The Motif-Based Approach to the Analysis of the Employee Trajectories within Organization

The analysis of the employees’ movement within organization building is an important task of the investigation of the business processes existing in the organization, including provision its cyberphysical security. In the paper, the motif-based approach to behavior pattern description and anomalies in organization staff movement is proposed. The motif of the employees’ movement represents a combination of the spatial and temporal attributes of the movement enforced by attributes of the visited controlled zone. The usage of motifs enables transformation of the raw logs from the proximity sensors of the access control system containing only identifiers of the controlled zones into semantically meaningful list of the activities. This approach is demonstrated with an application to the 2016 VAST Mini-Challenge 2 data set, which describes movement of the employees within organization building.

[1]  John C. Grundy,et al.  Predicting indoor spatial movement using data mining and movement patterns , 2017, 2017 IEEE International Conference on Big Data and Smart Computing (BigComp).

[2]  Slava Kisilevich,et al.  Spatio-temporal clustering , 2010, Data Mining and Knowledge Discovery Handbook.

[3]  Chelsea Dobbins,et al.  Scalable Daily Human Behavioral Pattern Mining from Multivariate Temporal Data , 2016, IEEE Transactions on Knowledge and Data Engineering.

[4]  Srivignessh Pss,et al.  RFID and pose invariant face verification based automated classroom attendance system , 2016, 2016 International Conference on Microelectronics, Computing and Communications (MicroCom).

[5]  Sangkyum Kim,et al.  Motion-Alert: Automatic Anomaly Detection in Massive Moving Objects , 2006, ISI.

[6]  Jaroslav Zendulka,et al.  Mining moving object data , 2012, Central European Journal of Computer Science.

[7]  Sangkyum Kim,et al.  ROAM: Rule- and Motif-Based Anomaly Detection in Massive Moving Object Data Sets , 2007, SDM.

[8]  M. Farnaghi,et al.  SPATIO-TEMPORAL PATTERN MINING ON TRAJECTORY DATA USING ARM , 2017 .

[9]  Li Li,et al.  Trajectory Pattern Identification and Anomaly Detection of Pedestrian Flows Based on Visual Clustering , 2016, Intelligent Information Processing.

[10]  Evgenia Novikova,et al.  Visualization-Driven Approach to Anomaly Detection in the Movement of Critical Infrastructure , 2017, MMM-ACNS.

[11]  Evgenia S. Novikova,et al.  Visualizing anomalous activity in the movement of critical infrastructure employees , 2017, 2017 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus).

[12]  Hui Xiong,et al.  Top-Eye: top-k evolving trajectory outlier detection , 2010, CIKM.

[13]  G. Elisabeta Marai,et al.  Spatial Analysis of Employee Safety Using Organizable Event Quiltmaps , 2016 .

[14]  Raymond T. Ng,et al.  Distance-based outliers: algorithms and applications , 2000, The VLDB Journal.

[15]  Kincho H. Law,et al.  A multi-agent based framework for the simulation of human and social behaviors during emergency evacuations , 2007, AI & SOCIETY.