DATA ANALYTIC ENGINE TOWARDS THE SELF-MANAGEMENT OF COMPLEX PHYSICAL SYSTEMS
Systems and method for modeling system dynamics, including extracting features representative of a temporal evolution of a dynamical system, further including deriving one or more vector trajectories by performing sliding window segmentation of one or more time series; applying a linear test to determine whether the one or more vector trajectories are linear or nonlinear; and performing linear or nonlinear subspace decomposition on the vector trajectory based on the linear test. The system and method may generate a system evolution model from the extracted features of the dynamical system and determine a fitness score of the system evolution model.
1 . A method for modeling system dynamics, comprising:
extracting features representative of a temporal evolution of a dynamical system, including;
deriving one or more vector trajectories by performing sliding window segmentation of one or more time series;
applying a linear test to determine whether the one or more vector trajectories are linear or nonlinear; and
performing linear or nonlinear subspace decomposition on the vector trajectory based on the linear test; and
generating, using a processor, a system evolution model from the extracted features of the dynamical system; and
determining a fitness score of the system evolution model.
2 . The method as recited in claim 1 , wherein the dynamical system is a deterministic system.
3 . The method as recited in claim 1 , wherein the system evolution model is constructed using a Vector-Autoregressive (VAR) technique.
4 . The method as recited in claim 1 , wherein the system evolution model is constructed using a density based approach for a time series which lack smoothness in the one or more vector trajectories.
5 . The method as recited in claim 1 , wherein the system evolution model monitors a current system status and compares the current system status with the system evolution model to detect anomalies.
6 . The method as recited in claim 1 , wherein a window size is increased during the sliding window segmentation to improve detection precision.
7 . A system for modeling system dynamics, comprising:
a processor configured to extract features representative of a temporal evolution of a dynamical system, including;
a sliding window segmentation module configured to derive one or more vector trajectories of one or more time series;
a linear testing module configured to determine whether the one or more vector trajectories are linear or nonlinear; and
a subspace decomposition module configured to perform linear or nonlinear subspace decomposition on the vector trajectory based on the linear test; and
a modeling module configured to generate a system evolution model from the extracted features of the dynamical system; and
an analytic engine configured to determine a fitness score of the system evolution model.
8 . The system as recited in claim 7 , wherein the dynamical system is a deterministic system.
9 . The system as recited in claim 7 , wherein the system evolution model is constructed using a Vector-Autoregressive (VAR) technique.
10 . The system as recited in claim 7 , wherein the system evolution model is constructed using a density based approach for a time series which lack smoothness in the one or more vector trajectories.
11 . The system as recited in claim 7 , wherein the system evolution model monitors a current system status and compares the current system status with the system evolution model to detect anomalies.
12 . The system as recited in claim 7 , wherein a window size is increased during the sliding window segmentation to improve detection precision.