Feature extractions to model large-scale complex control systems
Heterogeneous monitoring nodes may each generate a series of monitoring node values
over time associated with operation of an industrial asset. An offline abnormal state …
over time associated with operation of an industrial asset. An offline abnormal state …
Computer system and method for creating and deploying an anomaly detection model based on streaming data
M Cantrell - US Patent 10,579,932, 2020 - Google Patents
(57) ABSTRACT A computing system may operate in a first mode during which it calculates
a set of training metrics on a running basis as a stream of multivariate data points originating …
a set of training metrics on a running basis as a stream of multivariate data points originating …
Method and system for intelligently resolving failures recurring in information technology environments
AR Bansal, TB Dethe - US Patent 11,106,523, 2021 - Google Patents
A method and system for intelligently resolving failures recurring in information technology
(IT) environments. Specifically, the method and system disclosed herein may be directed to …
(IT) environments. Specifically, the method and system disclosed herein may be directed to …
Deep neural network training for application program generation
J Montantes - US Patent 11,537,871, 2022 - Google Patents
(Continued) Primary Examiner Gil H. Lee (74) Attorney, Agent, or Firm-Maschoff Brennan
(57) ABSTRACT A computer architecture may comprise a processor, a memory, and a …
(57) ABSTRACT A computer architecture may comprise a processor, a memory, and a …
Method and system for semi-supervised deep anomaly detection for large-scale industrial monitoring systems based on time-series data utilizing digital twin …
S Schmitt, A Castellani, S Squartini - US Patent 12,093,818, 2024 - Google Patents
A computer-implemented method for detecting an anomalous operating status of a technical
system. A training phase obtains a first set of time-series values generated by a digital twin …
system. A training phase obtains a first set of time-series values generated by a digital twin …
Phase aware performance modeling for cloud applications
A Bhattacharyya, C Amza… - 2020 IEEE 13th …, 2020 - ieeexplore.ieee.org
In this paper we propose a new methodology for performance modeling of applications
deployed in the cloud based on automatically discovered phases along with their inputs. Our …
deployed in the cloud based on automatically discovered phases along with their inputs. Our …
Performing multivariate time series prediction with three-dimensional transformations
A computer-implemented method according to one embodiment includes receiving historical
two-dimensional (2D) multivariate time series data; transforming the historical 2D …
two-dimensional (2D) multivariate time series data; transforming the historical 2D …
Asymmetric adversarial learning framework for multi-turn dialogue response generation
O Olabiyi, ET Mueller - US Patent App. 16/997,090, 2022 - Google Patents
In a variety of embodiments, machine classifiers may model multi-turn dialogue as a one-to-
many prediction task. The machine classifier may be trained using adversarial boot …
many prediction task. The machine classifier may be trained using adversarial boot …
Systems and methods for time series simulation
Abstract Systems, apparatuses, methods, and computer program products are disclosed for
generating time series. A time series simulator receives information corresponding to a …
generating time series. A time series simulator receives information corresponding to a …
Multi-turn dialogue response generation using asymmetric adversarial machine classifiers
O Olabiyi, ET Mueller - US Patent 11,836,452, 2023 - Google Patents
In a variety of embodiments, machine classifiers may model multi-turn dialogue as a one-to-
many prediction task. The machine classifier may be trained using adversarial bootstrapping …
many prediction task. The machine classifier may be trained using adversarial bootstrapping …