A method or system is disclosed to assess transmission errors in a visual media input. Domain knowledge is obtained from the visual media input by content analysis, codec analysis, distortion analysis, and human visual system modeling. The visual media input is divided into partitions, which are passed into deep neural networks (DNNs). The DNN outputs of all partitions are combined with the guidance of domain knowledge to produce an assessment of the transmission error. In one or more illustrative examples, transmission error assessment at a plurality of monitoring points in a visual media communication system is collected and assessed, followed by quality control processes and statistical performance assessment on the stability of the visual communication system.

A UART includes a transmission register, a receive register, a virtual remappable pin, a parity error check circuit to evaluate contents of the receive register for a parity error, and control logic to determine contents of the transmission register. The contents include underlying data and a parity bit based thereupon. The control logic is to route the contents through the first virtual remappable pin to the receive register. The control logic is to, before reception of the entire contents at the receive register, cause modified contents to be provided to the receive register. The modified contents are to cause a parity error. The modified contents are to include different underlying data or a different parity bit than the contents of the transmission register. The control logic is to determine whether the parity error check circuit detected the parity error.

Methods, systems, and devices for wireless communications are described. A first device may receive one or more signals from a second device. The first device may estimate one or more metrics associated with noise of the one or more signals. The first device may transmit, to the second device and based on the estimating, a report indicating the one or more metrics. The first device may receive a message indicating a multi-level coding scheme from the second device. The multi-level coding scheme may be based on the one or more metrics and may indicate a partitioning configuration of the multi-level coding scheme for communications between the first device and the second device. The first device may communicate with the second device using the partitioning configuration of the multi-level coding scheme.

Systems, methods, and computer-readable media are provided for generating a unique ID for a sensor in a network. Once the sensor is installed on a component of the network, the sensor can send attributes of the sensor to a control server of the network. The attributes of the sensor can include at least one unique identifier of the sensor or the host component of the sensor. The control server can determine a hash value using a one-way hash function and a secret key, send the hash value to the sensor, and designate the hash value as a sensor ID of the sensor. In response to receiving the sensor ID, the sensor can incorporate the sensor ID in subsequent communication messages. Other components of the network can verify the validity of the sensor using a hash of the at least one unique identifier of the sensor and the secret key.

A method includes moving one or more transmit facility or transmit facilities attached to a first component with regard to at least two receive facilities attached at a fixed position to the second component; and at least one of registering a respective error if an error condition exists for the respective receive facility or modifying an operation of an apparatus comprising the first and a second component if the error condition exists for the respective receive facility, the error condition for the respective receive facility depends on location information relating to at least one of the position of the first component with regard to the second component or orientation of the first component with regard to the second component, and/or at least one of a measure for a receive quality of the signals or data packets received from the transmit facility or from at least one of the transmit facilities.

Techniques for testing a networked system using simulated abnormal node failure are disclosed. In some embodiments, a computer system performs operations comprising: repeatedly transmitting simulated requests to a networked system on which a software application is implemented using a plurality of nodes, the networked system being configured to respond to the simulated requests using the plurality of nodes; randomly selecting one or more nodes from the plurality of nodes; terminating the randomly selected one or more nodes; restarting the terminated randomly selected one or more nodes; repeating the randomly selecting one or more nodes, the terminating the randomly selected one or more nodes, and the restarting the terminated randomly selected one or more nodes until each one of the plurality of nodes has been terminated and restarted at least once during the first period of time; and determining response times of the networked system in responding to the simulated requests.

A system for load-testing a cloud radio access network (C-RAN) is provided. The system includes at least one radio point (RP), each being configured to exchange radio frequency (RF) signals with at least one user equipment (UE). The system also includes a baseband controller communicatively coupled to the at least one RP via a front-haul ETHERNET network. The front-haul ETHERNET network includes at least one switch; and a testing device that is time-synchronized to the baseband controller and the at least one RP. The testing device is configured to receive at least one packet from each of the at least one RP. The testing device is also configured to replicate each of at least some of the received packets to produce a respective replicated packet. The testing device is also configured to transmit at least one replicated packet to the baseband controller.

A system for load-testing a cloud radio access network (C-RAN) is provided. The system includes at least one radio point (RP), each being configured to exchange radio frequency (RF) signals with at least one user equipment (UE). The system also includes a baseband controller communicatively coupled to the at least one RP via a front-haul ETHERNET network. The front-haul ETHERNET network includes at least one switch; and a testing device that is time-synchronized to the baseband controller and the at least one RP. The testing device is configured to receive at least one packet from each of the at least one RP. The testing device is also configured to replicate each of at least some of the received packets to produce a respective replicated packet. The testing device is also configured to transmit at least one replicated packet to the baseband controller.

Some embodiments provide a method for training a machine-trained (MT) network. The method propagates multiple inputs through the MT network to generate an output for each of the inputs. each of the inputs is associated with an expected output, the MT network uses multiple network parameters to process the inputs, and each network parameter of a set of the network parameters is defined during training as a probability distribution across a discrete set of possible values for the network parameter. The method calculates a value of a loss function for the MT network that includes (i) a first term that measures network error based on the expected outputs compared to the generated outputs and (ii) a second term that penalizes divergence of the probability distribution for each network parameter in the set of network parameters from a predefined probability distribution for the network parameter.

Some embodiments provide a method for training a machine-trained (MT) network. The method propagates multiple inputs through the MT network to generate an output for each of the inputs. each of the inputs is associated with an expected output, the MT network uses multiple network parameters to process the inputs, and each network parameter of a set of the network parameters is defined during training as a probability distribution across a discrete set of possible values for the network parameter. The method calculates a value of a loss function for the MT network that includes (i) a first term that measures network error based on the expected outputs compared to the generated outputs and (ii) a second term that penalizes divergence of the probability distribution for each network parameter in the set of network parameters from a predefined probability distribution for the network parameter.