Affiliations: [a] Department of Mathematics, School of Engineering, Australian College of Kuwait, Kuwait
| [b] Department of Physics, College of Sciences, University of Bisha, Bisha, Saudi Arabia
| [c] Department of Physics, Faculty of Science, Al-Azhar University, Assiut, Egypt
Correspondence:
[*]
Corresponding author. Mohamed A. Mabrok, Mathematics Department, School of Engineering, Australian College of Kuwait, Kuwait. E-mail: [email protected].
Abstract: Extracting repeated unknown maneuvers or patterns preformed by a human operator in a cyber-physical systems can lead to better understanding of the behavior of the human operator who is controlling or sharing tasks with dynamical systems. These repeated maneuvers can be extracted by analyzing the inputs and outputs of the human operator using control theory and data mining tools. In this paper, we introduce geometrical shape-based pattern detection approach for input-output data. A pattern or a maneuver is defined as the maximum repeated behavior in time series trajectory data that is generated from the operator’s inputs and outputs. A two-phase algorithm is developed in this paper, the first phase consists of trajectory segmentation, creating segment fingerprint, clustering, and symbolic representations. The second phase of the proposed algorithm is pattern extraction phase, which is inherited from the motif finding algorithms in time series data and DNA sequences.
Keywords: Pattern recognition, human in the loop, trajectory
segmentation
