IEEE Transactions on Knowledge and Data Engineering
Effect of Network Quality on Player Departure Behavior in Online Games
IEEE Transactions on Parallel and Distributed Systems
A Movement Data Analysis and Synthesis Tool for Museum Visitors' Behaviors
PCM '09 Proceedings of the 10th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Eigenplaces: Segmenting Space through Digital Signatures
IEEE Pervasive Computing
Empirical study of routine structure in university campus
OCSC'13 Proceedings of the 5th international conference on Online Communities and Social Computing
Hi-index | 0.00 |
Behavioral structure can be represented by the principal components of the spatiotemporal data set, termed eigen-behaviors. The eigenbehaviors have been used in a number of researches for finding the behavior patterns of users of personalized mobile devices. To utilize eigenbehaviors for analyzing the behavioral structures in virtual environments, a challenging problem is the decomposition of target space in terms of non-convex intrinsic geometric shapes. This paper proposes a systematic analysis approach for discovering the primary players' behaviors associated with the target space. In experiments, our approach was applied to real players' movement obtained from Angel Love Online (ALO), a massively multiplayer online game. Before discovering the behavioral structure, we successfully utilized a hierarchical Isomap to decompose the ALO space so that any distances among the connected locations were considered as the shortest path in the Euclidean distance set. In previous work, the eigenbehaviors were extracted from the binary data representation where its elements indicate whether the locations of players are inside or outside the region. In contrast, we computed the eigenbehaviors from a proximity data representation where the Isomap-based distance was between players' locations and their reference. As a consequence, the movement direction can be inferred from the eigenbehaviors derived from the Isomap-based distance.