Abstract:
A computer-implemented pre-processed time-delay autoencoder based anomaly detection method are provided for detecting anomalous states of machines arranged in a factory automation (FA) system or a manufacturing production line. The method includes acquiring source signals from the machines via an interface performing a data pre-processing process for the acquired source signals by normalizing value ranges of the acquired source signals and filtering undesired features from the acquired source signals performing a time-delayed data reform process for the pre-processed source signals based on a time-delay window to generate pre-processed time-delay data submitting pre-processed time-delay testing data to a pre-processed time- delayed autoencoder (Prep-TDAE) neural network, wherein the pre-processed time-delay testing data are collected online while the machines are operated, wherein the Prep-TDAE neural network has been pre-trained by using the pre-processed time-delay training data detecting, if an anomaly state is encountered with respect to the machines, by computing anomaly scores of the pre-processed time-delay testing data, and determining, when the anomaly state is detected, anomaly occurrence time, duration and severity with respect to the anomaly state of each of the machines.
Abstract:
Systems and methods for a communication system including a set of transmitters, wherein operations of the set of transmitters are synchronized with an accuracy bound by a synchronization error. A controller communicatively connected to each transmitter in the set of transmitters, wherein the controller is configured to: determine a tap delay for a communication channel between a receiver and each transmitter in the set of transmitters to produce a set of tap delays. Determine a minimal length of a cyclic prefix as a function of a sum of the synchronization error and a maximal tap delay in the set of tap delays. Finally, controls at least some transmitters in the set of transmitters to transmit a message to the receiver using a cyclic delay diversity (CDD) with the cyclic prefix having at least the minimal length.
Abstract:
A method decodes a block of data received over a communication channel. The method determines an initial estimate of bits in the block using a QR decomposition (QRD-M) method decoding the bits in the block sequentially by reducing an accumulated distance between the initial estimate and the bits of the block. Then, the method determines the block using a likelihood ascent (LAS) method that iteratively updates the bits of the block starting from the initial estimate.
Abstract:
An anomaly detector for detecting anomaly in input data comprises an auto-encoder trained to encode the input data and decode the encoded input data to reconstruct the input data. Further, the anomaly detector comprises a classifier trained to determine a reconstruction loss indicative of a difference between the accepted input data and the reconstructed input data, where the reconstruction loss includes a weighted combination of a plurality of loss functions evaluating reconstruction losses of a plurality of parts of the reconstructed input data, different types of loss functions, or both. The classifier is further configured to detect an anomaly in the reconstructed input data when the reconstruction loss is above a threshold.
Abstract:
A traffic control system for controlling traffic at interconnected intersections is provided, where the system comprises a receiver that receives traffic data that indicates states of vehicles approaching an intersection of the interconnected intersections and directions of the vehicles exiting the intersection. Further, the system comprises a processor that determines intersection crossing times and velocities of vehicles approaching the intersection by minimizing at least one of a total travel time or a maximum travel time of the vehicles for crossing the intersection. The contribution of each vehicle of the vehicles approaching the intersection in the at least one of a total travel time or a maximum travel time is weighted based on directions of the vehicles and traffic at next intersection. Further, the system comprises a transmitter that transmits the intersection crossing times and velocities to the vehicles exiting the intersection for controlling the traffic at the interconnected intersections.
Abstract:
A system jointly controls vehicles according to traffic configuration of a zone of intersection of a first road and a second road. The intersection zone includes a sequencing zone and a control zone covering sections of the first and the second road in proximity to the intersection. The system groups vehicles traveling within the sequencing zone on the first and the second roads into a set of groups of the vehicles and prevents the vehicles of different groups to travel concurrently in the control zone such that the first vehicle of the following group cannot pass the last vehicle of the preceding group. The system determines motion trajectories for the vehicles of the same group traveling in the control zone on the first and the second roads to pass the intersection and transmits the motion trajectories to the corresponding vehicles.
Abstract:
A method assigns backhaul links in a cooperative wireless network including a control unit (CU) connected to a set of access points (APs) by a set of backhaul links, and wherein the APs are connected to an end user by wireless channels. A reliability of each backhaul link is determined to produce a set of reliabilities. A distance between each AP and the end user is determined to produce a set of distances. Using the set of reliabilities and the set of distances, probabilities of successful reception of a message transmitted from the CU to the end user via the backhaul links and the wireless channels are determined. Then, the backhaul links are assigned according to the probabilities of successful reception of the message by the end user.
Abstract:
A probabilistic system for tracking a state of a vehicle using unsynchronized cooperation of information includes a probabilistic multi-head measurement model relating incoming measurements with the state of the vehicle. The first head of the model relates measurements of the satellite signals subject to measurement noise with a belief on the state of the vehicle, and a second head relates an estimation of the state of the vehicle subject to estimation noise with the belief on the state of the vehicle. A probabilistic filter of the system updates recursively the belief on the state of the vehicle based on the multi-head measurement model accepting one or a combination of the measurements of the satellite signals subject to the measurement noise and the estimation of the state of the vehicle subject to the estimation noise.
Abstract:
A server jointly tracks states of multiple vehicles using measurements of satellite signals received at each vehicle and parameters of the probabilistic distribution of the state of each vehicle. The server fuse states and measurements into an augmented state of the multiple vehicles and an augmented measurement of the augmented state subject to augmented measurement noise defined by a non-diagonal covariance matrix with non-zero off-diagonal elements, each non-zero off-diagonal elements relating errors in the measurements of a pair of corresponding vehicles. The server executes a probabilistic filter updating the augmented state and fuses the state of at least some of the multiple vehicles with a corresponding portion of the updated augmented state.
Abstract:
A method for decoding a symbol transmitted over a millimeter wave (mmWave) channel estimates channel state information (CSI) of the mmWave channel using a Bayesian inference on a test symbol according to a probabilistic model of the mmWave channel including statistics on paths and spread of mmWaves propagating in the mmWave channel and decodes a symbol received over the mmWave channel using the CSI.