Summary A parallel implementation of an agent‐based, artificial life model for graphical processing units (GPUs) is presented. The model represents predator‐prey populations as a collection of agents (animats) who act independently and interact with their environment and each other. Individual animat interactions include avoidance, mating, and hunting which contribute to emergent behavior in the system as a whole such as herd formation and defensive spirals. Computational simulations of the model exploring the behavior of the model are limited in size due to the large populations that may result from certain environments and rule combinations. Parallel methods for computing the model on GPUs and a CUDA implementation are presented and are shown to provide a significant performance improvement over existing sequential implementations without simplifying the model behavior. The reduced simulation run‐time can allow both larger systems to be computed and a wider range of rule combinations that may produce larger populations to be investigated in a feasible amount of time.

Recognizing human actions based on 3D skeleton data, commonly referred to as 3D action recognition, is fast gaining interest from the scientific community recently, because this approach presents a robust, compact and a perspective-invariant representation of motion data. Recent attempts on this problem proposed the development of RNN-based learning methods to model the temporal dependency in the sequential data. In this paper, we extend this idea to a hierarchical spatio-temporal domains to exploit the local and global features embedded in the long skeleton sequence. We introduce a novel temporal-contextual recurrent layer to learn the local features from consecutive frames and then to aggregate the extracted features hierarchically, refining the sequence representation layer by layer. Our method achieves competitive performance on 3 popular benchmark datasets for 3D human action analysis.

Spatial agent models can be used to explore self-organizing effects such as pattern growth and segregation. An approximate time line of key animat ideas and agent systems is presented and discussed. These ideas have led to a unique animat simulation

Unified Modelling Language (UML) is rapidly becoming the international standard for software design notation and methods. However, it offers little or no support for the design of the user interface. Models and notations are required for describing user tasks and the structure of the human–computer dialogue to support these tasks. Lean Cuisine+ provides a notation for both dialogue and task modelling. This paper describes a method for the initial steps of interface design which incorporates both the UML and Lean Cuisine+ notations and provides a means of representing tasks in the context of the dialogue structure of the user interface.