a beacon during the header timeslot, wherein the beacon comprises i) synchronization information used by the plurality of child devices to synchronize to the header timeslot and ii) reservation information that indicates one or more reserved sub timeslots of the plurality of sub timeslots. The parent device may receive, from a particular child device of the plurality of child devices, a message during a particular sub timeslot of the plurality of sub timeslots that is different than the one or more reserved sub timeslots.

Abstract: Techniques for improved wireless ranging are provided. A first communication from a first device is received at a first access point. A predefined minimum distance is determined for the first access point, where the predefined minimum distance corresponds to a distance at which the vertical location of the first access point causes inaccurate location estimations. A first distance of the first device from the first access point is estimated. Upon determining that the first distance of the first device is below the predefined minimum distance, fine timing measurement (FTM) requests from the first device are declined.

Abstract: A time series system is updated using a data-verification system. The aggregation system may include one or more aggregators. When an upgrade is appropriate, a shadow aggregator may be added to the set of active aggregators. Metrics are provided from one or more collectors to an active aggregator. The shadow aggregator may receive the metrics intended for a particular aggregator, process the metric, and then pass the metric to the intended aggregator for processing. After a period of time, the shadow aggregator data is verified against the intended aggregator data. If the shadow aggregator data is verified, the shadow aggregator becomes an active aggregator and processes data as normal.

Abstract: A method comprises obtaining, from a client device, a first set of application authentication credentials formatted in accordance with a first authentication protocol. The first set of application authentication credentials corresponds to a first user profile. The method includes translating the first set of application authentication credentials to a second set of application authentication credentials. The second set of application authentication credentials is formatted in accordance with a second authentication protocol different from the first authentication protocol and corresponds to the first user profile. The method includes providing the second set of application authentication credentials to an application authentication system. The method includes, in response to providing the second set of application authentication credentials to the application authentication system, obtaining, from the application authentication system, an application authentication indicator.

Abstract: The disclosure provides a secure and scalable approach for (a) exchanging, between a first network and a second network, provisioning requirements of a user device, (b) executing a smart contract that includes the provisioning requirements, and (c) connecting the user device to one of the networks. The method comprises connecting the user device to a first network, and connecting the first and second networks through a scalable blockchain network. The method further comprises sending a smart contract, by the first network to the second network, through the blockchain network. The second network either accepts or rejects the contract. If the second network accepts, then the user device connects to the second network and the second network provides network services to the user device. The provided network services comply with the conditions or parameters of the smart contract.

Abstract: A driver circuit for a Mach-Zehnder modulator is provided that includes a first driver having an input to receive one of an input data or input data complement, and an output to be coupled to a first application voltage node associated with a first arm of a Mach-Zehnder modulator. The driver circuit includes a second driver having an input to receive the other of the input data complement or input data, and an output to be coupled to a second application voltage node associated with the first arm of the Mach-Zehnder modulator. The first driver and the second driver differentially drive the first and second application voltage nodes associated with the first arm of the Mach-Zehnder modulator to result in a voltage swing associated with a voltage applied to the first arm that is twice the supply voltage.

Abstract: A secure Simultaneous Authentication of Equals (SAE) anti-clogging mechanism may be provided. A public key of an access point may be provided from the access point to a client attempting to connect with a network via the access point. The access point may receive from the client a first anti-clogging token and a public key of the client. The first anti-clogging token may be generated by the first client using a shared secret based on a private key of the client and the public key of the access point and a multiplier. The access point may generate a second anti-clogging token using a shared secret based on a private key of the access point and the public key of the client and the multiplier. The access point may then verify the first anti-clogging token and the second anti-clogging token match to authenticate the client.

Abstract: The aspects ensure redundancy by including at least two access points (APs), in an environment, that are capable of serving at least one station (STA). A first AP functions as a primary AP and a second AP functions as a secondary AP. The primary AP can send a layer 2 (L2) control message, for example, a Target Wait Time (TWT) response, to a STA. The primary AP may then wait for an indication (e.g., an Acknowledgement (ACK) signal) of receipt of the L2 control message. The primary AP can also provide the L2 control message to the secondary AP that covers the same room. In at least some configurations, the L2 control message includes metadata about when the secondary AP is to send the copy of the L2 control message over the air. The secondary AP can then relay the L2 control message to the STA.

Abstract: Orthogonal frequency-division multiplexing (OFDM) equalization using a Deep Neural Network (DNN) may be provided. First, a signal in a packet structure may be received at an OFDM receiver from an OFDM transmitter. The signal may have distortion. Training constellation points, pilot constellation points, and data constellation points may be extracted from the signal based on the packet structure. Each data constellation point may correspond to a data subcarrier within a data symbol of the signal. Next, the training constellation points and the pilot constellation may be provided as input for the data symbol to a DNN. A coefficient for each data subcarrier within the data symbol that reverses the distortion may be received as output from the DNN. Then, the coefficient for each data subcarrier may be applied to the corresponding data constellation point to determine a per subcarrier constellation point prediction.

Abstract: The present disclosure discloses a distributed system. The distributed system includes a plurality of radio heads and a plurality of controllers disposed in one or more chassis external to the plurality of radio heads. Each of the plurality of controllers includes a baseband unit (BBU), an uplink time-division multiplexing (TDM) switch and a downlink TDM switch. The uplink TDM switch and the downlink TDM switch forward data bits between a radio head and a BBU by using TDM cells which may reduce latency relative to using Ethernet frames.

Abstract: In one implementation, the method comprises, in response to obtaining a request to associate an electronic device with the one or more WLAN termination nodes: generating, between a base station and a networking device, a control link based on a first identifier associated with the base station; generating, between the networking device and a first WLAN termination node, a control link based on a second identifier that corresponds to a pseudonym for the base station; and associating the first and second identifiers in a control table. The method further comprises: instantiating, between the base station and the networking device, a first data tunnel associated with a first tunneling protocol; instantiating, between the networking device and the first WLAN termination node, a second data tunnel associated with a second tunneling protocol; and associating the first and second data tunnels.

Abstract: Presented herein is an exemplified system and method that provides visibility, for traffic analytics, into secured encapsulated packet (e.g., secure VXLAN-GPE packet, a secure metadata-GPE packet or other GPE standards). The exemplified system and method facilitate encryption of traffic in a granular manner that also facilitate the monitoring of said secure traffic in a fabric network in an end-to-end manner throughout the network. Such monitoring can be beneficially used for analytics, performance analysis, and network debugging/troubleshooting.

Abstract: Presented herein are techniques for automatically generating object segmentation training data. In particular, a segmentation data generation system is configured to obtain training images derived from a scene captured by one or more image capture devices. Each training image is a still image that includes a foreground object and a background. The segmentation data generation system automatically generates a mask of the training image to delineate the object from the background and, based on the mask automatically generates a masked image. The masked image includes only the object present in the training image. The segmentation data generation system composites the masked image with an image of an environmental scene to generate a composite image that includes the masked image and the environmental scene.

Abstract: A method of measuring lengths of optical fibers on forward and return paths is provided in order to synchronize clocks of optical nodes connected by asymmetrical optical fiber paths. The method includes calculating, by a first optical network device, a first propagation delay of a first optical signal transmitted at a first wavelength on a first optical fiber to the first optical network device from a second optical network device and a second propagation delay of a second optical signal transmitted at a second wavelength on the first optical fiber to the first optical network device from the second optical network device. The second wavelength is different from the first wavelength. The method further includes determining, by the first optical network device, a first length of the first optical fiber based on the first propagation delay and the second propagation delay.