Abstract: One or more iterations are performed. Each iteration includes calculating, for each of a number of data points that each have a label probability distribution, a label quality measure based on the label probability distribution of the data point. Each iteration includes updating the label probability distribution of each of at least one of the data points using either or both of a classification technique and a constrained clustering technique based on the data points and the label quality measure of each data point.

Abstract: Command line inputs to a system by a user or automated script can comprise a number of legitimate commands but, as a series, reveal a reconnaissance attack, such as to gain knowledge of a system without a legitimate reason to do so. A trained artificial intelligence monitors the command line inputs to the system, as a series, and determines therefrom whether a match exists to a reconnaissance attack. The match may be a non-exact match, such as a match determined by a long short-term memory (LSTM) machine learning model. A reconnaissance attack response may then be initiated upon determining a match is present.

Abstract: Embodiments of the present disclosure provide a system for generating risk scores in near real-time. The system includes a processor and a memory coupled with and readable by the processor and storing therein a set of instructions. When executed by the processor, the processor is caused to generate risk scores in near real-time by receiving near real-time application events associated with an application in near real-time and identifying anomalies from the near real-time application events. The processor is further caused to generate risk scores in near real-time by generating an intermediate near real-time risk score for the identified anomalies and combining the intermediate near real-time risk score with a batch risk score generated from a batch process executed prior to receiving the near real-time application events to generate a near real-time risk score.

Abstract: The technique relates to a system and method for assessing corroded pipeline defect growth rate from partial defect growth rate information. The method involves obtaining a plurality of observed defect growth rates from the inspection data collected at different time intervals then determining at least one unobserved defect growth rate on the basis of distribution pattern of the plurality of observed defect growth rates thereafter simulating condition of at least one hyper parameter on the inspection data based on prior information of the at least one hyper parameter then simulating the plurality of observed defect growth rates and the at least one unobserved defect growth rate based on the simulated hyper parameters and finally obtaining defect growth rate point estimate from the simulated growth rate data. The method also involves determining a probability of failure of a defect from the defect growth rate point estimates.

Abstract: The technique relates to a system and method for assessing corroded pipeline defect growth rate from partial defect growth rate information. The method involves obtaining a plurality of observed defect growth rates from the inspection data collected at different time intervals then determining at least one unobserved defect growth rate on the basis of distribution pattern of the plurality of observed defect growth rates thereafter simulating condition of at least one hyper parameter on the inspection data based on prior information of the at least one hyper parameter then simulating the plurality of observed defect growth rates and the at least one unobserved defect growth rate based on the simulated hyper parameters and finally obtaining defect growth rate point estimate from the simulated growth rate data. The method also involves determining a probability of failure of a defect from the defect growth rate point estimates.

Abstract: The present invention provides a method and system for distributed probabilistic matrix factorization. In accordance with a disclosed embodiment, the method may include partitioning a sparse matrix into a first set of blocks on a distributed computer cluster, whereby a dimension of each block is MB rows and NB columns. Further, the method shall include initializing a plurality of matrices including first mean matrix ?, a first variance matrix ?, a first prior variance matrix ?P, a second mean matrix V, a second variance matrix {tilde over (V)}, and a second prior variance matrix {tilde over (V)}P, by a set of values from a probability distribution function. The plurality of matrices can be partitioned into a set of blocks on the distributed computer cluster, whereby each block can be of a shorter dimension K, and the plurality of matrices can be updated iteratively until a cost function of the sparse matrix converges.

Abstract: The present invention provides a method and system for determining a time-to-failure of an asset. A probabilistic non-linear model of a limit state of the asset is simulated and approximated by a predetermined set of particles. A numerical scheme for computation of a conditional probability distribution of a size of the defect, based on a value of the limit state is evaluated. A set of future values of a weight factor of each particle is predicted based on an initial assigned value. The predicted set of future values can be updated on capturing a new set of inspection data. A probability of the time-failure of the asset is estimated by summing the weight factor of a set of particles, the set of particles comprising particles at which the limit state is less than a zero limit threshold.